diff --git a/.gitignore b/.gitignore index 8279034..334d8da 100644 --- a/.gitignore +++ b/.gitignore @@ -4,3 +4,4 @@ mod.json mod.params model.tar tuning*.json +.nfs* diff --git a/a100_resnet50_tuned/tuning.2023-07-05T12:03+02:00.json b/a100_resnet50_tuned/tuning.2023-07-05T12:03+02:00.json new file mode 100644 index 0000000..7df2842 --- /dev/null +++ b/a100_resnet50_tuned/tuning.2023-07-05T12:03+02:00.json @@ -0,0 +1,957 @@ +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 20812262, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 7]], ["tile_x", "sp", [-1, 4, 7, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 7]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.2449185848236084, 1688551442.0959494], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 4034705, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 1]], ["tile_y", "sp", [-1, 4, 2, 1]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 7]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00010013381039255159], 0, 3.3758723735809326, 1688551455.6577284], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 39730645, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 8]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 1, 4, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[7.815848793069886e-05], 0, 3.511190414428711, 1688551458.652729], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 78979789, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 1, 4, 28]], ["tile_x", "sp", [-1, 1, 4, 28]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 7]], ["tile_rx", "sp", [-1, 7]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.4371063709259033, 1688551442.6747046], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 52776811, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 2]], ["tile_y", "sp", [-1, 2, 7, 8]], ["tile_x", "sp", [-1, 28, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688551451.9460711], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 66845741, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 4]], ["tile_y", "sp", [-1, 14, 4, 1]], ["tile_x", "sp", [-1, 14, 2, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.23816990852355957, 1688551451.9460957], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 38495021, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 1, 2, 2]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 7]], ["tile_rx", "sp", [-1, 7]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.000757659721555449], 0, 7.164881706237793, 1688551461.5742404], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 63833252, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 112]], ["tile_x", "sp", [-1, 1, 16, 7]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 7]], ["tile_rx", "sp", [-1, 7]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.13309168815612793, 1688551451.946107], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 77435950, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 8, 1, 7]], ["tile_x", "sp", [-1, 8, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 7]], ["tile_rx", "sp", [-1, 7]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688551451.9839413], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 54238951, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 8]], ["tile_y", "sp", [-1, 7, 4, 1]], ["tile_x", "sp", [-1, 4, 1, 28]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.1722419261932373, 1688551451.9839544], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 75211456, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 2]], ["tile_y", "sp", [-1, 1, 56, 2]], ["tile_x", "sp", [-1, 4, 1, 7]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 7]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.23229146003723145, 1688551451.9839623], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 37649588, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 1, 14, 2]], ["tile_x", "sp", [-1, 1, 2, 14]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 7]], ["tile_rx", "sp", [-1, 7]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0024924557496111975], 0, 6.682405471801758, 1688551464.5657895], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 25939054, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 1, 8, 7]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 7]], ["tile_rx", "sp", [-1, 7]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.29776883125305176, 1688551451.9839728], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 43703762, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 1, 56, 1]], ["tile_x", "sp", [-1, 2, 1, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 7]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002035545106007067], 0, 3.524384021759033, 1688551467.5899608], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 57330376, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 2]], ["tile_y", "sp", [-1, 8, 1, 1]], ["tile_x", "sp", [-1, 2, 7, 8]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 7]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688551452.230434], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 59450628, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 2]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 14, 2, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 7]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[4.8228627878314194e-05], 0, 3.9193620681762695, 1688551470.5581498], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 15658670, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 4]], ["tile_y", "sp", [-1, 1, 28, 2]], ["tile_x", "sp", [-1, 4, 14, 2]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.13882207870483398, 1688551452.230454], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 55882829, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 2, 1, 28]], ["tile_x", "sp", [-1, 2, 1, 28]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.1389164924621582, 1688551452.2304616], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 70782805, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 2]], ["tile_y", "sp", [-1, 4, 1, 28]], ["tile_x", "sp", [-1, 1, 2, 56]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 7]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.13263821601867676, 1688551452.2304692], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 54815475, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 4, 28, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.14305710792541504, 1688551452.2304761], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 35586140, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 8, 1, 1]], ["tile_x", "sp", [-1, 7, 4, 4]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 7]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688551452.2570193], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 32821733, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 16]], ["tile_y", "sp", [-1, 2, 2, 28]], ["tile_x", "sp", [-1, 1, 1, 28]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 7]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.1318674087524414, 1688551452.2570312], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 5304715, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 2]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 7, 8, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 7]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.000736747223690205], 0, 4.540984630584717, 1688551473.567575], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 11933549, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 7]], ["tile_x", "sp", [-1, 2, 14, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 7]], ["tile_rx", "sp", [-1, 7]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.13192176818847656, 1688551452.2570405], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 3639820, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 4, 14, 2]], ["tile_x", "sp", [-1, 1, 8, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 7]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00011021175499863051], 0, 3.508702516555786, 1688551476.5738926], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 9212891, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 14, 2, 2]], ["tile_x", "sp", [-1, 7, 2, 4]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 7]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.1638655662536621, 1688551452.2570496], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 36828741, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 2]], ["tile_y", "sp", [-1, 16, 1, 7]], ["tile_x", "sp", [-1, 28, 1, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 7]], ["tile_rx", "sp", [-1, 7]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.12213730812072754, 1688551452.257057], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 7632974, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 4]], ["tile_y", "sp", [-1, 56, 1, 1]], ["tile_x", "sp", [-1, 4, 7, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 7]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.13352012634277344, 1688551452.257064], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 76803146, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 4, 2, 14]], ["tile_x", "sp", [-1, 1, 14, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 7]], ["tile_rx", "sp", [-1, 7]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.15719962120056152, 1688551452.2570708], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 72613317, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 14, 2, 4]], ["tile_x", "sp", [-1, 8, 2, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 7]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688551452.2571244], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 74391278, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 2]], ["tile_y", "sp", [-1, 7, 1, 8]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 7]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.17076349258422852, 1688551452.257133], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 6528950, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 1, 4, 28]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 7]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.13423752784729004, 1688551452.257145], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 19299074, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 8, 2, 7]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 7]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.004669015995348837], 0, 2.155468463897705, 1688551478.002362], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 43459037, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 2]], ["tile_y", "sp", [-1, 1, 14, 2]], ["tile_x", "sp", [-1, 4, 2, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 7]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.000121491456094068], 0, 3.5380496978759766, 1688551480.993576], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 7, 7], "float32"], [2, 2], [3, 3, 3, 3], [1, 1], "float32"], {}], "config": {"index": 71646276, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 8]], ["tile_y", "sp", [-1, 28, 1, 2]], ["tile_x", "sp", [-1, 1, 28, 2]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 7]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.15202593803405762, 1688551452.2571557], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7436192, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 2, 14, 2]], ["tile_x", "sp", [-1, 1, 8, 7]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.023812294006347656, 1688551481.7783499], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 22201683, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 2, 4, 7]], ["tile_x", "sp", [-1, 7, 8, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03485393524169922, 1688551481.7922957], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 19171641, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 8]], ["tile_y", "sp", [-1, 1, 2, 14]], ["tile_x", "sp", [-1, 1, 2, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0003843844413179413], 0, 9.227386236190796, 1688551494.5709913], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13288881, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 32]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006030717493423524], 0, 3.625962257385254, 1688551497.5265372], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11925743, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 1]], ["tile_y", "sp", [-1, 7, 2, 4]], ["tile_x", "sp", [-1, 1, 4, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00030365631185421755], 0, 3.986257314682007, 1688551500.5127811], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 20227832, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 56, 1, 1]], ["tile_x", "sp", [-1, 7, 1, 4]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688551491.7564013], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4513841, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 1]], ["tile_y", "sp", [-1, 1, 14, 4]], ["tile_x", "sp", [-1, 2, 1, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[8.736077644439617e-05], 0, 3.709787368774414, 1688551503.5213804], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 21837559, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 16]], ["tile_y", "sp", [-1, 7, 1, 4]], ["tile_x", "sp", [-1, 2, 1, 4]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.008735816619565217], 0, 10.253167390823364, 1688551506.570894], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 19208831, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 2, 1, 7]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.576818875807064e-05], 0, 3.5604686737060547, 1688551509.5181384], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3039964, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 2, 4]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[4.2017884951508043e-05], 0, 3.4560012817382812, 1688551512.4675562], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 5272654, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 2, 1, 4]], ["tile_x", "sp", [-1, 1, 4, 7]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[4.8502138881326196e-05], 0, 3.6846470832824707, 1688551515.4128404], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7999324, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00024231779662294586], 0, 3.7467968463897705, 1688551518.378657], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 20880067, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 14, 2, 1]], ["tile_x", "sp", [-1, 1, 1, 8]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.700440023432508e-05], 0, 4.729179620742798, 1688551521.377198], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 16609953, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 2, 1, 14]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.001020322665615142], 0, 6.39992618560791, 1688551524.3551447], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 16328734, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 1, 7, 8]], ["tile_x", "sp", [-1, 1, 56, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.026080608367919922, 1688551491.7564416], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13521034, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 8, 1, 1]], ["tile_x", "sp", [-1, 14, 2, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00037603616228172295], 0, 5.097876787185669, 1688551527.344957], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 6592014, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 28]], ["tile_x", "sp", [-1, 4, 7, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02427387237548828, 1688551491.7564533], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2263846, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 7, 4, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[4.709317369472015e-05], 0, 3.611748695373535, 1688551530.3294234], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 12898837, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 1, 1, 56]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.001005231323125], 0, 4.443021059036255, 1688551533.2945943], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 18737552, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 4, 14, 1]], ["tile_x", "sp", [-1, 7, 1, 8]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.034774065017700195, 1688551491.7564645], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3455719, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 14, 1, 2]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02814006805419922, 1688551491.7564719], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 19041168, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 2]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 7, 1, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.686409546407427e-05], 0, 3.5044100284576416, 1688551536.2661805], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 18255921, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 2]], ["tile_y", "sp", [-1, 1, 2, 4]], ["tile_x", "sp", [-1, 1, 1, 28]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.006702866708609272], 0, 2.69254732131958, 1688551537.7533693], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 15257205, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 2]], ["tile_y", "sp", [-1, 7, 1, 2]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688551491.7721744], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11507426, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 7, 1, 2]], ["tile_x", "sp", [-1, 4, 1, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[9.030692587608636e-05], 0, 3.8510732650756836, 1688551540.7597575], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11943745, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 2]], ["tile_y", "sp", [-1, 1, 28, 1]], ["tile_x", "sp", [-1, 14, 4, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[9.256835264034937e-05], 0, 4.196026563644409, 1688551543.7470858], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 15962715, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 1]], ["tile_y", "sp", [-1, 4, 1, 2]], ["tile_x", "sp", [-1, 2, 7, 4]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[7.49690653500396e-05], 0, 3.537580966949463, 1688551546.7455363], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 10778908, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 8, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00012362951313767668], 0, 4.556086301803589, 1688551549.7277942], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13487929, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 4, 2, 1]], ["tile_x", "sp", [-1, 56, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0014333381172291298], 0, 4.57376503944397, 1688551552.7301595], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 9661671, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 4, 1, 7]], ["tile_x", "sp", [-1, 2, 1, 28]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.024632692337036133, 1688551491.772196], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 19232200, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 2, 2, 14]], ["tile_x", "sp", [-1, 1, 2, 7]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0009647769139270772], 0, 8.352379322052002, 1688551555.7553432], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 12545297, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 7, 1, 8]], ["tile_x", "sp", [-1, 4, 14, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.12458157539367676, 1688551491.7722056], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 5875631, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 64]], ["tile_y", "sp", [-1, 1, 28, 1]], ["tile_x", "sp", [-1, 2, 2, 14]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.024631261825561523, 1688551491.7722123], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 5467893, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 32]], ["tile_y", "sp", [-1, 7, 2, 4]], ["tile_x", "sp", [-1, 28, 2, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.11898374557495117, 1688551491.7722192], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7022975, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 28, 1, 1]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02280116081237793, 1688551491.7722259], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 58335186, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 2]], ["tile_y", "sp", [-1, 1, 8, 7]], ["tile_x", "sp", [-1, 1, 4, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005509360041350792], 0, 3.8023548126220703, 1688551566.3668356], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 25973637, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 32]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 2, 14, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.13413238525390625, 1688551558.2956417], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 69189931, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 1, 14, 4]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00013933189669778698], 0, 4.366687774658203, 1688551569.365628], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 32059553, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 7, 1, 4]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.025547570800000002], 0, 3.5702483654022217, 1688551571.0210254], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 58163422, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 8, 7, 1]], ["tile_x", "sp", [-1, 2, 4, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00021700588725951837], 0, 3.594517707824707, 1688551574.0084], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6478329, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 32]], ["tile_y", "sp", [-1, 4, 1, 1]], ["tile_x", "sp", [-1, 8, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0758935699375], 0, 3.4791295528411865, 1688551576.4615414], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 18955771, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 16]], ["tile_y", "sp", [-1, 4, 2, 7]], ["tile_x", "sp", [-1, 4, 7, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.01152067056321839], 0, 2.5556023120880127, 1688551577.9551058], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 85318711, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 16]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 14, 4]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002886937994633274], 0, 4.515561103820801, 1688551580.929047], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 23875475, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 2, 1, 14]], ["tile_x", "sp", [-1, 4, 1, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.013438894040000001], 0, 3.6540231704711914, 1688551582.4966612], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 17316620, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 7, 4, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0024626470835380837], 0, 3.194549083709717, 1688551583.916942], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 63002815, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 7, 1, 2]], ["tile_x", "sp", [-1, 2, 4, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00022694600000000003], 0, 3.998953342437744, 1688551586.8788795], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 22749909, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 4, 1, 2]], ["tile_x", "sp", [-1, 2, 14, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002065396411568979], 0, 3.9496049880981445, 1688551589.890919], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 65885929, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 4, 7, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00010005449794699515], 0, 4.269925355911255, 1688551592.8439705], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5781726, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 8, 1, 7]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 4, 13.570373773574829, 1688551603.1598334], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 83248387, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 14, 2, 1]], ["tile_x", "sp", [-1, 7, 1, 8]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.008476645771186439], 0, 8.340781688690186, 1688551604.5504735], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 39245656, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 4, 2, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00020489270849689755], 0, 4.149900197982788, 1688551607.5521965], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 82431498, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 1, 28, 2]], ["tile_x", "sp", [-1, 4, 14, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.10322928428649902, 1688551563.5810971], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 63361888, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 7, 1, 8]], ["tile_x", "sp", [-1, 7, 1, 8]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.1500096321105957, 1688551563.5811107], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 15648574, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 1, 2, 4]], ["tile_x", "sp", [-1, 1, 2, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00010308323360471825], 0, 3.5552585124969482, 1688551610.5086596], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 78096723, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 8, 7, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.15991806983947754, 1688551563.5811207], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 34052693, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 1]], ["tile_y", "sp", [-1, 1, 56, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03600907325744629, 1688551563.581129], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 40051666, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 14, 1, 1]], ["tile_x", "sp", [-1, 1, 4, 2]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[8.41300948298395e-05], 0, 3.8394150733947754, 1688551613.5310402], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 11978075, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 1]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 1, 8, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0001275699226506215], 0, 3.5956718921661377, 1688551616.5177023], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 25468755, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 56]], ["tile_x", "sp", [-1, 1, 56, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04284095764160156, 1688551563.581141], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 52717697, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 4]], ["tile_y", "sp", [-1, 2, 1, 14]], ["tile_x", "sp", [-1, 8, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 4, 12.03430438041687, 1688551626.7291403], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 38658723, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 2, 2, 7]], ["tile_x", "sp", [-1, 4, 1, 14]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.10829558099999999], 0, 3.3090076446533203, 1688551628.2669072], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 61877762, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 2, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0010182803362720403], 0, 4.087821960449219, 1688551631.3348866], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 47056691, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 4]], ["tile_y", "sp", [-1, 7, 2, 2]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0007690853418925344], 0, 3.8904078006744385, 1688551634.324686], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 17060813, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 16]], ["tile_y", "sp", [-1, 1, 4, 7]], ["tile_x", "sp", [-1, 2, 1, 7]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.009734213815533979], 0, 3.420578718185425, 1688551635.8361237], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 39979109, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 8, 7, 1]], ["tile_x", "sp", [-1, 1, 56, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.07698869705200195, 1688551563.5811563], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 76795139, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 1, 1, 8]], ["tile_x", "sp", [-1, 1, 1, 8]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0027669374640410956], 0, 6.51526951789856, 1688551638.8536706], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7541812, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 2]], ["tile_y", "sp", [-1, 7, 8, 1]], ["tile_x", "sp", [-1, 4, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006361363358238302], 0, 3.7462289333343506, 1688551641.8332949], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 37926772, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 1, 7, 8]], ["tile_x", "sp", [-1, 2, 7, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0016829008324661813], 0, 4.384105205535889, 1688551644.87632], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 64792468, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 16]], ["tile_y", "sp", [-1, 2, 1, 7]], ["tile_x", "sp", [-1, 7, 4, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.067634559625], 0, 7.626649618148804, 1688551647.1226583], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 32013729, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 8]], ["tile_y", "sp", [-1, 1, 4, 14]], ["tile_x", "sp", [-1, 2, 7, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.13201427459716797, 1688551563.581169], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 51701, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 2]], ["tile_x", "sp", [-1, 1, 4, 1]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[3.2441204238322885e-05], 0, 5.597836256027222, 1688551660.6879427], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 156752, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 1, 2, 7]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[9.375294480140187e-05], 0, 6.209332466125488, 1688551663.676934], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 189725, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 4]], ["tile_x", "sp", [-1, 7, 7, 4]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0014979155273401295], 0, 6.834774494171143, 1688551666.6646454], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 257447, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 8]], ["tile_x", "sp", [-1, 14, 1, 7]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006382723674288006], 0, 7.380709648132324, 1688551669.6437552], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 343838, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 32, 1]], ["tile_x", "sp", [-1, 1, 2, 49]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.0033189695845004e-05], 0, 6.585602283477783, 1688551672.6042674], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 29397, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 32]], ["tile_x", "sp", [-1, 1, 14, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[6.018519027246116e-05], 0, 6.054615497589111, 1688551675.5711608], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 20958, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 2]], ["tile_x", "sp", [-1, 1, 14, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.5895322758461818e-05], 0, 5.639861345291138, 1688551678.5084858], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 169661, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 8]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[3.9967951429788726e-05], 0, 5.921606063842773, 1688551681.4456356], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 228884, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 8]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[2.4626839951622657e-05], 0, 5.860720634460449, 1688551684.384726], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 297392, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 2]], ["tile_x", "sp", [-1, 49, 1, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688551657.911894], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 297596, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 8]], ["tile_x", "sp", [-1, 1, 2, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[8.422968118147e-05], 0, 7.366821765899658, 1688551687.387868], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 230741, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 16]], ["tile_x", "sp", [-1, 2, 7, 2]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[4.924861562308164e-05], 0, 5.603996753692627, 1688551690.3359587], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 95724, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 2]], ["tile_x", "sp", [-1, 14, 1, 2]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[3.5559985675778034e-05], 0, 6.003820896148682, 1688551693.3052044], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 297533, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 1, 1]], ["tile_x", "sp", [-1, 1, 2, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00011745214594279043], 0, 5.8028435707092285, 1688551696.3042626], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 318291, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 1]], ["tile_x", "sp", [-1, 1, 7, 28]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[4.415389404265887e-05], 0, 6.0112738609313965, 1688551699.2458837], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 260870, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 4]], ["tile_x", "sp", [-1, 28, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.000216835773557047], 0, 6.356353998184204, 1688551702.2337306], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 315267, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 1]], ["tile_x", "sp", [-1, 1, 98, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.49226737871392e-05], 0, 6.100049734115601, 1688551705.2221365], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 26107, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 8]], ["tile_x", "sp", [-1, 2, 2, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00014526637230215825], 0, 5.928791284561157, 1688551708.1906018], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 141315, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 64, 1]], ["tile_x", "sp", [-1, 1, 2, 14]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[3.0109073194651382e-05], 0, 6.10242772102356, 1688551711.1277454], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 216820, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 1]], ["tile_x", "sp", [-1, 14, 1, 14]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00159869877666999], 0, 6.486593961715698, 1688551714.1691127], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 337965, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 1, 2]], ["tile_x", "sp", [-1, 28, 7, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688551657.9511232], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14557, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 1]], ["tile_x", "sp", [-1, 2, 7, 7]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[3.7933324315368415e-05], 0, 5.658526659011841, 1688551717.1181507], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 206777, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 4]], ["tile_x", "sp", [-1, 2, 1, 7]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.01963311168627451], 0, 5.522641181945801, 1688551718.7003663], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 116077, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 8]], ["tile_x", "sp", [-1, 14, 1, 14]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.5395731925964355, 1688551657.9511473], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 338437, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 7, 28, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.1068455725907384e-05], 0, 7.822084903717041, 1688551721.669958], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 260146, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 32]], ["tile_x", "sp", [-1, 1, 1, 98]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.007010069527777778], 0, 5.3540849685668945, 1688551723.1134744], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 55392, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 2]], ["tile_x", "sp", [-1, 1, 49, 4]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.5961079597473145, 1688551657.9511607], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 267972, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 2, 1]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.005461376021739131], 0, 4.6835713386535645, 1688551724.5438807], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 118401, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 2]], ["tile_x", "sp", [-1, 1, 2, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[5.418734668747244e-05], 0, 6.017914295196533, 1688551727.5772555], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 209511, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 1]], ["tile_x", "sp", [-1, 2, 2, 49]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0007163863286031042], 0, 5.95639181137085, 1688551730.558611], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 15551, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 2, 1]], ["tile_x", "sp", [-1, 2, 7, 14]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00028182527048885693], 0, 5.900790452957153, 1688551733.4532633], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 73566, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 8]], ["tile_x", "sp", [-1, 1, 14, 7]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[5.621319058972022e-05], 0, 5.862453460693359, 1688551736.4972057], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 191041, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 1]], ["tile_x", "sp", [-1, 4, 7, 7]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[4.389276057766086e-05], 0, 5.563360691070557, 1688551739.4415252], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 106128, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 2]], ["tile_x", "sp", [-1, 7, 1, 7]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.00164486403125], 0, 4.880156517028809, 1688551740.8167107], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 154186, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 2]], ["tile_x", "sp", [-1, 1, 196, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.5750644207000732, 1688551657.9511774], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 24137292, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 4]], ["tile_y", "sp", [-1, 2, 14, 2]], ["tile_x", "sp", [-1, 7, 1, 8]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.008422460218487396], 0, 3.4565682411193848, 1688551753.0029678], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4081827, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 2]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 8]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0001038074254482136], 0, 3.501448631286621, 1688551755.9791336], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 29287945, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 2, 2, 7]], ["tile_x", "sp", [-1, 2, 1, 7]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.022994279861450195, 1688551743.7484903], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 23071162, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 32, 1]], ["tile_y", "sp", [-1, 2, 4, 7]], ["tile_x", "sp", [-1, 1, 1, 8]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008145236034201955], 0, 2.012418270111084, 1688551757.381917], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 15571854, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 16]], ["tile_y", "sp", [-1, 1, 7, 4]], ["tile_x", "sp", [-1, 4, 1, 7]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.001975588921760391], 0, 3.6337761878967285, 1688551760.424458], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13490688, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 8]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 2, 2, 7]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.001418929101604278], 0, 4.711766004562378, 1688551763.4284995], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 6656944, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 2, 14, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.025483131408691406, 1688551743.7485135], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 41338646, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 64, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 7, 2, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[6.50202483697193e-05], 0, 4.011565685272217, 1688551766.403144], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 21187332, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00010439019678631051], 0, 3.141880750656128, 1688551767.805959], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 672777, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 2, 1, 28]], ["tile_x", "sp", [-1, 7, 1, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0031385697021943577], 0, 2.5261363983154297, 1688551769.2223692], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 39829496, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 32]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.006377791675159236], 0, 6.928770542144775, 1688551770.6666358], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 35303096, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 7, 2, 2]], ["tile_x", "sp", [-1, 14, 1, 2]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.06152462959289551, 1688551747.2220204], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 31167859, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 7, 4, 1]], ["tile_x", "sp", [-1, 7, 4, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00025719166014319807], 0, 4.973821640014648, 1688551773.7113166], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 18592576, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 1, 1, 4]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00010942844666259253], 0, 3.4637234210968018, 1688551776.6818087], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 34732923, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 4]], ["tile_y", "sp", [-1, 1, 8, 1]], ["tile_x", "sp", [-1, 2, 1, 14]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.002162212462203024], 0, 3.913576364517212, 1688551778.0833297], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 24612789, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[2.9126586063100138e-05], 0, 3.3105156421661377, 1688551781.062974], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 14871195, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 2]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 28, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[7.36672886139748e-05], 0, 3.4195330142974854, 1688551784.0429692], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 26281456, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 4]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 2, 1, 14]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.004612629267281106], 0, 2.554443836212158, 1688551785.4780633], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13143634, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 2]], ["tile_y", "sp", [-1, 2, 1, 7]], ["tile_x", "sp", [-1, 28, 1, 2]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.024188756942749023, 1688551747.2220457], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 43778217, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 1, 4]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 1, 2, 2]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.06818819046020508, 1688551747.2220545], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 30161675, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 28]], ["tile_x", "sp", [-1, 4, 7, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.004266655063829787], 0, 6.32282280921936, 1688551786.9495049], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 5239060, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 32]], ["tile_y", "sp", [-1, 2, 1, 14]], ["tile_x", "sp", [-1, 1, 1, 28]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.022808074951171875, 1688551747.222065], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 31288061, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 4]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 7, 1, 4]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00030290886884017234], 0, 5.1185009479522705, 1688551789.9628994], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 18875720, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 2]], ["tile_y", "sp", [-1, 1, 2, 28]], ["tile_x", "sp", [-1, 1, 7, 8]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.025908231735229492, 1688551747.2220786], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 26161693, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 8]], ["tile_y", "sp", [-1, 1, 4, 14]], ["tile_x", "sp", [-1, 1, 2, 7]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.004161586900414938], 0, 3.385650873184204, 1688551791.3926356], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 29559158, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 4, 14, 1]], ["tile_x", "sp", [-1, 1, 1, 56]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02511763572692871, 1688551747.2220874], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4989336, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 1, 2, 28]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003621475441077441], 0, 4.374427795410156, 1688551794.423369], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 12959395, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 8, 7, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.026274442672729492, 1688551747.2220974], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 32255589, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 2, 7, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[7.02447235263204e-05], 0, 4.115910530090332, 1688551797.3879669], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 41278022, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 16]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 56, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688551751.6668396], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 42027732, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 1, 4]], ["tile_y", "sp", [-1, 1, 2, 14]], ["tile_x", "sp", [-1, 4, 2, 7]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03776383399963379, 1688551751.6668656], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 33603742, "code_hash": null, "entity": [["tile_f", "sp", [-1, 128, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 7]], ["tile_x", "sp", [-1, 2, 4, 7]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.048134565353393555, 1688551751.6668754], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 43806023, "code_hash": null, "entity": [["tile_f", "sp", [-1, 256, 1, 1]], ["tile_y", "sp", [-1, 14, 1, 4]], ["tile_x", "sp", [-1, 7, 2, 2]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.729835033416748, 1688551751.6668847], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 12463173, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 2]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 1, 4, 7]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[4.207027927194411e-05], 0, 3.5754411220550537, 1688551800.3826725], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 56, 56], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 24267775, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 8, 2]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 1, 2, 28]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.003420198511945393], 0, 2.2048940658569336, 1688551801.8271735], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 22456295, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 1, 14, 4]], ["tile_x", "sp", [-1, 1, 2, 7]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.13312315940856934, 1688551803.4501197], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 10531911, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 1, 28, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00016829558130081301], 0, 3.4475769996643066, 1688551816.210373], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7068044, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 4, 2, 7]], ["tile_x", "sp", [-1, 7, 2, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.027307987213134766, 1688551803.4501412], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3949717, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 2]], ["tile_y", "sp", [-1, 8, 1, 7]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03007030487060547, 1688551803.4501498], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 15255909, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 32]], ["tile_y", "sp", [-1, 14, 4, 1]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0056238653595505625], 0, 2.1077771186828613, 1688551817.6343312], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 22141292, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 8, 7]], ["tile_x", "sp", [-1, 1, 4, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[7.998254394157683e-05], 0, 3.8534226417541504, 1688551820.6731126], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1506928, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 4]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 1, 4, 7]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0015519915158501442], 0, 3.7756521701812744, 1688551823.669653], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 15505099, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 1, 1, 8]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[5.615627555321391e-05], 0, 3.268439769744873, 1688551826.6155481], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 18993032, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 1, 28, 1]], ["tile_x", "sp", [-1, 4, 14, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.025044918060302734, 1688551803.5185356], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 6487143, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 1, 28, 1]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.002127099350923483], 0, 4.00414776802063, 1688551829.6627395], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 5526475, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 2]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 1, 8, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[6.942277177436784e-05], 0, 3.3786509037017822, 1688551832.6367247], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 419269, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 2, 2, 7]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00012462219695564828], 0, 3.402179718017578, 1688551835.613329], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 16315344, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00012832333261734286], 0, 3.4243083000183105, 1688551838.6301239], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11601152, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 32]], ["tile_y", "sp", [-1, 2, 28, 1]], ["tile_x", "sp", [-1, 2, 14, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04131269454956055, 1688551803.6670406], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 28773464, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 7, 4, 2]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.038080453872680664, 1688551803.66705], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 22941177, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 1, 7, 8]], ["tile_x", "sp", [-1, 7, 2, 4]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.036310434341430664, 1688551803.6670582], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 26298401, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 1]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 1, 2, 14]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008434651517706575], 0, 3.7164289951324463, 1688551840.0144508], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 8859370, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 2, 28, 1]], ["tile_x", "sp", [-1, 7, 2, 2]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04417061805725098, 1688551805.0537453], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 19372031, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 4, 1, 7]], ["tile_x", "sp", [-1, 4, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.003365433824267782], 0, 4.957167863845825, 1688551843.063918], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 21336474, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 14, 1, 1]], ["tile_x", "sp", [-1, 2, 7, 4]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0013225090639868745], 0, 7.4088134765625, 1688551846.0930817], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 23083270, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 4, 14]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0013779093938618926], 0, 8.394572496414185, 1688551849.0834532], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 15480564, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 2]], ["tile_y", "sp", [-1, 1, 2, 4]], ["tile_x", "sp", [-1, 4, 2, 7]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.002914486880866426], 0, 4.587630987167358, 1688551852.1116095], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3144924, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 2]], ["tile_y", "sp", [-1, 1, 1, 56]], ["tile_x", "sp", [-1, 1, 1, 8]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02172541618347168, 1688551808.1213841], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 10361911, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 28]], ["tile_x", "sp", [-1, 8, 7, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0007609428052681092], 0, 4.266021013259888, 1688551855.1449997], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 26839094, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 14]], ["tile_x", "sp", [-1, 1, 2, 14]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04874563217163086, 1688551808.121399], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13267679, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 2, 28, 1]], ["tile_x", "sp", [-1, 1, 7, 4]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03533530235290527, 1688551808.1214066], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13818159, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 8, 7, 1]], ["tile_x", "sp", [-1, 1, 14, 4]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.027039766311645508, 1688551808.1214147], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 8917114, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 28]], ["tile_x", "sp", [-1, 2, 14, 2]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04746747016906738, 1688551808.1214216], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3209659, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 7, 1, 4]], ["tile_x", "sp", [-1, 2, 1, 28]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.0265958309173584, 1688551808.1214292], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 28299124, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 14, 1, 4]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03334760665893555, 1688551808.1214366], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11954169, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 2, 1, 14]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00019529633510702624], 0, 3.5941154956817627, 1688551858.13812], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11769445, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 2]], ["tile_y", "sp", [-1, 4, 1, 2]], ["tile_x", "sp", [-1, 2, 1, 14]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688551812.634168], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 8252510, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 8, 1, 1]], ["tile_x", "sp", [-1, 2, 28, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02815103530883789, 1688551812.6341946], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 20016220, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00018598426772108056], 0, 3.322448492050171, 1688551861.115135], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [64, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 19804305, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 14, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 8]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688551813.3619354], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 19554128, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 2, 1, 14]], ["tile_x", "sp", [-1, 1, 2, 2]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.028391599655151367, 1688551861.9103577], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 6544973, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 2]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 7, 4, 2]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.023497581481933594, 1688551861.9103773], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 6410787, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 4, 2, 7]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.027800798416137695, 1688551861.9103887], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 27873668, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 4]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 7, 8, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.003986290051980198], 0, 6.211547136306763, 1688551874.7764866], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 34492706, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 56]], ["tile_x", "sp", [-1, 4, 1, 14]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.023691892623901367, 1688551865.2470644], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 16128591, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 32]], ["tile_y", "sp", [-1, 8, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.004693685939252336], 0, 2.9199090003967285, 1688551876.230488], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 30779568, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 2]], ["tile_y", "sp", [-1, 7, 4, 1]], ["tile_x", "sp", [-1, 28, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.030205726623535156, 1688551865.247081], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 6317328, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 2]], ["tile_y", "sp", [-1, 8, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02279806137084961, 1688551865.2470891], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 10892044, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 1, 28, 2]], ["tile_x", "sp", [-1, 1, 4, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0001316706584627964], 0, 4.056645393371582, 1688551879.2181144], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 40696680, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 56]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.024114608764648438, 1688551865.247103], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 12873594, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 32]], ["tile_y", "sp", [-1, 1, 1, 56]], ["tile_x", "sp", [-1, 8, 1, 7]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.022733449935913086, 1688551865.2471118], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11803681, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 4, 7, 2]], ["tile_x", "sp", [-1, 1, 56, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.0422670841217041, 1688551865.2471218], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 33999159, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 2]], ["tile_y", "sp", [-1, 2, 14, 2]], ["tile_x", "sp", [-1, 8, 7, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.07145524024963379, 1688551865.2471287], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 23377079, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 128]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 28, 1, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.04930721028571429], 0, 2.4140565395355225, 1688551881.2340503], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 37582731, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 2]], ["tile_y", "sp", [-1, 1, 7, 8]], ["tile_x", "sp", [-1, 2, 2, 14]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.08334970474243164, 1688551865.2471373], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13339296, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 8]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 1, 56, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.023857593536376953, 1688551865.2471442], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 10567445, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 7]], ["tile_x", "sp", [-1, 8, 1, 7]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.026253223419189453, 1688551865.247152], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 24342455, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 8]], ["tile_y", "sp", [-1, 7, 2, 4]], ["tile_x", "sp", [-1, 2, 7, 4]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05433344841003418, 1688551865.24716], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 25339059, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 8]], ["tile_y", "sp", [-1, 7, 2, 2]], ["tile_x", "sp", [-1, 1, 1, 56]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.023283004760742188, 1688551865.2471683], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 32559230, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 32]], ["tile_y", "sp", [-1, 2, 14, 2]], ["tile_x", "sp", [-1, 2, 1, 2]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.038616180419921875, 1688551865.2471757], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 38261820, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 2]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 2, 4, 7]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.002199023167032967], 0, 3.214069366455078, 1688551882.6527584], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 15715130, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 56]], ["tile_x", "sp", [-1, 1, 2, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0020231074968710887], 0, 4.291731119155884, 1688551885.7020295], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13013745, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 16]], ["tile_y", "sp", [-1, 1, 28, 2]], ["tile_x", "sp", [-1, 1, 4, 14]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.026323795318603516, 1688551865.2471864], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 35864045, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 8]], ["tile_x", "sp", [-1, 2, 7, 4]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.004932824945812808], 0, 6.803430795669556, 1688551887.167089], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 39391361, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 2]], ["tile_y", "sp", [-1, 8, 7, 1]], ["tile_x", "sp", [-1, 7, 8, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.06832003593444824, 1688551867.3426619], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 34693332, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 1]], ["tile_y", "sp", [-1, 2, 1, 14]], ["tile_x", "sp", [-1, 28, 2, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688551871.9207697], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 21895890, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 2, 4, 7]], ["tile_x", "sp", [-1, 1, 4, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00019894314458128077], 0, 3.428471088409424, 1688551890.1884158], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 33140426, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 4, 2, 1]], ["tile_x", "sp", [-1, 14, 2, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.032079219818115234, 1688551871.920804], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 29776234, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 64, 1]], ["tile_y", "sp", [-1, 2, 7, 4]], ["tile_x", "sp", [-1, 1, 2, 7]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0029172535860058305], 0, 2.304919719696045, 1688551891.5931635], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 28237824, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 28, 1, 2]], ["tile_x", "sp", [-1, 1, 2, 7]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.01142123065909091], 0, 5.599137783050537, 1688551893.1737392], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 27973013, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 2]], ["tile_y", "sp", [-1, 7, 1, 8]], ["tile_x", "sp", [-1, 7, 1, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688551871.9224656], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 26061167, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 2]], ["tile_y", "sp", [-1, 1, 14, 4]], ["tile_x", "sp", [-1, 2, 2, 14]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0278775691986084, 1688551871.922479], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 39419473, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 4]], ["tile_y", "sp", [-1, 2, 4, 1]], ["tile_x", "sp", [-1, 4, 14, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.037577152252197266, 1688551871.9224875], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 27259312, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 32]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 14, 2, 2]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.026825666427612305, 1688551871.9224956], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [128, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2958315, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 14, 2, 1]], ["tile_x", "sp", [-1, 7, 1, 8]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03211641311645508, 1688551871.922503], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 33648606, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 1, 1]], ["tile_y", "sp", [-1, 28, 1, 1]], ["tile_x", "sp", [-1, 1, 4, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.12073493003845215, 1688551894.8814292], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 16731635, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 128, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 28, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.11807632446289062, 1688551894.8814547], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 32467034, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 4]], ["tile_y", "sp", [-1, 1, 2, 14]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.1695697875], 0, 8.784245252609253, 1688551906.1192214], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 11634931, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 8]], ["tile_y", "sp", [-1, 2, 1, 14]], ["tile_x", "sp", [-1, 7, 2, 2]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.030678987503051758, 1688551900.645709], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 28053898, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00040952993970103877], 0, 4.380229711532593, 1688551909.1538463], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 176619, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 8]], ["tile_y", "sp", [-1, 2, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.026446335631578943], 0, 2.920989513397217, 1688551910.8047612], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 27307342, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 14, 2, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.036077022552490234, 1688551900.6457267], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 22534868, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 4, 7, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03865933418273926, 1688551900.645734], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 9146749, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 16]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 2, 7, 2]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04047799110412598, 1688551900.6457407], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 32361766, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 2]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 2, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00032104834706467663], 0, 4.367877244949341, 1688551913.8428738], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6255241, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 7, 2, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.03849609842307692], 0, 5.102470874786377, 1688551915.6344879], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 13193744, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 16]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 7, 1, 4]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.05224125365], 0, 3.2272865772247314, 1688551917.616309], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1827235, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 32]], ["tile_y", "sp", [-1, 1, 14, 2]], ["tile_x", "sp", [-1, 7, 1, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.01462562891304348], 0, 2.3649730682373047, 1688551919.202483], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 13981249, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 4, 1, 7]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.016260888854838708], 0, 6.271139860153198, 1688551920.769991], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 17605302, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 4]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.026335177763157892], 0, 2.8149502277374268, 1688551922.4554968], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3166705, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 8, 1]], ["tile_y", "sp", [-1, 1, 7, 4]], ["tile_x", "sp", [-1, 2, 1, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0018936121487119438], 0, 3.87831449508667, 1688551925.5049458], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1437724, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 14, 1, 2]], ["tile_x", "sp", [-1, 2, 1, 2]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03518176078796387, 1688551900.6457586], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 19162367, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 2]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 4, 1, 7]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.021384779893617024], 0, 2.9307138919830322, 1688551927.1130865], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 18109934, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.05401349067687988, 1688551900.645767], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 31651291, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 2, 2, 7]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006854118361891707], 0, 4.08867335319519, 1688551928.4812922], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 11508297, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 2]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 2, 1, 14]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.0655825138092041, 1688551900.645775], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14306891, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 7, 1, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688551904.0038917], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 24651437, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 4]], ["tile_y", "sp", [-1, 7, 1, 4]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.009662631105769232], 0, 4.590386867523193, 1688551930.007571], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 34564912, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 32]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 2, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.015224010106060606], 0, 8.536043643951416, 1688551931.539388], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 17585160, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 7, 2, 2]], ["tile_x", "sp", [-1, 7, 2, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03287816047668457, 1688551904.0039196], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8968432, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 32]], ["tile_y", "sp", [-1, 2, 14, 1]], ["tile_x", "sp", [-1, 7, 1, 4]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.050279855728149414, 1688551904.0039294], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 16255535, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 8]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 1, 14, 2]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00023908368694493785], 0, 3.8304457664489746, 1688551934.5126998], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 9504794, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 4]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 7, 1, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.009731708407766989], 0, 3.4215855598449707, 1688551936.0279531], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 22672742, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 2]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04372048377990723, 1688551904.0039399], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6448981, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 2]], ["tile_y", "sp", [-1, 14, 1, 2]], ["tile_x", "sp", [-1, 7, 2, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.1283990478], 0, 6.568262577056885, 1688551937.799981], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1984546, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 16]], ["tile_y", "sp", [-1, 1, 28, 1]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.006259161756249999], 0, 2.211015224456787, 1688551939.237645], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 28531391, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0004446295924497107], 0, 8.774886131286621, 1688551942.256039], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 36647846, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 1, 2, 14]], ["tile_x", "sp", [-1, 2, 2, 7]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05682992935180664, 1688551904.003951], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 16194005, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.010555004231578949], 0, 3.64884877204895, 1688551943.7342234], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 56, 56], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3401659, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 7, 1, 4]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.036288255928571427], 0, 3.0173754692077637, 1688551945.511079], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 585801, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 8]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 1, 14, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00024168908618082854], 0, 3.17565655708313, 1688551955.8830361], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 15648773, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 16]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.027624845504760742, 1688551946.6522727], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2671329, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 16, 2]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 7, 2, 2]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.024519920349121094, 1688551946.6522918], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 16620184, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 2]], ["tile_y", "sp", [-1, 1, 14, 2]], ["tile_x", "sp", [-1, 7, 2, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0003588603125833704], 0, 4.65841007232666, 1688551958.9132845], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 10090565, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 1]], ["tile_y", "sp", [-1, 1, 14, 2]], ["tile_x", "sp", [-1, 1, 14, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03720808029174805, 1688551948.0139918], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1827739, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 32]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 2, 2, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.021737098693847656, 1688551948.0140057], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 16853536, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 256]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 1, 4, 7]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.006298263452830188], 0, 2.813248634338379, 1688551960.3940415], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 5521703, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 1, 4]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0013669056707650276], 0, 2.4252729415893555, 1688551961.78301], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2639489, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 2, 1, 14]], ["tile_x", "sp", [-1, 2, 1, 2]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02282857894897461, 1688551948.0140178], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 5177676, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 32]], ["tile_y", "sp", [-1, 4, 7, 1]], ["tile_x", "sp", [-1, 7, 1, 4]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03653693199157715, 1688551948.0140252], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13455882, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 14, 2, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.005292651684210527], 0, 7.942459344863892, 1688551963.268116], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 8897262, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 4, 1, 1]], ["tile_x", "sp", [-1, 7, 4, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03409576416015625, 1688551952.8501244], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 5465420, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 16]], ["tile_y", "sp", [-1, 4, 1, 1]], ["tile_x", "sp", [-1, 14, 1, 2]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03461885452270508, 1688551952.850138], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 12503845, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 8]], ["tile_y", "sp", [-1, 1, 4, 7]], ["tile_x", "sp", [-1, 7, 1, 2]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02674078941345215, 1688551952.850146], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2734554, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 16]], ["tile_y", "sp", [-1, 1, 7, 4]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.027474403381347656, 1688551952.8501544], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7304017, "code_hash": null, "entity": [["tile_f", "sp", [-1, 128, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0201125476], 0, 4.434734106063843, 1688551964.862712], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 16461317, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 16, 1]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00015185346826144283], 0, 3.563082456588745, 1688551967.8427594], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 18328697, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 4, 1, 7]], ["tile_x", "sp", [-1, 4, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05717301368713379, 1688551952.8501685], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11525792, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 128]], ["tile_y", "sp", [-1, 1, 7, 4]], ["tile_x", "sp", [-1, 1, 7, 4]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02605915069580078, 1688551952.8501754], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3759558, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 32]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 1, 1, 4]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0054656028524590165], 0, 2.076817512512207, 1688551969.3653247], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7966997, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 2, 7, 2]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.028931856155395508, 1688551952.8501866], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 8996191, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 16]], ["tile_y", "sp", [-1, 7, 4, 1]], ["tile_x", "sp", [-1, 1, 2, 2]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.024674177169799805, 1688551952.8501937], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 15382284, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 28]], ["tile_x", "sp", [-1, 1, 1, 4]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.023958206176757812, 1688551952.8502004], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 17468259, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 16, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 2, 7, 2]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002888672659631551], 0, 4.2523722648620605, 1688551972.3545802], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 12720197, "code_hash": null, "entity": [["tile_f", "sp", [-1, 128, 2, 1]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 28, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.08172492975], 0, 9.317322015762329, 1688551974.9922173], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13346685, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 1, 14, 2]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0030892752160493826], 0, 3.723978042602539, 1688551976.4884272], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3343849, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 2]], ["tile_y", "sp", [-1, 1, 1, 28]], ["tile_x", "sp", [-1, 2, 1, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.1852548095], 0, 4.150162220001221, 1688551978.8987608], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 16463420, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 8]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.012475290555555555], 0, 5.056495189666748, 1688551980.445701], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1022237, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 4]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0004138923137957512], 0, 3.453965902328491, 1688551983.4916854], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 8949212, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 256, 1]], ["tile_y", "sp", [-1, 1, 2, 14]], ["tile_x", "sp", [-1, 2, 14, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.028812885284423828, 1688551953.0808864], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13660831, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 8]], ["tile_y", "sp", [-1, 4, 7, 1]], ["tile_x", "sp", [-1, 4, 1, 7]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.049437522888183594, 1688551953.080895], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 5208992, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 256, 1]], ["tile_y", "sp", [-1, 2, 1, 14]], ["tile_x", "sp", [-1, 2, 1, 7]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.024983644485473633, 1688551953.0809019], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 15018035, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 16]], ["tile_y", "sp", [-1, 7, 2, 2]], ["tile_x", "sp", [-1, 1, 14, 2]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04538679122924805, 1688551953.0809095], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 6022538, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 16, 1]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.026203632354736328, 1688551953.0809174], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 56, 56], "float32"], ["TENSOR", [512, 256, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 633833, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 4, 1, 7]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0063930014777070065], 0, 2.236398696899414, 1688551984.9516633], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 14249404, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 2, 1, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[7.926894300284987e-05], 0, 3.2826948165893555, 1688551998.5633492], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 15087826, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 1, 1]], ["tile_y", "sp", [-1, 14, 1, 2]], ["tile_x", "sp", [-1, 2, 2, 7]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688551995.7674117], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 52990, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 32]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 2, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003499558833838165], 0, 3.311133623123169, 1688552001.5366528], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 10787843, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 4, 7]], ["tile_x", "sp", [-1, 2, 7, 2]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04460763931274414, 1688551995.767459], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11605842, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 16]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 1, 2, 14]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.004245477966101695], 0, 2.8482861518859863, 1688552002.9671474], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7597829, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 16, 4]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 7, 2, 2]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.029417037963867188, 1688551995.7674718], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 12939780, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 1, 28, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[4.175598798007979e-05], 0, 3.375253200531006, 1688552005.9631207], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3146746, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 7, 2, 2]], ["tile_x", "sp", [-1, 2, 1, 14]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0022977362110091744], 0, 4.859665155410767, 1688552007.3485627], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2895953, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 32, 2]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 14, 2, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688551995.775486], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3872066, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005442615033670033], 0, 3.3162221908569336, 1688552010.3442597], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7909929, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 128, 1]], ["tile_y", "sp", [-1, 2, 2, 7]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.0224301815032959, 1688551995.775501], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 15344240, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 4, 4]], ["tile_y", "sp", [-1, 1, 14, 2]], ["tile_x", "sp", [-1, 7, 2, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688551995.7755592], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11802129, "code_hash": null, "entity": [["tile_f", "sp", [-1, 512, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 14, 1, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688551995.7772324], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 15374747, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 64, 1]], ["tile_y", "sp", [-1, 28, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 4]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006297153283989093], 0, 6.373523235321045, 1688552013.3645866], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 15692239, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 7, 2, 2]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00010967197895668755], 0, 4.956320285797119, 1688552016.3372362], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2442956, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 2]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 2, 1, 14]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.025474071502685547, 1688551995.777247], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 9173059, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 8]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 4, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[8.377004863965042e-05], 0, 3.2954225540161133, 1688552019.293706], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4191464, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 4, 1]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00034321483384080033], 0, 3.9170312881469727, 1688552022.2856264], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1097387, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 7, 1, 4]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006589281288743882], 0, 4.383613586425781, 1688552025.2632022], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11097977, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 4, 2]], ["tile_y", "sp", [-1, 28, 1, 1]], ["tile_x", "sp", [-1, 14, 1, 2]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.024305105209350586, 1688551995.7772603], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 8277655, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 8]], ["tile_y", "sp", [-1, 2, 7, 2]], ["tile_x", "sp", [-1, 7, 1, 2]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.033125877380371094, 1688551995.7772682], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 10985470, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 128]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 7, 2, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.024729490280151367, 1688551995.7772753], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 6572875, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 8]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 1, 14, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006673694816343377], 0, 3.6689047813415527, 1688552028.2450838], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13990254, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 1]], ["tile_y", "sp", [-1, 4, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 4]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03794217109680176, 1688551995.7772844], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13908856, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 2, 1]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 7, 1, 2]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.041406869888305664, 1688551995.7772918], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 10158641, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 8]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 2, 2, 7]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.004893363812121212], 0, 4.1044762134552, 1688552031.3183763], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 9271540, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 7, 2, 2]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[6.980497325970696e-05], 0, 3.375399351119995, 1688552034.2828183], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7603234, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[4.25569496962592e-05], 0, 3.3621814250946045, 1688552037.2292104], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 10884388, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 2, 2, 7]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0229799747467041, 1688551995.7773037], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11510283, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 28]], ["tile_x", "sp", [-1, 1, 1, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.018036077214285712], 0, 2.3881683349609375, 1688552038.8525946], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4359558, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 16, 1]], ["tile_y", "sp", [-1, 2, 14, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03507089614868164, 1688551995.7773142], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 10705557, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 14, 1, 2]], ["tile_x", "sp", [-1, 2, 14, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04450821876525879, 1688551995.7773223], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 858486, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 64, 1]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03340315818786621, 1688551995.7773294], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 254426, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 7, 1, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 4, 4.109633684158325, 1688552039.2957041], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [512, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 5952083, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 64]], ["tile_y", "sp", [-1, 4, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.019740611352941178], 0, 4.487509727478027, 1688552040.9032156], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3620828, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 4]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 2, 2, 7]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.025556564331054688, 1688552041.7092834], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 216105, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 16]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 28, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00452340036056338], 0, 3.4114367961883545, 1688552054.557335], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 9896874, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 32]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 14, 1, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688552051.6831748], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 9140392, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 32]], ["tile_y", "sp", [-1, 14, 2, 1]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03236889839172363, 1688552051.6831996], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 5626236, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 28, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.021123886108398438, 1688552051.6832106], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3025869, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 4]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.004826850934131737], 0, 5.437161207199097, 1688552057.581822], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11268376, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 7, 2, 2]], ["tile_x", "sp", [-1, 1, 1, 4]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.029442548751831055, 1688552051.6832194], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2145069, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 4]], ["tile_y", "sp", [-1, 1, 4, 7]], ["tile_x", "sp", [-1, 1, 2, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00713338735460993], 0, 2.7212412357330322, 1688552059.0159662], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4711114, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 64, 1]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 14, 1, 2]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003397889684409847], 0, 4.416742563247681, 1688552062.0252082], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3662973, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 8]], ["tile_y", "sp", [-1, 14, 1, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.06904006004333496, 1688552051.6832309], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4141564, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 1, 2, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00036826404421148585], 0, 3.4618823528289795, 1688552065.0145578], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1883872, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 32]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 4, 1, 7]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02154374122619629, 1688552051.6832457], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 8802421, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 2]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 1, 2, 7]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00020839378530854635], 0, 4.227169513702393, 1688552068.0089707], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3085540, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 4, 1, 7]], ["tile_x", "sp", [-1, 4, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.08505267331250001], 0, 3.547441244125366, 1688552070.7063293], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 9826614, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 2, 2, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[9.853269046891239e-05], 0, 3.313042163848877, 1688552073.7127533], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1695332, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 8]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 1, 2, 7]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02449345588684082, 1688552051.683258], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1001612, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 8]], ["tile_y", "sp", [-1, 1, 14, 2]], ["tile_x", "sp", [-1, 7, 2, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.028825998306274414, 1688552051.6832669], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7216195, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 32]], ["tile_y", "sp", [-1, 4, 7, 1]], ["tile_x", "sp", [-1, 7, 2, 2]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.028272151947021484, 1688552051.683274], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 5252166, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 1, 1]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 4, 7, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.028902769088745117, 1688552051.683281], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 6240294, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 4, 1, 1]], ["tile_x", "sp", [-1, 7, 1, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00015102555300403037], 0, 3.456819534301758, 1688552076.6751602], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 5285753, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 32]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 14, 1, 2]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04576873779296875, 1688552051.6832895], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3707935, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.025180578231811523, 1688552051.6832967], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3924780, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 2]], ["tile_y", "sp", [-1, 1, 14, 2]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.024306535720825195, 1688552051.6833048], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2798420, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 7, 2, 2]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.001781530412811388], 0, 2.6120193004608154, 1688552078.09026], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1390541, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 14, 2, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.025137662887573242, 1688552051.6833143], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 9543448, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 8]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 7, 1, 4]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.08670544624328613, 1688552051.6833205], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11219775, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.034898996353149414, 1688552051.6833286], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 10319431, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 1]], ["tile_y", "sp", [-1, 1, 4, 7]], ["tile_x", "sp", [-1, 1, 7, 4]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.000705207006538797], 0, 3.7265613079071045, 1688552081.064892], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7627075, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 32]], ["tile_y", "sp", [-1, 1, 2, 14]], ["tile_x", "sp", [-1, 7, 1, 4]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.021971940994262695, 1688552051.683336], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3686309, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 28]], ["tile_x", "sp", [-1, 2, 2, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.0302889347076416, 1688552051.6833417], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 5063822, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 2]], ["tile_y", "sp", [-1, 1, 2, 14]], ["tile_x", "sp", [-1, 4, 7, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.025601625442504883, 1688552051.6833482], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 8459592, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 2, 14, 1]], ["tile_x", "sp", [-1, 4, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001989977147258164], 0, 3.8546059131622314, 1688552084.0432339], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4847264, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 16]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 14, 2, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.023259639739990234, 1688552051.6833565], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4867743, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 2]], ["tile_y", "sp", [-1, 14, 1, 1]], ["tile_x", "sp", [-1, 4, 7, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.12123823165893555, 1688552051.6833627], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [128, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 6322484, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 2, 1, 14]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0004637818152610442], 0, 3.504974126815796, 1688552087.1181645], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 18696318, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 4]], ["tile_y", "sp", [-1, 4, 1, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00045714162950257295], 0, 3.4004600048065186, 1688552097.6974328], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 30641338, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 7, 2, 2]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.07222199440002441, 1688552089.2088852], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2840337, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 2]], ["tile_y", "sp", [-1, 1, 7, 4]], ["tile_x", "sp", [-1, 2, 1, 7]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.13074254989624023, 1688552089.2089033], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4515004, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 2, 7, 2]], ["tile_x", "sp", [-1, 7, 1, 2]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.0364687442779541, 1688552089.2089126], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 33516959, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 128]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 1, 2, 2]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.11368346214294434, 1688552089.2089202], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4727684, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 2, 1, 14]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0020287059594320486], 0, 2.156611204147339, 1688552099.1093166], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 235237, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 14, 2, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0007708484804575786], 0, 3.5091140270233154, 1688552102.0855405], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 18239417, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 1, 4, 7]], ["tile_x", "sp", [-1, 1, 1, 28]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02722001075744629, 1688552089.2089338], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7563684, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 4]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.032010555267333984, 1688552089.2089412], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 26739416, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 7, 1, 4]], ["tile_x", "sp", [-1, 1, 4, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0007691189505468379], 0, 4.510901212692261, 1688552105.0913], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 30605207, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 2]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 2, 14, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0845041275024414, 1688552089.5305917], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 30116090, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 2]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 2, 2, 7]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00023361179132321043], 0, 5.02453875541687, 1688552108.1055608], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2787756, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 2, 1, 7]], ["tile_x", "sp", [-1, 7, 1, 2]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03621268272399902, 1688552090.0333853], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 12849990, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 2, 1, 14]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0027769376371191137], 0, 2.9237892627716064, 1688552109.489927], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 24220637, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 4]], ["tile_y", "sp", [-1, 1, 2, 14]], ["tile_x", "sp", [-1, 28, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.040407657623291016, 1688552090.0333998], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2925489, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 14, 2, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04208850860595703, 1688552090.0334072], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 35210203, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 2]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00016996188768306816], 0, 9.848716974258423, 1688552112.4635913], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5143231, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 1]], ["tile_y", "sp", [-1, 7, 1, 2]], ["tile_x", "sp", [-1, 2, 1, 7]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0038375361034482755], 0, 2.869245767593384, 1688552113.8959699], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 30108551, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 4, 1, 7]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00377675919245283], 0, 5.220366477966309, 1688552115.3097937], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3462413, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 2]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 2, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0012710976111817026], 0, 1.944580316543579, 1688552116.6791866], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14241252, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 1]], ["tile_y", "sp", [-1, 2, 1, 14]], ["tile_x", "sp", [-1, 1, 2, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0028198005297202797], 0, 4.522234916687012, 1688552119.7206328], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 31230734, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 2, 1]], ["tile_y", "sp", [-1, 2, 14, 1]], ["tile_x", "sp", [-1, 1, 14, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.006114054237804877], 0, 4.323694705963135, 1688552121.1505032], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 29497726, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 2]], ["tile_y", "sp", [-1, 4, 7, 1]], ["tile_x", "sp", [-1, 2, 7, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0015218087507598782], 0, 3.7542378902435303, 1688552122.5280519], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 16340553, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 1]], ["tile_y", "sp", [-1, 7, 4, 1]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.09003686904907227, 1688552094.9054978], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 34172292, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 1]], ["tile_y", "sp", [-1, 14, 2, 1]], ["tile_x", "sp", [-1, 1, 1, 28]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.085167167625], 0, 8.149657487869263, 1688552125.225679], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 19076878, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 64]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 4, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.014710377411764704], 0, 2.350360155105591, 1688552126.7617724], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1346349, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 4]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02851390838623047, 1688552094.9055161], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1539199, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 1, 14, 2]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00017085478280638678], 0, 3.4260497093200684, 1688552129.7436042], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 22188796, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 4]], ["tile_y", "sp", [-1, 1, 14, 2]], ["tile_x", "sp", [-1, 1, 2, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00012423054204887074], 0, 3.4936025142669678, 1688552132.749044], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8261648, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 2, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0004192327060653188], 0, 3.630312919616699, 1688552135.7250104], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 829200, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.002354400131764706], 0, 1.8946607112884521, 1688552137.1243308], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 17074260, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 2]], ["tile_y", "sp", [-1, 28, 1, 1]], ["tile_x", "sp", [-1, 2, 1, 14]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.09054361718750001], 0, 4.6458659172058105, 1688552139.9663386], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 24699327, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 2, 7, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0068124630408163255], 0, 4.562024116516113, 1688552141.4199564], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8948978, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 8]], ["tile_y", "sp", [-1, 4, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.07473111152648926, 1688552094.9055345], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 12334141, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 2]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 14, 2, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0011114154722222222], 0, 1.921785593032837, 1688552142.8086247], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 460080, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 2, 98, 1]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.34873318672180176, 1688552143.9226966], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 58068, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 16]], ["tile_x", "sp", [-1, 7, 2, 14]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.002706971697297297], 0, 2.9549813270568848, 1688552154.9600487], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 79269, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 1, 4]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.05741038677777778], 0, 3.9102959632873535, 1688552156.989975], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 549721, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 14, 1, 14]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0019313015135135137], 0, 4.483304500579834, 1688552158.4433768], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 249202, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 4]], ["tile_x", "sp", [-1, 2, 14, 7]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[4.542637459597392e-05], 0, 3.9418601989746094, 1688552161.3865764], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 561901, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 2]], ["tile_x", "sp", [-1, 1, 2, 14]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.363422482297817e-05], 0, 4.060515880584717, 1688552164.3596988], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 405966, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 64, 1, 1]], ["tile_x", "sp", [-1, 7, 2, 14]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688552153.6930175], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 420915, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 98, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0018342229022988506], 0, 6.229168653488159, 1688552167.3694882], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 404933, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 4, 2]], ["tile_x", "sp", [-1, 4, 7, 7]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0016352593583756345], 0, 4.860623121261597, 1688552170.3544574], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 403628, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 4]], ["tile_x", "sp", [-1, 7, 1, 7]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.05064366145], 0, 5.245931386947632, 1688552172.300446], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 222708, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 16]], ["tile_x", "sp", [-1, 7, 1, 4]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.003247552584126984], 0, 3.510618209838867, 1688552173.7520442], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 534453, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 8]], ["tile_x", "sp", [-1, 1, 98, 2]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[6.909305053500065e-05], 0, 4.158297061920166, 1688552176.7316368], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 505328, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 7, 2, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002606773720967742], 0, 6.569048881530762, 1688552179.707079], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 531345, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 16]], ["tile_x", "sp", [-1, 14, 14, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006860922541648869], 0, 5.842670917510986, 1688552182.7028377], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 131720, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 4]], ["tile_x", "sp", [-1, 2, 1, 98]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0018237255028248586], 0, 6.482093334197998, 1688552185.7115195], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 445499, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 16, 2]], ["tile_x", "sp", [-1, 14, 2, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[3.616350340800654e-05], 0, 4.459282875061035, 1688552188.6554658], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 227779, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 4, 1]], ["tile_x", "sp", [-1, 1, 2, 98]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.003409689951271187], 0, 4.025632381439209, 1688552191.6894193], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 556900, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 16]], ["tile_x", "sp", [-1, 49, 1, 2]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.029330081600000002], 0, 6.190956115722656, 1688552193.4336104], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 492750, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 1]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.41245790325845e-05], 0, 3.901341676712036, 1688552196.404343], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 531015, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 2, 14, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[4.625249458890075e-05], 0, 4.179037094116211, 1688552199.4017467], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 72675, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 28, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00010505731921696573], 0, 3.957980155944824, 1688552202.3711233], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 516797, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 4]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00356424200443459], 0, 9.805436372756958, 1688552205.3852322], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 265542, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 16]], ["tile_x", "sp", [-1, 14, 2, 1]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.003580891563474388], 0, 7.202893257141113, 1688552208.420008], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 544640, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 4]], ["tile_x", "sp", [-1, 7, 1, 2]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[7.505384986007464e-05], 0, 5.0295233726501465, 1688552211.37327], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 400924, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 1]], ["tile_x", "sp", [-1, 98, 1, 2]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.044422856869565215], 0, 2.9068171977996826, 1688552213.2484033], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 98468, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 4]], ["tile_x", "sp", [-1, 4, 7, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.00020511775549345867], 0, 4.066354513168335, 1688552216.2880363], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 219296, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 2]], ["tile_x", "sp", [-1, 14, 14, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[4.4661146022885845e-05], 0, 3.9868462085723877, 1688552219.2438204], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 393001, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 14, 7]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[7.732896877701988e-05], 0, 3.712204933166504, 1688552222.1972115], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 516897, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 8, 2]], ["tile_x", "sp", [-1, 98, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688552153.6931248], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 366178, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 2]], ["tile_x", "sp", [-1, 1, 49, 2]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[3.212272361535984e-05], 0, 3.838618040084839, 1688552225.1932726], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 498996, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 7, 7, 4]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00011350706233637587], 0, 3.9530856609344482, 1688552228.1412973], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 260763, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 1]], ["tile_x", "sp", [-1, 2, 7, 7]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[8.175577864384328e-05], 0, 4.61759090423584, 1688552231.0851536], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 327458, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 8]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[3.096284052942438e-05], 0, 3.6431119441986084, 1688552234.0701406], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 425914, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 64, 1]], ["tile_x", "sp", [-1, 1, 14, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[4.0376711655976974e-05], 0, 3.728156805038452, 1688552237.008433], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 128, 28, 28], "float32"], ["TENSOR", [128, 128, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 557733, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 8]], ["tile_x", "sp", [-1, 7, 7, 2]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.29679298400878906, 1688552153.6931539], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4608320, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 14, 2, 1]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00012818573857786356], 0, 3.882944107055664, 1688552250.6035826], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1476298, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 128, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 7, 2, 2]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02393317222595215, 1688552238.88607], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3531382, "code_hash": null, "entity": [["tile_f", "sp", [-1, 128, 1, 2]], ["tile_y", "sp", [-1, 4, 1, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.007914528188976377], 0, 5.2583630084991455, 1688552252.054293], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 5393866, "code_hash": null, "entity": [["tile_f", "sp", [-1, 128, 2, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005593590221376687], 0, 3.343229293823242, 1688552255.0343943], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 14077498, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 8, 1]], ["tile_y", "sp", [-1, 1, 2, 14]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00041122615114503816], 0, 4.067917346954346, 1688552258.049804], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 9002835, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 4]], ["tile_y", "sp", [-1, 4, 1, 1]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.004296400862660944], 0, 5.446639060974121, 1688552259.4863224], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 12230798, "code_hash": null, "entity": [["tile_f", "sp", [-1, 256, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03490281105041504, 1688552241.9046576], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 6474845, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 128, 2]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 14, 1, 2]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.024662494659423828, 1688552241.9046714], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 6390206, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 4]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 7, 2, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688552247.8097517], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11702748, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 8]], ["tile_y", "sp", [-1, 28, 1, 1]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688552247.8152356], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2692770, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 16]], ["tile_y", "sp", [-1, 1, 1, 28]], ["tile_x", "sp", [-1, 2, 2, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0019066345781990522], 0, 3.4102489948272705, 1688552262.4694612], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 15261577, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 4, 7, 1]], ["tile_x", "sp", [-1, 4, 1, 7]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.06251144409179688, 1688552247.8152575], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7240101, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 28]], ["tile_x", "sp", [-1, 2, 14, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.043569087982177734, 1688552247.8152664], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 14596643, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 7, 4, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03847241401672363, 1688552247.815274], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13394399, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 7, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008115890968389362], 0, 3.8666744232177734, 1688552265.503504], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2382380, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 1, 2, 14]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.021776437759399414, 1688552247.8152847], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 15118692, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 7, 1, 4]], ["tile_x", "sp", [-1, 1, 4, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.051396846771240234, 1688552247.8152912], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 9676985, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 4, 2]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 1, 14, 2]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03140425682067871, 1688552247.8152983], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 555229, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 28, 1, 1]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.20241008300000002], 0, 11.95055365562439, 1688552268.0886226], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 6098616, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 1, 2]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688552247.8153546], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1352514, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 2, 1, 14]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04279971122741699, 1688552247.8153636], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 8640288, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 2]], ["tile_y", "sp", [-1, 28, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 4]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00877651549122807], 0, 3.0037524700164795, 1688552269.588824], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 12612133, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 8, 1]], ["tile_y", "sp", [-1, 2, 1, 14]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.028020381927490234, 1688552247.8153727], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2467465, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 2]], ["tile_y", "sp", [-1, 2, 2, 7]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02840423583984375, 1688552247.8153796], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 182615, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 8]], ["tile_y", "sp", [-1, 1, 14, 2]], ["tile_x", "sp", [-1, 1, 1, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002741573730279898], 0, 3.3556790351867676, 1688552272.6024137], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 10995605, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 14, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00012243870373185376], 0, 3.4377191066741943, 1688552275.5941083], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 9354814, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 16]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02609872817993164, 1688552247.8153908], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 8293337, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 4]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 2, 14, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00034697464255045084], 0, 3.2689528465270996, 1688552278.573657], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3891181, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 32]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 1, 7, 4]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.004245734004237289], 0, 2.4860804080963135, 1688552280.020518], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1161756, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 64]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 2, 14, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0023265947186046514], 0, 1.896942138671875, 1688552281.4095805], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 6948072, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 1, 4]], ["tile_y", "sp", [-1, 1, 7, 4]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.027273893356323242, 1688552247.8154042], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3364684, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 4]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.009283944018518519], 0, 3.4990274906158447, 1688552282.8899443], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2966294, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 1, 28, 1]], ["tile_x", "sp", [-1, 14, 2, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00022259146417745937], 0, 3.581738233566284, 1688552285.9096723], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 8514785, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 8]], ["tile_y", "sp", [-1, 14, 1, 1]], ["tile_x", "sp", [-1, 1, 4, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00037100103353238404], 0, 3.632723808288574, 1688552288.924506], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [256, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 6890968, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 2]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04959368705749512, 1688552247.8154168], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4241926, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 4]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00032853750833333333], 0, 3.399209499359131, 1688552303.3527653], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4424304, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 64]], ["tile_y", "sp", [-1, 2, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.05507826805114746, 1688552291.095782], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6006106, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.026302337646484375, 1688552291.0957992], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8485404, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 8]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 2, 7]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.28157644039999996], 0, 10.815703868865967, 1688552306.8291912], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2637857, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 14, 1, 1]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.035607337951660156, 1688552297.1772535], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 195574, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 7, 1, 2]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.1263259643], 0, 3.6030211448669434, 1688552308.676522], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4133304, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 7, 1, 2]], ["tile_x", "sp", [-1, 2, 1, 7]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02889227867126465, 1688552297.1772711], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1298476, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 4]], ["tile_y", "sp", [-1, 2, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.017863734642857145], 0, 2.994053840637207, 1688552310.2490585], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5285059, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 2, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.024869203567504883, 1688552297.1772811], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4991460, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.007184983607142857], 0, 1.9389867782592773, 1688552311.6945295], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7113467, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 32]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0860750675201416, 1688552297.1772904], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6416337, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 32]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 2, 7]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0590968132019043, 1688552297.1773014], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8658556, "code_hash": null, "entity": [["tile_f", "sp", [-1, 128, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.029462814331054688, 1688552297.1773095], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1666410, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 2]], ["tile_y", "sp", [-1, 14, 1, 1]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0014577908965014575], 0, 2.5520706176757812, 1688552313.1584423], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4580279, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 256, 1]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.027704715728759766, 1688552297.1773205], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4007638, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 2, 7]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.018655060944444444], 0, 3.1681926250457764, 1688552314.735136], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3296988, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 8]], ["tile_y", "sp", [-1, 2, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.025818586349487305, 1688552297.1773343], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2783605, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 2]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 2, 7]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0013382220447390222], 0, 4.473735094070435, 1688552317.7253366], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1065727, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 64]], ["tile_y", "sp", [-1, 7, 1, 2]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.09981131553649902, 1688552297.1773438], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3009757, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 64]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 2, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.024512529373168945, 1688552297.1773527], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8246799, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05156111717224121, 1688552297.1773615], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5936009, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 16]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0332341194152832, 1688552297.1773684], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3209447, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0029250650672514623], 0, 3.0233750343322754, 1688552319.1640396], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8140772, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 7, 1, 2]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688552299.7694592], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3279443, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 14, 1, 1]], ["tile_x", "sp", [-1, 7, 1, 2]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.10340404510498047, 1688552299.7694738], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5185108, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 32]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.024997234344482422, 1688552299.7694812], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 183589, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 7, 2, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.018984535056603774], 0, 2.108917236328125, 1688552320.737323], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7414018, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 2]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04932546615600586, 1688552299.7694905], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8705765, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 7, 1, 2]], ["tile_x", "sp", [-1, 2, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.046367645263671875, 1688552299.7694974], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8026825, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 8, 2]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006190811558789736], 0, 5.357095003128052, 1688552323.7730577], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6695432, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 2]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04644489288330078, 1688552299.769506], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1173405, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.004123976716049383], 0, 2.341984987258911, 1688552325.223728], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7715352, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 8]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 7, 1, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688552300.5245807], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5364757, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 8]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0020483478884664136], 0, 3.6857340335845947, 1688552328.2575107], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 28, 28], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6025741, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 4]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 7, 1, 2]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.12994599342346191, 1688552300.524597], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 405608, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 256, 1]], ["tile_y", "sp", [-1, 7, 1, 2]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.025878429412841797, 1688552329.0564046], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1826306, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 8]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006904399650259067], 0, 3.5431368350982666, 1688552341.886694], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2693699, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 7, 1, 2]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.024399757385253906, 1688552329.7692792], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3193864, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 2]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005069024653496394], 0, 4.12739896774292, 1688552344.899254], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2016011, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 512]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.024252891540527344, 1688552330.2511199], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2066891, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 64]], ["tile_y", "sp", [-1, 7, 1, 2]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.047742366790771484, 1688552330.2511322], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2892015, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 128]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.023252010345458984, 1688552330.2511404], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2559049, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 16]], ["tile_y", "sp", [-1, 14, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03337359428405762, 1688552330.2511475], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3148570, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 512]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.016139792161290325], 0, 5.919701099395752, 1688552346.4505546], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2469830, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 16]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00045989024501992033], 0, 3.3409006595611572, 1688552349.5129719], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1493054, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 4]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002680756090999668], 0, 3.300185203552246, 1688552352.5002468], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2079927, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 4]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.029265642166137695, 1688552333.5283735], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1508985, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 32, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0007374531298997264], 0, 3.3516881465911865, 1688552355.4892058], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3228274, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 8]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 2, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[9.280053447878228e-05], 0, 3.8177878856658936, 1688552358.5250022], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4015347, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 8]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 2, 1, 7]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04003143310546875, 1688552333.5283859], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 124578, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 8]], ["tile_y", "sp", [-1, 14, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.013277575039473685], 0, 2.4191770553588867, 1688552360.0446846], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1446016, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.013224124302631578], 0, 2.463158369064331, 1688552361.5788553], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 559019, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 8]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 7, 1, 2]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03245687484741211, 1688552333.5283978], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4095694, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0003933326825147347], 0, 3.792144536972046, 1688552363.0025506], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1957237, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 4]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03074026107788086, 1688552333.5284073], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3054796, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001154805534287976], 0, 3.22296404838562, 1688552365.959746], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2094926, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 64]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.021494150161743164, 1688552333.5284164], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1017962, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 2]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 1, 2, 7]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0008474262409638554], 0, 4.633928060531616, 1688552368.9680116], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3046334, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 4]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00027494791994549483], 0, 3.6239640712738037, 1688552371.9970763], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2578481, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 8, 8]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.030277729034423828, 1688552333.5284352], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 206484, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 256]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 2, 1, 7]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 4, 10.91480016708374, 1688552382.2186491], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1450114, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.023174524307250977, 1688552333.5284436], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3548974, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.025604248046875, 1688552333.528452], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1947961, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 1]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688552339.0761807], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 528199, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 32]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.05592656135559082, 1688552339.0762], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4099429, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 8, 8]], ["tile_y", "sp", [-1, 2, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.031061649322509766, 1688552339.0762076], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4071892, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 32, 2]], ["tile_y", "sp", [-1, 2, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.08213305473327637, 1688552339.0762148], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2537997, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 7, 1, 2]], ["tile_x", "sp", [-1, 7, 1, 2]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05093646049499512, 1688552339.076222], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 697233, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 64]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02439737319946289, 1688552339.07623], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 28, 28], "float32"], ["TENSOR", [1024, 512, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3272955, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 64]], ["tile_y", "sp", [-1, 14, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03577113151550293, 1688552339.0762372], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2648514, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 16, 4]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.014180784408450704], 0, 10.523282289505005, 1688552394.4196289], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3238031, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 16]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.1231997013092041, 1688552392.802658], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3598631, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 8]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688552393.0353124], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3454576, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 128]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0765733795], 0, 10.419243335723877, 1688552396.864974], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2527726, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 128, 1]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02398204803466797, 1688552393.0353346], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 45546, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.1850030029], 0, 3.640681266784668, 1688552399.4057066], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 241007, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 16, 8]], ["tile_y", "sp", [-1, 7, 1, 2]], ["tile_x", "sp", [-1, 1, 2, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0021165322410147992], 0, 2.3770172595977783, 1688552400.8519435], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3938896, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 16, 2]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.08845400810241699, 1688552393.0353472], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1539657, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 256, 2]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02287745475769043, 1688552393.0353546], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 584617, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.039778709411621094, 1688552393.0353618], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2963660, "code_hash": null, "entity": [["tile_f", "sp", [-1, 128, 1, 4]], ["tile_y", "sp", [-1, 7, 1, 2]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688552393.0423467], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 157021, "code_hash": null, "entity": [["tile_f", "sp", [-1, 128, 1, 1]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688552393.042595], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3530397, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[7.703956615177972e-05], 0, 3.845651626586914, 1688552403.8026502], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3339042, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 256]], ["tile_y", "sp", [-1, 7, 1, 2]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.2539659179], 0, 6.20799446105957, 1688552406.972812], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1378368, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 4]], ["tile_y", "sp", [-1, 14, 1, 1]], ["tile_x", "sp", [-1, 2, 1, 7]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.03834170644444444], 0, 4.953152656555176, 1688552408.9008634], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1850453, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 2, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[4.2779825071103905e-05], 0, 5.537470579147339, 1688552411.923807], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1902779, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 2, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02083587646484375, 1688552393.042614], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2727021, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0003611160232506148], 0, 4.4282262325286865, 1688552414.901671], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1507619, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 64, 2]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00014785675717034728], 0, 3.3278603553771973, 1688552417.8958158], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1313411, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03589630126953125, 1688552393.0426252], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3604467, "code_hash": null, "entity": [["tile_f", "sp", [-1, 512, 1, 1]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688552393.0493612], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3211126, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 16]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 2, 1, 7]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05051565170288086, 1688552393.0493712], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1413434, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 1, 2, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[5.5711685752930565e-05], 0, 3.3463025093078613, 1688552420.8780742], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2519177, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 2]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.07869720458984375, 1688552393.04938], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1754025, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 128]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04766082763671875, 1688552393.0493867], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1180050, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 2, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0001388738054684779], 0, 4.305495262145996, 1688552423.8134432], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2227194, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 64, 2]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.09164595603942871, 1688552393.0493965], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3382917, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 32, 2]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00027289340216289285], 0, 4.166860580444336, 1688552426.831492], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1449859, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 4]], ["tile_y", "sp", [-1, 2, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.123932666], 0, 3.2127015590667725, 1688552428.6116536], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 101437, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 8]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00012864499361583273], 0, 3.516038417816162, 1688552431.5994396], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1027860, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 64]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.06624031066894531, 1688552393.0494096], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2102173, "code_hash": null, "entity": [["tile_f", "sp", [-1, 128, 1, 2]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.010901982836956522], 0, 3.0498015880584717, 1688552433.1305947], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3000978, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 128]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.07548461149999999], 0, 3.696244955062866, 1688552435.5276694], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1466399, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[6.325779641565792e-05], 0, 3.4060943126678467, 1688552438.5333626], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [1024, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 875684, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 32]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.243999121], 0, 6.218523740768433, 1688552441.6286092], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1545393, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00011508815266898751], 0, 3.2321245670318604, 1688552455.2328439], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 69388, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 7, 1, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003011286773472429], 0, 3.3520846366882324, 1688552458.201961], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2755952, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 8]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 1024]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.042626380920410156, 1688552443.5648143], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1227488, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 2]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00025034703456328815], 0, 6.066858530044556, 1688552461.1883018], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2259425, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 128, 2]], ["tile_y", "sp", [-1, 2, 1, 7]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.033132314682006836, 1688552445.5902755], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 294463, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.024648666381835938, 1688552445.5902917], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 109448, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 2]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00010417020032404407], 0, 3.477726459503174, 1688552464.191507], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 879886, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 4]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 2, 1, 7]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.021847963333129883, 1688552445.5903044], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 794991, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 2, 1, 7]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.022843360900878906, 1688552445.590313], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1100726, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002457951580066849], 0, 3.854738712310791, 1688552467.1627285], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1193057, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 4]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.042319297790527344, 1688552445.5903225], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1617275, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 2, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00024889113968889576], 0, 3.635042428970337, 1688552470.1617067], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1324734, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 7, 2, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04041647911071777, 1688552445.5903313], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1874618, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 2]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00014781155585106382], 0, 1.7984247207641602, 1688552471.560596], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2011060, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 64, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001870736449594438], 0, 3.6461918354034424, 1688552474.5699522], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2153680, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 4]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0052724789263157885], 0, 7.238189220428467, 1688552475.9915183], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1893535, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 64]], ["tile_y", "sp", [-1, 14, 1, 1]], ["tile_x", "sp", [-1, 2, 1, 7]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.1255229492], 0, 4.470804929733276, 1688552477.806987], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2346567, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 4]], ["tile_y", "sp", [-1, 2, 1, 7]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.004558233640909091], 0, 3.0408761501312256, 1688552479.2617393], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1047022, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 4]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.006308541924528302], 0, 2.8021249771118164, 1688552480.700136], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2453885, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 1]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 2, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001849431932416953], 0, 3.9621200561523438, 1688552483.7056553], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1121308, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 16]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0029008258318840574], 0, 2.181736707687378, 1688552485.096546], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2326243, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 2]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 2, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00046170757840616964], 0, 3.6911532878875732, 1688552488.1010485], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1160074, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 8]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00015455767059499858], 0, 3.7536983489990234, 1688552491.1148906], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2722134, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 8]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0354762077331543, 1688552448.332056], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1168989, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 8]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 7, 1, 2]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.010772424838709677], 0, 3.357868194580078, 1688552492.5929172], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1272901, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 4]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.07276248931884766, 1688552448.3320673], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1868424, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 8]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.001124431073713491], 0, 3.8195908069610596, 1688552495.572984], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1175967, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 2, 1, 7]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0011814810490124359], 0, 4.8638739585876465, 1688552498.6067033], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 500619, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 7, 1, 2]], ["tile_x", "sp", [-1, 2, 1, 7]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.001145076416430595], 0, 3.7493464946746826, 1688552501.6159112], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1509988, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 2]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006241342989969135], 0, 3.5614705085754395, 1688552504.5962186], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2033392, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 4]], ["tile_y", "sp", [-1, 14, 1, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688552452.4422705], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 750094, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.04137640136], 0, 3.1601803302764893, 1688552506.4841568], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1016975, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 128, 2]], ["tile_y", "sp", [-1, 14, 1, 1]], ["tile_x", "sp", [-1, 2, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02895832061767578, 1688552452.4422967], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1936158, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 2]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 2, 1, 7]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006874283767006802], 0, 4.1748247146606445, 1688552509.478868], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [256, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1221340, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 7, 1, 2]], ["tile_x", "sp", [-1, 1, 2, 7]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.1202535629272461, 1688552452.4423075], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1380005, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 7, 1, 2]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.13051652908325195, 1688552511.0965889], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3239573, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 8]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.000752830239416745], 0, 3.9737963676452637, 1688552523.1221101], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5263123, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.030688762664794922, 1688552512.212672], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7531678, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 1, 2, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03337979316711426, 1688552512.212683], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 188833, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 2]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03636670112609863, 1688552512.2126906], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 375950, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 128, 2]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 2, 7]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.031928062438964844, 1688552512.212701], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 405092, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00021514220735607676], 0, 3.397374153137207, 1688552526.1281483], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4203469, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 14, 1, 1]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00047967063957282707], 0, 3.637895345687866, 1688552529.1115806], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6820852, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 7, 1, 2]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04337286949157715, 1688552512.2127113], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7475477, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 32]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05285763740539551, 1688552512.212721], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1535465, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 16]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 7, 2, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.011565668206896551], 0, 2.6638412475585938, 1688552530.6479204], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6477155, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 128, 2]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 7, 2, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0436093807220459, 1688552512.2127306], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7909525, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 2, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0015833146297468354], 0, 3.218428134918213, 1688552532.0287023], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5210886, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 1]], ["tile_y", "sp", [-1, 2, 1, 7]], ["tile_x", "sp", [-1, 7, 2, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.030736923217773438, 1688552512.2422457], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6179194, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 2, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005486398622327791], 0, 3.7313668727874756, 1688552535.0135503], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2038979, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 16, 2]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 1, 2, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0010067187173038229], 0, 2.290433883666992, 1688552536.4315119], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2286156, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 2, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0012898844525139664], 0, 3.48720121383667, 1688552539.4254985], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1596113, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0008830945745494265], 0, 3.5461716651916504, 1688552542.405517], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4836130, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 32]], ["tile_y", "sp", [-1, 2, 1, 7]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03253579139709473, 1688552512.2422636], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7854491, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 128]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.8072336425], 0, 10.777976274490356, 1688552551.6882966], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7727232, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 1, 2, 7]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688552520.3210268], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1136047, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 4, 1]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 1, 2, 7]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03873276710510254, 1688552520.3210468], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5478379, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0196878458627451], 0, 3.1011853218078613, 1688552553.3311658], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7571182, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 64]], ["tile_y", "sp", [-1, 2, 1, 7]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05297493934631348, 1688552520.3210578], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8926701, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 1]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 7, 2, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.12485361099243164, 1688552520.3210664], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2447358, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0004157447833247555], 0, 3.5139498710632324, 1688552556.3366106], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3532271, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.012001012154761907], 0, 3.0458524227142334, 1688552557.8748112], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3912010, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 2, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003341068233835984], 0, 3.6231443881988525, 1688552560.8591657], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 247105, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 4]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 2, 1, 7]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.001851720365406644], 0, 3.691852569580078, 1688552563.8603637], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5857790, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 8]], ["tile_y", "sp", [-1, 2, 1, 7]], ["tile_x", "sp", [-1, 7, 1, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.052690297947368424], 0, 3.6057088375091553, 1688552565.8637264], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7019675, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 128, 2]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.1020505428314209, 1688552520.3210847], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8515177, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 4, 1]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.000956868175074184], 0, 5.749274015426636, 1688552568.8408937], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5641891, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0033075031716171613], 0, 1.9036505222320557, 1688552570.2594388], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5326480, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 2, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00046364078022922636], 0, 3.452970027923584, 1688552573.2788916], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4612819, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 64, 2]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.001029676683640993], 0, 3.4293432235717773, 1688552576.2884195], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 52554, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 4]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00028487640848333634], 0, 4.0451719760894775, 1688552589.9207394], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 49284, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 1, 8]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00797041780952381], 0, 3.3210933208465576, 1688552591.3900282], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 40867, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 8]], ["tile_x", "sp", [-1, 7, 1, 7]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.1831590942], 0, 5.863417387008667, 1688552593.799585], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 54347, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 2]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0010308327442455243], 0, 4.7317376136779785, 1688552596.8299205], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 27285, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 1, 49, 1]], ["tile_rc", "sp", [-1, 128]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[3.479817142422992e-05], 0, 3.7385361194610596, 1688552599.781064], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 87705, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 4]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688552587.101549], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 88085, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 16]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 256]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.3053579330444336, 1688552587.1015813], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 40624, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 16, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.24904441833496094, 1688552587.101592], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 10944, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002406439692903995], 0, 3.9297878742218018, 1688552602.7890918], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 34511, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 1]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00015315102802051673], 0, 4.2055230140686035, 1688552605.7856393], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 31563, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 2]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.000272643032105441], 0, 4.235429525375366, 1688552608.9643507], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 21243, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 8]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0008250756442257897], 0, 4.27048397064209, 1688552612.116868], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 16461, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 8]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.011188326677777777], 0, 3.2864105701446533, 1688552613.835792], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 78377, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 1]], ["tile_x", "sp", [-1, 1, 49, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.859171431752945e-05], 0, 5.0705726146698, 1688552616.8608246], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 12070, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 128]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[4.665493572655648e-05], 0, 3.9940061569213867, 1688552619.9766407], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 11968, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 4]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00025293104787317533], 0, 4.119808912277222, 1688552623.1601274], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 18148, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 128]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.07124172968749999], 0, 3.527641773223877, 1688552625.6502142], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 27662, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 32, 4]], ["tile_x", "sp", [-1, 7, 1, 7]], ["tile_rc", "sp", [-1, 128]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.22925019264221191, 1688552587.1016207], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 10863, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 16]], ["tile_x", "sp", [-1, 1, 49, 1]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.23887181282043457, 1688552587.1016293], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 88917, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 32]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 256]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.3350210189819336, 1688552587.1016371], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 37330, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 64, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[3.218930049046998e-05], 0, 4.016291618347168, 1688552628.7623675], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 9051, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 16]], ["tile_x", "sp", [-1, 7, 7, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0015892630748031496], 0, 4.345852851867676, 1688552631.9488955], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 28974, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 4]], ["tile_x", "sp", [-1, 1, 49, 1]], ["tile_rc", "sp", [-1, 256]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.1909480094909668, 1688552587.1016483], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 63086, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 2]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.007727331483091787], 0, 4.800266265869141, 1688552635.218631], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 48436, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 4]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00018451761265909873], 0, 3.973905324935913, 1688552638.38006], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 79184, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 32]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.021978556739130434], 0, 3.4100515842437744, 1688552640.204579], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 76135, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 8, 2]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00022937177146932952], 0, 4.885174751281738, 1688552643.374238], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 82244, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 16, 2]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[8.389613781441556e-05], 0, 4.3748602867126465, 1688552646.6179523], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 31637, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 8]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002488031900123686], 0, 4.420999765396118, 1688552649.8284516], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 42947, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 2]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.000836406600416233], 0, 4.33619236946106, 1688552653.038532], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 13838, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 16]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 256]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.22364115715026855, 1688552587.1016693], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 55985, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 1, 2]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.05466742263157895], 0, 3.2584245204925537, 1688552655.2688215], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 63479, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 2, 8]], ["tile_x", "sp", [-1, 7, 7, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0025108862783825812], 0, 5.09308385848999, 1688552658.5706437], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 74203, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 8]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 256]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.31711673736572266, 1688552587.1016836], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 256, 14, 14], "float32"], ["TENSOR", [256, 256, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 11279, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 64, 2, 2]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.2965202331542969, 1688552587.101692], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3627500, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 8]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.08215141296386719, 1688552660.4145734], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2412372, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 2]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 2, 1, 7]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05421924591064453, 1688552660.4146123], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1546761, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 8]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.05618882179260254, 1688552660.414629], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3323655, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 14, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002501624374416433], 0, 6.006074666976929, 1688552670.7912078], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3586790, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 4]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 7, 1, 2]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.09052467346191406, 1688552663.382597], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 249211, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 16]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0010875459086956522], 0, 2.5412371158599854, 1688552672.1973825], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 569289, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 2, 1, 1]], ["tile_rc", "sp", [-1, 1024]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04832315444946289, 1688552663.382633], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1100317, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 128, 2]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.0481266975402832, 1688552663.3826492], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1082650, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.10629773139953613, 1688552663.3826778], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2130072, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 8, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 2, 1, 7]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.02736227662162162], 0, 7.26156210899353, 1688552673.9488192], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1926748, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 64]], ["tile_y", "sp", [-1, 7, 2, 1]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.2519235595], 0, 9.331180572509766, 1688552677.1038506], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1574476, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 8]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.005606777424581005], 0, 5.227369070053101, 1688552678.584785], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 805445, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 4, 1]], ["tile_y", "sp", [-1, 2, 1, 7]], ["tile_x", "sp", [-1, 1, 2, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0167077891], 0, 3.9893362522125244, 1688552680.1892428], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3102032, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 8, 1]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 2, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006095068358490566], 0, 3.9807863235473633, 1688552683.1870337], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 954040, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 4, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.08386921882629395, 1688552666.6317773], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3086830, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 14]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 1024]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.06695675849914551, 1688552666.6317992], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1797950, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 2, 7]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.10101962089538574, 1688552666.6318133], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 596577, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 8]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 1024]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.05105757713317871, 1688552666.6318264], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3575249, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 1, 7, 2]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.09220671653747559, 1688552666.631839], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2956419, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0737762451171875, 1688552666.6318514], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 815916, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 8]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0029071985261627906], 0, 3.331151008605957, 1688552684.61066], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2107993, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 16]], ["tile_y", "sp", [-1, 2, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.017002148644067797], 0, 3.263741970062256, 1688552686.211184], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2364892, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 4]], ["tile_y", "sp", [-1, 2, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.06651520729064941, 1688552666.631871], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 193806, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 64]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.011786143576470589], 0, 2.9278054237365723, 1688552687.7054722], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1731421, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 1, 2, 7]], ["tile_x", "sp", [-1, 1, 7, 2]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.09376215934753418, 1688552666.631885], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1356979, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 2, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00010342976415637597], 0, 3.6804351806640625, 1688552690.7012925], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3566112, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 32, 4]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 7, 2, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0693047046661377, 1688552666.6318998], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1409723, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 16]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0004502844679665738], 0, 4.416979789733887, 1688552693.7256835], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2668765, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006594768976345839], 0, 5.510777473449707, 1688552696.7053137], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3454978, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 128, 2]], ["tile_y", "sp", [-1, 1, 14, 1]], ["tile_x", "sp", [-1, 7, 2, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.09231877326965332, 1688552666.6319175], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2644110, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 8]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 14]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.028658921571428575], 0, 8.96174669265747, 1688552698.4138563], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2182832, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 128]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04012918472290039, 1688552667.798538], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1596207, "code_hash": null, "entity": [["tile_f", "sp", [-1, 128, 1, 4]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 7, 2, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.053403377532958984, 1688552667.7985628], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 994356, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 16]], ["tile_y", "sp", [-1, 2, 7, 1]], ["tile_x", "sp", [-1, 7, 1, 2]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.06265044212341309, 1688552667.7985775], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [512, 1024, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 540578, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.054196834564208984, 1688552667.7985904], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 33563, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03030085563659668, 1688552699.2236655], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 49671, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 16]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.008992338446428572], 0, 2.1055452823638916, 1688552710.581755], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 750085, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 4]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.078377853375], 0, 9.735911846160889, 1688552713.098501], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 650585, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.000981293390776699], 0, 4.964775085449219, 1688552716.1363041], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 147857, "code_hash": null, "entity": [["tile_f", "sp", [-1, 128, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0068140233809523805], 0, 3.992236852645874, 1688552717.6531582], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 405917, "code_hash": null, "entity": [["tile_f", "sp", [-1, 128, 2, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.029015302658081055, 1688552706.5108595], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 279920, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.12716269493103027, 1688552706.5108745], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 477582, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 16]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03666853904724121, 1688552706.5108838], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 451825, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.054920196533203125, 1688552706.5108929], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 150558, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.5092005859], 0, 10.087650299072266, 1688552723.655466], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 455028, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04400181770324707, 1688552706.5109034], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 677555, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 16]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.03886351834615384], 0, 3.2694501876831055, 1688552725.4859436], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 803966, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.06252169609069824, 1688552706.5109124], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 425785, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.007076979514084507], 0, 1.9238941669464111, 1688552727.0096555], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 751279, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 32]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04700660705566406, 1688552706.5109217], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 267149, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 2]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03422355651855469, 1688552706.510929], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 187327, "code_hash": null, "entity": [["tile_f", "sp", [-1, 128, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02514028549194336, 1688552706.5109415], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 162532, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 16]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.01617327091935484], 0, 2.473482131958008, 1688552728.586175], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 470558, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 32]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03400731086730957, 1688552706.510953], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 390510, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.007119065737588652], 0, 2.950810432434082, 1688552730.0665383], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 75438, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 32]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.03381247963333333], 0, 2.384361743927002, 1688552731.876058], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 414834, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 64, 4]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02536296844482422, 1688552706.5109656], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 288170, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 32]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.3191573486], 0, 4.637014627456665, 1688552735.8010178], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 400603, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 64]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02422928810119629, 1688552706.5109763], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 78844, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 8, 2]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.03488549172413793], 0, 3.270098924636841, 1688552737.5911248], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 216669, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 32]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688552709.2357078], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 173341, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 64]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.043272972106933594, 1688552709.2357333], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 797857, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04464364051818848, 1688552709.2357433], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 792937, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0012545978549262995], 0, 7.501542091369629, 1688552740.638476], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 27343, "code_hash": null, "entity": [["tile_f", "sp", [-1, 256, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.026959896087646484, 1688552709.2357528], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 526532, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 2]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05431795120239258, 1688552709.2357605], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 221380, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 2]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.022417635088888888], 0, 6.574639558792114, 1688552742.3246014], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 487366, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 2]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04920697212219238, 1688552709.2357688], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 550633, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 32]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0483088493347168, 1688552709.2357757], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 14, 14], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [2, 2], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 201718, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 32]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02684617042541504, 1688552709.2357821], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 236316, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.025403261184692383, 1688552743.165166], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 325186, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 128, 2]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.024188756942749023, 1688552743.1651816], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 362155, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 128]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03152823448181152, 1688552743.1669614], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 183032, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 32]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02721118927001953, 1688552743.1669703], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 204595, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 1]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00018546310504539707], 0, 3.203359842300415, 1688552756.0468445], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 216112, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 16]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0010341997580144778], 0, 1.8228988647460938, 1688552757.483451], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 258809, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.2069156982], 0, 5.298834800720215, 1688552760.1778884], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 293971, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 8]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03243756294250488, 1688552745.8441489], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 346489, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 64]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.029097318649291992, 1688552745.8441644], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 214958, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 512, 4]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.023950815200805664, 1688552745.8441741], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 316994, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 64]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 1024]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03200578689575195, 1688552745.8441813], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 160919, "code_hash": null, "entity": [["tile_f", "sp", [-1, 256, 4, 1]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.027836322784423828, 1688552745.8441885], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 367141, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02082538604736328, 1688552745.8441956], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 94698, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 64, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00033166669287620616], 0, 3.437957525253296, 1688552763.2255054], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 69723, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.006065269884848485], 0, 2.1031112670898438, 1688552764.674911], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 66505, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 16]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.097225151], 0, 4.271794080734253, 1688552767.6937444], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 243802, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 1, 32]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02064967155456543, 1688552745.844206], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2406, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 4, 8]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.050734234600000004], 0, 4.868781089782715, 1688552769.7027092], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 250309, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 128, 8]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0212404727935791, 1688552746.1139703], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 271524, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 256]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.017349508344827586], 0, 3.7533998489379883, 1688552771.3037264], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 96755, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 32]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.029443979263305664, 1688552746.113979], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 142884, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 256, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.026994943618774414, 1688552746.1139865], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 351506, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 16]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.4106006346999999], 0, 7.389245510101318, 1688552776.220742], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 350439, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 16]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05193209648132324, 1688552746.113999], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 382735, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 1024]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03253316879272461, 1688552746.1140068], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 253032, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 32, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 1024]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02280402183532715, 1688552746.114014], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 328231, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 16]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.04755795563636364], 0, 5.3938727378845215, 1688552778.236117], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 21362, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 1, 16]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.01548243876923077], 0, 2.0320417881011963, 1688552779.8444576], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 64678, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 1, 16]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 4, 13.216237545013428, 1688552790.0648293], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 189173, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 16]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 1024]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02261662483215332, 1688552746.6455295], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 345687, "code_hash": null, "entity": [["tile_f", "sp", [-1, 128, 1, 16]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.13986802101135254, 1688552746.6455376], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 270109, "code_hash": null, "entity": [["tile_f", "sp", [-1, 512, 2, 1]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688552753.1825292], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 183837, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.027631044387817383, 1688552753.182557], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 204137, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 32]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.013844227410958905], 0, 1.9088854789733887, 1688552791.5771272], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1024, 14, 14], "float32"], ["TENSOR", [2048, 1024, 1, 1], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 170123, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 128, 2]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.021526098251342773, 1688552753.182568], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 203783, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 32]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.1169276237487793, 1688552793.1511207], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 12194, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 16, 4]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0026533959177718835], 0, 2.121488571166992, 1688552803.6595953], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 239406, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 2, 16]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688552802.4008076], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 75547, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0011160755855855855], 0, 4.030126571655273, 1688552806.6709704], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 204695, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 32, 2]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0849142074584961, 1688552802.400836], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 331429, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 4]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.027728557586669922, 1688552802.4008455], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 114767, "code_hash": null, "entity": [["tile_f", "sp", [-1, 256, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.0547327995300293, 1688552802.4008534], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 119791, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00015456870461509002], 0, 3.2553794384002686, 1688552809.6693246], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 247398, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 128, 8]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02607274055480957, 1688552802.4008632], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 18611, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005681465881939564], 0, 3.4875853061676025, 1688552812.7001028], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11625, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 128]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.040848261680000005], 0, 2.3596584796905518, 1688552814.5390122], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 104475, "code_hash": null, "entity": [["tile_f", "sp", [-1, 128, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.020217180252075195, 1688552802.4008734], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 259140, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 128]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.029303312301635742, 1688552802.4008799], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 17142, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.000178694688482835], 0, 3.4033656120300293, 1688552817.569811], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 123142, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[9.43991031974186e-05], 0, 3.2538363933563232, 1688552820.5815754], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 120788, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 32]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.008444084613445379], 0, 2.8174612522125244, 1688552822.0470579], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 268094, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 64, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02945399284362793, 1688552802.400891], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 178238, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 128, 8]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0370481014251709, 1688552802.4008973], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 188524, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 128]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.1002927124], 0, 4.547253131866455, 1688552823.534322], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 154827, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 32, 2]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.025139331817626953, 1688552802.4009051], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 279752, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0018010779197324416], 0, 3.846834897994995, 1688552826.6438453], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 168003, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02743363380432129, 1688552802.4009123], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 286132, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 4, 1]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03856515884399414, 1688552802.4009194], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 117178, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 128]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.011156229644444444], 0, 3.0581343173980713, 1688552828.1714187], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 184244, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 64, 1]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02959895133972168, 1688552802.4009273], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 312279, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 128]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.02065890687755102], 0, 8.531912326812744, 1688552829.7829065], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 117148, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 32]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.010203641867088607], 0, 4.742443084716797, 1688552832.9247162], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 209221, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 32]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.026039600372314453, 1688552802.4009364], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 126319, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2048, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.11221729729999999], 0, 2.871652841567993, 1688552834.5339549], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 213233, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 32]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005640895982547993], 0, 3.4748096466064453, 1688552837.5905008], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 272523, "code_hash": null, "entity": [["tile_f", "sp", [-1, 128, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03229022026062012, 1688552802.4009461], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 183038, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 64]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.011492937357142859], 0, 3.5511159896850586, 1688552840.7538435], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 201576, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 32]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.01866943472222222], 0, 2.1879308223724365, 1688552842.3400958], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 226244, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04840445518493652, 1688552802.4009552], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [2048, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7643, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2048]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.11078809810000001], 0, 2.0227036476135254, 1688552843.9717631], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 206465, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 4]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 1024]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.12108612060546875, 1688552845.5656013], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 134376, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 16]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008216832217659138], 0, 3.400545358657837, 1688552852.255277], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 91406, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 4, 14.80197525024414, 1688552862.4803314], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 14837, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 128, 2]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02226567268371582, 1688552849.4475484], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 125751, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 4]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 2048]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.0408482551574707, 1688552849.4475586], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 279, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0014486354269175107], 0, 1.8618857860565186, 1688552863.8438206], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 245513, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 128]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.06439042091369629, 1688552849.447568], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 58849, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005759427321937322], 0, 3.4683587551116943, 1688552866.8344357], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 155292, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 32]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02373051643371582, 1688552849.4475787], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 129283, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.000696918681533101], 0, 1.7202961444854736, 1688552868.2127895], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 97437, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 32]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0007915534987763094], 0, 3.582920789718628, 1688552871.2488158], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 238379, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 4]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0651099681854248, 1688552849.4475892], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 222767, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005450320138186721], 0, 3.7897961139678955, 1688552874.2412615], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 137984, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 32, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0015879541777777777], 0, 1.8996384143829346, 1688552875.6418679], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 128633, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.002396493133971292], 0, 1.9198365211486816, 1688552877.0705123], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 194084, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 32, 1]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.027752399444580078, 1688552849.447602], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 16576, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0020120287835820893], 0, 3.5090832710266113, 1688552880.0709772], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 143138, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 8]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00022845318997734992], 0, 3.4593377113342285, 1688552883.0487041], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 158176, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 256]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02292919158935547, 1688552849.4476147], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 186330, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 128]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.01168368530232558], 0, 5.159122705459595, 1688552884.5997844], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 15876, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00010284619086688291], 0, 3.383103847503662, 1688552887.5765948], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 153921, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.023494720458984375, 1688552849.447625], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 82252, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 32]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 2048]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03897571563720703, 1688552849.447632], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 252308, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 32]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 2048]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.030690431594848633, 1688552849.4476392], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 220534, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 2]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04275965690612793, 1688552849.4476464], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 175434, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 2]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006839471602536998], 0, 3.627359628677368, 1688552890.581848], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 250069, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2048]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.023729562759399414, 1688552849.447655], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 74272, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 32, 4]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.024260520935058594, 1688552849.4476619], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 98247, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 4]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00039942220251914053], 0, 3.499880790710449, 1688552893.6217086], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 198901, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00012300100649301047], 0, 5.002884149551392, 1688552896.5897417], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 220583, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00017653764796587924], 0, 3.3324553966522217, 1688552899.5713844], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 66668, "code_hash": null, "entity": [["tile_f", "sp", [-1, 256, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02452254295349121, 1688552849.447676], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 206066, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 1024]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.039817094802856445, 1688552849.4476833], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 230729, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04546856880187988, 1688552849.4476907], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 2048, 7, 7], "float32"], ["TENSOR", [512, 2048, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 70308, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 4]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.11683011054992676, 1688552849.4476974], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 474275, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 16]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0037193544498141263], 0, 1.872420310974121, 1688552911.647727], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 529586, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 64, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0014719141338235295], 0, 1.8318331241607666, 1688552913.0802693], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 263886, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.0360107421875, 1688552900.9382029], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 167451, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 8, 1]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03206610679626465, 1688552900.9382164], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 131813, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04560256004333496, 1688552900.9382248], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 443450, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 8]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.03391262816666666], 0, 2.6533989906311035, 1688552914.8770778], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 265422, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688552910.3653934], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 58225, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.034447669982910156, 1688552910.36542], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 441878, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.003835625540229885], 0, 1.852403163909912, 1688552916.3738601], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 61473, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 32, 2]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.030318498611450195, 1688552910.3654315], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 659016, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 4]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.030471324920654297, 1688552910.3654394], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 45962, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 64]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.06552973175], 0, 3.0027012825012207, 1688552918.5418184], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 253273, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 256, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.025720834732055664, 1688552910.3654475], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 406561, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0018872542077294687], 0, 5.125735282897949, 1688552921.5051103], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 216295, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.001343882927680798], 0, 3.522850513458252, 1688552924.5976162], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 334489, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 16, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.034757375717163086, 1688552910.3654566], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 364336, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.006351589352], 0, 9.573976039886475, 1688552927.630488], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 700259, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 512]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04257917404174805, 1688552910.3654654], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 374517, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 4, 2]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03487706184387207, 1688552910.3654742], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 827918, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.003299627805921053], 0, 5.910802125930786, 1688552929.0558364], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 755010, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 32]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0786212463125], 0, 4.555624485015869, 1688552931.6112342], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 422515, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0019943093824701195], 0, 1.737513780593872, 1688552933.0478988], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 67202, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.041961669921875, 1688552910.365486], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1493, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 16]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.05667851422222222], 0, 2.7293899059295654, 1688552935.082044], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 688129, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 32]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02896571159362793, 1688552910.3654938], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 609654, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00029696998841059605], 0, 3.5128352642059326, 1688552938.140093], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 815763, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0011022081694169416], 0, 2.652693748474121, 1688552939.594155], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 802150, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0489349365234375, 1688552910.365504], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 40951, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 8, 1]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0012626268787878788], 0, 1.7107324600219727, 1688552941.0070233], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 424698, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 128, 2]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0315401554107666, 1688552910.3655133], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 80918, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 16]], ["tile_y", "sp", [-1, 1, 1, 7]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.338708374], 0, 5.1749303340911865, 1688552945.179413], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 186849, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 2]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.03337745156666667], 0, 2.8778398036956787, 1688552946.9641545], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 119111, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 2]], ["tile_y", "sp", [-1, 7, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0025311727803030305], 0, 2.075425148010254, 1688552948.416831], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 231168, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 16]], ["tile_y", "sp", [-1, 1, 7, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03861880302429199, 1688552910.3655264], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 140842, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 32, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00208336639375], 0, 1.7031309604644775, 1688552949.8689444], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 280047, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 64]], ["tile_x", "sp", [-1, 1, 8, 1]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.215745210647583, 1688552950.8812435], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 278243, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 64, 8]], ["tile_x", "sp", [-1, 16, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.18086791038513184, 1688552950.8812737], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 377606, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 16, 2]], ["tile_x", "sp", [-1, 2, 1, 1]], ["tile_rc", "sp", [-1, 512]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.1889784336090088, 1688552950.8812873], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 280280, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 16, 1]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00015457683764930722], 0, 3.736774444580078, 1688552961.5089602], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 59466, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 2]], ["tile_x", "sp", [-1, 1, 1, 4]], ["tile_rc", "sp", [-1, 128]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00025611548471408203], 0, 3.856174945831299, 1688552964.5748355], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 270637, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 16, 1]], ["tile_x", "sp", [-1, 1, 2, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[6.494172812461968e-05], 0, 3.7203454971313477, 1688552967.5604231], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 282343, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 8, 2]], ["tile_x", "sp", [-1, 2, 4, 2]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.18282270431518555, 1688552951.5599663], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 404558, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 32]], ["tile_x", "sp", [-1, 8, 1, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.010344754247422679], 0, 9.379072904586792, 1688552969.0721383], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 373454, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 64, 2, 4]], ["tile_x", "sp", [-1, 4, 1, 2]], ["tile_rc", "sp", [-1, 256]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.25467872619628906, 1688552958.6453278], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 259070, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 4]], ["tile_x", "sp", [-1, 1, 4, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[5.408572140391648e-05], 0, 3.628880262374878, 1688552972.0846217], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 288174, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 32]], ["tile_x", "sp", [-1, 1, 16, 1]], ["tile_rc", "sp", [-1, 128]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.1505274772644043, 1688552958.6453433], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 67886, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 4]], ["tile_x", "sp", [-1, 1, 2, 4]], ["tile_rc", "sp", [-1, 256]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.2323768138885498, 1688552958.645352], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 110577, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 8]], ["tile_x", "sp", [-1, 1, 8, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[7.40127051975052e-05], 0, 5.117732286453247, 1688552975.064793], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 423001, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 8]], ["tile_x", "sp", [-1, 2, 1, 8]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00019749423152952804], 0, 4.384935140609741, 1688552978.0404496], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 257742, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 4]], ["tile_x", "sp", [-1, 2, 1, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00012640609342915812], 0, 3.859827756881714, 1688552981.089435], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 21375, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 16, 1]], ["tile_x", "sp", [-1, 4, 1, 4]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[7.638651365409622e-05], 0, 3.7575466632843018, 1688552984.0424361], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 139853, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 4, 8]], ["tile_x", "sp", [-1, 1, 2, 1]], ["tile_rc", "sp", [-1, 256]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.16634392738342285, 1688552958.6453686], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 236124, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 2, 4, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00014298139338431441], 0, 3.766056776046753, 1688552987.0428324], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 128536, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 1, 8, 2]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[7.8220357160283e-05], 0, 3.8671929836273193, 1688552990.0772624], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 37098, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 8]], ["tile_x", "sp", [-1, 1, 2, 4]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00036747213615664844], 0, 4.223981618881226, 1688552993.0936887], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 97967, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 2]], ["tile_x", "sp", [-1, 1, 1, 4]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.00030162370318687537], 0, 3.8492274284362793, 1688552996.0754068], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 358220, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 1, 2]], ["tile_x", "sp", [-1, 8, 1, 2]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0755186538125], 0, 7.782115459442139, 1688552998.5472245], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 271083, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 32, 1]], ["tile_x", "sp", [-1, 4, 2, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[6.35965029609316e-05], 0, 3.7307956218719482, 1688553001.5287576], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 246369, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 32]], ["tile_x", "sp", [-1, 1, 1, 16]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.06459616087499999], 0, 3.8727762699127197, 1688553003.6833096], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 140023, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 4]], ["tile_x", "sp", [-1, 2, 2, 1]], ["tile_rc", "sp", [-1, 256]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005470652933884298], 0, 3.8239972591400146, 1688553006.7297404], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 290663, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 32, 1]], ["tile_x", "sp", [-1, 2, 1, 4]], ["tile_rc", "sp", [-1, 128]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.21134018898010254, 1688552958.645393], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 189426, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 64, 1, 1]], ["tile_x", "sp", [-1, 4, 2, 2]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00921359504587156], 0, 3.754505157470703, 1688553008.2635784], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 287930, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 16]], ["tile_x", "sp", [-1, 2, 8, 1]], ["tile_rc", "sp", [-1, 128]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[6.36693245614035e-05], 0, 3.643165349960327, 1688553011.232342], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 412993, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 256, 1]], ["tile_x", "sp", [-1, 1, 4, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[9.029487425658454e-05], 0, 3.7613165378570557, 1688553014.2648995], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 222219, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 1, 4, 4]], ["tile_rc", "sp", [-1, 256]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[6.772264951945467e-05], 0, 5.999757528305054, 1688553017.2399285], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 331583, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 32, 1]], ["tile_x", "sp", [-1, 4, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[8.256301444323653e-05], 0, 3.8729653358459473, 1688553020.212603], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 53843, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 64, 8]], ["tile_x", "sp", [-1, 1, 1, 16]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.23904633522033691, 1688552958.645409], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 333130, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 128, 1]], ["tile_x", "sp", [-1, 1, 4, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[6.977148999258711e-05], 0, 3.7197470664978027, 1688553023.2413461], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 126692, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 32]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.23348069190979004, 1688552958.6454175], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 512, 7, 7], "float32"], ["TENSOR", [512, 512, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 83622, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 1]], ["tile_x", "sp", [-1, 1, 4, 4]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[8.700702533783784e-05], 0, 3.540933847427368, 1688553026.2558043], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "dense_small_batch.gpu", [["TENSOR", [1, 2048], "float32"], ["TENSOR", [1000, 2048], "float32"], null, "float32"], {}], "config": {"index": 1, "code_hash": null, "entity": [["tile_k", "sp", [-1, 2]]]}, "result": [[2.737333909726637e-05], 0, 2.9489645957946777, 1688553029.9696276], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "dense_small_batch.gpu", [["TENSOR", [1, 2048], "float32"], ["TENSOR", [1000, 2048], "float32"], null, "float32"], {}], "config": {"index": 5, "code_hash": null, "entity": [["tile_k", "sp", [-1, 32]]]}, "result": [[5.573990157237754e-06], 0, 3.05703067779541, 1688553032.8340316], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "dense_small_batch.gpu", [["TENSOR", [1, 2048], "float32"], ["TENSOR", [1000, 2048], "float32"], null, "float32"], {}], "config": {"index": 10, "code_hash": null, "entity": [["tile_k", "sp", [-1, 1024]]]}, "result": [[1.1611851587201681e-05], 0, 3.1085662841796875, 1688553035.761258], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "dense_small_batch.gpu", [["TENSOR", [1, 2048], "float32"], ["TENSOR", [1000, 2048], "float32"], null, "float32"], {}], "config": {"index": 0, "code_hash": null, "entity": [["tile_k", "sp", [-1, 1]]]}, "result": [[5.729600664329964e-05], 0, 2.8653340339660645, 1688553038.4234746], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "dense_small_batch.gpu", [["TENSOR", [1, 2048], "float32"], ["TENSOR", [1000, 2048], "float32"], null, "float32"], {}], "config": {"index": 7, "code_hash": null, "entity": [["tile_k", "sp", [-1, 128]]]}, "result": [[5.5980176056995415e-06], 0, 3.0273048877716064, 1688553041.2700508], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "dense_small_batch.gpu", [["TENSOR", [1, 2048], "float32"], ["TENSOR", [1000, 2048], "float32"], null, "float32"], {}], "config": {"index": 8, "code_hash": null, "entity": [["tile_k", "sp", [-1, 256]]]}, "result": [[5.6349375429014015e-06], 0, 3.042715549468994, 1688553044.1355407], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "dense_small_batch.gpu", [["TENSOR", [1, 2048], "float32"], ["TENSOR", [1000, 2048], "float32"], null, "float32"], {}], "config": {"index": 11, "code_hash": null, "entity": [["tile_k", "sp", [-1, 2048]]]}, "result": [[1000000000.0], 1, 0.0059702396392822266, 1688553027.3323865], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "dense_small_batch.gpu", [["TENSOR", [1, 2048], "float32"], ["TENSOR", [1000, 2048], "float32"], null, "float32"], {}], "config": {"index": 4, "code_hash": null, "entity": [["tile_k", "sp", [-1, 16]]]}, "result": [[6.979172299560275e-06], 0, 3.0657451152801514, 1688553047.0123427], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "dense_small_batch.gpu", [["TENSOR", [1, 2048], "float32"], ["TENSOR", [1000, 2048], "float32"], null, "float32"], {}], "config": {"index": 2, "code_hash": null, "entity": [["tile_k", "sp", [-1, 4]]]}, "result": [[1.556208033052395e-05], 0, 3.047816753387451, 1688553049.875144], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "dense_small_batch.gpu", [["TENSOR", [1, 2048], "float32"], ["TENSOR", [1000, 2048], "float32"], null, "float32"], {}], "config": {"index": 6, "code_hash": null, "entity": [["tile_k", "sp", [-1, 64]]]}, "result": [[5.9966135739397935e-06], 0, 3.078866481781006, 1688553052.7635925], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "dense_small_batch.gpu", [["TENSOR", [1, 2048], "float32"], ["TENSOR", [1000, 2048], "float32"], null, "float32"], {}], "config": {"index": 9, "code_hash": null, "entity": [["tile_k", "sp", [-1, 512]]]}, "result": [[7.112014644723778e-06], 0, 3.0126914978027344, 1688553055.5973523], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "dense_small_batch.gpu", [["TENSOR", [1, 2048], "float32"], ["TENSOR", [1000, 2048], "float32"], null, "float32"], {}], "config": {"index": 3, "code_hash": null, "entity": [["tile_k", "sp", [-1, 8]]]}, "result": [[1.0396575194880119e-05], 0, 3.1307692527770996, 1688553058.5363739], "version": 0.2, "tvm_version": "0.11.dev0"} diff --git a/a100_squeezenet_tuned/tuning.2023-03-25T09:50+01:00.json b/a100_squeezenet_tuned/tuning.2023-03-25T09:50+01:00.json new file mode 100644 index 0000000..16ec232 --- /dev/null +++ b/a100_squeezenet_tuned/tuning.2023-03-25T09:50+01:00.json @@ -0,0 +1,990 @@ +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 772875, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 111]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.03445524493333333], 0, 7.231717348098755, 1679734235.1123297], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 16434, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 111, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 37]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.24057388305664062, 1679734228.2209787], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 447109, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 37, 1, 3]], ["tile_x", "sp", [-1, 1, 1, 37]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.21374893188476562, 1679734228.2209926], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 603997, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 2]], ["tile_y", "sp", [-1, 1, 37, 1]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[4.054851436599752e-05], 0, 3.7061424255371094, 1679734238.1849763], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 968016, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00031600848835844255], 0, 3.622807025909424, 1679734241.2807455], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 592661, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 111]], ["tile_x", "sp", [-1, 1, 111, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.21529388427734375, 1679734228.2210057], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 909220, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 1, 111, 1]], ["tile_x", "sp", [-1, 1, 3, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.1194202299652504e-05], 0, 3.9281671047210693, 1679734244.3134444], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 445317, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 2]], ["tile_y", "sp", [-1, 37, 3, 1]], ["tile_x", "sp", [-1, 1, 37, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.21802234649658203, 1679734228.2210155], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 458357, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 37, 3, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.022122362217391302], 0, 6.722279071807861, 1679734246.0839455], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 354843, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 111, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.21662449836730957, 1679734228.2210255], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 333181, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 2]], ["tile_y", "sp", [-1, 1, 3, 37]], ["tile_x", "sp", [-1, 3, 37, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.22316312789916992, 1679734228.2210324], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 893849, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 1]], ["tile_y", "sp", [-1, 3, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 3]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00022333029990303366], 0, 5.063096284866333, 1679734249.1865184], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 716132, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 3, 1, 37]], ["tile_x", "sp", [-1, 1, 3, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0024885918873456788], 0, 4.227694034576416, 1679734252.3055727], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 159567, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 1, 37, 3]], ["tile_x", "sp", [-1, 1, 37, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.2285172939300537, 1679734228.2210438], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 866163, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 2]], ["tile_y", "sp", [-1, 3, 37, 1]], ["tile_x", "sp", [-1, 1, 3, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[4.7277802636988314e-05], 0, 4.147233009338379, 1679734255.4050217], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 117336, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 8]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 3, 37, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.9439876926835226e-05], 0, 3.6454968452453613, 1679734258.4778373], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 678858, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 3, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 3]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00013113049683081423], 0, 3.7283828258514404, 1679734261.6177697], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 193900, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002460402151667428], 0, 3.599668502807617, 1679734264.7216158], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 61738, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 32]], ["tile_y", "sp", [-1, 1, 3, 37]], ["tile_x", "sp", [-1, 3, 1, 37]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.21220660209655762, 1679734228.2210584], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 438815, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 64]], ["tile_y", "sp", [-1, 3, 37, 1]], ["tile_x", "sp", [-1, 1, 37, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.21531248092651367, 1679734228.2210658], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 821121, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 111]], ["tile_x", "sp", [-1, 37, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.23178815841674805, 1679734228.221073], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 865426, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 1, 3, 37]], ["tile_x", "sp", [-1, 111, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.23803353309631348, 1679734228.22108], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 715748, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 111, 1]], ["tile_x", "sp", [-1, 1, 3, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[6.787588885610723e-05], 0, 4.060134649276733, 1679734267.826275], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 977132, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 3, 37, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.1331417766326873e-05], 0, 3.683314323425293, 1679734270.7680197], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 947336, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 3, 1, 37]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0031423232957198443], 0, 12.878313302993774, 1679734273.8952186], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 721032, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 4]], ["tile_y", "sp", [-1, 3, 37, 1]], ["tile_x", "sp", [-1, 1, 111, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.22226357460021973, 1679734232.7479887], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 626648, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 37, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00018409343872660884], 0, 3.6730525493621826, 1679734276.981202], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 819887, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 37, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[3.172297909421514e-05], 0, 4.839120388031006, 1679734280.0431874], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 784138, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 32]], ["tile_y", "sp", [-1, 1, 37, 1]], ["tile_x", "sp", [-1, 3, 37, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.22060585021972656, 1679734232.748005], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 842568, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 2]], ["tile_y", "sp", [-1, 1, 3, 37]], ["tile_x", "sp", [-1, 37, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.21412277221679688, 1679734232.7480128], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 188010, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 1, 3, 37]], ["tile_x", "sp", [-1, 1, 37, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.2198164463043213, 1679734232.7480206], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 314985, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 8]], ["tile_y", "sp", [-1, 37, 3, 1]], ["tile_x", "sp", [-1, 37, 1, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.21289825439453125, 1679734232.7480283], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 350151, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 2]], ["tile_y", "sp", [-1, 1, 111, 1]], ["tile_x", "sp", [-1, 1, 3, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.22426509857177734, 1679734232.7480354], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 751250, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 2]], ["tile_y", "sp", [-1, 1, 1, 111]], ["tile_x", "sp", [-1, 1, 3, 37]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.21342706680297852, 1679734232.7480423], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 265145, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 2]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 37, 3, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[8.533513067517279e-05], 0, 4.083227157592773, 1679734283.158477], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 306299, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 1, 3, 37]], ["tile_x", "sp", [-1, 111, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.21775221824645996, 1679734232.7480516], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 371408, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 37, 3, 1]], ["tile_x", "sp", [-1, 1, 3, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[6.437895462765744e-05], 0, 4.722805738449097, 1679734286.2382467], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 804542, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 1, 37, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1.4176474267955926e-05], 0, 3.9796640872955322, 1679734289.2484822], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 487548, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 37]], ["tile_x", "sp", [-1, 37, 1, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.24320721626281738, 1679734232.748063], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1017699, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 2]], ["tile_y", "sp", [-1, 111, 1, 1]], ["tile_x", "sp", [-1, 37, 3, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.21350765228271484, 1679734232.7480705], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 828252, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 1]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 1, 111, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[2.17869858547572e-05], 0, 3.923882484436035, 1679734292.2944546], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 697770, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 8]], ["tile_y", "sp", [-1, 37, 1, 1]], ["tile_x", "sp", [-1, 3, 37, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.22905683517456055, 1679734232.7480798], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 822496, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 111]], ["tile_x", "sp", [-1, 111, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.26204848289489746, 1679734232.7480865], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 619242, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 16]], ["tile_y", "sp", [-1, 1, 37, 3]], ["tile_x", "sp", [-1, 1, 1, 37]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2124955654144287, 1679734232.7480931], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 597278, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 2]], ["tile_y", "sp", [-1, 1, 37, 1]], ["tile_x", "sp", [-1, 1, 1, 37]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.21760082244873047, 1679734232.7481003], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 132316, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 1, 1, 11]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[4.387804671294632e-05], 0, 3.39813494682312, 1679734306.6667366], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 115938, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00884365810989011], 0, 7.64759087562561, 1679734309.8391628], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 330985, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.300761874401242e-05], 0, 4.156405448913574, 1679734312.9282382], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 338552, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 1, 55, 1]], ["tile_x", "sp", [-1, 1, 1, 11]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.079991861274603e-05], 0, 4.376511573791504, 1679734316.0277474], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 59715, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 11, 1, 5]], ["tile_x", "sp", [-1, 11, 1, 5]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04094052314758301, 1679734298.2728446], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 36618, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 1, 11, 1]], ["tile_x", "sp", [-1, 5, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.4239161762855654e-05], 0, 3.60256290435791, 1679734319.0544894], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 19783, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 55, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.003025407114446529], 0, 4.211406230926514, 1679734322.1711123], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 313560, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 1, 5, 11]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02667093276977539, 1679734298.2728631], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 180636, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00024992609989159053], 0, 3.7696681022644043, 1679734325.2506611], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 188020, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 11]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.024316072463989258, 1679734298.2728732], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 205055, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 11, 1, 1]], ["tile_x", "sp", [-1, 1, 5, 11]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006144632579150579], 0, 4.218397855758667, 1679734328.3044438], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4508, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 55, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[9.873300864195953e-06], 0, 3.282240152359009, 1679734331.2661738], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 116717, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 1, 11, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1.1841131042844985e-05], 0, 3.50949764251709, 1679734334.2839081], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 338401, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 2]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 1, 1, 11]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.0129913473769906e-05], 0, 4.02999210357666, 1679734337.3113701], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 201793, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 2]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 1, 55, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006359622092741936], 0, 3.8462648391723633, 1679734340.3355584], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 192696, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 2]], ["tile_y", "sp", [-1, 5, 1, 1]], ["tile_x", "sp", [-1, 1, 55, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[2.311053080479427e-05], 0, 3.6268837451934814, 1679734343.3777437], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 365502, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 11, 1, 5]], ["tile_x", "sp", [-1, 1, 1, 11]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.07806682586669922, 1679734298.2728913], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 156581, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 5, 11, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[9.774109345509892e-05], 0, 4.3076183795928955, 1679734346.4755483], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 37447, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.011864641964705883], 0, 3.1388919353485107, 1679734348.0870025], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 323851, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.3269285240197656e-05], 0, 3.62347149848938, 1679734351.1514764], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 282338, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 11, 1, 1]], ["tile_x", "sp", [-1, 1, 55, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[2.0905231868678928e-05], 0, 3.9459402561187744, 1679734354.2085755], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 173212, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 11, 5, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[6.4890953421886e-05], 0, 5.92501163482666, 1679734357.0735035], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 149244, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 1, 55, 1]], ["tile_x", "sp", [-1, 11, 1, 5]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.001074751189261745], 0, 4.979444265365601, 1679734360.1531925], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 195170, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 55, 1]], ["tile_x", "sp", [-1, 1, 1, 11]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[4.56289746810264e-05], 0, 3.4540324211120605, 1679734363.2229304], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 209665, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 1, 11, 1]], ["tile_x", "sp", [-1, 1, 11, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[8.421612453056114e-06], 0, 3.4488167762756348, 1679734366.199771], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 137069, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 11]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[3.450782712542767e-05], 0, 4.105064630508423, 1679734369.272493], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 95458, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 11, 1, 5]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.07540774345397949, 1679734298.2729142], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 217805, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 55]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00014154788368421053], 0, 3.5457868576049805, 1679734372.3474207], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 230297, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 1, 11, 5]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.056650638580322266, 1679734298.2729235], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 166519, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 1, 1, 5]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[6.804165311825225e-05], 0, 3.6461687088012695, 1679734375.431084], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 277531, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0018992974430082255], 0, 5.763373851776123, 1679734378.539884], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 348104, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679734303.7824092], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 213149, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 1, 1, 11]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006647623282312926], 0, 4.259432554244995, 1679734381.5869048], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 371287, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 5, 11, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[9.144122592121075e-06], 0, 6.246304273605347, 1679734384.5797584], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 164490, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 1, 11, 5]], ["tile_x", "sp", [-1, 11, 5, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.05045795440673828, 1679734303.7824447], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 356711, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 55]], ["tile_x", "sp", [-1, 1, 1, 11]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679734303.8000443], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 337355, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 1, 11, 1]], ["tile_x", "sp", [-1, 11, 1, 5]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[6.880979247298048e-05], 0, 5.45122504234314, 1679734387.6581156], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 215178, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0003541467897206704], 0, 3.9878978729248047, 1679734390.6950085], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 17635, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.008262960733333333], 0, 5.246958255767822, 1679734393.8737383], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 96145, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 11, 5]], ["tile_x", "sp", [-1, 1, 11, 5]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.024062156677246094, 1679734303.800085], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 215131, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 2]], ["tile_y", "sp", [-1, 11, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.9846342597929876e-05], 0, 3.8976850509643555, 1679734396.9317586], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 107115, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00027278184628378376], 0, 3.5671181678771973, 1679734400.0662448], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 19729, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 55, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.006728690127516779], 0, 2.5253868103027344, 1679734401.624633], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 309380, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 1, 55, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0238955020904541, 1679734303.8001013], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 64452, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 5, 1, 1]], ["tile_x", "sp", [-1, 55, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0033213913305954823], 0, 4.083679437637329, 1679734404.781178], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 522313, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 11, 1, 5]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[3.7182018149800426e-05], 0, 3.7848708629608154, 1679734419.2103996], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 106486, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02640223503112793, 1679734407.0893173], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 212869, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 1, 11, 1]], ["tile_x", "sp", [-1, 1, 5, 11]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1.2106343338886207e-05], 0, 3.499835968017578, 1679734422.1969543], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 44164, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.000989131111318408], 0, 4.168944597244263, 1679734425.2875316], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 216570, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 11, 1, 1]], ["tile_x", "sp", [-1, 5, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.3099628082603757e-05], 0, 3.9587976932525635, 1679734428.31815], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 352041, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 32]], ["tile_y", "sp", [-1, 1, 5, 11]], ["tile_x", "sp", [-1, 11, 5, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0012732022456000002], 0, 4.775317192077637, 1679734431.382615], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 237679, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.4849032881956887e-05], 0, 3.5361194610595703, 1679734434.4072812], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 485853, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 32]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 1, 1, 5]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.000432998510568213], 0, 4.131911516189575, 1679734437.4410493], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 276689, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 16]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00866559100862069], 0, 4.246530532836914, 1679734439.1016607], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 311175, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 2]], ["tile_y", "sp", [-1, 1, 55, 1]], ["tile_x", "sp", [-1, 5, 11, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02178668975830078, 1679734408.8858094], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 52629, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 11, 1, 1]], ["tile_x", "sp", [-1, 5, 11, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0007340772036363636], 0, 7.3158159255981445, 1679734442.2623336], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 257113, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 8]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[7.411999658577097e-05], 0, 4.104037523269653, 1679734445.3576322], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 553816, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 5, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 11]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00032432224316605466], 0, 7.846966028213501, 1679734448.4242883], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 500811, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 11, 1, 5]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00018496740567290284], 0, 6.094074249267578, 1679734451.4315503], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 428863, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 5, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002772563951571355], 0, 5.135940790176392, 1679734454.5143917], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 469584, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_y", "sp", [-1, 1, 11, 1]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[7.133499295587454e-05], 0, 4.183730840682983, 1679734457.5860047], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 614236, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 5]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.716617705671947e-05], 0, 3.765415668487549, 1679734460.6473656], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 492336, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 1]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 1, 5, 11]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0703880786895752, 1679734411.086038], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 203250, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 5, 11, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04535722732543945, 1679734411.0860484], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 359919, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 1, 1, 11]], ["tile_x", "sp", [-1, 1, 11, 5]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[3.789168363748254e-05], 0, 3.6060163974761963, 1679734463.7076414], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 593852, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 1, 1, 5]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679734416.2670205], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 599141, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 11]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679734416.3224013], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 335156, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 32]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 1, 1, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0012064662757296468], 0, 3.5526294708251953, 1679734466.7776585], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 331828, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 1, 5, 11]], ["tile_x", "sp", [-1, 1, 11, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.523606599014263e-05], 0, 3.5217740535736084, 1679734469.7986307], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 585901, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 55]], ["tile_x", "sp", [-1, 55, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.005053972646464647], 0, 2.758544683456421, 1679734471.3382344], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 57564, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 11, 1, 5]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.07502126693725586, 1679734416.322425], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 89629, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 1, 11, 5]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[4.091093620720513e-05], 0, 3.769787549972534, 1679734474.4122245], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 17714, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 11, 1, 1]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0057855409028776976], 0, 5.331423282623291, 1679734477.554954], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 179365, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 11, 5, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03083944320678711, 1679734416.322435], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 633600, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 8]], ["tile_y", "sp", [-1, 1, 11, 1]], ["tile_x", "sp", [-1, 5, 11, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.143273169054905e-05], 0, 5.541015148162842, 1679734480.6145318], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 613499, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 1, 55, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.039649009704589844, 1679734416.3224428], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 396909, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 5, 11, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.056301116943359375, 1679734416.322449], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 560643, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 1]], ["tile_y", "sp", [-1, 11, 1, 1]], ["tile_x", "sp", [-1, 5, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.3786460038952307e-05], 0, 4.131860017776489, 1679734483.6288226], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 639221, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 1, 11, 5]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[7.648720658191511e-05], 0, 9.02533745765686, 1679734486.5258987], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 57852, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 11, 5]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[8.898270204739827e-06], 0, 3.4875428676605225, 1679734489.5074623], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 454043, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 5, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001283274324302789], 0, 4.148573160171509, 1679734492.593063], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 171156, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 2]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.05147504806518555, 1679734416.3224611], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 513823, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 16]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 1, 5, 11]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[2.693428641651095e-05], 0, 3.940971851348877, 1679734495.6583226], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 476912, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0011281709379932358], 0, 6.189249277114868, 1679734497.1867917], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 469836, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0019717503326771653], 0, 5.342466354370117, 1679734498.6856117], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 573677, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 2]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 11, 1, 5]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679734416.3225248], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 427078, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 11]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00012032042506913821], 0, 4.353988409042358, 1679734501.810961], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 424078, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 1, 55, 1]], ["tile_x", "sp", [-1, 1, 11, 5]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04574012756347656, 1679734416.322534], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 310122, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 16]], ["tile_y", "sp", [-1, 1, 11, 5]], ["tile_x", "sp", [-1, 1, 11, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[2.5275024872237077e-05], 0, 3.5366244316101074, 1679734504.867455], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 9555, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 5, 1, 1]], ["tile_x", "sp", [-1, 5, 11, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.5624602154170227e-05], 0, 3.4740469455718994, 1679734507.8806393], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1306741, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 2]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 1, 1, 11]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00018713309594438007], 0, 3.83329176902771, 1679734522.4205327], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1351127, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0012599695232100709], 0, 4.190676212310791, 1679734525.5218565], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1676484, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 1]], ["tile_y", "sp", [-1, 1, 11, 1]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.003021981688821752], 0, 2.6821248531341553, 1679734527.0482183], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 676848, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 4]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 5, 11, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003345014917115624], 0, 4.547987937927246, 1679734530.1654038], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1120931, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[7.266752943042277e-05], 0, 4.0077314376831055, 1679734533.2376425], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 663267, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 1, 55, 1]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006189312476044461], 0, 4.321954727172852, 1679734536.3235457], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 856636, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 1, 11, 1]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.09411287307739258, 1679734511.5955093], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 654413, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 4]], ["tile_y", "sp", [-1, 1, 5, 11]], ["tile_x", "sp", [-1, 1, 11, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00914920709090909], 0, 2.9572536945343018, 1679734537.897177], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 240353, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.020079349360000002], 0, 3.7605793476104736, 1679734539.5834632], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1830775, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 16]], ["tile_y", "sp", [-1, 11, 1, 1]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.010967039684782609], 0, 4.296951055526733, 1679734541.1937022], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1854213, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 32]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 55, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.094312126125], 0, 6.344690322875977, 1679734544.2586672], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1535956, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 1, 11, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.002244023470833333], 0, 4.27752423286438, 1679734547.4229462], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 838083, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.001815269509981851], 0, 3.583200693130493, 1679734548.9164193], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1497632, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 32]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 11, 1, 5]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0030487822905660377], 0, 4.199826717376709, 1679734552.0791388], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 442373, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 11, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003121119097061099], 0, 4.0808961391448975, 1679734555.1962404], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1991893, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 5, 1, 1]], ["tile_x", "sp", [-1, 11, 1, 5]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00653711611038961], 0, 3.67883038520813, 1679734556.75985], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 443276, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 1, 1, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0034246508050847454], 0, 5.497817277908325, 1679734559.896813], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1534220, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 1, 55, 1]], ["tile_x", "sp", [-1, 11, 5, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.10073351860046387, 1679734512.6614313], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1970740, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 11, 1, 5]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679734519.3834226], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2471971, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[4.295290051935536e-05], 0, 5.68352484703064, 1679734562.9811451], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1885234, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 1, 11, 5]], ["tile_x", "sp", [-1, 11, 1, 5]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.1329498291015625, 1679734519.3834598], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1221150, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 1, 1, 11]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0012182808187451589], 0, 5.974859952926636, 1679734566.0075371], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1721507, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 1]], ["tile_y", "sp", [-1, 1, 5, 11]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001209820512935883], 0, 4.1508283615112305, 1679734569.0949264], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 73143, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 1, 11, 1]], ["tile_x", "sp", [-1, 1, 11, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.0935969352722168, 1679734519.383479], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1056562, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 11, 1, 1]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0030231327819548875], 0, 12.816953182220459, 1679734572.2010522], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 596132, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 55, 1]], ["tile_x", "sp", [-1, 1, 11, 5]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.10865092277526855, 1679734519.383492], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 201000, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 8]], ["tile_y", "sp", [-1, 1, 55, 1]], ["tile_x", "sp", [-1, 11, 5, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.1252896785736084, 1679734519.383503], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1644039, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 5, 11, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.012555187225], 0, 6.434222936630249, 1679734573.8389263], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 412898, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 2]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 55, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.08587002754211426, 1679734519.3835151], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 710160, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_y", "sp", [-1, 1, 11, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[2.5531868875385804e-05], 0, 3.8403139114379883, 1679734576.89815], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2129135, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 11, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[7.004021213042157e-05], 0, 4.7655346393585205, 1679734579.973513], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1984773, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 11]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[7.247476500540735e-05], 0, 4.525942087173462, 1679734583.036007], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 540709, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.001074162828141783], 0, 3.883309841156006, 1679734584.5104337], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1489797, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 4]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001054504425993724], 0, 4.082017660140991, 1679734587.581886], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1624115, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 4]], ["tile_y", "sp", [-1, 1, 11, 1]], ["tile_x", "sp", [-1, 1, 55, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.1083991527557373, 1679734519.3835397], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2296676, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 1, 1, 11]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679734519.4469218], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2297346, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679734519.4469864], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 347210, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 2]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1679734519.4470427], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1202360, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 1, 5, 11]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005468180943843031], 0, 4.914155960083008, 1679734590.6691117], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 718811, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 1, 11, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[9.267609268516924e-05], 0, 4.135774850845337, 1679734593.743984], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1392600, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 2]], ["tile_y", "sp", [-1, 11, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 11]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00030720797338403043], 0, 4.881836175918579, 1679734596.8617759], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 507019, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 16]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 5]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.075140029875], 0, 4.857312202453613, 1679734599.3890345], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 383073, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0769597473125], 0, 3.8382699489593506, 1679734601.940402], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 734626, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[5.13791118903513e-05], 0, 3.9335825443267822, 1679734605.0217257], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 648317, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 1]], ["tile_y", "sp", [-1, 1, 11, 1]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0001807196681212935], 0, 4.154718399047852, 1679734608.1137211], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 704235, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 4]], ["tile_x", "sp", [-1, 4, 2, 98]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0007218788777075812], 0, 4.897592544555664, 1679734622.5653248], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 220563, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 4]], ["tile_x", "sp", [-1, 2, 14, 4]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[2.1632410144240533e-05], 0, 4.009347438812256, 1679734625.6136734], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 160322, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 4]], ["tile_x", "sp", [-1, 196, 1, 4]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0408661206], 0, 7.26150918006897, 1679734627.564556], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 94101, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 8, 1]], ["tile_x", "sp", [-1, 2, 49, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.6550610419581878e-05], 0, 4.072122097015381, 1679734630.6011095], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 30550, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 392, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.006558962448979591], 0, 5.791170835494995, 1679734633.7980928], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 445016, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 8]], ["tile_x", "sp", [-1, 2, 8, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.7753086167468374e-05], 0, 3.966824531555176, 1679734636.818766], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 215816, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 1]], ["tile_x", "sp", [-1, 4, 7, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1.895922468813461e-05], 0, 3.9856786727905273, 1679734639.83046], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 237667, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 2]], ["tile_x", "sp", [-1, 4, 4, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[2.6198281219028738e-05], 0, 4.225527048110962, 1679734642.8677952], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 335504, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 1, 98, 2]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.7363042491460105e-05], 0, 4.0029308795928955, 1679734645.899389], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 134614, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 2]], ["tile_x", "sp", [-1, 28, 2, 7]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00011444725831256674], 0, 5.017475605010986, 1679734649.0371919], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1068, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 4]], ["tile_x", "sp", [-1, 196, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0021634718894878702], 0, 4.2674031257629395, 1679734652.1318583], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 579059, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 16, 2]], ["tile_x", "sp", [-1, 14, 7, 8]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.3298776149749756, 1679734614.8482242], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 128927, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 8]], ["tile_x", "sp", [-1, 1, 28, 2]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.3043413976355104e-05], 0, 3.9836361408233643, 1679734655.1505167], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 356798, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 4]], ["tile_x", "sp", [-1, 2, 8, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[2.0273007849737272e-05], 0, 4.009799242019653, 1679734658.1641726], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 825305, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 1, 1]], ["tile_x", "sp", [-1, 196, 2, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.003287957651731161], 0, 4.682293653488159, 1679734661.281364], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 856059, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 1]], ["tile_x", "sp", [-1, 14, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.8078193035018568e-05], 0, 5.595120906829834, 1679734664.3571906], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 97879, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 1]], ["tile_x", "sp", [-1, 49, 4, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.8323284416069428e-05], 0, 4.124974012374878, 1679734667.395173], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 204517, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 4]], ["tile_x", "sp", [-1, 1, 4, 98]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.00016643143869771274], 0, 4.391202926635742, 1679734670.4800808], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 88212, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 2, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00016345607660392633], 0, 4.045258522033691, 1679734673.5629086], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 479441, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 4]], ["tile_x", "sp", [-1, 28, 2, 2]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0029862224507462686], 0, 3.567720413208008, 1679734675.1165912], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 45805, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 1]], ["tile_x", "sp", [-1, 112, 1, 7]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00020318755639476334], 0, 5.118723154067993, 1679734678.2133667], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 255000, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 4]], ["tile_x", "sp", [-1, 49, 1, 8]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0018511012977011497], 0, 5.337961912155151, 1679734681.3134098], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 502531, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 28, 4, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.8806135174366725e-05], 0, 3.9697394371032715, 1679734684.3514352], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 330493, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 2]], ["tile_x", "sp", [-1, 1, 196, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.6075128014271656e-05], 0, 3.9309937953948975, 1679734687.3602095], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 511443, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 4]], ["tile_x", "sp", [-1, 1, 49, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.4744930209531713e-05], 0, 3.9624171257019043, 1679734690.3616688], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 272663, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 64]], ["tile_x", "sp", [-1, 14, 1, 2]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0023518462634643375], 0, 4.383638143539429, 1679734693.4866672], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 669795, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 4]], ["tile_x", "sp", [-1, 1, 14, 14]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[3.229244583942792e-05], 0, 4.12863564491272, 1679734696.5459304], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 265296, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 16, 1]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[3.969880191527269e-05], 0, 4.439058303833008, 1679734699.6161714], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 432255, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 16]], ["tile_x", "sp", [-1, 7, 14, 8]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.20223402976989746, 1679734614.8483148], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 147109, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 1]], ["tile_x", "sp", [-1, 2, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[4.1982525349123584e-05], 0, 4.08907413482666, 1679734702.6754136], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 724420, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 1]], ["tile_x", "sp", [-1, 7, 16, 7]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.20062875747680664, 1679734614.8483374], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 232959, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 64, 1]], ["tile_x", "sp", [-1, 7, 2, 56]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.00022047801448285285], 0, 4.259910345077515, 1679734705.7867856], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 842916, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 4]], ["tile_x", "sp", [-1, 14, 1, 8]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679734619.6466398], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 867772, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 4]], ["tile_x", "sp", [-1, 1, 49, 4]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.3787763857285205e-05], 0, 4.528720140457153, 1679734708.8476667], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 393335, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 16, 2]], ["tile_x", "sp", [-1, 14, 14, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[2.4111701236368055e-05], 0, 4.435910224914551, 1679734711.8899548], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 544821, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 32]], ["tile_x", "sp", [-1, 1, 196, 4]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[5.0480894982349974e-05], 0, 4.881472826004028, 1679734714.9563136], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 718205, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 4]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.00010323405643355302], 0, 4.645933151245117, 1679734718.036053], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 542042, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 16]], ["tile_x", "sp", [-1, 4, 1, 4]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00016015864563933112], 0, 5.039384841918945, 1679734721.1499252], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 571893, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 8, 1]], ["tile_x", "sp", [-1, 196, 1, 4]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.292285680770874, 1679734619.6467123], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 323009, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 1, 4, 196]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.000983835566749073], 0, 5.391031265258789, 1679734724.2124486], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 627673, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 1]], ["tile_x", "sp", [-1, 14, 7, 2]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[2.365422563495002e-05], 0, 3.924823045730591, 1679734727.2653322], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 642692, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 2, 14, 28]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[4.122005380119957e-05], 0, 4.078662395477295, 1679734730.3501046], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 539306, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 32, 1]], ["tile_x", "sp", [-1, 7, 7, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[2.0576680746766795e-05], 0, 3.664980173110962, 1679734733.374561], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 300109, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 4]], ["tile_x", "sp", [-1, 8, 49, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.7372246945344662e-05], 0, 3.8600101470947266, 1679734736.4441435], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 713178, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 1]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[4.8010353289828174e-05], 0, 3.664254665374756, 1679734739.5069818], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 285750, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 1, 5, 11]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03025364875793457, 1679734740.915956], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 139533, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 2]], ["tile_y", "sp", [-1, 11, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 5]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00021188189094048884], 0, 4.305012226104736, 1679734753.859506], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 58113, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 11]], ["tile_x", "sp", [-1, 5, 11, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.059240102767944336, 1679734742.2971063], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 143356, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 55]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.030237197875976562, 1679734742.2971358], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 74040, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002658548608094768], 0, 3.5079500675201416, 1679734756.9362094], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 196480, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 1, 5, 11]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02343606948852539, 1679734742.2971635], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 55817, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 11, 1, 5]], ["tile_x", "sp", [-1, 55, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04170799255371094, 1679734742.2971835], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 222156, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 1, 11, 5]], ["tile_x", "sp", [-1, 1, 1, 11]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00021539816962261635], 0, 3.547738552093506, 1679734760.0100236], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 392425, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 11]], ["tile_x", "sp", [-1, 1, 1, 11]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[9.188714170040486e-05], 0, 6.747027158737183, 1679734763.0978165], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 412236, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 11, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.252495603025347e-05], 0, 6.528843402862549, 1679734766.162155], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 179828, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 5, 1, 1]], ["tile_x", "sp", [-1, 5, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[6.787735517997135e-05], 0, 3.9793543815612793, 1679734769.2489915], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 51661, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 1, 1, 11]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0001077069694579964], 0, 3.453118085861206, 1679734772.3320603], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 25668, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.012544230649999998], 0, 3.0804243087768555, 1679734773.9575794], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 239385, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 1, 11, 5]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00016977363658357], 0, 3.6248676776885986, 1679734777.1032658], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 63973, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.05423378944396973, 1679734744.652759], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 204998, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 5, 1, 1]], ["tile_x", "sp", [-1, 1, 5, 11]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.033629417419433594, 1679734744.652769], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 261164, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0999908447265625, 1679734744.6527758], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 128438, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 2]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 11, 5, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.06656098365783691, 1679734744.6527824], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 77379, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 11, 1, 1]], ["tile_x", "sp", [-1, 11, 1, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.007596675984848485], 0, 7.848790645599365, 1679734778.6922395], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 368591, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679734750.961769], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 190256, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 1, 11, 5]], ["tile_x", "sp", [-1, 55, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03904151916503906, 1679734750.9617875], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 156288, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 5, 1, 1]], ["tile_x", "sp", [-1, 5, 11, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[3.6508699277756254e-05], 0, 3.5251238346099854, 1679734781.7621982], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 44731, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 1, 5, 11]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.030368566513061523, 1679734750.961796], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 384883, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 2]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[8.330325335196976e-05], 0, 4.865151882171631, 1679734784.8462596], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 367617, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.110478617280013e-05], 0, 4.27478289604187, 1679734787.8872378], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 76362, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 1, 55, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00025490540085186937], 0, 3.6546638011932373, 1679734791.0112474], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 47084, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 5, 1, 1]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.5931829650856656e-05], 0, 3.409062147140503, 1679734794.0271437], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 56668, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 11, 5, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.0783989429473877, 1679734750.961809], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 191725, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 1, 11, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.057626962661743164, 1679734750.9618142], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 25633, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 11]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.002523659654911839], 0, 2.4042739868164062, 1679734795.5414982], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 131158, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 11, 1, 5]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.25098323822021484, 1679734750.961821], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 44265, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003095664531519448], 0, 3.619734287261963, 1679734798.6640198], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 142397, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 1, 5, 11]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.25986814498901367, 1679734750.9618285], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 396081, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 2]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 55, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.000639349026703866], 0, 7.111926078796387, 1679734801.7403138], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 53917, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[3.5095337165510404e-05], 0, 3.4261300563812256, 1679734804.7888882], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 134217, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 11, 1, 5]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04701685905456543, 1679734750.961836], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 161077, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 11, 1, 5]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.01796631730357143], 0, 2.5853235721588135, 1679734806.4710016], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 377334, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 11]], ["tile_x", "sp", [-1, 5, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0009326717862108921], 0, 8.150294780731201, 1679734809.6414454], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 341769, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[3.6089379393475125e-05], 0, 6.285527944564819, 1679734812.7118137], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 270193, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.028423070907592773, 1679734750.9618454], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 337230, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 11, 1, 5]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.25760769844055176, 1679734750.9618502], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 267072, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 2]], ["tile_y", "sp", [-1, 1, 5, 11]], ["tile_x", "sp", [-1, 1, 1, 11]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04434776306152344, 1679734750.9618554], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 68855, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 55]], ["tile_x", "sp", [-1, 11, 1, 5]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.040909767150878906, 1679734750.9618607], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 242107, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[2.4393999206881825e-05], 0, 3.3804681301116943, 1679734815.7836804], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 190551, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.0627457619199176e-05], 0, 3.6005921363830566, 1679734818.8026764], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 821620, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 4]], ["tile_y", "sp", [-1, 3, 1, 3]], ["tile_x", "sp", [-1, 1, 3, 3]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[8.365155271313758e-05], 0, 4.5751824378967285, 1679734833.179139], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 584200, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 9, 1, 3]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005989350269953052], 0, 4.536934852600098, 1679734836.1343157], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 949588, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 9]], ["tile_x", "sp", [-1, 1, 9, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[4.64055962806571e-05], 0, 4.200711011886597, 1679734839.1980386], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 195773, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 1, 9, 3]], ["tile_x", "sp", [-1, 3, 3, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0016339487687626775], 0, 3.70090651512146, 1679734842.3431263], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 837999, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 3, 9, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1.1535705149172921e-05], 0, 4.1924662590026855, 1679734845.325066], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 99703, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 27, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.215265635752207e-05], 0, 3.590378761291504, 1679734848.31938], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 684703, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 9, 3, 1]], ["tile_x", "sp", [-1, 3, 1, 3]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.030666589736938477, 1679734822.864498], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 639858, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 9, 3, 1]], ["tile_x", "sp", [-1, 3, 1, 3]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006670983197505198], 0, 4.396884441375732, 1679734851.3893583], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 489358, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 2]], ["tile_y", "sp", [-1, 1, 3, 9]], ["tile_x", "sp", [-1, 1, 1, 9]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002501639720800372], 0, 5.582076549530029, 1679734854.4748518], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 457581, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 1]], ["tile_y", "sp", [-1, 3, 1, 3]], ["tile_x", "sp", [-1, 3, 9, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0017317153663793103], 0, 5.880454778671265, 1679734857.613103], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 45095, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 3, 3, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.3942488361996402e-05], 0, 3.430335760116577, 1679734860.6316812], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 176970, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 3, 9]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.000106909864570898], 0, 3.6744399070739746, 1679734863.712076], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 223348, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 3, 9, 1]], ["tile_x", "sp", [-1, 1, 1, 27]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00020165014246472719], 0, 3.584261894226074, 1679734866.7968287], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 215990, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 16]], ["tile_y", "sp", [-1, 1, 1, 9]], ["tile_x", "sp", [-1, 9, 1, 3]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.053401222578947374], 0, 4.074981212615967, 1679734868.8692875], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 842366, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 9, 1, 1]], ["tile_x", "sp", [-1, 9, 1, 3]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679734830.2706401], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 902520, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 9]], ["tile_x", "sp", [-1, 3, 3, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.000629204198515045], 0, 4.8469202518463135, 1679734871.9539585], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 521426, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 1]], ["tile_y", "sp", [-1, 3, 1, 3]], ["tile_x", "sp", [-1, 3, 3, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.033881187438964844, 1679734830.2706683], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 340588, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 3, 1, 1]], ["tile_x", "sp", [-1, 1, 3, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[6.263533807648824e-05], 0, 4.441951751708984, 1679734875.061717], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 532953, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 3, 1, 9]], ["tile_x", "sp", [-1, 1, 9, 3]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03166985511779785, 1679734830.2706807], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 194786, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 1, 3, 9]], ["tile_x", "sp", [-1, 1, 3, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[5.2539870861143824e-05], 0, 3.503537178039551, 1679734878.139398], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 269157, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 9, 3, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[2.6675057474927044e-05], 0, 3.7337288856506348, 1679734881.188235], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 292095, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 32]], ["tile_y", "sp", [-1, 1, 9, 3]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[4.5315401789494486e-05], 0, 4.057349443435669, 1679734884.2561846], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 482226, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 1]], ["tile_y", "sp", [-1, 3, 1, 3]], ["tile_x", "sp", [-1, 1, 1, 3]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0010501539508840864], 0, 5.791125297546387, 1679734887.3301802], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 560687, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 9, 1, 3]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[2.6842689699124545e-05], 0, 3.5057373046875, 1679734890.386813], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 962579, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 3, 9, 1]], ["tile_x", "sp", [-1, 1, 1, 27]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0015436588395773294], 0, 6.371425151824951, 1679734893.532814], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1048448, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 9, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 9]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.313581063815702e-05], 0, 6.699872255325317, 1679734896.598485], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 474673, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 9]], ["tile_x", "sp", [-1, 27, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0022546104909909907], 0, 6.028580188751221, 1679734898.0999641], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 888754, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 1, 3, 3]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1.864354732768415e-05], 0, 4.590809106826782, 1679734901.1557207], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 95507, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 3, 3, 1]], ["tile_x", "sp", [-1, 3, 3, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[6.203847013027056e-05], 0, 3.5732975006103516, 1679734904.231497], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 329943, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 3, 1, 3]], ["tile_x", "sp", [-1, 3, 3, 3]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.030869483947753906, 1679734830.270704], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 234903, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 4]], ["tile_y", "sp", [-1, 3, 3, 3]], ["tile_x", "sp", [-1, 1, 27, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002033791185865191], 0, 3.944167137145996, 1679734907.3110278], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 667565, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 9]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.9597877898582025e-05], 0, 3.552067995071411, 1679734910.3438268], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 991134, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 1, 3, 9]], ["tile_x", "sp", [-1, 1, 3, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.940345519950079e-05], 0, 5.280374526977539, 1679734913.4396043], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 986080, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 2]], ["tile_y", "sp", [-1, 3, 9, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.796912115822505e-05], 0, 3.9446816444396973, 1679734916.5148044], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 161759, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 2]], ["tile_y", "sp", [-1, 3, 9, 1]], ["tile_x", "sp", [-1, 1, 3, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.046434879302978516, 1679734830.2707167], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 913478, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 9, 1, 3]], ["tile_x", "sp", [-1, 1, 9, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00010393048785516397], 0, 3.6723110675811768, 1679734919.5897746], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 791527, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 3, 3, 3]], ["tile_x", "sp", [-1, 9, 3, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008158065131445905], 0, 11.715770959854126, 1679734922.6875095], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 255425, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 3, 1, 1]], ["tile_x", "sp", [-1, 3, 9, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[3.470481216489027e-05], 0, 3.7264225482940674, 1679734925.7368941], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 469349, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 3, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 27]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0010567990903693932], 0, 4.2560975551605225, 1679734928.8029997], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 885887, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 27]], ["tile_x", "sp", [-1, 1, 1, 3]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.012182644], 0, 11.071480751037598, 1679734932.0274136], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 622388, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 3, 3, 3]], ["tile_x", "sp", [-1, 1, 9, 3]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005232257792207793], 0, 4.066492080688477, 1679734935.1163044], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 417359, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 9, 1, 3]], ["tile_x", "sp", [-1, 9, 1, 3]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1679734830.2708042], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 548784, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 27]], ["tile_x", "sp", [-1, 1, 27, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001409632378080755], 0, 3.680872917175293, 1679734938.2533784], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 603722, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 27]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00047953056068324846], 0, 3.93414568901062, 1679734941.3313367], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 909323, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 3, 1, 9]], ["tile_x", "sp", [-1, 3, 1, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0062974646226415095], 0, 5.517149209976196, 1679734942.8703787], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 57150, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 1, 1, 9]], ["tile_x", "sp", [-1, 27, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[7.887646340617412e-05], 0, 5.908987045288086, 1679734958.3782487], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1199548, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 9]], ["tile_x", "sp", [-1, 1, 1, 27]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0003716839763163946], 0, 4.439316034317017, 1679734961.501476], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 758252, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 8]], ["tile_y", "sp", [-1, 1, 3, 9]], ["tile_x", "sp", [-1, 1, 9, 3]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00044112072559802034], 0, 4.964914798736572, 1679734964.604765], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1126559, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 128]], ["tile_y", "sp", [-1, 1, 9, 1]], ["tile_x", "sp", [-1, 1, 27, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[3.749168474417515e-05], 0, 3.706430673599243, 1679734967.6716383], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1030607, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 2]], ["tile_y", "sp", [-1, 3, 9, 1]], ["tile_x", "sp", [-1, 1, 27, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[3.7243832652018395e-05], 0, 3.688584804534912, 1679734970.7285216], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 428799, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 2]], ["tile_y", "sp", [-1, 1, 3, 3]], ["tile_x", "sp", [-1, 1, 3, 9]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00012379515193093347], 0, 4.170228004455566, 1679734973.7989082], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1126402, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 9, 3, 1]], ["tile_x", "sp", [-1, 1, 27, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.030046701431274414, 1679734948.4917443], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1125212, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 9]], ["tile_x", "sp", [-1, 3, 9, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00028440314724144047], 0, 4.070980787277222, 1679734976.8602147], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1366846, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 2]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 1, 27, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[8.474872127578511e-06], 0, 3.6614937782287598, 1679734979.8552763], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 22264, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 3, 3, 1]], ["tile_x", "sp", [-1, 1, 27, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[8.516397443680209e-06], 0, 3.4244117736816406, 1679734982.7920842], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1282200, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 3, 3, 1]], ["tile_x", "sp", [-1, 3, 3, 3]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[2.2744555193212318e-05], 0, 4.076207637786865, 1679734985.816792], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1205731, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 8]], ["tile_y", "sp", [-1, 1, 9, 1]], ["tile_x", "sp", [-1, 9, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1.8915752555117968e-05], 0, 4.061541795730591, 1679734988.8619628], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1126272, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 3, 3, 1]], ["tile_x", "sp", [-1, 1, 27, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.5327065534146175e-05], 0, 3.6104729175567627, 1679734991.8894536], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 194879, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 128]], ["tile_y", "sp", [-1, 27, 1, 1]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.012477275320987654], 0, 2.554835557937622, 1679734993.5402637], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1590339, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 8]], ["tile_y", "sp", [-1, 9, 1, 3]], ["tile_x", "sp", [-1, 9, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.001686327284671533], 0, 11.041274070739746, 1679734996.6694593], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1603250, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 3, 9, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.0178118163149795e-06], 0, 3.7661921977996826, 1679734999.6159022], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1620559, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 1, 9, 3]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[6.681293108871415e-06], 0, 3.8003857135772705, 1679735002.564679], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 382538, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 8]], ["tile_y", "sp", [-1, 1, 9, 1]], ["tile_x", "sp", [-1, 1, 1, 27]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00014090748356930606], 0, 4.037804126739502, 1679735005.6437452], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1135456, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 9, 1, 1]], ["tile_x", "sp", [-1, 1, 3, 3]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[2.5260949644973232e-05], 0, 3.6341805458068848, 1679735008.6858382], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 723505, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 8, 1]], ["tile_y", "sp", [-1, 1, 27, 1]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[2.31719730713246e-05], 0, 3.631417989730835, 1679735011.7253509], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1268088, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 2]], ["tile_y", "sp", [-1, 1, 9, 1]], ["tile_x", "sp", [-1, 3, 9, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[3.5342369033115516e-05], 0, 4.180368900299072, 1679735014.766692], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 213622, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 27, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[4.263766857100545e-06], 0, 3.426079034805298, 1679735017.662997], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 40065, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 16]], ["tile_y", "sp", [-1, 1, 3, 3]], ["tile_x", "sp", [-1, 1, 1, 9]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002802826541133455], 0, 3.6153745651245117, 1679735020.6145868], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1197452, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 8]], ["tile_y", "sp", [-1, 1, 3, 9]], ["tile_x", "sp", [-1, 1, 3, 9]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0011326607762039659], 0, 12.038982391357422, 1679735023.7055855], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 450313, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 4]], ["tile_y", "sp", [-1, 9, 1, 3]], ["tile_x", "sp", [-1, 1, 9, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0008417914462678666], 0, 4.992228031158447, 1679735026.7701695], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 160783, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 27]], ["tile_x", "sp", [-1, 9, 3, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.009830739398773006], 0, 4.301071643829346, 1679735030.0024674], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 695826, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 1, 3, 9]], ["tile_x", "sp", [-1, 1, 27, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[2.036910575172681e-05], 0, 3.8692996501922607, 1679735033.1218824], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1681278, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 4]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.6738565726360987e-05], 0, 7.4094953536987305, 1679735036.176448], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 990290, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 2]], ["tile_y", "sp", [-1, 9, 1, 3]], ["tile_x", "sp", [-1, 9, 1, 3]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0009909105142150805], 0, 7.7460551261901855, 1679735039.2535982], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1323865, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 8, 1]], ["tile_y", "sp", [-1, 9, 1, 3]], ["tile_x", "sp", [-1, 3, 1, 3]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679734954.4538617], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1009919, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 128]], ["tile_y", "sp", [-1, 1, 9, 3]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00014719858747697974], 0, 4.169525146484375, 1679735042.3160546], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 436781, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 27]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.009904969465346533], 0, 3.1167311668395996, 1679735043.8894608], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1632607, "code_hash": null, "entity": [["tile_f", "sp", [-1, 128, 1, 1]], ["tile_y", "sp", [-1, 3, 3, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679734954.4539447], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 529236, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[4.036510014645725e-05], 0, 3.6785836219787598, 1679735046.9494731], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 376941, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 3, 1, 1]], ["tile_x", "sp", [-1, 3, 1, 9]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[2.2541628589977e-05], 0, 3.676483154296875, 1679735050.0035267], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1198435, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 32]], ["tile_y", "sp", [-1, 9, 3, 1]], ["tile_x", "sp", [-1, 1, 1, 27]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.006509551375510204], 0, 10.919221639633179, 1679735053.1663606], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 434969, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 8]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00037073141331122694], 0, 5.493499040603638, 1679735056.1815665], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1213330, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 3, 1, 3]], ["tile_x", "sp", [-1, 3, 3, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1.5920869334521446e-05], 0, 3.9297029972076416, 1679735059.190579], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1463851, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 8]], ["tile_y", "sp", [-1, 1, 3, 9]], ["tile_x", "sp", [-1, 1, 27, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.1992352552914035e-05], 0, 3.8447816371917725, 1679735062.2420468], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1156583, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 1, 3, 9]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[2.1293975629298257e-05], 0, 3.753767728805542, 1679735065.2824843], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1324053, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 8]], ["tile_y", "sp", [-1, 1, 3, 3]], ["tile_x", "sp", [-1, 3, 1, 3]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005498823722050222], 0, 8.601371765136719, 1679735068.3608148], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 998687, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 2]], ["tile_y", "sp", [-1, 9, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 9]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0011406086019900498], 0, 4.489431858062744, 1679735071.4425163], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1710726, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 9]], ["tile_x", "sp", [-1, 9, 1, 3]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679734954.4567013], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1033147, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 4]], ["tile_y", "sp", [-1, 1, 27, 1]], ["tile_x", "sp", [-1, 1, 1, 3]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.3284448878063056e-05], 0, 3.8320302963256836, 1679735074.445617], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1342748, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 4]], ["tile_y", "sp", [-1, 1, 27, 1]], ["tile_x", "sp", [-1, 1, 1, 27]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679734955.5100822], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1791801, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 4]], ["tile_y", "sp", [-1, 3, 1, 3]], ["tile_x", "sp", [-1, 9, 3, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0426483205], 0, 5.120615482330322, 1679735087.8164964], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4177991, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 9]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002172981413394298], 0, 3.888150930404663, 1679735090.9100027], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1316463, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 2]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 3, 9, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[7.688973800649847e-05], 0, 3.861975908279419, 1679735093.9841914], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3057538, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 1, 1, 27]], ["tile_x", "sp", [-1, 1, 3, 3]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003854316112568567], 0, 4.503706693649292, 1679735097.071297], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4511513, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 32]], ["tile_y", "sp", [-1, 1, 9, 3]], ["tile_x", "sp", [-1, 1, 1, 27]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0072427704798206285], 0, 4.414411306381226, 1679735100.2346146], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1890594, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 32]], ["tile_y", "sp", [-1, 3, 3, 3]], ["tile_x", "sp", [-1, 1, 9, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.003605934856115108], 0, 2.7740626335144043, 1679735101.7470748], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3038587, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 4]], ["tile_y", "sp", [-1, 3, 1, 1]], ["tile_x", "sp", [-1, 9, 3, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1679735085.8313766], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3207422, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 2]], ["tile_y", "sp", [-1, 3, 9, 1]], ["tile_x", "sp", [-1, 1, 1, 9]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00021054613303769402], 0, 3.932213544845581, 1679735104.8450751], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5936539, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 1]], ["tile_y", "sp", [-1, 3, 1, 3]], ["tile_x", "sp", [-1, 1, 3, 3]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.000842635250795334], 0, 6.58440899848938, 1679735107.893462], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1844613, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 8]], ["tile_y", "sp", [-1, 3, 1, 3]], ["tile_x", "sp", [-1, 3, 9, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.04761916966666667], 0, 4.412744998931885, 1679735109.8927116], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1472206, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 2]], ["tile_y", "sp", [-1, 3, 9, 1]], ["tile_x", "sp", [-1, 1, 3, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00016969695582202588], 0, 3.983003854751587, 1679735112.9803925], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3685483, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 2]], ["tile_y", "sp", [-1, 9, 1, 3]], ["tile_x", "sp", [-1, 1, 9, 3]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0014021757311361664], 0, 4.009659767150879, 1679735116.1177962], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6454038, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 4]], ["tile_y", "sp", [-1, 27, 1, 1]], ["tile_x", "sp", [-1, 1, 27, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0038175307404580147], 0, 7.244638442993164, 1679735117.6305897], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6758830, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 27, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 9]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679735086.0051372], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1301749, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 16]], ["tile_y", "sp", [-1, 1, 9, 1]], ["tile_x", "sp", [-1, 9, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00012234406753680374], 0, 3.8239641189575195, 1679735120.7280247], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3026660, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 4, 1]], ["tile_y", "sp", [-1, 9, 1, 1]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.005322365292553191], 0, 5.627703428268433, 1679735122.2615252], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2757257, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 3, 1, 9]], ["tile_x", "sp", [-1, 3, 9, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00041835631360792494], 0, 6.350574731826782, 1679735125.3437839], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5674280, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 4]], ["tile_y", "sp", [-1, 3, 3, 1]], ["tile_x", "sp", [-1, 1, 3, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[9.009109342657343e-05], 0, 9.876547574996948, 1679735128.426357], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2370302, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 2]], ["tile_y", "sp", [-1, 9, 1, 3]], ["tile_x", "sp", [-1, 1, 9, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002246706988035615], 0, 4.095006465911865, 1679735131.517449], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5644707, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 27]], ["tile_x", "sp", [-1, 3, 1, 3]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679735086.02267], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1970289, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 27]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006598261911764706], 0, 3.995535135269165, 1679735134.6502864], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1603951, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 1]], ["tile_y", "sp", [-1, 9, 3, 1]], ["tile_x", "sp", [-1, 3, 9, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003694804964571429], 0, 3.8980088233947754, 1679735137.738001], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3620468, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 3, 9, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.002864534634751773], 0, 4.455881595611572, 1679735140.8603787], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 104819, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 1, 3, 3]], ["tile_x", "sp", [-1, 27, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0010210178918367346], 0, 2.4283945560455322, 1679735142.3538008], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2032732, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 27]], ["tile_x", "sp", [-1, 9, 3, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.01186220845882353], 0, 3.200618028640747, 1679735143.958254], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 670786, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 16]], ["tile_y", "sp", [-1, 1, 27, 1]], ["tile_x", "sp", [-1, 1, 1, 27]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.012405115197530863], 0, 2.943773031234741, 1679735145.572765], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4105463, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 9, 1, 3]], ["tile_x", "sp", [-1, 1, 1, 3]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006224075327174749], 0, 4.441762685775757, 1679735148.6709945], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2363643, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 3, 1, 9]], ["tile_x", "sp", [-1, 1, 3, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003937257463450292], 0, 4.761722803115845, 1679735151.7549908], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2109072, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 1, 9, 3]], ["tile_x", "sp", [-1, 1, 3, 9]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.001202380653243848], 0, 4.9326348304748535, 1679735154.8488123], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2558987, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 16]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 9, 3, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00020640718770764118], 0, 4.190434694290161, 1679735157.9341059], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3916547, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 16]], ["tile_y", "sp", [-1, 3, 1, 9]], ["tile_x", "sp", [-1, 3, 1, 3]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.1208062011], 0, 3.8704915046691895, 1679735159.7642546], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4229519, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 128]], ["tile_y", "sp", [-1, 3, 3, 1]], ["tile_x", "sp", [-1, 9, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0126368125875], 0, 2.541940927505493, 1679735161.3993218], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1639052, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 8]], ["tile_y", "sp", [-1, 1, 3, 9]], ["tile_x", "sp", [-1, 9, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1679735086.0274868], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6830877, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 64]], ["tile_y", "sp", [-1, 27, 1, 1]], ["tile_x", "sp", [-1, 9, 3, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.07312679290771484, 1679735086.0275059], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4577100, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 2]], ["tile_y", "sp", [-1, 9, 1, 1]], ["tile_x", "sp", [-1, 1, 9, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.06825470924377441, 1679735086.0275135], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6188892, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 1]], ["tile_y", "sp", [-1, 3, 3, 3]], ["tile_x", "sp", [-1, 1, 3, 9]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679735086.0275688], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 897495, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 27]], ["tile_x", "sp", [-1, 1, 3, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003001097951337296], 0, 3.932419538497925, 1679735164.4817526], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3538767, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 8]], ["tile_y", "sp", [-1, 1, 27, 1]], ["tile_x", "sp", [-1, 3, 3, 3]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0004677869652777778], 0, 4.413883209228516, 1679735167.5786893], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 633098, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 8]], ["tile_y", "sp", [-1, 1, 9, 3]], ["tile_x", "sp", [-1, 27, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.032291377870967745], 0, 3.4051449298858643, 1679735169.4422097], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 29641, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 1, 9, 1]], ["tile_x", "sp", [-1, 9, 1, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00011699309298105539], 0, 3.7536888122558594, 1679735172.515883], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5985664, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 3, 3, 3]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00024315389445196214], 0, 6.838479518890381, 1679735175.623681], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4279034, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 4]], ["tile_y", "sp", [-1, 1, 3, 9]], ["tile_x", "sp", [-1, 9, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.21919012069702148, 1679735086.0275872], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5249193, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 1]], ["tile_y", "sp", [-1, 27, 1, 1]], ["tile_x", "sp", [-1, 1, 9, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00013321783717662615], 0, 4.145404100418091, 1679735178.7173698], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4283075, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 128, 1]], ["tile_y", "sp", [-1, 9, 1, 3]], ["tile_x", "sp", [-1, 1, 3, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.24136042594909668, 1679735086.0275953], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 966884, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 3, 1, 9]], ["tile_x", "sp", [-1, 9, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.004057054773279352], 0, 3.3859047889709473, 1679735180.2724555], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 418933, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 2, 1]], ["tile_x", "sp", [-1, 2, 1, 49]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0024000869090909094], 0, 6.532034158706665, 1679735194.3175004], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 183746, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 1]], ["tile_x", "sp", [-1, 2, 49, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.8300522538573508e-05], 0, 3.9138498306274414, 1679735197.3224125], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 157360, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 2]], ["tile_x", "sp", [-1, 7, 2, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[6.183280991289601e-05], 0, 4.201483726501465, 1679735200.3923993], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 320203, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 7, 2, 7]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[5.034532423811779e-05], 0, 4.698207855224609, 1679735203.4809477], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 408120, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 2, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002871070311111111], 0, 4.1087071895599365, 1679735206.562764], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 36166, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 2]], ["tile_x", "sp", [-1, 2, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[8.254517423621079e-05], 0, 4.124077081680298, 1679735209.633125], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 377694, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 7, 7, 2]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.557772779753979e-05], 0, 4.897590160369873, 1679735212.6362464], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 263922, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 64, 1, 2]], ["tile_x", "sp", [-1, 1, 1, 196]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.21641625969999997], 0, 4.596171140670776, 1679735215.5068812], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 34401, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 4]], ["tile_x", "sp", [-1, 1, 14, 14]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[5.307537125390392e-05], 0, 4.215780973434448, 1679735218.6250694], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 80366, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 8]], ["tile_x", "sp", [-1, 14, 2, 7]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0026299545800524933], 0, 3.2614493370056152, 1679735220.1351202], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 339015, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 2, 14, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1.957133851242117e-05], 0, 4.127223491668701, 1679735223.1774445], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 93568, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 8]], ["tile_x", "sp", [-1, 2, 1, 14]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0018612285552995391], 0, 4.991137266159058, 1679735226.2884672], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 152198, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 2]], ["tile_x", "sp", [-1, 7, 2, 7]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0009926026764705883], 0, 4.445265531539917, 1679735229.3683288], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 194192, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 32, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.6610726639539184e-05], 0, 4.073216676712036, 1679735232.37847], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 340179, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 8]], ["tile_x", "sp", [-1, 2, 98, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.25238633155822754, 1679735186.7966712], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 172160, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 4]], ["tile_x", "sp", [-1, 2, 98, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.754100247560798e-05], 0, 4.029676198959351, 1679735235.3752756], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 393324, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 4]], ["tile_x", "sp", [-1, 1, 28, 7]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[4.180012433675737e-05], 0, 4.719709873199463, 1679735238.43411], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 377041, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 2, 2]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00013810034402806298], 0, 4.13000226020813, 1679735241.5131273], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 27734, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 64, 2, 1]], ["tile_x", "sp", [-1, 2, 49, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.3032972579312746e-05], 0, 4.073130369186401, 1679735244.5560715], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 85617, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 8, 2]], ["tile_x", "sp", [-1, 49, 2, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0007093412659060992], 0, 4.534660816192627, 1679735247.6526875], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 134508, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 16]], ["tile_x", "sp", [-1, 4, 7, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[3.202364335426583e-05], 0, 4.094691038131714, 1679735250.7127745], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 356496, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 8]], ["tile_x", "sp", [-1, 1, 4, 7]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[3.281892790269828e-05], 0, 4.46216607093811, 1679735253.7829618], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 156081, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 4]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[5.129913196752749e-05], 0, 4.697200775146484, 1679735256.9029639], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 264359, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 128]], ["tile_x", "sp", [-1, 4, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0013296484130255566], 0, 8.97710108757019, 1679735260.012351], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 145088, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 1, 2, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.000340879673628692], 0, 4.070531368255615, 1679735263.1093862], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 428486, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 8]], ["tile_x", "sp", [-1, 1, 4, 7]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.102571742582694e-05], 0, 5.287920713424683, 1679735266.1700006], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 198782, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 32, 2]], ["tile_x", "sp", [-1, 49, 1, 4]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0004579172284580499], 0, 5.204052686691284, 1679735269.2607026], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 133719, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 2]], ["tile_x", "sp", [-1, 98, 2, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0023722343246445495], 0, 2.553208827972412, 1679735270.7605455], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 374119, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 4]], ["tile_x", "sp", [-1, 49, 4, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.5484675733024693e-05], 0, 4.604036808013916, 1679735273.7818837], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 133112, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 32, 1]], ["tile_x", "sp", [-1, 1, 2, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[2.197724797993098e-05], 0, 4.073621034622192, 1679735276.8231282], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 236956, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 4]], ["tile_x", "sp", [-1, 4, 7, 7]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[3.978081569456535e-05], 0, 4.202038288116455, 1679735279.886133], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 408665, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 4]], ["tile_x", "sp", [-1, 28, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[9.479932946033618e-05], 0, 5.7450644969940186, 1679735282.9812248], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 421655, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 8]], ["tile_x", "sp", [-1, 49, 2, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679735191.7574527], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 235436, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 64]], ["tile_x", "sp", [-1, 2, 1, 7]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.005256937235602094], 0, 2.4569485187530518, 1679735284.510709], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 111374, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 64, 2, 1]], ["tile_x", "sp", [-1, 1, 28, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[2.0398971260732035e-05], 0, 4.040969371795654, 1679735287.5387397], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 418050, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 8]], ["tile_x", "sp", [-1, 7, 2, 14]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006550527538980194], 0, 11.671846628189087, 1679735290.5808938], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 193497, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 8, 2]], ["tile_x", "sp", [-1, 14, 2, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[3.7104701197074846e-05], 0, 4.761313199996948, 1679735293.6384916], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 84550, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 4]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[4.32391420889069e-05], 0, 3.941967725753784, 1679735296.6966584], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 146826, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 4]], ["tile_x", "sp", [-1, 28, 7, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.000174220469096485], 0, 4.084900617599487, 1679735299.5529878], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 244412, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 8]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[8.99441514965035e-05], 0, 4.049021005630493, 1679735302.659935], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 397815, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 1, 4, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.931847338463418e-05], 0, 3.6579527854919434, 1679735305.7182138], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 367366, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 2]], ["tile_x", "sp", [-1, 2, 1, 7]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[7.589537129690586e-05], 0, 4.35319447517395, 1679735308.7931473], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 390489, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 1, 1, 4]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[8.522866869961816e-05], 0, 3.9510855674743652, 1679735311.8601787], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 181189, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 16]], ["tile_x", "sp", [-1, 1, 2, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[2.7075672874921262e-05], 0, 3.994516134262085, 1679735314.8995922], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 406748, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 4]], ["tile_x", "sp", [-1, 1, 7, 28]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679735192.9417417], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1113938, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 3, 1, 3]], ["tile_x", "sp", [-1, 3, 3, 3]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679735326.3594396], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 260481, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 3, 1, 3]], ["tile_x", "sp", [-1, 9, 1, 3]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.074374595625], 0, 6.492477178573608, 1679735328.6860194], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 823781, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 1, 9, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[8.164813880158168e-05], 0, 3.478600263595581, 1679735331.7726238], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 625112, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 9, 1, 1]], ["tile_x", "sp", [-1, 1, 3, 9]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0014994645007496252], 0, 2.4034249782562256, 1679735333.270213], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 383005, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 27]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03202342987060547, 1679735326.359513], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 317125, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 9, 1, 1]], ["tile_x", "sp", [-1, 27, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.2735203369], 0, 7.185538053512573, 1679735336.8033311], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 24730, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 3, 1, 1]], ["tile_x", "sp", [-1, 9, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[9.367580929393974e-05], 0, 3.7064428329467773, 1679735339.90224], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 23767, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[4.7734073159173036e-05], 0, 3.467493772506714, 1679735343.0119507], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 821353, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 1, 9, 1]], ["tile_x", "sp", [-1, 1, 3, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[3.2686555021193344e-05], 0, 3.3897767066955566, 1679735346.0704048], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 195437, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 1, 27, 1]], ["tile_x", "sp", [-1, 3, 3, 3]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02947521209716797, 1679735326.3595555], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1181027, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 1, 27, 1]], ["tile_x", "sp", [-1, 3, 3, 3]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.06687307357788086, 1679735326.3595743], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 55336, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 3, 9, 1]], ["tile_x", "sp", [-1, 1, 27, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[6.687015169029898e-05], 0, 3.406947374343872, 1679735349.1375031], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1065641, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 1, 27, 1]], ["tile_x", "sp", [-1, 3, 1, 3]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[7.280343583710406e-05], 0, 3.5395052433013916, 1679735352.212075], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 270206, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 3, 3, 1]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[3.599017251712329e-05], 0, 3.4654359817504883, 1679735355.2601733], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 327197, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 9, 1, 1]], ["tile_x", "sp", [-1, 9, 1, 3]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.026679053052631584], 0, 3.925715208053589, 1679735357.0430505], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 236327, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 3, 1, 3]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[4.669810398249453e-05], 0, 3.4006547927856445, 1679735360.1061914], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1087397, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 3, 1, 9]], ["tile_x", "sp", [-1, 1, 1, 3]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0013344058426666668], 0, 3.5923054218292236, 1679735361.5958467], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 177284, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 4]], ["tile_y", "sp", [-1, 3, 3, 1]], ["tile_x", "sp", [-1, 1, 3, 9]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03672313690185547, 1679735326.359616], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 21617, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 9, 3, 1]], ["tile_x", "sp", [-1, 1, 1, 27]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0024865335784615386], 0, 3.685570478439331, 1679735364.7634134], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1041226, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 1, 3, 3]], ["tile_x", "sp", [-1, 1, 27, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.059797048568725586, 1679735326.3596375], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 265660, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 27, 1, 1]], ["tile_x", "sp", [-1, 3, 1, 9]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.05473237047368421], 0, 3.8208892345428467, 1679735366.8918474], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 36001, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 9, 1, 1]], ["tile_x", "sp", [-1, 9, 1, 3]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0654188155625], 0, 4.439759016036987, 1679735369.166136], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 573391, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 27]], ["tile_x", "sp", [-1, 3, 1, 3]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04457235336303711, 1679735326.3596623], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 451770, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 1, 9, 1]], ["tile_x", "sp", [-1, 27, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[7.445791538675055e-05], 0, 3.4643020629882812, 1679735372.257868], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1116866, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 3, 1, 9]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001633775375430075], 0, 5.370687484741211, 1679735375.3469183], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 147430, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 9, 1, 3]], ["tile_x", "sp", [-1, 3, 1, 3]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.05671262741088867, 1679735326.359687], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 521967, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 9, 3, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00019404591041366045], 0, 5.672442197799683, 1679735378.4373422], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 540308, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 3, 9, 1]], ["tile_x", "sp", [-1, 9, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.030475854873657227, 1679735326.359708], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 114783, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 4]], ["tile_y", "sp", [-1, 1, 27, 1]], ["tile_x", "sp", [-1, 9, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006662820837804375], 0, 3.8955509662628174, 1679735381.5267513], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 568476, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 3, 1, 3]], ["tile_x", "sp", [-1, 1, 9, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.028879642486572266, 1679735326.3597286], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 567370, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 3, 1, 3]], ["tile_x", "sp", [-1, 9, 3, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03784346580505371, 1679735326.359745], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 514315, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 1, 1, 27]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[5.692145679756167e-05], 0, 4.131727933883667, 1679735384.6020153], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 400254, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 1, 9, 1]], ["tile_x", "sp", [-1, 3, 1, 9]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.028830528259277344, 1679735326.3597658], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1165718, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 9]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[7.483316713182622e-05], 0, 8.33472204208374, 1679735387.6958408], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 451905, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 1, 27, 1]], ["tile_x", "sp", [-1, 27, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002079072192168985], 0, 4.052494525909424, 1679735390.8350172], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 532053, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 9, 3]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[9.368856235046975e-05], 0, 4.248491525650024, 1679735393.90565], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 425374, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 16]], ["tile_y", "sp", [-1, 1, 9, 3]], ["tile_x", "sp", [-1, 1, 1, 27]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0035732479084821427], 0, 5.750749826431274, 1679735397.0123377], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 846273, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 9, 1, 3]], ["tile_x", "sp", [-1, 1, 9, 3]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002328919405997693], 0, 4.212636709213257, 1679735400.1036959], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 828237, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 1, 27, 1]], ["tile_x", "sp", [-1, 1, 1, 27]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.003204931107142857], 0, 3.906148672103882, 1679735403.2188122], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 463120, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 1, 3, 3]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[5.496640501889747e-05], 0, 3.4985315799713135, 1679735406.3466296], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 280956, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 3, 1, 9]], ["tile_x", "sp", [-1, 1, 1, 3]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.015222706181818181], 0, 2.9115254878997803, 1679735408.0108829], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 559173, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 3, 3, 1]], ["tile_x", "sp", [-1, 1, 1, 27]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03870868682861328, 1679735326.359815], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 463152, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 1, 3, 3]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[6.815273042889199e-05], 0, 3.481095790863037, 1679735411.0842063], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1018379, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 3, 3, 1]], ["tile_x", "sp", [-1, 1, 27, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03045964241027832, 1679735326.3598351], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 691358, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 3, 3, 1]], ["tile_x", "sp", [-1, 3, 1, 9]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.043883563478260876], 0, 4.208197832107544, 1679735413.0469596], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 25680, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 3, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0015641319432485323], 0, 5.608175039291382, 1679735427.4454699], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 93506, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 6, 8]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[7.1440593008296e-05], 0, 3.918797492980957, 1679735430.5197718], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 74923, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00021852788287800922], 0, 3.840858221054077, 1679735433.5988483], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 28467, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[6.925500030124372e-05], 0, 3.7286362648010254, 1679735436.724256], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 50955, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 3, 16]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00012591141260923845], 0, 3.807976007461548, 1679735439.8007061], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 69275, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 6]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[6.424713469909348e-05], 0, 3.5752367973327637, 1679735442.8790731], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 60750, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 12]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00014194569590077408], 0, 3.617779493331909, 1679735445.9520805], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 67859, "code_hash": null, "entity": [["tile_f", "sp", [-1, 6, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.000447425660486995], 0, 4.13876485824585, 1679735449.034619], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 119315, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.124365490065707e-05], 0, 10.000958442687988, 1679735452.0995972], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 117397, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 3]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.06963968276977539, 1679735423.3584847], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1569, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 6, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[8.2416145632561e-05], 0, 3.6204946041107178, 1679735455.2284584], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 99607, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 6, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.049260616302490234, 1679735423.3585024], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 29778, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00011422737483181077], 0, 4.3090996742248535, 1679735458.3049254], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 62522, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 3]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00013981033763645816], 0, 3.5647003650665283, 1679735461.3718123], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 75779, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 12, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03618812561035156, 1679735423.3585184], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 92533, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001507990778650215], 0, 6.029240608215332, 1679735464.4427385], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 77549, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 12]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03900575637817383, 1679735423.3585312], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 62677, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.004074128737373737], 0, 5.761162042617798, 1679735467.558126], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 112497, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 3]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001172326960663128], 0, 5.394410848617554, 1679735470.6437783], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 58808, "code_hash": null, "entity": [["tile_f", "sp", [-1, 24, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005093383017023959], 0, 3.837491273880005, 1679735473.7817793], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 45597, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1679735424.5026646], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 99311, "code_hash": null, "entity": [["tile_f", "sp", [-1, 12, 1, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.20804953575134277, 1679735424.5026906], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 19068, "code_hash": null, "entity": [["tile_f", "sp", [-1, 12, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.07417511940002441, 1679735424.5027013], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 9290, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.4569501482442325e-05], 0, 3.992095470428467, 1679735476.822912], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 6206, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[8.021209403795388e-05], 0, 3.53120756149292, 1679735479.8936372], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 66422, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 3, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[6.566103700684707e-05], 0, 3.533508062362671, 1679735482.9557457], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 112913, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 12, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[7.400807562600505e-05], 0, 3.6958885192871094, 1679735486.03786], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 75700, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 3, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00017187057950793482], 0, 3.5601749420166016, 1679735489.1186535], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4896, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 24]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[3.1639934786447196e-05], 0, 4.251118421554565, 1679735492.218803], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1092, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 6]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0030731761523809524], 0, 4.277994394302368, 1679735495.3359659], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 87354, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679735424.5398784], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13714, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 1, 16]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.005290604986885246], 0, 4.510854482650757, 1679735498.4733598], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 110083, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 24, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.3593687969827025e-05], 0, 3.9738283157348633, 1679735501.479406], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 81651, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 6, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0014751139392824289], 0, 4.034459829330444, 1679735504.5532691], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 43591, "code_hash": null, "entity": [["tile_f", "sp", [-1, 12, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.03413087563333333], 0, 4.576287269592285, 1679735506.4280424], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 78370, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 6]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.050518035888671875, 1679735424.539901], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 21181, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0008689142484795831], 0, 2.5305299758911133, 1679735507.9057245], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 118062, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 24, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.06789255142211914, 1679735424.5399096], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 37036, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 3]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1.9137503590078326e-05], 0, 4.095131874084473, 1679735510.928377], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 76730, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[6.650723984413863e-05], 0, 3.630526304244995, 1679735514.010825], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 89736, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 24]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[6.775201782854253e-05], 0, 4.557232856750488, 1679735517.0707364], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 83507, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 6, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[4.5823824637515694e-05], 0, 3.5669901371002197, 1679735520.1396146], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 91621, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 3, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[7.99841207213473e-05], 0, 3.8576600551605225, 1679735523.205393], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 56947, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 12, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.043833255767822266, 1679735424.539934], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 69261, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 3, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00019607623209516874], 0, 3.6472463607788086, 1679735526.2997708], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 188702, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 6, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[3.296571224519541e-05], 0, 3.7755322456359863, 1679735540.7343414], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 227775, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 12, 16]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0012045505546407185], 0, 6.467202186584473, 1679735543.8340476], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 107815, "code_hash": null, "entity": [["tile_f", "sp", [-1, 6, 2, 16]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[6.182596853872157e-05], 0, 3.6705164909362793, 1679735546.916208], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 301567, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.750879494748098e-05], 0, 4.255600214004517, 1679735549.9673045], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 32936, "code_hash": null, "entity": [["tile_f", "sp", [-1, 24, 1, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.6425110600226266e-05], 0, 3.5453457832336426, 1679735553.0004952], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 119813, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 3, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0007056671335149864], 0, 5.524657249450684, 1679735555.995656], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 69565, "code_hash": null, "entity": [["tile_f", "sp", [-1, 192, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.013866081499999999], 0, 5.676126003265381, 1679735559.24436], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 225122, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 1, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[2.101033975291659e-05], 0, 3.760375499725342, 1679735562.3443031], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 736, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 16, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[7.713735352788692e-06], 0, 3.36749005317688, 1679735565.2860334], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 74908, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 1, 32]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0011379530446808512], 0, 3.951693296432495, 1679735568.3652785], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 187367, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00028766010473815464], 0, 4.564812183380127, 1679735571.4469361], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 30785, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.7895365611869007e-05], 0, 3.64920973777771, 1679735574.4890075], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 101031, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 6]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1.5139849383856168e-05], 0, 4.117085695266724, 1679735577.5182388], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7719, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 48]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.000873343388254486], 0, 3.721405267715454, 1679735580.5992033], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 61053, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 6]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1679735537.8246818], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 214842, "code_hash": null, "entity": [["tile_f", "sp", [-1, 6, 16, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.033449411392211914, 1679735537.824735], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 592, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 3, 8]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[3.246648915878709e-05], 0, 3.6531856060028076, 1679735583.6621058], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 96408, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 24]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0004744100638047633], 0, 3.920269727706909, 1679735586.746759], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 52744, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 48]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003242957756952842], 0, 3.783663511276245, 1679735589.825741], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 171175, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 3]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.016594109917525773], 0, 4.906729221343994, 1679735593.0895925], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 66518, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 48]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0035202027702407003], 0, 6.646337032318115, 1679735596.2214477], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 90064, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1.3040043882339286e-05], 0, 3.7531814575195312, 1679735599.2500238], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 287366, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005929275700660308], 0, 11.037801265716553, 1679735602.3410058], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 72437, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 3, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.006143753633587786], 0, 5.016394138336182, 1679735605.4820638], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 196458, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 6]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[6.371093054346966e-05], 0, 3.627520799636841, 1679735608.5815344], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 116901, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 24]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00013369295898372634], 0, 4.361940622329712, 1679735611.6693716], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 188021, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 3, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.005841500543478261], 0, 4.7263383865356445, 1679735614.8202913], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 278279, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 24, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.018688114591781e-05], 0, 3.8496687412261963, 1679735617.9079583], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 180124, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 3, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[6.1443316429855965e-06], 0, 3.4757437705993652, 1679735620.8355644], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 70611, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 8, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[5.085409319299375e-06], 0, 3.427607774734497, 1679735623.7696633], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 15931, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 24, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00015808475007347898], 0, 4.450333833694458, 1679735626.8514209], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 187420, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 12, 8]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.000653263673992674], 0, 4.3424177169799805, 1679735629.9182458], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 131197, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 3]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[7.832533360911038e-05], 0, 4.337082862854004, 1679735633.0365756], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 314625, "code_hash": null, "entity": [["tile_f", "sp", [-1, 6, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[7.255891066109665e-06], 0, 4.42450475692749, 1679735636.0399628], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 305026, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 12]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679735537.865418], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 224378, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 8]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1.8668258254758627e-05], 0, 3.7452988624572754, 1679735639.0747883], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 226825, "code_hash": null, "entity": [["tile_f", "sp", [-1, 96, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0009789659834558825], 0, 5.09387731552124, 1679735642.153369], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 229989, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 3]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1.0006910704141706e-05], 0, 3.5351314544677734, 1679735645.1259904], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 268928, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.376031409458385e-05], 0, 4.521944046020508, 1679735648.1600606], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 78652, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 3, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[6.091342311618036e-06], 0, 3.4010398387908936, 1679735651.0783324], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 278927, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 6, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[4.491167965683526e-05], 0, 4.2426018714904785, 1679735654.1332054], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 182431, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 2, 32]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0007712618688760808], 0, 3.7997395992279053, 1679735657.2125754], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 209316, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 48]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008059178188660312], 0, 3.7196943759918213, 1679735660.3257182], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 54468, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[7.909513256701005e-06], 0, 3.558084011077881, 1679735663.2821376], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 56620, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 3]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1.0353072910921355e-05], 0, 3.576521873474121, 1679735666.2694814], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 721809, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 96, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2210068702697754, 1679735668.9742405], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 634322, "code_hash": null, "entity": [["tile_f", "sp", [-1, 6, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.049779415130615234, 1679735668.974257], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 580341, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 24, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005782918364937388], 0, 4.970354080200195, 1679735680.92893], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 952428, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 6, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1.8291855450291856e-05], 0, 3.946131944656372, 1679735683.9753237], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 645181, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 12, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0003303821279640229], 0, 3.6934924125671387, 1679735687.0521698], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 74244, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 48]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.017616482912280705], 0, 2.7001564502716064, 1679735688.7138615], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 376890, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 6]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.003122632177570094], 0, 4.056252479553223, 1679735690.2230804], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 849929, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.000206786515426962], 0, 3.7201385498046875, 1679735693.306551], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 358129, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 16]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.009365618831775701], 0, 3.662353515625, 1679735694.881216], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 657488, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 12]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008456584973849374], 0, 3.9996232986450195, 1679735697.9700625], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 39981, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 96]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.013321188671052633], 0, 2.470250368118286, 1679735699.5930655], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 282404, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 3]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00018541570837166512], 0, 4.610594749450684, 1679735702.678142], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 356625, "code_hash": null, "entity": [["tile_f", "sp", [-1, 6, 8, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1679735677.956422], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 645192, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00014643591046131492], 0, 3.681770086288452, 1679735705.80201], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 765958, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 12, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0126219009375], 0, 3.883009910583496, 1679735707.4288816], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1238770, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 12]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679735677.9587967], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 96306, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 8, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002632315861450693], 0, 3.8001177310943604, 1679735710.5234678], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 909154, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 12]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.01480419382352941], 0, 2.864232063293457, 1679735712.1680186], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 785291, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 12, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00017348718129032257], 0, 3.917104482650757, 1679735715.2545137], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1029590, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[2.1188465540495427e-05], 0, 3.814103364944458, 1679735718.2910821], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1086125, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 3]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002451103336874051], 0, 3.942896842956543, 1679735721.3717582], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7362, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 24]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1679735677.970379], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 755560, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 6]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[9.200187540628387e-05], 0, 3.61029314994812, 1679735724.4552972], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 444752, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 6]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00859273426737968], 0, 6.213688850402832, 1679735727.6505404], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1010939, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.000798742909744409], 0, 2.3004677295684814, 1679735729.1355314], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1213942, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 24]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679735677.9704394], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1193476, "code_hash": null, "entity": [["tile_f", "sp", [-1, 6, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002543627644836272], 0, 3.9065849781036377, 1679735732.2347906], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 889902, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 3]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[6.822511470126787e-05], 0, 3.8270511627197266, 1679735735.3008084], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 385668, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 12]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002425093116083496], 0, 4.112646818161011, 1679735738.4090748], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 718274, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005525890252904989], 0, 3.853982448577881, 1679735741.5051255], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1236617, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 16, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00015032883751690967], 0, 2.0874953269958496, 1679735742.9767551], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 32662, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 24, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00016067126368703963], 0, 3.900272846221924, 1679735746.0992494], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 567656, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 3]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.009789489375757576], 0, 9.989237070083618, 1679735749.2983146], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1236525, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 6, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00015653213280264052], 0, 3.7052958011627197, 1679735752.3819604], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1022319, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 6, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002230303663352665], 0, 4.097635507583618, 1679735755.4653916], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 724353, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 12]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0034389650515463917], 0, 2.435997486114502, 1679735756.9823642], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 928115, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 192, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.048583269119262695, 1679735677.9704742], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 232833, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 3, 32]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.010910152260869567], 0, 2.6065585613250732, 1679735758.5838342], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1041623, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0015951879731075699], 0, 5.598653793334961, 1679735761.6627133], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 159117, "code_hash": null, "entity": [["tile_f", "sp", [-1, 6, 2, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.06310868263244629, 1679735677.9704847], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 929321, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 12]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679735677.9759068], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1107052, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 12, 8]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.000215882016849425], 0, 4.9466516971588135, 1679735764.7413282], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 652997, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 3]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.04435878852173913], 0, 4.1156744956970215, 1679735766.760074], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 227337, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005134449790476191], 0, 4.406941652297974, 1679735769.8621702], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 847209, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 1, 3]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.23682332038879395, 1679735677.9759483], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 186023, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 4]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.5371732416472112e-05], 0, 3.918820858001709, 1679735783.1834948], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 67899, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 3, 1]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[4.828831060971201e-05], 0, 4.301539659500122, 1679735786.2475576], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 165393, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 96, 1]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 48]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[2.2821936365472857e-05], 0, 4.677190542221069, 1679735789.2725995], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2122, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 3, 2]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[4.015568423173804e-05], 0, 4.326577425003052, 1679735792.321616], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 181049, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 12]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.8379755312905693e-05], 0, 5.232310056686401, 1679735795.371992], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 171536, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 4]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00013980964565632044], 0, 5.269885063171387, 1679735798.444726], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 134483, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 192, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[2.6054416089381796e-05], 0, 4.255914688110352, 1679735801.490307], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 122241, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 12]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 12]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[5.0086892730109205e-05], 0, 4.352886199951172, 1679735804.5602205], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 38133, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 3]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1.6246356355158506e-05], 0, 4.2012856006622314, 1679735807.5734565], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 88960, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 3, 8]], ["tile_x", "sp", [-1, 7, 7, 1]], ["tile_rc", "sp", [-1, 12]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[3.09983432229735e-05], 0, 4.765599012374878, 1679735810.626067], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 63019, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 3, 2, 4]], ["tile_x", "sp", [-1, 7, 1, 7]], ["tile_rc", "sp", [-1, 24]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006340411080651569], 0, 5.444655418395996, 1679735813.6892061], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 136473, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 12, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[2.1086046436213335e-05], 0, 4.344047546386719, 1679735816.747086], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 49794, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 6, 16, 1]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 6]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[2.2057325174387033e-05], 0, 4.267424821853638, 1679735819.7862637], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 34887, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 12]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[4.8866433150684926e-05], 0, 4.4455788135528564, 1679735822.8471427], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 94702, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 16]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 24]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[5.841730802318376e-05], 0, 5.45664381980896, 1679735825.9104483], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 57634, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 4]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[6.135517296924139e-05], 0, 5.078616380691528, 1679735828.9824789], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 21342, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 64, 3]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 12]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.7072326163391934e-05], 0, 4.2449140548706055, 1679735832.0343158], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 62272, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 1, 49, 1]], ["tile_rc", "sp", [-1, 24]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1.4129118131818755e-05], 0, 4.204869031906128, 1679735835.041084], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 161718, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 12, 2, 2]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 24]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[7.58030486886095e-05], 0, 5.002785682678223, 1679735838.1342359], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 71694, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 2]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.557388163987202e-05], 0, 4.333795070648193, 1679735841.1469278], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 79171, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 6, 8, 4]], ["tile_x", "sp", [-1, 1, 49, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[2.122346807219983e-05], 0, 4.624335527420044, 1679735844.1648781], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 28913, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 24]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[4.787509401529923e-05], 0, 4.230087518692017, 1679735847.211409], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 45339, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 32]], ["tile_x", "sp", [-1, 7, 7, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0001443189851347721], 0, 4.966501235961914, 1679735850.2883368], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 22216, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 4, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 12]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[3.226959132295641e-05], 0, 4.350970268249512, 1679735853.3357387], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 154457, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 6]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.006051712667924528], 0, 5.438084125518799, 1679735856.4658036], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 54310, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 12, 4]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 12]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[3.56055110699046e-05], 0, 4.325217008590698, 1679735859.5130558], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 84194, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 3, 4]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[6.314295937647614e-05], 0, 4.77804708480835, 1679735862.635817], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 27425, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 4]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 24]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.593268849419342e-05], 0, 4.650213718414307, 1679735865.6830282], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 177541, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 12, 2]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.366574800339089e-05], 0, 4.36355447769165, 1679735868.7231395], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 156316, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 48, 1]], ["tile_x", "sp", [-1, 1, 49, 1]], ["tile_rc", "sp", [-1, 12]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.30217528343200684, 1679735773.8236506], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 190950, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 12, 2, 2]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 12]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.066558390410959e-05], 0, 4.872670650482178, 1679735871.7779446], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7477, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[6.849931024789164e-05], 0, 4.523672819137573, 1679735874.8495736], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 82467, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 1, 49, 1]], ["tile_rc", "sp", [-1, 6]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.4938896568641597e-05], 0, 4.383455991744995, 1679735877.8746665], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3590, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 2, 6]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00011070040799339617], 0, 4.412519931793213, 1679735880.9515953], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 196116, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 6]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 24]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.9012474157625923e-05], 0, 8.759407997131348, 1679735883.9900484], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 157274, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 12]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1.6596434590767007e-05], 0, 4.172037363052368, 1679735886.9843884], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 148281, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 48, 2, 2]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 6]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.004743580601895734], 0, 10.351412773132324, 1679735888.5116029], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 67248, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 6, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[5.2403745910221176e-05], 0, 4.276669502258301, 1679735891.5665386], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 188063, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 16, 6]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0004194684635067114], 0, 5.269854307174683, 1679735893.0431335], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 56697, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 8]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 12]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[2.0437284203731198e-05], 0, 4.262357234954834, 1679735896.0828135], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 114250, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 48, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 6]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00014032366142757903], 0, 4.623085021972656, 1679735899.1801767], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 13337, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 6]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.006049343581132075], 0, 4.799394369125366, 1679735902.3098528], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 139300, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 3, 4]], ["tile_x", "sp", [-1, 7, 7, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[4.577259036419683e-05], 0, 4.213492393493652, 1679735905.3757908], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 162940, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 3, 1, 32]], ["tile_x", "sp", [-1, 7, 7, 1]], ["tile_rc", "sp", [-1, 24]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005413548004726536], 0, 4.215025901794434, 1679735908.4678094], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 103416, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 6, 8]], ["tile_x", "sp", [-1, 7, 1, 7]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00035340393199105146], 0, 4.3768041133880615, 1679735911.491223], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 159325, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[2.0181272800853066e-05], 0, 3.3988265991210938, 1679735925.7874053], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 160256, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1.5214929564322338e-05], 0, 3.4735188484191895, 1679735928.8274243], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 84678, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00012146882452972161], 0, 3.721954107284546, 1679735931.9060497], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 85881, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 3, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1679735922.940858], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 117219, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 12, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0022566228254189942], 0, 7.268631458282471, 1679735935.0352225], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 80141, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 3, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00011632339961041772], 0, 3.574136257171631, 1679735938.1160989], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 116769, "code_hash": null, "entity": [["tile_f", "sp", [-1, 48, 1, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00018524829893360852], 0, 3.4688704013824463, 1679735941.2265441], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 182837, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 24]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0009556928049645391], 0, 6.227153062820435, 1679735944.3256967], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 171778, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 24]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 96]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0278780460357666, 1679735922.9409301], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 117500, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.000261636967595593], 0, 3.8245770931243896, 1679735947.4062674], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 136764, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 3, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[7.858018347059109e-05], 0, 3.4416024684906006, 1679735950.4894922], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 115963, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 24, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[5.571948228059204e-05], 0, 3.3842520713806152, 1679735953.556312], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 66955, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 8, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.027428388595581055, 1679735922.940963], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 31040, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 3, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04650235176086426, 1679735922.9409795], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 199595, "code_hash": null, "entity": [["tile_f", "sp", [-1, 12, 1, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.002033135839443742], 0, 6.0506510734558105, 1679735956.6521165], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 192764, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 3, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[4.7637107001869934e-05], 0, 3.6163620948791504, 1679735959.7481675], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 143193, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 6]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 384]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03587627410888672, 1679735922.941002], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 162618, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 3]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005778208963786303], 0, 5.101222991943359, 1679735962.8264658], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 12325, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.3801561312582147e-05], 0, 3.4055700302124023, 1679735965.8815117], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 183093, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 6]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001484095231575078], 0, 3.808875560760498, 1679735968.9699244], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 125519, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 3]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001864918830598567], 0, 3.5996196269989014, 1679735972.1135993], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 196775, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 3]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0027469949523809527], 0, 5.687222003936768, 1679735975.2367015], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 168054, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[4.279818473412921e-05], 0, 4.364590644836426, 1679735978.334285], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 211531, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 12]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 192]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.06433701515197754, 1679735922.9410374], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 105242, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 3, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 192]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.029324054718017578, 1679735922.941052], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 104027, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 192]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.043042659759521484, 1679735922.9410667], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 99263, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 96]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.11780667304992676, 1679735922.9410815], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 14656, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.6065391804042287e-05], 0, 3.370866537094116, 1679735981.364028], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 113266, "code_hash": null, "entity": [["tile_f", "sp", [-1, 12, 1, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00016006060924786663], 0, 3.775477409362793, 1679735984.4452994], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 93941, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0024019945155875303], 0, 2.211864948272705, 1679735985.9431615], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 59991, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[9.550633870967742e-05], 0, 3.8396847248077393, 1679735989.0249975], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 79718, "code_hash": null, "entity": [["tile_f", "sp", [-1, 12, 2, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.000522266217519685], 0, 4.905548334121704, 1679735992.0835407], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 67732, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 6]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 192]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00010398995621049916], 0, 3.428044080734253, 1679735995.1590996], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 34758, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 12, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 384]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.21588683128356934, 1679735922.9411163], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4465, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 3, 8]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.010165382454545454], 0, 4.200384855270386, 1679735996.7629397], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 135127, "code_hash": null, "entity": [["tile_f", "sp", [-1, 6, 4, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 96]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.10149216651916504, 1679735922.941134], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 201850, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 6]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008944951636851522], 0, 7.871393442153931, 1679735998.2459795], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 80425, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 4, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[8.715398214285714e-05], 0, 3.651695728302002, 1679736001.3201447], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 91553, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00922025571559633], 0, 3.0714879035949707, 1679736002.8996718], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 148247, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 12]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[4.6488629560771556e-05], 0, 3.4092066287994385, 1679736005.961206], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 211103, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 192]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008114770246107483], 0, 9.320939779281616, 1679736009.0601585], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 104280, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 192]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00012798433252173913], 0, 9.008705615997314, 1679736011.958888], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 200020, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 3, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[7.653986126425855e-05], 0, 4.863979339599609, 1679736015.034343], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 171557, "code_hash": null, "entity": [["tile_f", "sp", [-1, 6, 2, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 96]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.23343229293823242, 1679735922.941174], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 139131, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 6]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 192]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.009092617518181818], 0, 2.8992631435394287, 1679736016.6100945], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 102773, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 96]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04782557487487793, 1679736018.0449023], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 112833, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679736028.0916295], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2732, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[6.53164548334019e-05], 0, 3.3264591693878174, 1679736030.97035], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 252, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002529885123060041], 0, 3.4563753604888916, 1679736034.088064], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 57433, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[8.095174918238993e-05], 0, 3.509556531906128, 1679736037.1584883], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 26123, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 64]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0030441746109422497], 0, 1.9845082759857178, 1679736038.6579647], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 126725, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 192]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.07539916038513184, 1679736028.0917056], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 14565, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.5318893554], 0, 8.478478193283081, 1679736045.0185733], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 79684, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.004490919717488789], 0, 2.683525323867798, 1679736046.565407], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 125882, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.032962799072265625, 1679736028.0917363], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 117899, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[8.507013892411753e-05], 0, 4.188905477523804, 1679736049.6349323], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 124295, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 96]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.10725569725036621, 1679736028.0917575], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 28407, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[2.5210761870242845e-05], 0, 3.423792600631714, 1679736052.6959383], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 104690, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.06013202667236328, 1679736028.0917778], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 9181, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00029252526978091616], 0, 4.0806028842926025, 1679736055.794876], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 102698, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 96]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04431414604187012, 1679736028.0917988], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 62067, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 192]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00012701801885259224], 0, 9.328685998916626, 1679736058.7982006], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 34540, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0001238986588361738], 0, 3.5825955867767334, 1679736061.891873], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1081, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00017213344737122748], 0, 3.4775242805480957, 1679736064.9749343], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 117074, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00010216030034843206], 0, 3.93794322013855, 1679736068.0854323], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 65606, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.002776424222413793], 0, 3.942898988723755, 1679736071.2407858], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 113798, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03987765312194824, 1679736028.0918322], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 37301, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0012138933847891567], 0, 3.829437017440796, 1679736074.34641], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 15398, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.05318164825439453, 1679736028.0918522], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 64067, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 384]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.025444984436035156, 1679736028.09187], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 91112, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00023844057541322315], 0, 4.157382249832153, 1679736077.425667], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 121247, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[8.267816060155007e-05], 0, 4.805033445358276, 1679736080.50434], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2852, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 32]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0013949565369595538], 0, 2.019597291946411, 1679736081.9827592], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 6818, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[4.665985213804323e-05], 0, 3.4253292083740234, 1679736085.0438156], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 54351, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.011110972013793104], 0, 6.364953994750977, 1679736088.258338], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 54370, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002674957209071346], 0, 3.8411660194396973, 1679736091.3471868], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 73749, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 32]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.03980973461538462], 0, 4.320597171783447, 1679736093.3028376], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 27530, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.004978784661691542], 0, 4.0103559494018555, 1679736094.8510087], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 40206, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02369213104248047, 1679736028.091915], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 111389, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006473247080144986], 0, 5.847499847412109, 1679736097.9278896], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7577, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[9.516317834131346e-05], 0, 3.429656982421875, 1679736101.0069005], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 112522, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[6.721363890394962e-05], 0, 3.517544984817505, 1679736104.0971491], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 60093, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 96]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02678084373474121, 1679736028.0919676], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 65019, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001843947509709847], 0, 3.5742311477661133, 1679736107.2305944], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 51321, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 32]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00010532773646398015], 0, 4.044928789138794, 1679736110.3179824], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 85645, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 384]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03072333335876465, 1679736028.09199], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 34419, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00010738390760941865], 0, 3.4460108280181885, 1679736113.396812], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 90059, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[7.353241754626456e-05], 0, 3.5190606117248535, 1679736116.466585], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 75555, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[4.162396982702562e-05], 0, 3.4460203647613525, 1679736119.5209036], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 21803, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00013879701118183383], 0, 3.40903639793396, 1679736122.5941055], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 79044, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[6.39716833038158e-05], 0, 4.349817752838135, 1679736137.005777], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 72527, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.027215957641601562, 1679736126.4458032], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 93674, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.01741287231034483], 0, 5.194316148757935, 1679736138.6898699], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 37376, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[3.62804123460717e-05], 0, 3.5667903423309326, 1679736141.7815783], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 96066, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.364961507660534e-05], 0, 3.522660493850708, 1679736144.838155], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 70310, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.2280411032056172e-05], 0, 3.476459503173828, 1679736147.866195], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 71400, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[3.5496363028804385e-05], 0, 3.4412569999694824, 1679736150.9090912], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 44579, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 8, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002287130270653252], 0, 4.007613182067871, 1679736154.0267107], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 15715, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 64, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003657257583390061], 0, 3.8782994747161865, 1679736157.1039867], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 15498, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 32]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.06751704216003418, 1679736127.5910077], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 105893, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 8]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.1059782500953106e-05], 0, 5.3127148151397705, 1679736160.1712391], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 25694, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0012081786924231057], 0, 4.391762733459473, 1679736163.273595], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 73536, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 8]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03410053253173828, 1679736127.5910232], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 93903, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.0696911347517732e-05], 0, 3.4486000537872314, 1679736166.3105097], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 24519, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1.439485247586536e-05], 0, 3.490903615951538, 1679736169.3255315], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 63403, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 128, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03777575492858887, 1679736127.5910347], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 18490, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[9.801983744292238e-05], 0, 3.623440980911255, 1679736172.398826], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 75186, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.006170420870229008], 0, 4.981062889099121, 1679736175.557153], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 749, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[3.285570200950246e-05], 0, 3.5504720211029053, 1679736178.6144989], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 29439, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1.2747629052404706e-05], 0, 3.5443220138549805, 1679736181.6102698], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 84631, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 32]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00012311701573600184], 0, 3.8812007904052734, 1679736184.7000554], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 67121, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0003365465722070845], 0, 3.8965981006622314, 1679736187.8134716], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 10195, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0016075270448207173], 0, 4.565371751785278, 1679736190.9233136], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 103624, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[4.0791335416241585e-05], 0, 4.589033842086792, 1679736193.983457], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 54714, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04036211967468262, 1679736127.5910769], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 49999, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.007586908969696969], 0, 3.039824962615967, 1679736195.5343382], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 35466, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 64]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03730130195617676, 1679736127.5910966], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 27330, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1679736134.0642197], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 56949, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.433818945233638e-05], 0, 3.412703514099121, 1679736198.5563583], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 33213, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[3.9404248913443836e-05], 0, 4.549296140670776, 1679736201.6092303], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 103140, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 2, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.001114085442186405], 0, 12.193846464157104, 1679736204.6629932], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 46278, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[9.474626193238673e-06], 0, 3.403329372406006, 1679736207.6333477], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 26088, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1.2681225136700555e-05], 0, 3.4408016204833984, 1679736210.649041], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 93211, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 32]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.001705948054197662], 0, 3.842771291732788, 1679736213.7398076], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 99360, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.040398597717285156, 1679736134.0642524], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 72254, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 32]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04851388931274414, 1679736134.0642617], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 29277, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1.6781192251259916e-05], 0, 3.7776939868927, 1679736216.769121], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 51586, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[8.791221417830533e-06], 0, 3.4426331520080566, 1679736219.7333775], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 48695, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0020219170986093553], 0, 7.911269187927246, 1679736222.8233695], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 28033, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 32]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00201177734375], 0, 4.3996336460113525, 1679736225.9550264], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 95982, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 8]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679736134.1257224], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 50809, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 32]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003630296237646002], 0, 6.193381309509277, 1679736229.0548432], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 44271, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.017377033086206896], 0, 10.480352401733398, 1679736230.723562], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 91829, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[2.7729765654913153e-05], 0, 7.96705174446106, 1679736233.7821321], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 21337, "code_hash": null, "entity": [["tile_f", "sp", [-1, 128, 1, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1679736134.1257854], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 265353, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[8.158210291022943e-05], 0, 3.5538105964660645, 1679736248.2853942], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 10374, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 16]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005392080640426951], 0, 3.895380735397339, 1679736251.372235], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 301138, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.000524940839883079], 0, 4.8931169509887695, 1679736254.4606428], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 59381, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 32]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.05548883373684211], 0, 5.072067975997925, 1679736256.648754], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 103879, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.004188481414225941], 0, 5.625771999359131, 1679736258.2288067], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 147319, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 16]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04832053184509277, 1679736239.3700402], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 308404, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.005639892915730337], 0, 2.9407904148101807, 1679736259.769963], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 130612, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.033804970266666665], 0, 4.2624688148498535, 1679736261.6338964], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 281905, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.056039367666666666], 0, 3.6933276653289795, 1679736263.7336328], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 301821, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00135667368204698], 0, 7.046046018600464, 1679736266.8374927], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 295596, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05125570297241211, 1679736239.370089], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 137965, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[5.07826069793147e-05], 0, 4.08795952796936, 1679736269.9139695], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 48526, "code_hash": null, "entity": [["tile_f", "sp", [-1, 128, 2, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04585671424865723, 1679736239.3701122], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 134322, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00020350063999495966], 0, 4.038804531097412, 1679736273.00736], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 208975, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.000462970788277512], 0, 6.98129940032959, 1679736276.0251932], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 342567, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002198403951020408], 0, 4.527878284454346, 1679736279.1283288], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 247009, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0007383166447488584], 0, 3.9946117401123047, 1679736282.2396743], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 114531, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003238166589861751], 0, 4.053917407989502, 1679736285.3354728], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 81268, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00010420695186094598], 0, 3.6889426708221436, 1679736288.4148145], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 196630, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.016866969800000003], 0, 5.618604421615601, 1679736290.082513], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 129845, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 64]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00017517242108688576], 0, 3.9824039936065674, 1679736293.176247], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 99692, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0001407765810787223], 0, 3.8955349922180176, 1679736296.2620888], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3180, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00033195238725590957], 0, 3.6888976097106934, 1679736299.3470988], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 85728, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.1105504272], 0, 4.35666561126709, 1679736301.0552497], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 242189, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.1950739501], 0, 4.113601446151733, 1679736303.72064], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 373637, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 32, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00021587996001604706], 0, 3.8204092979431152, 1679736306.851912], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 287934, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00025098659586699813], 0, 3.8352386951446533, 1679736309.9917758], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 222247, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 64]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.003487906034707159], 0, 4.095026731491089, 1679736313.1064365], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 66103, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002944758801050175], 0, 2.1075448989868164, 1679736314.5823042], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 360428, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[5.072247838744383e-05], 0, 3.9060916900634766, 1679736317.648767], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 266374, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.004177173358333333], 0, 2.96321177482605, 1679736319.1756306], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1932, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.002451608582066869], 0, 4.055494546890259, 1679736322.2865822], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 120877, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0032044394345238096], 0, 4.3707122802734375, 1679736325.410767], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 172465, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 64, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0010250092797131148], 0, 4.480111598968506, 1679736326.9266467], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 275654, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.060323476791381836, 1679736239.370206], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 249670, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[4.464632533207095e-05], 0, 3.651510238647461, 1679736329.9975512], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 329723, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679736245.350513], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 404024, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.047249555587768555, 1679736245.3505356], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 194528, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 64]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003692948997259023], 0, 3.9327664375305176, 1679736333.0870073], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 299856, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 1, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679736245.3987784], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 163714, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.048002004623413086, 1679736245.3988187], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 18374, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 2, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.06803083419799805, 1679736245.3988411], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 396218, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[7.375464788087055e-05], 0, 4.528850555419922, 1679736336.214454], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 108983, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0011523597822580645], 0, 2.3503708839416504, 1679736337.7071977], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 334088, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002029019915829146], 0, 3.734804391860962, 1679736340.7916121], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6200, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 4]], ["tile_x", "sp", [-1, 7, 1, 7]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0011793192979985174], 0, 4.466571092605591, 1679736355.1353261], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 53743, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 8]], ["tile_x", "sp", [-1, 1, 49, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[2.4481329534574878e-05], 0, 3.9904792308807373, 1679736358.175664], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 29532, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 128]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.002077293030967742], 0, 4.58506965637207, 1679736361.2974188], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 12198, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 32]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[4.8967657415916194e-05], 0, 4.129405736923218, 1679736364.3570037], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 26738, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 256, 1, 1]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.14161080320000002], 0, 6.502543687820435, 1679736366.4021702], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 66038, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 32, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.8365334210666714e-05], 0, 5.991367816925049, 1679736369.483722], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 17667, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 1]], ["tile_x", "sp", [-1, 7, 1, 7]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0004824120297454769], 0, 4.472773551940918, 1679736372.51219], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 40345, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 4]], ["tile_x", "sp", [-1, 7, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00041847271949947863], 0, 4.727591276168823, 1679736375.5863519], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 22817, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 2]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[3.125589623511409e-05], 0, 4.234628677368164, 1679736378.6569479], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 29460, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 4]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[3.4719246620077066e-05], 0, 4.381402254104614, 1679736381.7145088], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1359, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 64, 1]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.8649170466433388e-05], 0, 4.052269220352173, 1679736384.7600899], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 57605, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 1]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0004198544116266945], 0, 4.320816516876221, 1679736387.8566895], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 43223, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 64]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00037073045561021313], 0, 4.366281032562256, 1679736390.9001355], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 13171, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 16]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.00304696568], 0, 4.584062814712524, 1679736394.0408072], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7145, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 1, 2]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[7.48609879826727e-05], 0, 4.2678375244140625, 1679736397.1129375], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 43740, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 64, 2, 1]], ["tile_x", "sp", [-1, 1, 49, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[3.519159002312521e-05], 0, 4.233645439147949, 1679736400.1658146], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6790, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.3908621540751543e-05], 0, 4.1462321281433105, 1679736403.175169], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1210, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 2]], ["tile_x", "sp", [-1, 7, 1, 7]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00020853312855280314], 0, 5.023288726806641, 1679736406.246735], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 39655, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 2]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001452233156280999], 0, 4.202703952789307, 1679736409.3682034], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 27523, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 16]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.001219133438490566], 0, 6.128206491470337, 1679736412.4686558], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 42337, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 4]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[7.830031711115437e-05], 0, 4.5290679931640625, 1679736415.552377], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 60059, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 256]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00021286940029266994], 0, 5.157316207885742, 1679736418.6169415], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 23358, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 2, 4]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0019924018], 0, 5.432084321975708, 1679736421.7341342], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 68872, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 2]], ["tile_x", "sp", [-1, 7, 1, 7]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[4.361496481370356e-05], 0, 6.827355146408081, 1679736424.7918124], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 61284, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 8, 2]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.7561621830886175e-05], 0, 4.7779541015625, 1679736427.8801894], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 40446, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 4, 1]], ["tile_x", "sp", [-1, 1, 49, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[2.5013843484564353e-05], 0, 3.9665262699127197, 1679736430.9083016], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 9764, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 8, 1]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0011416933938356165], 0, 2.5887248516082764, 1679736432.3955634], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 60889, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0007904141931931932], 0, 8.308673858642578, 1679736435.4371948], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 13177, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 16]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0004569382479452055], 0, 2.800100564956665, 1679736436.9185166], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 66163, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 128]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001834732483793927], 0, 4.402888536453247, 1679736440.0369048], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 40639, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 2]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00011854153878961689], 0, 4.532574415206909, 1679736443.1294057], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 16915, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 4]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.022570166000000003], 0, 3.129241704940796, 1679736444.8716626], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 24975, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[3.9281141485573974e-05], 0, 4.406053066253662, 1679736447.9423115], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 23188, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 4]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00023807591551164848], 0, 4.308171510696411, 1679736451.0340204], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 44660, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 8]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00020957321633554082], 0, 4.476063966751099, 1679736454.1703393], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 21875, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 4]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.00025034794577377255], 0, 4.678733587265015, 1679736457.253284], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 18748, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 4]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1.6508113672178683e-05], 0, 4.100329160690308, 1679736460.262379], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 13733, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 32, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[2.3728148106105868e-05], 0, 4.01208233833313, 1679736463.3021686], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 13519, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 32]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[6.963461733211948e-05], 0, 4.315280199050903, 1679736466.3720384], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 18080, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 4]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006309073191656828], 0, 4.744829893112183, 1679736469.485257], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 54604, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 32]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[7.49364312029026e-05], 0, 4.197328090667725, 1679736472.55842], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 44163, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 64, 4]], ["tile_x", "sp", [-1, 7, 1, 7]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[5.2019704262848605e-05], 0, 4.255070209503174, 1679736475.6333451], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4463, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 256, 1, 1]], ["tile_x", "sp", [-1, 7, 1, 7]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1679736352.2382798], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6476, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 64, 1]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[4.9923595329285384e-05], 0, 4.086648464202881, 1679736478.6949866], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6635, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.65437614488831e-05], 0, 3.7751660346984863, 1679736481.7387426], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 36429, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0023192292801161103], 0, 5.9003801345825195, 1679736496.0534747], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 46857, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 8]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.01313121764935065], 0, 4.102694988250732, 1679736497.6821084], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 58275, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0029508567964601773], 0, 5.030277252197266, 1679736499.1806417], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 45783, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00016273170816100073], 0, 3.8245737552642822, 1679736502.306422], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 73894, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.007171766878571429], 0, 8.327491760253906, 1679736503.8561594], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 773, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00030935656084959815], 0, 3.572849750518799, 1679736506.955165], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 22549, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.000348872789984891], 0, 4.167870044708252, 1679736510.0417864], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 61068, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0009381212193064667], 0, 2.323289155960083, 1679736511.572237], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 63953, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05699467658996582, 1679736489.9414856], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 33688, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00030192960500747385], 0, 5.065243482589722, 1679736514.66391], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 57270, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 8]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0011194397984764543], 0, 4.761313438415527, 1679736517.7582438], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 55554, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679736493.1418002], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 25301, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04132819175720215, 1679736493.1418192], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 32931, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[3.187301949922003e-05], 0, 3.45810866355896, 1679736520.8497117], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 45036, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00014175464362262824], 0, 3.4605979919433594, 1679736523.942268], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 36855, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.033306121826171875, 1679736493.1418307], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 8984, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 32]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03135871887207031, 1679736493.1418366], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 65504, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.053588151931762695, 1679736493.1418445], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 51259, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[2.2234737695287917e-05], 0, 3.3697757720947266, 1679736526.9826143], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11698, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02400040626525879, 1679736493.1418526], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 44138, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.036602512892857146], 0, 3.151762008666992, 1679736528.880943], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 31923, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00015977916577593034], 0, 3.750666379928589, 1679736531.9726646], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 40802, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.006197355290123457], 0, 7.412155628204346, 1679736533.5632942], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 50468, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[6.824108209680829e-05], 0, 3.4419567584991455, 1679736536.6482048], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 6330, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00030795199695121954], 0, 3.524247884750366, 1679736539.7922938], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7279, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003407659559350622], 0, 3.5782558917999268, 1679736542.903795], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 75176, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 32]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0023124207765042983], 0, 6.415077447891235, 1679736546.0233057], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 59467, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 16]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002700102886511783], 0, 4.376245975494385, 1679736549.1148863], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7769, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002722925404448938], 0, 3.4891653060913086, 1679736552.198808], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 76995, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005299882864634546], 0, 3.8370282649993896, 1679736555.283829], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11604, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.05024385452270508, 1679736493.141874], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 77267, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.07021570205688477, 1679736493.14188], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 47902, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.046823740005493164, 1679736493.1418858], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 72781, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[4.451901993125243e-05], 0, 3.895636558532715, 1679736558.3363123], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 77588, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05406546592712402, 1679736493.1418927], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 33086, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002795833673645959], 0, 3.9404990673065186, 1679736561.4149919], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 54908, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.01571804809375], 0, 3.8197083473205566, 1679736563.0513911], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 20963, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00013550930256970103], 0, 3.489118814468384, 1679736566.1418724], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 69907, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[6.603826418039183e-05], 0, 3.426771402359009, 1679736569.2418346], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 60400, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.055116641368421065], 0, 5.355492353439331, 1679736571.3713725], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 9063, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.021653175354003906, 1679736493.1419027], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 28994, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00016319448554679604], 0, 3.477656126022339, 1679736574.4611838], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 59642, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00013227995049991804], 0, 3.9145963191986084, 1679736577.5350246], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 37235, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.033618927001953125, 1679736493.141911], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11475, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[8.813578018372704e-05], 0, 3.421832799911499, 1679736580.6106482], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 280241, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 25, 5]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0028717398756660747], 0, 5.165704727172852, 1679736594.987083], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 53412, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 5]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.13703346252441406, 1679736585.1547468], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 160804, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00014868382264221207], 0, 3.6450397968292236, 1679736598.056649], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 163473, "code_hash": null, "entity": [["tile_f", "sp", [-1, 25, 2, 10]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.06806683540344238, 1679736585.1547623], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 37465, "code_hash": null, "entity": [["tile_f", "sp", [-1, 20, 1, 10]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 4, 12.231800079345703, 1679736608.690324], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 332624, "code_hash": null, "entity": [["tile_f", "sp", [-1, 40, 5, 5]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1679736592.0244737], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 240080, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 50, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05761361122131348, 1679736592.0245247], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 351192, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 250]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.07627177238464355, 1679736592.0245466], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 306291, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 25, 10]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0610809326171875, 1679736592.0245638], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 311232, "code_hash": null, "entity": [["tile_f", "sp", [-1, 25, 4, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.06037592887878418, 1679736592.0245802], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 27771, "code_hash": null, "entity": [["tile_f", "sp", [-1, 125, 2, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.06227922439575195, 1679736592.0245955], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 43352, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 100, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.028736591339111328, 1679736592.0246112], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 382276, "code_hash": null, "entity": [["tile_f", "sp", [-1, 5, 4, 10]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.054931640625, 1679736592.024627], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 244897, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 500, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.048821210861206055, 1679736592.0246425], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11870, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 10]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.017185160316666667], 0, 4.23876690864563, 1679736610.4187014], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 73173, "code_hash": null, "entity": [["tile_f", "sp", [-1, 5, 2, 100]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0319684161875], 0, 2.837106466293335, 1679736612.3109288], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 323960, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 50]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0032100893161033798], 0, 5.889162063598633, 1679736615.4516594], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 138197, "code_hash": null, "entity": [["tile_f", "sp", [-1, 25, 1, 5]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.014623595304347828], 0, 3.5245001316070557, 1679736617.1133683], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 339893, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 50, 10]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0003619309341840161], 0, 4.736292839050293, 1679736620.25906], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 299834, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 20, 5]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.06731891632080078, 1679736592.024675], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 236117, "code_hash": null, "entity": [["tile_f", "sp", [-1, 50, 2, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04891467094421387, 1679736592.0246892], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 99152, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 50]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.29726770010000003], 0, 5.388694763183594, 1679736624.0312483], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 228193, "code_hash": null, "entity": [["tile_f", "sp", [-1, 5, 1, 5]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00013157936808666612], 0, 3.633490800857544, 1679736627.1998901], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 330559, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 500, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0485844612121582, 1679736592.0247104], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 306741, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 20, 25]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.07117342948913574, 1679736592.0247257], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 266474, "code_hash": null, "entity": [["tile_f", "sp", [-1, 40, 25, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.036102294921875, 1679736592.024741], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 264860, "code_hash": null, "entity": [["tile_f", "sp", [-1, 100, 10, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.013718836945205478], 0, 10.89410138130188, 1679736628.8510215], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 381557, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 50]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0673973560333252, 1679736592.0247588], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 74699, "code_hash": null, "entity": [["tile_f", "sp", [-1, 10, 1, 20]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0004375819307171854], 0, 3.7274744510650635, 1679736631.9544911], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 276635, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 20, 5]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002248866744250871], 0, 3.925628662109375, 1679736635.0402145], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 218221, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 5, 5]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0025300997323232325], 0, 2.802821159362793, 1679736636.5524492], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 237216, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005457551227495909], 0, 1.978332757949829, 1679736638.0372348], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 240223, "code_hash": null, "entity": [["tile_f", "sp", [-1, 20, 5, 5]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04194998741149902, 1679736592.0247884], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 63731, "code_hash": null, "entity": [["tile_f", "sp", [-1, 50, 5, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.035675764083862305, 1679736592.0248036], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 59296, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 250, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03748011589050293, 1679736592.0248196], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 243688, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 125, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.046491146087646484, 1679736592.0248346], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 206009, "code_hash": null, "entity": [["tile_f", "sp", [-1, 50, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.019258564865384614], 0, 2.5745606422424316, 1679736639.7353606], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 215845, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 50, 5]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0055289040220994476], 0, 1.9642300605773926, 1679736641.2900248], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 298877, "code_hash": null, "entity": [["tile_f", "sp", [-1, 25, 40, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.044397592544555664, 1679736592.024855], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 60199, "code_hash": null, "entity": [["tile_f", "sp", [-1, 50, 1, 5]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03205108642578125, 1679736592.02487], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 207740, "code_hash": null, "entity": [["tile_f", "sp", [-1, 5, 20, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.009830520323529412], 0, 2.49851393699646, 1679736642.8916461], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 30298, "code_hash": null, "entity": [["tile_f", "sp", [-1, 5, 1, 20]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0066310101390728475], 0, 2.1137046813964844, 1679736644.4472466], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 227133, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 5, 25]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02466416358947754, 1679736592.0248907], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 113526, "code_hash": null, "entity": [["tile_f", "sp", [-1, 10, 2, 25]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.043901681900024414, 1679736592.0249057], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 368236, "code_hash": null, "entity": [["tile_f", "sp", [-1, 5, 20, 5]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04175305366516113, 1679736592.0249205], "version": 0.2, "tvm_version": "0.11.dev0"} diff --git a/a100_superresolution_1_tuned/README.md b/a100_superresolution_1_tuned/README.md new file mode 100644 index 0000000..12fe882 --- /dev/null +++ b/a100_superresolution_1_tuned/README.md @@ -0,0 +1,12 @@ +This is an extend version of the superresolution model. +Instead of using a fixed 3 upscale ratio with an input of 224x224, +we feed the model 640x480 inputs, similar to what would be a 480p video, +and by changing the value in UPSCALE_FACTOR, we can simulate various resolution enanchement. + +For instance, a 6x upscaling would be close to a 4K output. +A 4x would be similar to a FullHD output. +A 12x would be a 8K output + + +Original code available at https://raw.githubusercontent.com/pytorch/tutorials/main/advanced_source/super_resolution_with_onnxruntime.py +Surrounding scripts released under GNU GPL v3. See [../LICENSE](../LICENSE). diff --git a/a100_superresolution_1_tuned/UPSCALE_FACTOR b/a100_superresolution_1_tuned/UPSCALE_FACTOR new file mode 100644 index 0000000..d00491f --- /dev/null +++ b/a100_superresolution_1_tuned/UPSCALE_FACTOR @@ -0,0 +1 @@ +1 diff --git a/a100_superresolution_1_tuned/compile.sh b/a100_superresolution_1_tuned/compile.sh new file mode 100755 index 0000000..65b9e1f --- /dev/null +++ b/a100_superresolution_1_tuned/compile.sh @@ -0,0 +1,15 @@ +#!/bin/bash +TUNING=$(ls tuning* --sort=time -1 | head -n1) + +set -x +python3 -m tvm.driver.tvmc compile \ + --target cuda + --target-cuda-arch sm_80 \ + --output model.tar \ + --input-shape 'input:[1,1,640,480]' \ + --tuning-records $TUNING \ + super_resolution.onnx $@ \ + + #--output-shape 'input:[1,1,4096,3112]' \ + +tar -xvf model.tar diff --git a/a100_superresolution_1_tuned/convert_docker.sh b/a100_superresolution_1_tuned/convert_docker.sh new file mode 100755 index 0000000..3579269 --- /dev/null +++ b/a100_superresolution_1_tuned/convert_docker.sh @@ -0,0 +1,16 @@ +#!/bin/bash + +UPSCALE_FACTOR=$(cat UPSCALE_FACTOR) +#DIR=$(basename "$PWD") +DIR=a100_superresolution_${UPSCALE_FACTOR}_tuned +CMD="../a100_superresolution_1_tuned/super_resolution_with_onnxruntime.py $UPSCALE_FACTOR" + +echo $CMD +set -x +sudo docker run --rm --gpus 1 \ + -v $(pwd):/semla/modelzoo/$DIR \ + -v $(pwd)/../a100_superresolution_1_tuned:/semla/modelzoo/a100_superresolution_1_tuned \ + --workdir /semla/modelzoo/$DIR \ + --entrypoint "/usr/bin/python3" \ + semla/tvm_pytorch \ + $CMD diff --git a/a100_superresolution_1_tuned/do.sh b/a100_superresolution_1_tuned/do.sh new file mode 100755 index 0000000..0194417 --- /dev/null +++ b/a100_superresolution_1_tuned/do.sh @@ -0,0 +1,4 @@ +../a100_superresolution_1_tuned/convert.sh +../a100_superresolution_1_tuned/tune.sh +../a100_superresolution_1_tuned/compile.sh +../a100_superresolution_1_tuned/fix_sizes.sh diff --git a/a100_superresolution_1_tuned/download.sh b/a100_superresolution_1_tuned/download.sh new file mode 100755 index 0000000..d1ce822 --- /dev/null +++ b/a100_superresolution_1_tuned/download.sh @@ -0,0 +1,2 @@ +#!/bin/bash +wget https://github.com/onnx/models/raw/main/vision/super_resolution/sub_pixel_cnn_2016/model/super-resolution-10.onnx diff --git a/a100_superresolution_1_tuned/fix_sizes.sh b/a100_superresolution_1_tuned/fix_sizes.sh new file mode 100755 index 0000000..61d5397 --- /dev/null +++ b/a100_superresolution_1_tuned/fix_sizes.sh @@ -0,0 +1,13 @@ +#!/bin/bash + +UPSCALE_FACTOR=$(cat UPSCALE_FACTOR) +W_OUTPUT=$(($UPSCALE_FACTOR * 640)) +H_OUTPUT=$(($UPSCALE_FACTOR * 480)) +MODEL_NAME=a100_superresolution_${UPSCALE_FACTOR}_tuned + + +cat ../a100_superresolution_1_tuned/metadata.template.json \ + | sed -e "s/W_OUTPUT/${W_OUTPUT}/g" \ + | sed -e "s/H_OUTPUT/${H_OUTPUT}/g" \ + | sed -e "s/MODEL_NAME/${MODEL_NAME}/g" \ + | tee metadata.json diff --git a/a100_superresolution_1_tuned/metadata.json b/a100_superresolution_1_tuned/metadata.json new file mode 100644 index 0000000..9ba7eff --- /dev/null +++ b/a100_superresolution_1_tuned/metadata.json @@ -0,0 +1,16 @@ +{ + "load_time": 1000000000, + "exec_time": [1000000,2000000,4000000,8000000], + "weights_size": 100000000, + "workspace_size": 500000000, + "input_name" : "input", + "output_name" : "output", + "input_shape": [1,1,640,480], + "output_shape": [1,1,640,480], + "input_type": "FP32", + "output_type": "FP32", + "device": "CUDA", + "model" : "a100_superresolution_1_tuned", + "architecture" : "CUDA_80" + +} diff --git a/a100_superresolution_1_tuned/metadata.template.json b/a100_superresolution_1_tuned/metadata.template.json new file mode 100644 index 0000000..7f5d1ac --- /dev/null +++ b/a100_superresolution_1_tuned/metadata.template.json @@ -0,0 +1,16 @@ +{ + "load_time": 1000000000, + "exec_time": [1000000,2000000,4000000,8000000], + "weights_size": 100000000, + "workspace_size": 500000000, + "input_name" : "input", + "output_name" : "output", + "input_shape": [1,1,640,480], + "output_shape": [1,1,W_OUTPUT,H_OUTPUT], + "input_type": "FP32", + "output_type": "FP32", + "device": "CUDA", + "model" : "MODEL_NAME", + "architecture" : "CUDA_80" + +} diff --git a/a100_superresolution_1_tuned/model.tar b/a100_superresolution_1_tuned/model.tar new file mode 100644 index 0000000..f35936b Binary files /dev/null and b/a100_superresolution_1_tuned/model.tar differ diff --git a/a100_superresolution_1_tuned/super_resolution.tar b/a100_superresolution_1_tuned/super_resolution.tar new file mode 100644 index 0000000..0430b44 Binary files /dev/null and b/a100_superresolution_1_tuned/super_resolution.tar differ diff --git a/a100_superresolution_1_tuned/super_resolution_with_onnxruntime.py b/a100_superresolution_1_tuned/super_resolution_with_onnxruntime.py new file mode 100644 index 0000000..54beb53 --- /dev/null +++ b/a100_superresolution_1_tuned/super_resolution_with_onnxruntime.py @@ -0,0 +1,316 @@ +""" +(optional) Exporting a Model from PyTorch to ONNX and Running it using ONNX Runtime +======================================================================== + +In this tutorial, we describe how to convert a model defined +in PyTorch into the ONNX format and then run it with ONNX Runtime. + +ONNX Runtime is a performance-focused engine for ONNX models, +which inferences efficiently across multiple platforms and hardware +(Windows, Linux, and Mac and on both CPUs and GPUs). +ONNX Runtime has proved to considerably increase performance over +multiple models as explained `here +`__ + +For this tutorial, you will need to install `ONNX `__ +and `ONNX Runtime `__. +You can get binary builds of ONNX and ONNX Runtime with +``pip install onnx onnxruntime``. +ONNX Runtime recommends using the latest stable runtime for PyTorch. + +""" + +# Some standard imports +import io +import numpy as np + +from torch import nn +import torch.utils.model_zoo as model_zoo +import torch.onnx +import sys + + +###################################################################### +# Super-resolution is a way of increasing the resolution of images, videos +# and is widely used in image processing or video editing. For this +# tutorial, we will use a small super-resolution model. +# +# First, let's create a ``SuperResolution`` model in PyTorch. +# This model uses the efficient sub-pixel convolution layer described in `"Real-Time Single Image and Video Super-Resolution Using an Efficient +# Sub-Pixel Convolutional Neural Network" - Shi et al `__ +# for increasing the resolution of an image by an upscale factor. +# The model expects the Y component of the ``YCbCr`` of an image as an input, and +# outputs the upscaled Y component in super resolution. +# +# `The +# model `__ +# comes directly from PyTorch's examples without modification: +# + +# Super Resolution model definition in PyTorch +import torch.nn as nn +import torch.nn.init as init + + +class SuperResolutionNet(nn.Module): + def __init__(self, upscale_factor, inplace=False): + super(SuperResolutionNet, self).__init__() + + self.relu = nn.ReLU(inplace=inplace) + self.conv1 = nn.Conv2d(1, 64, (5, 5), (1, 1), (2, 2)) + self.conv2 = nn.Conv2d(64, 64, (3, 3), (1, 1), (1, 1)) + self.conv3 = nn.Conv2d(64, 32, (3, 3), (1, 1), (1, 1)) + self.conv4 = nn.Conv2d(32, upscale_factor ** 2, (3, 3), (1, 1), (1, 1)) + self.pixel_shuffle = nn.PixelShuffle(upscale_factor) + + self._initialize_weights() + + def forward(self, x): + x = self.relu(self.conv1(x)) + x = self.relu(self.conv2(x)) + x = self.relu(self.conv3(x)) + x = self.pixel_shuffle(self.conv4(x)) + return x + + def _initialize_weights(self): + init.orthogonal_(self.conv1.weight, init.calculate_gain('relu')) + init.orthogonal_(self.conv2.weight, init.calculate_gain('relu')) + init.orthogonal_(self.conv3.weight, init.calculate_gain('relu')) + init.orthogonal_(self.conv4.weight) + +# Create the super-resolution model by using the above model definition. + + +if len(sys.argv) > 1: + upscale_factor = int(sys.argv[1]) +else: + upscale_factor = 3 +torch_model = SuperResolutionNet(upscale_factor=upscale_factor) +print("Model created with upscale factor ", upscale_factor) + + +###################################################################### +# Ordinarily, you would now train this model; however, for this tutorial, +# we will instead download some pretrained weights. Note that this model +# was not trained fully for good accuracy and is used here for +# demonstration purposes only. +# +# It is important to call ``torch_model.eval()`` or ``torch_model.train(False)`` +# before exporting the model, to turn the model to inference mode. +# This is required since operators like dropout or batchnorm behave +# differently in inference and training mode. +# + +# # Load pretrained model weights +# model_url = 'https://s3.amazonaws.com/pytorch/test_data/export/superres_epoch100-44c6958e.pth' +batch_size = 1 # just a random number + +# # Initialize model with the pretrained weights +# map_location = lambda storage, loc: storage +# if torch.cuda.is_available(): +# map_location = None +# torch_model.load_state_dict(model_zoo.load_url(model_url, map_location=map_location)) + +# set the model to inference mode +torch_model.eval() + + +###################################################################### +# Exporting a model in PyTorch works via tracing or scripting. This +# tutorial will use as an example a model exported by tracing. +# To export a model, we call the ``torch.onnx.export()`` function. +# This will execute the model, recording a trace of what operators +# are used to compute the outputs. +# Because ``export`` runs the model, we need to provide an input +# tensor ``x``. The values in this can be random as long as it is the +# right type and size. +# Note that the input size will be fixed in the exported ONNX graph for +# all the input's dimensions, unless specified as a dynamic axes. +# In this example we export the model with an input of batch_size 1, +# but then specify the first dimension as dynamic in the ``dynamic_axes`` +# parameter in ``torch.onnx.export()``. +# The exported model will thus accept inputs of size [batch_size, 1, 224, 224] +# where batch_size can be variable. +# +# To learn more details about PyTorch's export interface, check out the +# `torch.onnx documentation `__. +# + +# Input to the model +x = torch.randn(batch_size, 1, 640, 480, requires_grad=True) +torch_out = torch_model(x) + +# Export the model +torch.onnx.export(torch_model, # model being run + x, # model input (or a tuple for multiple inputs) + "super_resolution.onnx", # where to save the model (can be a file or file-like object) + export_params=True, # store the trained parameter weights inside the model file + opset_version=10, # the ONNX version to export the model to + do_constant_folding=True, # whether to execute constant folding for optimization + input_names = ['input'], # the model's input names + output_names = ['output'], # the model's output names + dynamic_axes={'input' : {0 : 'batch_size'}, # variable length axes + 'output' : {0 : 'batch_size'}}) + +###################################################################### +# We also computed ``torch_out``, the output after of the model, +# which we will use to verify that the model we exported computes +# the same values when run in ONNX Runtime. +# +# But before verifying the model's output with ONNX Runtime, we will check +# the ONNX model with ONNX API. +# First, ``onnx.load("super_resolution.onnx")`` will load the saved model and +# will output a ``onnx.ModelProto`` structure (a top-level file/container format for bundling a ML model. +# For more information `onnx.proto documentation `__.). +# Then, ``onnx.checker.check_model(onnx_model)`` will verify the model's structure +# and confirm that the model has a valid schema. +# The validity of the ONNX graph is verified by checking the model's +# version, the graph's structure, as well as the nodes and their inputs +# and outputs. +# + +import onnx + +onnx_model = onnx.load("super_resolution.onnx") +onnx.checker.check_model(onnx_model) + + +###################################################################### +# Now let's compute the output using ONNX Runtime's Python APIs. +# This part can normally be done in a separate process or on another +# machine, but we will continue in the same process so that we can +# verify that ONNX Runtime and PyTorch are computing the same value +# for the network. +# +# In order to run the model with ONNX Runtime, we need to create an +# inference session for the model with the chosen configuration +# parameters (here we use the default config). +# Once the session is created, we evaluate the model using the run() API. +# The output of this call is a list containing the outputs of the model +# computed by ONNX Runtime. +# + +import onnxruntime + +ort_session = onnxruntime.InferenceSession("super_resolution.onnx", providers=["CUDAExecutionProvider"]) + +def to_numpy(tensor): + return tensor.detach().cpu().numpy() if tensor.requires_grad else tensor.cpu().numpy() + +# compute ONNX Runtime output prediction +ort_inputs = {ort_session.get_inputs()[0].name: to_numpy(x)} +ort_outs = ort_session.run(None, ort_inputs) + +# compare ONNX Runtime and PyTorch results +np.testing.assert_allclose(to_numpy(torch_out), ort_outs[0], rtol=1e-03, atol=1e-05) + +print("Exported model has been tested with ONNXRuntime, and the result looks good!") + + +###################################################################### +# We should see that the output of PyTorch and ONNX Runtime runs match +# numerically with the given precision (``rtol=1e-03`` and ``atol=1e-05``). +# As a side-note, if they do not match then there is an issue in the +# ONNX exporter, so please contact us in that case. +# + + +###################################################################### +# Running the model on an image using ONNX Runtime +# ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +# + + +###################################################################### +# So far we have exported a model from PyTorch and shown how to load it +# and run it in ONNX Runtime with a dummy tensor as an input. + +###################################################################### +# For this tutorial, we will use a famous cat image used widely which +# looks like below +# +# .. figure:: /_static/img/cat_224x224.jpg +# :alt: cat +# + +###################################################################### +# First, let's load the image, preprocess it using standard PIL +# python library. Note that this preprocessing is the standard practice of +# processing data for training/testing neural networks. +# +# We first resize the image to fit the size of the model's input (224x224). +# Then we split the image into its Y, Cb, and Cr components. +# These components represent a grayscale image (Y), and +# the blue-difference (Cb) and red-difference (Cr) chroma components. +# The Y component being more sensitive to the human eye, we are +# interested in this component which we will be transforming. +# After extracting the Y component, we convert it to a tensor which +# will be the input of our model. +# + +from PIL import Image +import torchvision.transforms as transforms + +img = Image.open("../a100_superresolution_1_tuned/cat.jpg") + +resize = transforms.Resize([640,480]) +img = resize(img) + +img_ycbcr = img.convert('YCbCr') +img_y, img_cb, img_cr = img_ycbcr.split() + +to_tensor = transforms.ToTensor() +img_y = to_tensor(img_y) +img_y.unsqueeze_(0) + + +###################################################################### +# Now, as a next step, let's take the tensor representing the +# grayscale resized cat image and run the super-resolution model in +# ONNX Runtime as explained previously. +# + +ort_inputs = {ort_session.get_inputs()[0].name: to_numpy(img_y)} +ort_outs = ort_session.run(None, ort_inputs) +img_out_y = ort_outs[0] + + +###################################################################### +# At this point, the output of the model is a tensor. +# Now, we'll process the output of the model to construct back the +# final output image from the output tensor, and save the image. +# The post-processing steps have been adopted from PyTorch +# implementation of super-resolution model +# `here `__. +# + +img_out_y = Image.fromarray(np.uint8((img_out_y[0] * 255.0).clip(0, 255)[0]), mode='L') + +# get the output image follow post-processing step from PyTorch implementation +final_img = Image.merge( + "YCbCr", [ + img_out_y, + img_cb.resize(img_out_y.size, Image.BICUBIC), + img_cr.resize(img_out_y.size, Image.BICUBIC), + ]).convert("RGB") + +# Save the image, we will compare this with the output image from mobile device +final_img.save("./cat_upscaled.jpg") + + +###################################################################### +# .. figure:: /_static/img/cat_superres_with_ort.jpg +# :alt: output\_cat +# +# +# ONNX Runtime being a cross platform engine, you can run it across +# multiple platforms and on both CPUs and GPUs. +# +# ONNX Runtime can also be deployed to the cloud for model inferencing +# using Azure Machine Learning Services. More information `here `__. +# +# More information about ONNX Runtime's performance `here `__. +# +# +# For more information about ONNX Runtime `here `__. +# diff --git a/a100_superresolution_1_tuned/tune.sh b/a100_superresolution_1_tuned/tune.sh new file mode 100755 index 0000000..11fc6c9 --- /dev/null +++ b/a100_superresolution_1_tuned/tune.sh @@ -0,0 +1,18 @@ +#!/bin/bash +source ../../scripts/activate_venv.sh + +TUNING=$(ls tuning* --sort=time -1 | head -n1) +if [ -n "$TUNING" ]; then + TUNING_OPT="--tuning-records $TUNING" +else + TUNING_OPT="" +fi + + +set -x +python3 -m tvm.driver.tvmc tune \ + --target "cuda" \ + --output tuning.$(date --iso-8601=minutes).json \ + --input-shape "input:[1,1,640,480]" \ + $TUNING_OPT \ + super_resolution.onnx $@ \ diff --git a/a100_superresolution_1_tuned/tuning.2023-07-05T22:25+02:00.json b/a100_superresolution_1_tuned/tuning.2023-07-05T22:25+02:00.json new file mode 100644 index 0000000..1bea40a --- /dev/null +++ b/a100_superresolution_1_tuned/tuning.2023-07-05T22:25+02:00.json @@ -0,0 +1,250 @@ +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 311273450, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 1]], ["tile_y", "sp", [-1, 16, 4, 1]], ["tile_x", "sp", [-1, 4, 2, 6]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.005260868231270359], 0, 7.513531684875488, 1688588766.6851933], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 409463761, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 5, 16, 2]], ["tile_x", "sp", [-1, 4, 20, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.24766993522644043, 1688588756.5254579], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 819779386, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 2]], ["tile_y", "sp", [-1, 16, 1, 20]], ["tile_x", "sp", [-1, 6, 5, 8]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.27286720275878906, 1688588756.5254743], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 490247687, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 64]], ["tile_y", "sp", [-1, 8, 2, 40]], ["tile_x", "sp", [-1, 8, 4, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.25490283966064453, 1688588756.5254834], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 402151315, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 1, 4, 160]], ["tile_x", "sp", [-1, 2, 12, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.23966598510742188, 1688588756.525491], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 717146558, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 10, 32, 2]], ["tile_x", "sp", [-1, 1, 1, 20]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.24798321723937988, 1688588756.5254998], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 460303564, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 4, 2, 2]], ["tile_x", "sp", [-1, 3, 4, 10]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.03665865214285714], 0, 4.287174224853516, 1688588768.8369927], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 112640939, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 10, 8, 8]], ["tile_x", "sp", [-1, 60, 8, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.24495291709899902, 1688588756.5255105], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 221477268, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 1]], ["tile_y", "sp", [-1, 2, 2, 160]], ["tile_x", "sp", [-1, 1, 12, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.008369493099999998], 0, 3.7195513248443604, 1688588770.6645353], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 146235805, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 2]], ["tile_y", "sp", [-1, 2, 2, 32]], ["tile_x", "sp", [-1, 120, 2, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.22681188583374023, 1688588756.5255206], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 332198307, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 10, 2, 1]], ["tile_x", "sp", [-1, 1, 80, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.23963642120361328, 1688588756.525528], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 596465040, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 5, 12, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00361119346412556], 0, 4.642070770263672, 1688588774.1161246], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 386663630, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 2]], ["tile_y", "sp", [-1, 5, 1, 32]], ["tile_x", "sp", [-1, 1, 12, 8]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.2373974323272705, 1688588756.5255375], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 153085200, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 8]], ["tile_y", "sp", [-1, 2, 32, 10]], ["tile_x", "sp", [-1, 4, 2, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0036220210448430494], 0, 5.491139650344849, 1688588777.5022342], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 357818446, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 2]], ["tile_y", "sp", [-1, 2, 5, 4]], ["tile_x", "sp", [-1, 1, 1, 30]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.005978263796296297], 0, 6.247608661651611, 1688588780.9202664], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 303987732, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 2]], ["tile_y", "sp", [-1, 2, 40, 2]], ["tile_x", "sp", [-1, 1, 16, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.24476885795593262, 1688588756.5255492], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 173972901, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 32]], ["tile_y", "sp", [-1, 8, 5, 16]], ["tile_x", "sp", [-1, 2, 8, 15]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.2917180061340332, 1688588756.5255563], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 546705295, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 2]], ["tile_y", "sp", [-1, 2, 20, 1]], ["tile_x", "sp", [-1, 5, 12, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00019716111545555146], 0, 4.673030614852905, 1688588784.280138], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 730661651, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 64]], ["tile_y", "sp", [-1, 4, 4, 5]], ["tile_x", "sp", [-1, 24, 1, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688588762.1395404], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 401000552, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 4, 4, 4]], ["tile_x", "sp", [-1, 10, 6, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006575866051344744], 0, 5.685016870498657, 1688588787.6208522], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 771792608, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 8, 10, 8]], ["tile_x", "sp", [-1, 2, 1, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.014166953492957745], 0, 6.443981170654297, 1688588789.510978], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 130338059, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 4, 16, 5]], ["tile_x", "sp", [-1, 8, 1, 6]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.26828861236572266, 1688588762.1395702], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 440544714, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 16]], ["tile_y", "sp", [-1, 8, 80, 1]], ["tile_x", "sp", [-1, 8, 60, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.24707293510437012, 1688588762.1395795], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 111729357, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 2]], ["tile_y", "sp", [-1, 2, 4, 1]], ["tile_x", "sp", [-1, 96, 5, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00873589556521739], 0, 2.8049566745758057, 1688588791.3907804], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 177492997, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 8]], ["tile_y", "sp", [-1, 2, 8, 1]], ["tile_x", "sp", [-1, 8, 2, 30]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.007077426528169014], 0, 6.077179193496704, 1688588793.2832272], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 445344491, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 1]], ["tile_y", "sp", [-1, 160, 1, 2]], ["tile_x", "sp", [-1, 3, 16, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.22621607780456543, 1688588762.1395912], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 106103437, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 2, 1, 5]], ["tile_x", "sp", [-1, 12, 1, 40]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.024837420195121952], 0, 2.9688408374786377, 1688588795.3143578], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 756467781, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 8]], ["tile_y", "sp", [-1, 1, 64, 5]], ["tile_x", "sp", [-1, 2, 2, 40]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2757692337036133, 1688588762.1396], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 103918787, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 5, 16, 2]], ["tile_x", "sp", [-1, 2, 6, 20]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.2009897232055664, 1688588762.1396067], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 232018307, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 4]], ["tile_y", "sp", [-1, 80, 1, 4]], ["tile_x", "sp", [-1, 8, 20, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.21588540077209473, 1688588762.1396136], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 685006735, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 1, 1, 60]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0024725833086419752], 0, 3.4305028915405273, 1688588797.1154692], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 93070770, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 2, 5, 2]], ["tile_x", "sp", [-1, 8, 6, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0035762211352549887], 0, 7.016414642333984, 1688588800.4930959], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 160970506, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 8, 8, 2]], ["tile_x", "sp", [-1, 6, 2, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.008536211432203391], 0, 5.210039854049683, 1688588802.3217125], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 798303670, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 10, 64, 1]], ["tile_x", "sp", [-1, 5, 6, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.3362259864807129, 1688588762.1396265], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 434010006, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 8]], ["tile_y", "sp", [-1, 32, 10, 1]], ["tile_x", "sp", [-1, 24, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.01740821153448276], 0, 3.0290753841400146, 1688588804.3187916], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 319490095, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 2, 16, 20]], ["tile_x", "sp", [-1, 1, 6, 16]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.24735045433044434, 1688588762.1396356], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 298360516, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 16]], ["tile_y", "sp", [-1, 4, 10, 16]], ["tile_x", "sp", [-1, 16, 3, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.22897052764892578, 1688588762.1396432], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 139053102, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 10]], ["tile_x", "sp", [-1, 2, 15, 16]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.2219524383544922, 1688588762.1396506], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 404462499, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 32, 5, 2]], ["tile_x", "sp", [-1, 1, 80, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.2288813591003418, 1688588762.139658], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 535517965, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 8]], ["tile_y", "sp", [-1, 1, 40, 8]], ["tile_x", "sp", [-1, 3, 1, 16]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2316117286682129, 1688588762.1396654], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 718702772, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 2, 4, 80]], ["tile_x", "sp", [-1, 5, 2, 24]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.24669289588928223, 1688588762.1396725], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 676430857, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 32, 2, 5]], ["tile_x", "sp", [-1, 48, 1, 10]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.24060487747192383, 1688588762.1396794], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 688513187, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 1, 320, 1]], ["tile_x", "sp", [-1, 32, 3, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.24737834930419922, 1688588762.1396868], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 78567957, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 8]], ["tile_y", "sp", [-1, 2, 1, 8]], ["tile_x", "sp", [-1, 16, 30, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.004141174566115703], 0, 3.431983470916748, 1688588806.166068], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 496578654, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 5, 1, 64]], ["tile_x", "sp", [-1, 12, 4, 10]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.15234732627868652, 1688588762.1396961], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 45825888, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_y", "sp", [-1, 8, 2, 5]], ["tile_x", "sp", [-1, 6, 4, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0036742678545454545], 0, 7.8632001876831055, 1688588809.560622], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 151511421, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 2]], ["tile_y", "sp", [-1, 16, 2, 10]], ["tile_x", "sp", [-1, 4, 60, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.22440767288208008, 1688588762.1397054], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 350739634, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 8]], ["tile_y", "sp", [-1, 2, 10, 32]], ["tile_x", "sp", [-1, 1, 20, 8]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.2435894012451172, 1688588762.1397119], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 314491789, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 8]], ["tile_y", "sp", [-1, 4, 5, 32]], ["tile_x", "sp", [-1, 1, 15, 8]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.14108753204345703, 1688588762.1397192], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 740504655, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 2, 20, 8]], ["tile_x", "sp", [-1, 1, 8, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.003650492645985402], 0, 10.216843128204346, 1688588811.3697338], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 660867211, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 8]], ["tile_y", "sp", [-1, 8, 2, 5]], ["tile_x", "sp", [-1, 10, 6, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688588762.5611637], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 54419196, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 2]], ["tile_y", "sp", [-1, 8, 10, 8]], ["tile_x", "sp", [-1, 6, 10, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.1644277572631836, 1688588762.5611782], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 413454496, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 20, 8, 2]], ["tile_x", "sp", [-1, 24, 1, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.21426987648010254, 1688588762.561186], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 755396084, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 64, 1, 1]], ["tile_x", "sp", [-1, 1, 2, 30]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.007366271970588235], 0, 5.9469687938690186, 1688588813.2044122], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 471259385, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 160]], ["tile_x", "sp", [-1, 48, 2, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.20461010932922363, 1688588762.5611959], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 562628400, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 1]], ["tile_y", "sp", [-1, 20, 4, 1]], ["tile_x", "sp", [-1, 2, 6, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00648951175502008], 0, 7.1627936363220215, 1688588816.6531527], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 410374042, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 1, 8, 40]], ["tile_x", "sp", [-1, 1, 120, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.22504043579101562, 1688588762.5612044], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 72705010, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 8]], ["tile_y", "sp", [-1, 10, 64, 1]], ["tile_x", "sp", [-1, 20, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.14751076698303223, 1688588762.5612116], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 555840128, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 2, 2, 10]], ["tile_x", "sp", [-1, 80, 2, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2003316879272461, 1688588762.5612187], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 347118964, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 4]], ["tile_y", "sp", [-1, 64, 5, 1]], ["tile_x", "sp", [-1, 10, 1, 6]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.23661422729492188, 1688588762.5612261], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 558197090, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 2]], ["tile_y", "sp", [-1, 4, 32, 1]], ["tile_x", "sp", [-1, 2, 2, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0037414234282407404], 0, 5.319203615188599, 1688588820.0983293], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 122603641, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 5, 1, 16]], ["tile_x", "sp", [-1, 20, 4, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.21629619598388672, 1688588762.5612354], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 330564404, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 2, 40, 4]], ["tile_x", "sp", [-1, 6, 16, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.2410588264465332, 1688588762.5612423], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 179110860, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 1]], ["tile_y", "sp", [-1, 8, 1, 2]], ["tile_x", "sp", [-1, 1, 5, 48]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.1833885742], 0, 6.367061138153076, 1688588822.8779573], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 388009108, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 32, 1, 2]], ["tile_x", "sp", [-1, 2, 4, 10]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688588762.7442355], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 445677385, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 1, 20, 4]], ["tile_x", "sp", [-1, 12, 20, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.22141289710998535, 1688588762.7442663], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 600055824, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 4]], ["tile_y", "sp", [-1, 4, 10, 2]], ["tile_x", "sp", [-1, 16, 1, 6]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.008476420254237288], 0, 10.973556280136108, 1688588824.7859917], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 706363484, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 2, 1, 64]], ["tile_x", "sp", [-1, 8, 2, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0211612586875], 0, 5.26535439491272, 1688588826.8668625], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 764401641, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 10, 32, 2]], ["tile_x", "sp", [-1, 6, 20, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.22119736671447754, 1688588762.7442865], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 706373586, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 4, 40, 1]], ["tile_x", "sp", [-1, 12, 2, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2777266502380371, 1688588762.7442994], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 83954084, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 2, 64, 1]], ["tile_x", "sp", [-1, 8, 15, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.22492432594299316, 1688588762.7443109], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 795651105, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 32]], ["tile_y", "sp", [-1, 8, 1, 4]], ["tile_x", "sp", [-1, 160, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 4, 2.591930627822876, 1688588827.7992342], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 306040374, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 8]], ["tile_y", "sp", [-1, 5, 4, 2]], ["tile_x", "sp", [-1, 40, 3, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.14338159561157227, 1688588762.7443256], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 511055266, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 2, 1, 160]], ["tile_x", "sp", [-1, 1, 16, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.002870031019607843], 0, 4.236960411071777, 1688588831.1429706], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 329419630, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 4, 10, 1]], ["tile_x", "sp", [-1, 1, 10, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.2233436107635498, 1688588762.74434], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 226071521, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 4]], ["tile_y", "sp", [-1, 1, 16, 40]], ["tile_x", "sp", [-1, 10, 3, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.23209214210510254, 1688588762.744351], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 624776705, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 16]], ["tile_y", "sp", [-1, 5, 4, 4]], ["tile_x", "sp", [-1, 20, 6, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.26817774772644043, 1688588762.7443624], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 733899308, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 2, 1, 32]], ["tile_x", "sp", [-1, 1, 12, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.002175304750542299], 0, 5.024906873703003, 1688588832.9433432], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 246090086, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 160, 1, 4]], ["tile_x", "sp", [-1, 4, 4, 15]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.19924473762512207, 1688588762.7443767], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 833982861, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 2]], ["tile_y", "sp", [-1, 32, 5, 1]], ["tile_x", "sp", [-1, 6, 5, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688588762.7452452], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 306996522, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 3, 8, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00024331987719033234], 0, 4.184392929077148, 1688588836.2706618], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 50114253, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 1, 2, 40]], ["tile_x", "sp", [-1, 1, 4, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.004674139004672897], 0, 2.525801181793213, 1688588838.054467], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 38116321, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 1, 16, 2]], ["tile_x", "sp", [-1, 10, 3, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003637372249774572], 0, 3.946444272994995, 1688588841.4375808], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 701547798, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 2]], ["tile_y", "sp", [-1, 1, 16, 4]], ["tile_x", "sp", [-1, 1, 20, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.18653559684753418, 1688588762.7452798], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 285979898, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 2, 32, 10]], ["tile_x", "sp", [-1, 2, 4, 30]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.14024806022644043, 1688588762.7452936], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 744719334, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 2, 320, 1]], ["tile_x", "sp", [-1, 1, 2, 6]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.003945597229828851], 0, 4.877487897872925, 1688588844.8307836], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 313405819, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 1, 2, 80]], ["tile_x", "sp", [-1, 30, 2, 8]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.2076420783996582, 1688588762.745308], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 830685740, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 32]], ["tile_y", "sp", [-1, 8, 8, 2]], ["tile_x", "sp", [-1, 3, 1, 160]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.21431946754455566, 1688588762.7453196], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 466400143, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 1, 5, 4]], ["tile_x", "sp", [-1, 1, 2, 30]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.004388440040871935], 0, 4.885736703872681, 1688588848.2140548], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 469966501, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 2, 2, 40]], ["tile_x", "sp", [-1, 10, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.003991429541832669], 0, 2.989636182785034, 1688588850.033968], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 285838448, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 64, 1, 2]], ["tile_x", "sp", [-1, 4, 2, 30]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.17875194549560547, 1688588762.7453375], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 769800025, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 2]], ["tile_x", "sp", [-1, 4, 10, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0009834799970501475], 0, 9.768030643463135, 1688588851.7802465], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 366839423, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 64]], ["tile_y", "sp", [-1, 10, 64, 1]], ["tile_x", "sp", [-1, 1, 20, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.1313495635986328, 1688588762.7453518], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 543339455, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 4, 10, 8]], ["tile_x", "sp", [-1, 20, 2, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2502131462097168, 1688588762.745363], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 477638080, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 4]], ["tile_y", "sp", [-1, 1, 40, 1]], ["tile_x", "sp", [-1, 15, 1, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00477013148816568], 0, 5.71029257774353, 1688588855.169555], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 808892927, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 4]], ["tile_y", "sp", [-1, 8, 1, 20]], ["tile_x", "sp", [-1, 5, 4, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688588762.745467], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 481269854, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 2, 15, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.000216276437912014], 0, 3.7254843711853027, 1688588935.6902666], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 336762974, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 2, 15, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00022527341566601507], 0, 3.859869956970215, 1688588939.0668995], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 770283614, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 2, 15, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00022586242254310948], 0, 4.608455419540405, 1688588942.3942409], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 47749214, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 2, 15, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00021620558357968286], 0, 3.7724151611328125, 1688588945.7165093], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 474092900, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 6, 10, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002377244278973754], 0, 3.795060396194458, 1688588949.0936599], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 625776734, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 2, 15, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00022587572173913043], 0, 4.520100831985474, 1688588952.4211886], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 192256094, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 2, 15, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00022526403689780006], 0, 3.783129930496216, 1688588955.758923], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 526703786, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 2, 5, 1]], ["tile_x", "sp", [-1, 2, 8, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002839595782708223], 0, 3.7028300762176514, 1688588959.1315305], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 510791834, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 2, 4, 4]], ["tile_x", "sp", [-1, 1, 15, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002111565718770438], 0, 3.723623037338257, 1688588962.4739647], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 481027946, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 2, 12, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001441730463363573], 0, 2.095745325088501, 1688588964.2253346], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 509696390, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 4, 8, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00012432087999076852], 0, 2.24845552444458, 1688588966.0704343], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 40572260, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 6, 10, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00023858896736562315], 0, 3.7828621864318848, 1688588969.4316614], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 516551630, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 5, 2]], ["tile_x", "sp", [-1, 3, 8, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00014385480965034968], 0, 2.1296987533569336, 1688588971.2191465], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 93183146, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 2, 5, 1]], ["tile_x", "sp", [-1, 2, 8, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00028408726330630946], 0, 3.79671049118042, 1688588974.5931501], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 511078106, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 2, 5]], ["tile_x", "sp", [-1, 2, 16, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00014949275608308604], 0, 2.1570990085601807, 1688588976.319831], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 764316281, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 3, 20, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002712728562058527], 0, 6.7304840087890625, 1688588979.6556509], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 330795641, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 3, 20, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002877644319558247], 0, 4.1033594608306885, 1688588983.0322194], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 77271194, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 2, 4, 4]], ["tile_x", "sp", [-1, 1, 15, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00021117116959140913], 0, 3.721395969390869, 1688588986.3635106], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 509662795, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 3, 8, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001499737362932062], 0, 2.0880002975463867, 1688588988.0950775], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 517154654, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 2, 12, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002575944657402971], 0, 3.759247303009033, 1688588991.4909341], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 763106660, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 6, 10, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0003219804362255098], 0, 7.5741376876831055, 1688588994.8544893], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 329586020, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 6, 10, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003924094329446064], 0, 4.2628443241119385, 1688588998.225843], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 185079140, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 6, 10, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.000201535992864222], 0, 2.300299644470215, 1688589000.0281572], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 618599780, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 6, 10, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00020115715647873393], 0, 2.8990821838378906, 1688589001.7669752], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 517564754, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 2, 2, 4]], ["tile_x", "sp", [-1, 1, 16, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00015043870989560356], 0, 2.0742602348327637, 1688589003.525606], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 47507306, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 2, 12, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00014554475142737781], 0, 2.2209198474884033, 1688589005.3383188], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 76175750, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 4, 8, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0001248445737364413], 0, 2.111070394515991, 1688589007.1386523], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 806168414, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 2, 12, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00016647416227999354], 0, 2.8871583938598633, 1688589008.9150379], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 372647774, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 2, 12, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0001882210909432544], 0, 2.2410624027252197, 1688589010.6820624], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2376487, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 16, 6, 4]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589022.8434167], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 951920, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 2]], ["tile_x", "sp", [-1, 16, 40, 30]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 3.8922059535980225, 1688589022.8434677], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2325750, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 2]], ["tile_x", "sp", [-1, 2, 75, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589022.8435626], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 601006, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 8]], ["tile_x", "sp", [-1, 60, 64, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589022.843658], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2614224, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 4]], ["tile_x", "sp", [-1, 32, 20, 30]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 3.83894944190979, 1688589022.8436732], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 161895, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 64, 1]], ["tile_x", "sp", [-1, 1, 10, 4]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589022.8443656], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2990052, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 8]], ["tile_x", "sp", [-1, 2, 192, 5]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589023.0097687], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1979543, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 64]], ["tile_x", "sp", [-1, 32, 4, 15]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589023.009836], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2449286, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 1]], ["tile_x", "sp", [-1, 2, 20, 6]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589023.0098863], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2341412, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 32]], ["tile_x", "sp", [-1, 128, 1, 3]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589023.2005312], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1598700, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 2, 1]], ["tile_x", "sp", [-1, 1, 1, 120]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589023.2005992], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1664705, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 16]], ["tile_x", "sp", [-1, 48, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589023.2006495], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1999239, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 24, 10, 16]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589023.2007005], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 834025, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 8]], ["tile_x", "sp", [-1, 160, 4, 10]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589023.200756], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 905626, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 1]], ["tile_x", "sp", [-1, 2, 3, 20]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589023.2008064], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 732438, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 2]], ["tile_x", "sp", [-1, 25, 64, 4]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589023.200853], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1230194, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 1]], ["tile_x", "sp", [-1, 2, 1600, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 3.7098143100738525, 1688589023.2008722], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 779788, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 1]], ["tile_x", "sp", [-1, 2, 4, 6]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589023.200923], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1144353, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 8, 1]], ["tile_x", "sp", [-1, 32, 25, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589023.2514715], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 736002, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 16]], ["tile_x", "sp", [-1, 10, 120, 4]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589023.2888925], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1341451, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 4]], ["tile_x", "sp", [-1, 1, 25, 6]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589023.4697015], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 592204, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 1]], ["tile_x", "sp", [-1, 3, 32, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589023.4697673], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1393048, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 16]], ["tile_x", "sp", [-1, 3, 10, 10]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589023.4698195], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2147407, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 2]], ["tile_x", "sp", [-1, 3, 2, 100]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589023.46987], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1648715, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 16, 2]], ["tile_x", "sp", [-1, 1, 8, 600]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589023.469918], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2392928, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 1]], ["tile_x", "sp", [-1, 5, 48, 4]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589023.4699707], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 91981, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 16, 15, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589023.4700236], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2501028, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 2, 1]], ["tile_x", "sp", [-1, 30, 8, 10]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589023.5309668], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3324230, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 1]], ["tile_x", "sp", [-1, 1, 8, 2400]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 3.52604603767395, 1688589023.5309975], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1708947, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 4]], ["tile_x", "sp", [-1, 4, 64, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589023.531081], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1464585, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 2]], ["tile_x", "sp", [-1, 20, 6, 20]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589023.531161], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1410902, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 2, 2]], ["tile_x", "sp", [-1, 4, 4, 12]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589023.5312395], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 511952, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 4]], ["tile_x", "sp", [-1, 2, 5, 192]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589023.531329], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1152047, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 8]], ["tile_x", "sp", [-1, 4, 50, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589023.7060244], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2386592, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 8]], ["tile_x", "sp", [-1, 30, 20, 4]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589023.7061212], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2514495, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 2, 192, 10]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589023.7062025], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 924504, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 25, 2, 24]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589023.7062886], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 673196, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 1]], ["tile_x", "sp", [-1, 24, 400, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 3.4840450286865234, 1688589023.7063146], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3190726, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 8]], ["tile_x", "sp", [-1, 160, 3, 40]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 3.622133493423462, 1688589023.7063282], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2270174, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 16]], ["tile_x", "sp", [-1, 160, 120, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 3.3811724185943604, 1688589023.7063391], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2810643, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 1]], ["tile_x", "sp", [-1, 25, 32, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589023.7939608], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1530229, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 8, 6, 40]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589023.794061], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2037552, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 2]], ["tile_x", "sp", [-1, 1, 16, 24]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589023.852951], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1088501, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 8, 3, 400]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589023.8530514], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1008708, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 2]], ["tile_x", "sp", [-1, 15, 1, 64]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589023.9728303], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2456467, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 4]], ["tile_x", "sp", [-1, 4, 400, 6]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589023.9729345], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3040107, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 4]], ["tile_x", "sp", [-1, 5, 120, 8]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 3.366708755493164, 1688589023.9729624], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2326251, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 128, 75, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 3.264958620071411, 1688589023.9729772], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1071141, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 4]], ["tile_x", "sp", [-1, 16, 6, 200]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 3.3560807704925537, 1688589023.9729898], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 728151, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 1, 40, 4]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589024.1032767], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3264940, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 8, 120]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589024.103374], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3317991, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 16]], ["tile_x", "sp", [-1, 5, 1, 960]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589024.3092172], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1339340, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 2]], ["tile_x", "sp", [-1, 320, 10, 6]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 3.258148670196533, 1688589024.30924], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1684356, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 8]], ["tile_x", "sp", [-1, 75, 8, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589024.3093016], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2652133, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 5, 10, 48]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589024.3093562], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2856118, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 32, 6, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589024.309405], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2244778, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 2]], ["tile_x", "sp", [-1, 5, 15, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589024.309453], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2863247, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 16, 1]], ["tile_x", "sp", [-1, 200, 12, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589024.3095012], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2187108, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 300]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589024.309547], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 229174, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 1]], ["tile_x", "sp", [-1, 100, 8, 6]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589024.3095968], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1070329, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 4, 4, 200]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589024.3096433], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3313158, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 2]], ["tile_x", "sp", [-1, 3, 2, 640]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589025.8685443], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 387996, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 64, 25]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589026.171734], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1081970, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 4]], ["tile_x", "sp", [-1, 5, 2, 320]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589026.1717901], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 408008, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 1]], ["tile_x", "sp", [-1, 60, 10, 32]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 2.67655611038208, 1688589026.171806], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2058754, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 32]], ["tile_x", "sp", [-1, 1, 16, 30]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589026.171859], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2960152, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 16]], ["tile_x", "sp", [-1, 10, 1, 5]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589026.1719081], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 176918, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 1]], ["tile_x", "sp", [-1, 2, 60, 4]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589026.1719563], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2763583, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 8]], ["tile_x", "sp", [-1, 5, 1, 960]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589026.172004], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 404922, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 2]], ["tile_x", "sp", [-1, 6, 5, 32]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589026.1720526], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2444530, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 2]], ["tile_x", "sp", [-1, 2, 5, 6]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589026.1720989], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 389275, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 1]], ["tile_x", "sp", [-1, 2, 192, 25]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 3.1618242263793945, 1688589026.1721082], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1170418, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 2]], ["tile_x", "sp", [-1, 48, 400, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 2.8427815437316895, 1688589026.1721163], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1505962, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 1]], ["tile_x", "sp", [-1, 1, 40, 30]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589026.1721692], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 18933, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 1, 2]], ["tile_x", "sp", [-1, 320, 6, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589026.1722171], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2786710, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 1]], ["tile_x", "sp", [-1, 5, 5, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589026.1722627], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1306521, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 8]], ["tile_x", "sp", [-1, 16, 5, 5]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589026.1723077], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2137118, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 16]], ["tile_x", "sp", [-1, 6, 10, 80]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589026.1723552], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2049509, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 16]], ["tile_x", "sp", [-1, 24, 16, 25]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589026.1724026], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1059084, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 2, 1]], ["tile_x", "sp", [-1, 12, 2, 160]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589026.1724508], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2769937, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 2]], ["tile_x", "sp", [-1, 1, 1, 3200]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589026.1724956], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3013501, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 96, 1, 8]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589026.1725411], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2672650, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 1]], ["tile_x", "sp", [-1, 300, 1, 64]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 2.8037192821502686, 1688589026.1725502], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3155424, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 2]], ["tile_x", "sp", [-1, 2, 6, 25]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589026.1725967], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2645321, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 16]], ["tile_x", "sp", [-1, 2, 40, 40]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589026.1726425], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1517253, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 2]], ["tile_x", "sp", [-1, 25, 12, 32]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589026.1726887], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 243088, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 16]], ["tile_x", "sp", [-1, 5, 2, 8]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589026.1727364], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 266802, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 1]], ["tile_x", "sp", [-1, 30, 80, 8]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 2.749265193939209, 1688589026.1727455], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2548719, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 16]], ["tile_x", "sp", [-1, 75, 4, 16]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589026.1727924], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 156450, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 2]], ["tile_x", "sp", [-1, 6, 5, 4]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589026.1728394], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3069211, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 1]], ["tile_x", "sp", [-1, 2, 240, 10]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 2.6830661296844482, 1688589026.1728485], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3104100, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 2]], ["tile_x", "sp", [-1, 12, 5, 16]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589026.172895], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1432234, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 1, 256, 15]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589026.172941], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2655663, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 1]], ["tile_x", "sp", [-1, 16, 1, 50]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589026.1729884], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 426338, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 2, 2]], ["tile_x", "sp", [-1, 1, 24, 40]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589026.1730344], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3234250, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 32]], ["tile_x", "sp", [-1, 4, 75, 64]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 2.7193875312805176, 1688589026.173043], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1768764, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 4]], ["tile_x", "sp", [-1, 24, 50, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589038.3523996], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1753685, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 4, 1]], ["tile_x", "sp", [-1, 16, 12, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589038.3813376], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3299961, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 8, 1]], ["tile_x", "sp", [-1, 1, 3, 320]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589038.3813949], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2220813, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 8, 1]], ["tile_x", "sp", [-1, 600, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589038.4025817], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3133015, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 8]], ["tile_x", "sp", [-1, 1, 20, 20]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589038.4026299], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2115048, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 2, 1]], ["tile_x", "sp", [-1, 1, 20, 60]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589038.4026773], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 566994, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 16]], ["tile_x", "sp", [-1, 64, 4, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589038.4506953], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2893421, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 2]], ["tile_x", "sp", [-1, 2, 1600, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 2.0399436950683594, 1688589038.4507241], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2706611, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 16, 2]], ["tile_x", "sp", [-1, 2, 32, 100]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589038.450781], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1489340, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 1]], ["tile_x", "sp", [-1, 12, 2, 25]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589038.4511085], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1562618, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 4]], ["tile_x", "sp", [-1, 3, 1, 64]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589038.4887002], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2259393, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 2]], ["tile_x", "sp", [-1, 2, 48, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589038.4887555], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2015199, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 64, 3, 20]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589038.526841], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 231533, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 200, 16, 6]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 2.118317127227783, 1688589038.5268598], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 527728, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 2]], ["tile_x", "sp", [-1, 10, 2, 320]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589038.5269144], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 68977, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 20, 1, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589038.5547552], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 364780, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 4]], ["tile_x", "sp", [-1, 20, 48, 20]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 2.066319704055786, 1688589038.5547698], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3062808, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 3, 32, 10]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589038.5670102], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 825886, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 32]], ["tile_x", "sp", [-1, 1, 1, 10]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589039.6412458], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1935787, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 32, 1, 10]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589039.6413004], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1031133, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 1, 2]], ["tile_x", "sp", [-1, 2, 40, 80]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589039.703537], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 519320, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 2]], ["tile_x", "sp", [-1, 40, 1, 240]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589039.703597], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1803291, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 4]], ["tile_x", "sp", [-1, 16, 80, 3]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 1.5592052936553955, 1688589039.703616], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1808350, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 32]], ["tile_x", "sp", [-1, 1, 6400, 3]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 1.5982441902160645, 1688589039.7036245], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1747856, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 8]], ["tile_x", "sp", [-1, 160, 6, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589039.8674464], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2760652, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 16]], ["tile_x", "sp", [-1, 5, 5, 768]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 1.736908197402954, 1688589039.8674586], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 320498, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 2, 2]], ["tile_x", "sp", [-1, 32, 20, 15]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589039.8675117], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3242834, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 1]], ["tile_x", "sp", [-1, 10, 4, 80]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688589040.1018338], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 659783, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 16, 2]], ["tile_x", "sp", [-1, 12, 50, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688589040.101893], "version": 0.2, "tvm_version": "0.11.dev0"} diff --git a/a100_superresolution_4_tuned/README.md b/a100_superresolution_4_tuned/README.md new file mode 100644 index 0000000..07ef5db --- /dev/null +++ b/a100_superresolution_4_tuned/README.md @@ -0,0 +1,2 @@ +This is just another version of the superresolution model. +Everything is linked to the "1" upscale factor version, but with different factors, of course. diff --git a/a100_superresolution_4_tuned/UPSCALE_FACTOR b/a100_superresolution_4_tuned/UPSCALE_FACTOR new file mode 100644 index 0000000..b8626c4 --- /dev/null +++ b/a100_superresolution_4_tuned/UPSCALE_FACTOR @@ -0,0 +1 @@ +4 diff --git a/a100_superresolution_4_tuned/do.sh b/a100_superresolution_4_tuned/do.sh new file mode 120000 index 0000000..57921dc --- /dev/null +++ b/a100_superresolution_4_tuned/do.sh @@ -0,0 +1 @@ +../a100_superresolution_1_tuned/do.sh \ No newline at end of file diff --git a/a100_superresolution_4_tuned/metadata.json b/a100_superresolution_4_tuned/metadata.json new file mode 100644 index 0000000..1dbe1d5 --- /dev/null +++ b/a100_superresolution_4_tuned/metadata.json @@ -0,0 +1,16 @@ +{ + "load_time": 1000000000, + "exec_time": [1000000,2000000,4000000,8000000], + "weights_size": 100000000, + "workspace_size": 500000000, + "input_name" : "input", + "output_name" : "output", + "input_shape": [1,1,640,480], + "output_shape": [1,1,2560,1920], + "input_type": "FP32", + "output_type": "FP32", + "device": "CUDA", + "model" : "a100_superresolution_4_tuned", + "architecture" : "CUDA_80" + +} diff --git a/a100_superresolution_4_tuned/tuning.2023-07-24T14:54+02:00.json b/a100_superresolution_4_tuned/tuning.2023-07-24T14:54+02:00.json new file mode 100644 index 0000000..34248ab --- /dev/null +++ b/a100_superresolution_4_tuned/tuning.2023-07-24T14:54+02:00.json @@ -0,0 +1,1000 @@ +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 743785985, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 1]], ["tile_y", "sp", [-1, 10, 4, 1]], ["tile_x", "sp", [-1, 8, 12, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.344801664352417, 1690203274.463635], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 153615488, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 4, 1, 40]], ["tile_x", "sp", [-1, 1, 3, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.015244722303030301], 0, 5.041356801986694, 1690203286.8777258], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 696876055, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 4, 2, 8]], ["tile_x", "sp", [-1, 4, 6, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0014427560549054904], 0, 10.23303747177124, 1690203290.201275], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 777572179, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 80, 1, 1]], ["tile_x", "sp", [-1, 1, 30, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203284.0212884], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 507898953, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 10]], ["tile_x", "sp", [-1, 32, 3, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.016033548015873016], 0, 2.825629711151123, 1690203292.123819], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 281222971, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 1, 2, 16]], ["tile_x", "sp", [-1, 1, 5, 12]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00040930774112841464], 0, 4.83048677444458, 1690203295.493552], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 29419338, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 2, 4, 8]], ["tile_x", "sp", [-1, 1, 8, 15]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0012002108997772828], 0, 4.543039798736572, 1690203298.8595202], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 439798305, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 2, 40, 8]], ["tile_x", "sp", [-1, 8, 30, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2957279682159424, 1690203284.0213199], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 49597409, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 8, 5, 1]], ["tile_x", "sp", [-1, 80, 1, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.02691804905263158], 0, 3.3347625732421875, 1690203300.938717], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 594117769, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 30, 1, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.016499359622950818], 0, 5.788715124130249, 1690203302.949853], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 856327739, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 5, 4, 2]], ["tile_x", "sp", [-1, 5, 12, 8]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2734391689300537, 1690203284.0213332], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 145318576, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 8, 10, 1]], ["tile_x", "sp", [-1, 120, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.014721394855072465], 0, 3.1152281761169434, 1690203304.8618598], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 629091068, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 10, 4, 4]], ["tile_x", "sp", [-1, 16, 10, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2521517276763916, 1690203284.0213435], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 603838703, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 64]], ["tile_y", "sp", [-1, 1, 20, 1]], ["tile_x", "sp", [-1, 2, 1, 10]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.004414522546255507], 0, 2.987075090408325, 1690203306.6954286], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 718801027, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 5, 1, 4]], ["tile_x", "sp", [-1, 5, 4, 24]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.012092761662650602], 0, 3.6237003803253174, 1690203308.6138098], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 763483119, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 8, 16, 5]], ["tile_x", "sp", [-1, 5, 12, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.30068135261535645, 1690203284.0213544], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 616084236, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 1]], ["tile_y", "sp", [-1, 2, 1, 32]], ["tile_x", "sp", [-1, 5, 3, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.016790306583333334], 0, 11.67369818687439, 1690203310.537308], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 649763697, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 2, 32, 1]], ["tile_x", "sp", [-1, 1, 1, 120]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0033784146689189187], 0, 7.128852367401123, 1690203312.355812], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 714143578, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 4, 5, 32]], ["tile_x", "sp", [-1, 5, 1, 12]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.23583126068115234, 1690203284.1860886], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 632571202, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 10, 1, 16]], ["tile_x", "sp", [-1, 2, 12, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.24208688735961914, 1690203284.186101], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 784729628, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 16, 1, 5]], ["tile_x", "sp", [-1, 16, 1, 10]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.221038818359375, 1690203284.186109], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 142923988, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 10]], ["tile_x", "sp", [-1, 1, 2, 48]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.2408304214477539, 1690203284.1861176], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 502869642, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 4, 2, 80]], ["tile_x", "sp", [-1, 2, 8, 30]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2493436336517334, 1690203284.1861253], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 248365742, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 32]], ["tile_x", "sp", [-1, 6, 4, 20]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.21766090393066406, 1690203284.186133], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 472145361, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 2, 1, 80]], ["tile_x", "sp", [-1, 6, 4, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.011452567352272729], 0, 2.8435606956481934, 1690203314.2749603], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 614389735, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 8, 2, 20]], ["tile_x", "sp", [-1, 6, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.006472598361290323], 0, 5.7559733390808105, 1690203316.091463], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 308872593, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 4]], ["tile_y", "sp", [-1, 1, 160, 4]], ["tile_x", "sp", [-1, 4, 2, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.2252335548400879, 1690203284.1861458], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 599538408, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 10, 16, 4]], ["tile_x", "sp", [-1, 2, 24, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2745518684387207, 1690203284.1861534], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 483713244, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 20]], ["tile_x", "sp", [-1, 4, 4, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2572021484375, 1690203284.1861606], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 292330332, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 48, 5, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.015250168303030304], 0, 4.45148491859436, 1690203318.00405], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 681320849, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 2]], ["tile_y", "sp", [-1, 4, 2, 20]], ["tile_x", "sp", [-1, 24, 1, 20]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.22954392433166504, 1690203284.1861696], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 493567063, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 2]], ["tile_y", "sp", [-1, 64, 1, 2]], ["tile_x", "sp", [-1, 15, 1, 8]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.22708916664123535, 1690203284.186177], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 804750682, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 8, 5, 1]], ["tile_x", "sp", [-1, 1, 5, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00028316252765583845], 0, 4.6131720542907715, 1690203321.3967128], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 725382178, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 2, 2, 8]], ["tile_x", "sp", [-1, 60, 4, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203284.2491853], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 518143787, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 1, 4, 16]], ["tile_x", "sp", [-1, 1, 30, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00029716200220831796], 0, 4.062129497528076, 1690203324.758215], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 332991264, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 4]], ["tile_y", "sp", [-1, 32, 1, 10]], ["tile_x", "sp", [-1, 6, 1, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203284.3882153], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 107318970, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 8]], ["tile_y", "sp", [-1, 4, 10, 8]], ["tile_x", "sp", [-1, 2, 4, 60]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.219498872756958, 1690203284.3882308], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 77148204, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 320, 2]], ["tile_x", "sp", [-1, 10, 12, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.22429418563842773, 1690203284.3882396], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 445066465, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 20, 16, 2]], ["tile_x", "sp", [-1, 20, 12, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2345137596130371, 1690203284.388247], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 70477244, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 5, 64]], ["tile_x", "sp", [-1, 1, 12, 40]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.24114751815795898, 1690203284.3882537], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 841717425, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 1, 8, 40]], ["tile_x", "sp", [-1, 3, 8, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2966420650482178, 1690203284.388261], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 131008571, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 1, 320, 1]], ["tile_x", "sp", [-1, 5, 4, 6]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.2301652431488037, 1690203284.3882678], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 107923719, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 4, 10, 8]], ["tile_x", "sp", [-1, 2, 1, 120]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.22876501083374023, 1690203284.3882747], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 847510658, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 2, 1, 8]], ["tile_x", "sp", [-1, 15, 2, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203284.3883286], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 843371216, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 5, 2, 64]], ["tile_x", "sp", [-1, 4, 30, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2065575122833252, 1690203284.388338], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 173703194, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 10, 8, 1]], ["tile_x", "sp", [-1, 16, 2, 15]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.25975775718688965, 1690203284.3883448], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 509268266, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 2]], ["tile_y", "sp", [-1, 4, 5, 8]], ["tile_x", "sp", [-1, 4, 6, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.003993722374501992], 0, 3.747284173965454, 1690203326.5524485], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 753768097, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 1, 4, 8]], ["tile_x", "sp", [-1, 6, 2, 20]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203284.4448414], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 187329429, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 4, 4, 1]], ["tile_x", "sp", [-1, 12, 40, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.26386213302612305, 1690203284.4448557], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 644563876, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 2]], ["tile_y", "sp", [-1, 8, 80, 1]], ["tile_x", "sp", [-1, 6, 5, 16]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2602658271789551, 1690203284.4448647], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 305545415, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 10, 1, 1]], ["tile_x", "sp", [-1, 12, 2, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203284.4449155], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 697094510, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 32, 2, 1]], ["tile_x", "sp", [-1, 1, 8, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00024046465348314606], 0, 5.72331690788269, 1690203329.923087], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 293658815, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 4, 80, 1]], ["tile_x", "sp", [-1, 48, 10, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.14245867729187012, 1690203284.4449267], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 740668172, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 1, 16, 10]], ["tile_x", "sp", [-1, 1, 10, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.24376344680786133, 1690203284.4449346], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 852057731, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 1, 64, 2]], ["tile_x", "sp", [-1, 1, 12, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.16716241836547852, 1690203284.444942], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 147861224, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 1, 64, 1]], ["tile_x", "sp", [-1, 96, 5, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.221571683883667, 1690203284.4449487], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 376271079, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 20, 8, 1]], ["tile_x", "sp", [-1, 2, 16, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.22370266914367676, 1690203284.444956], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 435895968, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 4]], ["tile_y", "sp", [-1, 16, 1, 40]], ["tile_x", "sp", [-1, 3, 4, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.016923988850000002], 0, 3.6693367958068848, 1690203331.8704588], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 440786784, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 4]], ["tile_y", "sp", [-1, 5, 128, 1]], ["tile_x", "sp", [-1, 5, 96, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2372877597808838, 1690203284.4449654], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 672895576, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 4]], ["tile_y", "sp", [-1, 1, 2, 32]], ["tile_x", "sp", [-1, 4, 4, 6]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.009151150789772728], 0, 7.387798309326172, 1690203335.4239647], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 438006513, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 8, 10, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0004117752073979592], 0, 4.888199090957642, 1690203338.875392], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 848421759, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 8, 80, 1]], ["tile_x", "sp", [-1, 4, 5, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2941586971282959, 1690203284.4449763], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 383186460, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 2]], ["tile_y", "sp", [-1, 4, 2, 8]], ["tile_x", "sp", [-1, 5, 1, 6]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203284.4450262], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 602581140, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 80]], ["tile_x", "sp", [-1, 5, 3, 8]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.1824948787689209, 1690203284.4450357], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 128643706, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 4, 4, 5]], ["tile_x", "sp", [-1, 8, 3, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.004100196713114754], 0, 4.711694002151489, 1690203340.6609201], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 636698019, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 1]], ["tile_y", "sp", [-1, 40, 8, 1]], ["tile_x", "sp", [-1, 2, 4, 6]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2595348358154297, 1690203284.4450443], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 131558509, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 1, 16, 20]], ["tile_x", "sp", [-1, 2, 10, 6]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.24088478088378906, 1690203284.445052], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 352991342, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 8, 8, 10]], ["tile_x", "sp", [-1, 20, 1, 12]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.3046073913574219, 1690203284.4450586], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 832021413, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 8]], ["tile_y", "sp", [-1, 4, 4, 4]], ["tile_x", "sp", [-1, 4, 2, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203284.5205424], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 122074450, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 20, 2, 8]], ["tile_x", "sp", [-1, 5, 2, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.003699521685779817], 0, 5.9598448276519775, 1690203344.0532887], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 282231570, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 2, 4, 16]], ["tile_x", "sp", [-1, 4, 4, 15]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.21052002906799316, 1690203284.5205574], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 48561108, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 2]], ["tile_y", "sp", [-1, 4, 80, 2]], ["tile_x", "sp", [-1, 4, 30, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.254852294921875, 1690203284.5205646], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 512638403, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 1]], ["tile_y", "sp", [-1, 64, 1, 2]], ["tile_x", "sp", [-1, 10, 48, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.19222688674926758, 1690203284.5205712], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 447895773, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 1, 80, 4]], ["tile_x", "sp", [-1, 4, 5, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.22272062301635742, 1690203284.5205786], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 685952988, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 2, 10]], ["tile_x", "sp", [-1, 2, 1, 120]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.21466875076293945, 1690203284.5205853], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 199728457, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 8, 8, 5]], ["tile_x", "sp", [-1, 3, 40, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.2085568904876709, 1690203284.5205925], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 539036229, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 32]], ["tile_y", "sp", [-1, 1, 1, 80]], ["tile_x", "sp", [-1, 1, 16, 30]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.21007251739501953, 1690203284.5205996], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 188873482, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 8]], ["tile_y", "sp", [-1, 4, 20, 2]], ["tile_x", "sp", [-1, 48, 1, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.1915757656097412, 1690203284.520607], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 479990867, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 64]], ["tile_y", "sp", [-1, 2, 1, 5]], ["tile_x", "sp", [-1, 48, 5, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.033196793064516124], 0, 3.8220338821411133, 1690203346.2565665], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 447233205, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 8]], ["tile_y", "sp", [-1, 4, 5, 1]], ["tile_x", "sp", [-1, 8, 2, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00552771546875], 0, 5.066028118133545, 1690203349.7727427], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 550626610, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 16, 1, 4]], ["tile_x", "sp", [-1, 10, 2, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.013581602351351352], 0, 3.9733948707580566, 1690203351.6829185], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 343840918, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 4, 5, 16]], ["tile_x", "sp", [-1, 1, 20, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.2251136302947998, 1690203284.5206196], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 231831456, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_y", "sp", [-1, 1, 4, 16]], ["tile_x", "sp", [-1, 5, 16, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.21924042701721191, 1690203284.5206256], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 60663099, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 16, 1, 5]], ["tile_x", "sp", [-1, 5, 3, 8]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.009171018281818183], 0, 3.9885013103485107, 1690203353.6043456], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 518742592, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 20, 2, 8]], ["tile_x", "sp", [-1, 1, 120, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.17857074737548828, 1690203284.5206342], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 53614859, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 1]], ["tile_y", "sp", [-1, 8, 4, 10]], ["tile_x", "sp", [-1, 3, 5, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.1424427032470703, 1690203284.520641], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 615644457, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 4]], ["tile_y", "sp", [-1, 8, 1, 80]], ["tile_x", "sp", [-1, 24, 2, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.1883540153503418, 1690203284.5206478], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 860881376, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 640, 1]], ["tile_x", "sp", [-1, 1, 2, 16]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.22831964492797852, 1690203284.5206552], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 119863479, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 1, 8, 16]], ["tile_x", "sp", [-1, 5, 12, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.16644787788391113, 1690203284.520662], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 223699001, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 2, 5, 1]], ["tile_x", "sp", [-1, 2, 60, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00019469376984318455], 0, 4.009869337081909, 1690203356.9955864], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 836346748, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 16]], ["tile_y", "sp", [-1, 32, 2, 10]], ["tile_x", "sp", [-1, 6, 16, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.26215553283691406, 1690203284.5206716], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 742717371, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 2]], ["tile_y", "sp", [-1, 8, 4, 5]], ["tile_x", "sp", [-1, 2, 3, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00421279755613577], 0, 12.395153999328613, 1690203360.3904004], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 351937756, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 8, 1, 8]], ["tile_x", "sp", [-1, 3, 4, 10]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0966260451875], 0, 11.446822881698608, 1690203363.7784545], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 304004377, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 2, 4, 16]], ["tile_x", "sp", [-1, 1, 16, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.004056964510050251], 0, 4.960422992706299, 1690203367.2216237], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 846500022, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 64, 1, 5]], ["tile_x", "sp", [-1, 1, 160, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.19829726219177246, 1690203284.5206828], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 142792665, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 4]], ["tile_y", "sp", [-1, 10, 8, 4]], ["tile_x", "sp", [-1, 2, 1, 48]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 5]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.24644947052001953, 1690203284.5206885], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 490027197, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 5, 4, 4]], ["tile_x", "sp", [-1, 1, 4, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0030419039735849057], 0, 4.064956903457642, 1690203580.4134705], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 56506557, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 5, 4, 4]], ["tile_x", "sp", [-1, 1, 4, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0030402211285444234], 0, 4.08941388130188, 1690203583.753385], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 5898209, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 4, 4, 2]], ["tile_x", "sp", [-1, 1, 24, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00022667456330713082], 0, 3.7889750003814697, 1690203587.1407335], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 439418849, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 4, 4, 2]], ["tile_x", "sp", [-1, 1, 24, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00022659910050533405], 0, 3.795036792755127, 1690203590.479887], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 438773665, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 2]], ["tile_x", "sp", [-1, 1, 16, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0014224976799431012], 0, 2.021360158920288, 1690203592.1968386], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 5253025, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 2]], ["tile_x", "sp", [-1, 1, 16, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.001422417927880387], 0, 3.7070748805999756, 1690203595.579606], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 438201688, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 16, 5, 1]], ["tile_x", "sp", [-1, 1, 12, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0004562522718978102], 0, 2.2256948947906494, 1690203597.302709], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 4681048, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 16, 5, 1]], ["tile_x", "sp", [-1, 1, 12, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00045612904483925546], 0, 3.877108573913574, 1690203600.6481], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 634534077, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 5, 4, 4]], ["tile_x", "sp", [-1, 1, 4, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.001332335774966711], 0, 6.185529708862305, 1690203602.4066179], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 201013437, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 5, 4, 4]], ["tile_x", "sp", [-1, 1, 4, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0016421497453608248], 0, 4.912898778915405, 1690203605.7339015], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 479173730, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 20, 2, 2]], ["tile_x", "sp", [-1, 2, 4, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0007073407487901451], 0, 4.091086149215698, 1690203609.0872386], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 45653951, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 10, 4, 2]], ["tile_x", "sp", [-1, 2, 4, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005904172035818713], 0, 4.298046350479126, 1690203612.4891834], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 479174591, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 10, 4, 2]], ["tile_x", "sp", [-1, 2, 4, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005902638971361777], 0, 2.6944754123687744, 1690203614.260728], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 45653090, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 20, 2, 2]], ["tile_x", "sp", [-1, 2, 4, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0007069665557122707], 0, 2.4451231956481934, 1690203615.9919906], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 149759989, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 5, 4, 2]], ["tile_x", "sp", [-1, 1, 16, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006023502673378076], 0, 3.853814125061035, 1690203619.3784692], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 583280629, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 5, 4, 2]], ["tile_x", "sp", [-1, 1, 16, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006181808108776266], 0, 3.3022961616516113, 1690203621.1083882], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 582708568, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 16, 5, 1]], ["tile_x", "sp", [-1, 1, 12, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0004496918530805687], 0, 4.524312973022461, 1690203624.4501905], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 149187928, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 16, 5, 1]], ["tile_x", "sp", [-1, 1, 12, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00045558160928961755], 0, 2.3212227821350098, 1690203626.214257], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 5576425, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 4, 5, 2]], ["tile_x", "sp", [-1, 1, 20, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0010286663874614593], 0, 2.061904191970825, 1690203627.9280832], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 439097065, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 4, 5, 2]], ["tile_x", "sp", [-1, 1, 20, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0010286485097636177], 0, 2.094010829925537, 1690203629.693484], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 5567128, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 10, 4, 1]], ["tile_x", "sp", [-1, 1, 20, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0011101001054384016], 0, 2.1813900470733643, 1690203631.4724681], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 474328408, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 16, 5, 1]], ["tile_x", "sp", [-1, 1, 12, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002521649062841104], 0, 3.8565404415130615, 1690203634.7940066], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 40807768, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 16, 5, 1]], ["tile_x", "sp", [-1, 1, 12, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00025211342431800466], 0, 3.8358349800109863, 1690203638.147032], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 47156862, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 2, 4, 5]], ["tile_x", "sp", [-1, 1, 10, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0001858704294097342], 0, 3.8224425315856934, 1690203641.5421386], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 480677502, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 2, 4, 5]], ["tile_x", "sp", [-1, 1, 10, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00018578519194356784], 0, 2.034843683242798, 1690203643.2943118], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 190159970, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 20, 2, 2]], ["tile_x", "sp", [-1, 2, 4, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006649062459893047], 0, 4.333078622817993, 1690203646.6454818], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 623680610, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 20, 2, 2]], ["tile_x", "sp", [-1, 2, 4, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006899824953071671], 0, 7.096621036529541, 1690203650.0138803], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 475215329, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 8, 5, 1]], ["tile_x", "sp", [-1, 1, 20, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00022861998784108581], 0, 3.8006556034088135, 1690203653.3532767], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 41694689, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 8, 5, 1]], ["tile_x", "sp", [-1, 1, 20, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 5]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00022866066647815638], 0, 3.6713173389434814, 1690203656.6731656], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2190127, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 16]], ["tile_x", "sp", [-1, 12, 1, 320]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203668.7363906], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 694731, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 4]], ["tile_x", "sp", [-1, 80, 80, 3]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 4.2927775382995605, 1690203668.7364404], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1618826, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 4]], ["tile_x", "sp", [-1, 3, 40, 160]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 3.808863401412964, 1690203668.7364552], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 142121, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 16]], ["tile_x", "sp", [-1, 40, 160, 3]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 3.998570680618286, 1690203668.7364686], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 906093, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 8]], ["tile_x", "sp", [-1, 16, 3, 20]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203668.8754184], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2030876, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 1, 480, 20]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203668.9944205], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2826242, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 4]], ["tile_x", "sp", [-1, 128, 150, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 4.227950096130371, 1690203668.9944549], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1214454, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 8]], ["tile_x", "sp", [-1, 32, 50, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203668.9945507], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2205992, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 8]], ["tile_x", "sp", [-1, 5, 1, 768]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203668.994635], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2214219, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 4]], ["tile_x", "sp", [-1, 10, 1, 1920]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 3.726078510284424, 1690203668.994651], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2614317, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 8]], ["tile_x", "sp", [-1, 1, 32, 30]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203669.0067687], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3060181, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 4]], ["tile_x", "sp", [-1, 120, 16, 10]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 4.011627197265625, 1690203669.0067966], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2898178, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 1]], ["tile_x", "sp", [-1, 200, 2, 3]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203669.2660985], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3304609, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 4, 1, 400]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203669.266199], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2337433, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 1, 640, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203669.2662861], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1501216, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 4]], ["tile_x", "sp", [-1, 1, 4, 30]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203669.2663698], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2832343, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 2]], ["tile_x", "sp", [-1, 1, 384, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203669.2664506], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2752801, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 2]], ["tile_x", "sp", [-1, 2, 8, 400]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203669.2665312], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2350088, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 1]], ["tile_x", "sp", [-1, 80, 10, 3]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203669.2669392], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2070474, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 2]], ["tile_x", "sp", [-1, 3, 10, 32]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203669.2989547], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 454788, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 2, 1]], ["tile_x", "sp", [-1, 75, 1, 64]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203669.2990468], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 263749, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 8]], ["tile_x", "sp", [-1, 1, 48, 8]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203669.2991302], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2240144, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 2]], ["tile_x", "sp", [-1, 2, 10, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203669.2992108], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 921121, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 4]], ["tile_x", "sp", [-1, 8, 120, 20]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 4.142470598220825, 1690203669.2992365], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 19520, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 2]], ["tile_x", "sp", [-1, 2, 8, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203669.3678555], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 400530, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 1]], ["tile_x", "sp", [-1, 120, 1, 32]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203669.411466], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 276791, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 2, 1]], ["tile_x", "sp", [-1, 8, 3, 10]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203669.4115553], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2319017, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 20, 32, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203669.527231], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2969950, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 2]], ["tile_x", "sp", [-1, 48, 5, 5]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203669.5461178], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3177654, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 1]], ["tile_x", "sp", [-1, 60, 5, 32]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203669.5462449], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 790860, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 20, 80, 6]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203669.5463388], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1636261, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 1]], ["tile_x", "sp", [-1, 3, 2, 320]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203669.697255], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1503348, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 16, 8, 30]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203669.6973588], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1945191, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 1]], ["tile_x", "sp", [-1, 64, 6, 10]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203669.6974466], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 126113, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 160, 2, 3]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203669.6975403], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1032375, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 1]], ["tile_x", "sp", [-1, 4, 1, 96]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203669.6976254], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3018213, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 1]], ["tile_x", "sp", [-1, 80, 3, 8]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203669.6977277], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3272071, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 1]], ["tile_x", "sp", [-1, 16, 1, 150]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203669.7018087], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2853742, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 1]], ["tile_x", "sp", [-1, 30, 5, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203669.7372694], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2324801, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 4, 1]], ["tile_x", "sp", [-1, 3, 64, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203669.7373712], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1718671, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 2]], ["tile_x", "sp", [-1, 60, 160, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203669.8978424], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2489410, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 8]], ["tile_x", "sp", [-1, 5, 1, 10]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203669.8979473], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1610069, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 2]], ["tile_x", "sp", [-1, 8, 4, 150]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203669.8980353], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 528580, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 4]], ["tile_x", "sp", [-1, 3, 4, 320]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203669.918588], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2879365, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 6, 64, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203670.0284123], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2400296, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 32]], ["tile_x", "sp", [-1, 6, 160, 4]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203670.0284731], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2825034, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 2]], ["tile_x", "sp", [-1, 10, 128, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203670.028524], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2425974, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 4]], ["tile_x", "sp", [-1, 5, 24, 5]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203670.0285735], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2985325, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 16, 60, 5]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203670.0286229], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2508816, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 8]], ["tile_x", "sp", [-1, 10, 32, 10]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203670.0286698], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 275090, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 16]], ["tile_x", "sp", [-1, 20, 2, 10]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203670.1557505], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 800734, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 2]], ["tile_x", "sp", [-1, 100, 3, 8]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203670.1558442], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2865926, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 1]], ["tile_x", "sp", [-1, 30, 16, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203670.1559322], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1173345, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 1, 2]], ["tile_x", "sp", [-1, 2, 960, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203670.22053], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 866883, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 1]], ["tile_x", "sp", [-1, 1, 800, 12]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203670.2206519], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 111973, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 4, 120, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203670.2207553], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3227829, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 2]], ["tile_x", "sp", [-1, 30, 2, 64]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203670.2384279], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2700554, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 2, 2]], ["tile_x", "sp", [-1, 2, 1, 100]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203671.958906], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2141255, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 2, 1]], ["tile_x", "sp", [-1, 5, 1, 96]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203671.958972], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1526245, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 60, 2, 40]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203672.02778], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2482911, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 5, 60, 8]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203672.5219543], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1274629, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 32, 15, 4]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203672.7219617], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2902326, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 2]], ["tile_x", "sp", [-1, 5, 8, 3]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203672.7504857], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 616684, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 2]], ["tile_x", "sp", [-1, 40, 480, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 2.689213991165161, 1690203672.750504], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1801771, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 4]], ["tile_x", "sp", [-1, 32, 50, 3]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203672.750558], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3010401, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 1]], ["tile_x", "sp", [-1, 2, 320, 6]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203672.7506077], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2253326, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 32, 1]], ["tile_x", "sp", [-1, 64, 25, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203672.750657], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1697932, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 2]], ["tile_x", "sp", [-1, 800, 24, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 3.394179582595825, 1690203672.7506669], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1204065, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 1]], ["tile_x", "sp", [-1, 6, 20, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203672.750716], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 413044, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 1]], ["tile_x", "sp", [-1, 3, 100, 32]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203672.7507675], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1525625, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 4, 1]], ["tile_x", "sp", [-1, 15, 2, 40]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203672.750816], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3172, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 8]], ["tile_x", "sp", [-1, 480, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203672.7508628], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1178563, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 64, 1, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203672.7509093], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1887438, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 2]], ["tile_x", "sp", [-1, 25, 2, 6]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203672.7509575], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1009487, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 4]], ["tile_x", "sp", [-1, 300, 1, 64]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 3.339664936065674, 1690203672.7509663], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1140277, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 4]], ["tile_x", "sp", [-1, 8, 20, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203672.7510126], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3061629, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 32]], ["tile_x", "sp", [-1, 8, 24, 10]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203672.7510586], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 88421, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 4]], ["tile_x", "sp", [-1, 15, 10, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203672.7511044], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2495128, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 16]], ["tile_x", "sp", [-1, 128, 3, 10]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203672.7511513], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 891982, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 8]], ["tile_x", "sp", [-1, 8, 15, 16]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203672.7511978], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3251023, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 4]], ["tile_x", "sp", [-1, 4, 2, 96]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203672.751242], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1493243, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 4]], ["tile_x", "sp", [-1, 8, 8, 25]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203672.7512877], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1392227, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 2, 1]], ["tile_x", "sp", [-1, 30, 8, 10]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203672.7513359], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2206928, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 32]], ["tile_x", "sp", [-1, 12, 1, 800]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203672.751381], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 457490, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 32, 1]], ["tile_x", "sp", [-1, 2, 5, 64]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203672.7514284], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 100913, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 4, 32, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203672.7514732], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 544324, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 1]], ["tile_x", "sp", [-1, 1, 3, 800]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203672.75152], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 312852, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 2]], ["tile_x", "sp", [-1, 2, 1, 15]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203672.7515655], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 202309, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 2]], ["tile_x", "sp", [-1, 6, 10, 5]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203672.7516096], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 262976, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 4]], ["tile_x", "sp", [-1, 4, 40, 8]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203672.751658], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 613397, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 8, 300, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203672.7517054], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 873357, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 1]], ["tile_x", "sp", [-1, 32, 10, 15]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203672.7517545], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 174367, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 8]], ["tile_x", "sp", [-1, 10, 40, 4]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203672.7518008], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3080756, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 4]], ["tile_x", "sp", [-1, 5, 32, 12]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203672.7518466], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 124960, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 4]], ["tile_x", "sp", [-1, 4, 2, 3]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203672.7518923], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1093689, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 1]], ["tile_x", "sp", [-1, 4, 2, 600]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203672.7519374], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 737826, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 4]], ["tile_x", "sp", [-1, 3, 200, 4]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203684.9529104], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 921773, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 2]], ["tile_x", "sp", [-1, 2, 240, 20]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203684.9740846], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 878882, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 16]], ["tile_x", "sp", [-1, 5, 1, 16]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203684.9741447], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2228359, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 6400, 3, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 2.534329414367676, 1690203684.9741776], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1599890, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 32, 1]], ["tile_x", "sp", [-1, 4, 2, 120]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203684.9866493], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1860049, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 2]], ["tile_x", "sp", [-1, 320, 4, 5]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203685.0042725], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 166834, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 1]], ["tile_x", "sp", [-1, 10, 16, 4]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203685.0213444], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2166529, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 10, 1, 160]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203685.0213966], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1780884, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 10, 320, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203685.0272095], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2883704, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 8]], ["tile_x", "sp", [-1, 48, 100, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203685.0637317], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2990516, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 2]], ["tile_x", "sp", [-1, 2, 240, 5]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203686.5014384], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1847948, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 2]], ["tile_x", "sp", [-1, 16, 300, 4]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 2.0330147743225098, 1690203686.5014644], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1832588, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 2]], ["tile_x", "sp", [-1, 120, 20, 4]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203686.50152], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2931162, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 8]], ["tile_x", "sp", [-1, 32, 6, 4]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203686.5015721], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2228784, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 2, 1]], ["tile_x", "sp", [-1, 5, 4, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203686.6362438], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 607206, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 4]], ["tile_x", "sp", [-1, 3, 128, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203686.7662709], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 161451, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 1]], ["tile_x", "sp", [-1, 120, 8, 4]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203686.7663236], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 485206, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 1]], ["tile_x", "sp", [-1, 4, 3, 100]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203686.7663743], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 556455, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 100, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203686.8429308], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2189373, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 32]], ["tile_x", "sp", [-1, 2, 32, 300]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 1.8526241779327393, 1690203686.8429482], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1941040, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 4]], ["tile_x", "sp", [-1, 1, 4, 10]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203686.843003], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 968366, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 1]], ["tile_x", "sp", [-1, 1, 600, 32]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 1.671025276184082, 1690203686.843013], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 1500172, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 1]], ["tile_x", "sp", [-1, 4, 2, 30]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203687.0295858], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2081989, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 1, 4, 40]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203687.0296378], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 2344334, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 4]], ["tile_x", "sp", [-1, 3200, 2, 3]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 1.7540006637573242, 1690203687.0296502], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 3264310, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 8]], ["tile_x", "sp", [-1, 20, 4, 120]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203687.0296988], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 957667, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 8]], ["tile_x", "sp", [-1, 50, 3, 32]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203687.0297527], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 120526, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 8]], ["tile_x", "sp", [-1, 6, 800, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 1.6571862697601318, 1690203687.029762], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 1, 640, 480], "float32"], ["TENSOR", [64, 1, 5, 5], "float32"], [1, 1], [2, 2, 2, 2], [1, 1], "float32"], {}], "config": {"index": 680675, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 16, 1]], ["tile_x", "sp", [-1, 320, 2, 3]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203687.0298104], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5682126643, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 16]], ["tile_x", "sp", [-1, 12, 5, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.5478484630584717, 1690203691.844608], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5819800008, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 2]], ["tile_y", "sp", [-1, 160, 2, 2]], ["tile_x", "sp", [-1, 1, 6, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203701.573745], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3140218671, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 5, 1, 4]], ["tile_x", "sp", [-1, 3, 1, 32]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 4, 12.171279430389404, 1690203711.746666], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2292588482, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 20]], ["tile_x", "sp", [-1, 15, 2, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.5148813476], 0, 9.23997974395752, 1690203718.508425], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 608485386, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 2, 1, 4]], ["tile_x", "sp", [-1, 1, 6, 16]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.1055483886], 0, 3.383676767349243, 1690203720.768911], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3120052046, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 4]], ["tile_y", "sp", [-1, 32, 1, 2]], ["tile_x", "sp", [-1, 4, 1, 3]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.2752589843], 0, 10.77735424041748, 1690203724.903188], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3486258940, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 4]], ["tile_y", "sp", [-1, 2, 32, 10]], ["tile_x", "sp", [-1, 15, 8, 4]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.5028536319732666, 1690203701.573784], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1421444221, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 10, 4, 1]], ["tile_x", "sp", [-1, 1, 40, 2]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.236037015914917, 1690203701.573794], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1101720112, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 4]], ["tile_y", "sp", [-1, 5, 1, 4]], ["tile_x", "sp", [-1, 20, 6, 4]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.4457545280456543, 1690203701.5738018], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1226702372, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 16, 20, 1]], ["tile_x", "sp", [-1, 1, 2, 48]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.16550469398498535, 1690203701.5738103], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2058928748, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 10]], ["tile_x", "sp", [-1, 1, 4, 120]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.06571334075], 0, 5.369298934936523, 1690203727.8644896], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2077059587, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 10, 32, 2]], ["tile_x", "sp", [-1, 5, 6, 4]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.3349912166595459, 1690203701.5738199], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1734189984, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 8]], ["tile_y", "sp", [-1, 8, 5, 8]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.32668399810791016, 1690203701.5738266], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 860639294, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 1, 320, 1]], ["tile_x", "sp", [-1, 3, 1, 16]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.16305065155029297, 1690203701.5738332], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2324145380, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 8, 10, 4]], ["tile_x", "sp", [-1, 3, 20, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.34162449836730957, 1690203701.5738404], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3267011694, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 16, 4, 1]], ["tile_x", "sp", [-1, 1, 1, 4]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.21766948699951172, 1690203701.5738478], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2226218131, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 8]], ["tile_y", "sp", [-1, 4, 8, 10]], ["tile_x", "sp", [-1, 40, 2, 6]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.5552773475646973, 1690203701.5738554], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5035074862, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 2]], ["tile_y", "sp", [-1, 4, 4, 20]], ["tile_x", "sp", [-1, 40, 1, 3]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2095050811767578, 1690203701.5738623], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 653688607, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 1, 32, 4]], ["tile_x", "sp", [-1, 1, 6, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.27445435523986816, 1690203701.5738692], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4354883548, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 80, 1, 1]], ["tile_x", "sp", [-1, 96, 1, 5]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.22548460960388184, 1690203701.5738754], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3332367373, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 10, 2, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.024317536833333334], 0, 2.934678554534912, 1690203730.2462103], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5668815860, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 4, 2, 8]], ["tile_x", "sp", [-1, 1, 4, 30]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.24151325225830078, 1690203701.5738847], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3960800871, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 1]], ["tile_y", "sp", [-1, 8, 16, 1]], ["tile_x", "sp", [-1, 2, 8, 6]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2537109851837158, 1690203701.5738916], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5431184423, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 2, 1, 320]], ["tile_x", "sp", [-1, 12, 20, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.20031094551086426, 1690203701.573898], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1531014549, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 4]], ["tile_y", "sp", [-1, 4, 16, 5]], ["tile_x", "sp", [-1, 5, 2, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.12649237060000001], 0, 8.944005489349365, 1690203732.7199464], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3612683462, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 2]], ["tile_y", "sp", [-1, 4, 4, 2]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.023169489068181823], 0, 3.573439359664917, 1690203735.1698132], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3650419839, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 8, 80, 1]], ["tile_x", "sp", [-1, 60, 2, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.1642155647277832, 1690203701.5739071], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3380694379, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 1, 16, 5]], ["tile_x", "sp", [-1, 1, 8, 5]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.15949583053588867, 1690203701.5739133], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1835360220, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 2]], ["tile_y", "sp", [-1, 2, 4, 20]], ["tile_x", "sp", [-1, 32, 1, 15]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.18504786491394043, 1690203701.5739198], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4571838954, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 1, 32, 20]], ["tile_x", "sp", [-1, 4, 2, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2579922676086426, 1690203701.5739262], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3548549615, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 8, 5, 8]], ["tile_x", "sp", [-1, 24, 1, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.19860172271728516, 1690203701.5739338], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 51889096, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 1, 16, 40]], ["tile_x", "sp", [-1, 4, 1, 4]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.2073822021484375, 1690203701.5739405], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 581949930, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 2, 4, 2]], ["tile_x", "sp", [-1, 4, 8, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.005387913526881721], 0, 3.101612091064453, 1690203737.3325639], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4377361032, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 8]], ["tile_y", "sp", [-1, 2, 16, 4]], ["tile_x", "sp", [-1, 5, 24, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.230987548828125, 1690203701.573949], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1068070607, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 2, 4, 20]], ["tile_x", "sp", [-1, 1, 4, 5]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.020243784160000004], 0, 3.805607318878174, 1690203739.670427], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4752140437, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 2]], ["tile_y", "sp", [-1, 80, 1, 8]], ["tile_x", "sp", [-1, 16, 1, 5]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.3617885112762451, 1690203701.5739574], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3781735441, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 1]], ["tile_x", "sp", [-1, 10, 3, 8]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.25661134719848633, 1690203701.5739655], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5313802471, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 16, 4, 10]], ["tile_x", "sp", [-1, 12, 5, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.29607295989990234, 1690203701.5739725], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4028859616, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 2]], ["tile_y", "sp", [-1, 8, 8, 1]], ["tile_x", "sp", [-1, 6, 20, 4]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.4219050407409668, 1690203701.5739796], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 370562853, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 128, 1, 5]], ["tile_x", "sp", [-1, 10, 3, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.17817115783691406, 1690203701.573987], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5479111820, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 2, 8, 8]], ["tile_x", "sp", [-1, 20, 1, 8]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.18052291870117188, 1690203701.5739932], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3651395574, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 16]], ["tile_y", "sp", [-1, 4, 1, 4]], ["tile_x", "sp", [-1, 12, 4, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.2531572753], 0, 6.59616494178772, 1690203743.5959582], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5196709697, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 4]], ["tile_y", "sp", [-1, 4, 4, 8]], ["tile_x", "sp", [-1, 3, 10, 16]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.1948227882385254, 1690203701.5740008], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4457145625, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 2]], ["tile_y", "sp", [-1, 5, 4, 2]], ["tile_x", "sp", [-1, 1, 2, 3]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.056249572722222224], 0, 7.1803388595581055, 1690203746.3446462], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2925882464, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 1, 160, 4]], ["tile_x", "sp", [-1, 1, 2, 120]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.23754286766052246, 1690203701.5740097], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2810719586, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 2]], ["tile_y", "sp", [-1, 8, 5, 2]], ["tile_x", "sp", [-1, 16, 1, 15]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.2260112762451172, 1690203701.574016], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5066824687, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 20, 4, 2]], ["tile_x", "sp", [-1, 1, 3, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0056717567175141245], 0, 5.127138376235962, 1690203748.4930458], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4811132253, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 32]], ["tile_y", "sp", [-1, 1, 2, 10]], ["tile_x", "sp", [-1, 8, 30, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.073758529625], 0, 10.238626480102539, 1690203751.609609], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1611836652, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 2]], ["tile_y", "sp", [-1, 2, 8, 1]], ["tile_x", "sp", [-1, 4, 2, 6]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00253150646969697], 0, 2.892939567565918, 1690203753.773357], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4125374563, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 16]], ["tile_y", "sp", [-1, 2, 2, 20]], ["tile_x", "sp", [-1, 1, 60, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.38190746307373047, 1690203701.574028], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4027417547, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 64]], ["tile_y", "sp", [-1, 2, 16, 2]], ["tile_x", "sp", [-1, 30, 4, 4]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2044970989227295, 1690203701.5740347], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4015620255, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 1, 64, 10]], ["tile_x", "sp", [-1, 30, 16, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2145063877105713, 1690203701.5740418], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2991355866, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 10, 32, 2]], ["tile_x", "sp", [-1, 16, 1, 15]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.1582014560699463, 1690203701.574048], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2150166498, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 32, 1, 5]], ["tile_x", "sp", [-1, 1, 20, 4]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.21510934829711914, 1690203701.5740542], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5999974336, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 16]], ["tile_y", "sp", [-1, 1, 4, 32]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.33515310287475586, 1690203701.5740612], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 892293903, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 2]], ["tile_y", "sp", [-1, 4, 5, 2]], ["tile_x", "sp", [-1, 2, 10, 8]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.15641379356384277, 1690203701.574068], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5538674541, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 4]], ["tile_y", "sp", [-1, 8, 2, 40]], ["tile_x", "sp", [-1, 12, 10, 2]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.29904651641845703, 1690203701.574075], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5231963545, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 3, 1, 16]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0058267683837209296], 0, 3.6982526779174805, 1690203755.973587], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4702807164, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 2]], ["tile_y", "sp", [-1, 40, 4, 1]], ["tile_x", "sp", [-1, 1, 32, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.16161632537841797, 1690203701.5740833], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3451872838, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 4, 4, 40]], ["tile_x", "sp", [-1, 3, 2, 5]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.16295623779296875, 1690203701.574093], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 470548046, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 2]], ["tile_y", "sp", [-1, 8, 10, 2]], ["tile_x", "sp", [-1, 240, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.13147735595703125, 1690203701.5740988], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1623547813, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 1, 4, 5]], ["tile_x", "sp", [-1, 3, 2, 40]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.16868257522583008, 1690203701.5741055], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3380083071, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 1, 2, 4]], ["tile_x", "sp", [-1, 16, 3, 5]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0790587539375], 0, 5.504194974899292, 1690203759.2722178], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2457462257, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 80]], ["tile_x", "sp", [-1, 120, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.21427512168884277, 1690203701.5741143], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 198495026, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 320]], ["tile_x", "sp", [-1, 5, 6, 4]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.14007949829101562, 1690203701.5741208], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1216504390, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 20, 1, 2]], ["tile_x", "sp", [-1, 15, 2, 8]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.17649626731872559, 1690203701.574128], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5312028715, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 8, 8, 10]], ["tile_x", "sp", [-1, 16, 2, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.17869114875793457, 1690203701.5741339], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1797197603, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 10, 16, 2]], ["tile_x", "sp", [-1, 2, 6, 10]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.3746800422668457, 1690203701.5741463], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5186911936, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 4]], ["tile_y", "sp", [-1, 4, 4, 8]], ["tile_x", "sp", [-1, 4, 6, 5]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.6109364032745361, 1690203701.5741544], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5746425364, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 8, 5, 4]], ["tile_x", "sp", [-1, 1, 4, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.26311564445495605, 1690203701.574161], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4440902172, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 160, 1, 4]], ["tile_x", "sp", [-1, 1, 3, 32]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.10236263275146484, 1690203701.574168], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 554725806, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 32, 4, 1]], ["tile_x", "sp", [-1, 4, 60, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.34908413887023926, 1690203701.5741773], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3296101451, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 64]], ["tile_y", "sp", [-1, 128, 1, 5]], ["tile_x", "sp", [-1, 4, 2, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 4, 8.916951656341553, 1690203760.4459267], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2570054578, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 8]], ["tile_y", "sp", [-1, 5, 2, 4]], ["tile_x", "sp", [-1, 2, 15, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.07857683562500001], 0, 7.144329309463501, 1690203763.6940026], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2695790593, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 1, 4, 32]], ["tile_x", "sp", [-1, 10, 2, 6]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.13204073905944824, 1690203701.5741882], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2808900201, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 2, 40, 1]], ["tile_x", "sp", [-1, 2, 8, 10]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.16072797775268555, 1690203701.574195], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5246105579, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 8, 8, 10]], ["tile_x", "sp", [-1, 3, 1, 2]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.15728354454040527, 1690203701.5742016], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4132942516, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 4]], ["tile_y", "sp", [-1, 2, 1, 5]], ["tile_x", "sp", [-1, 32, 5, 3]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.15220403671264648, 1690203701.5742087], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4573389489, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 32]], ["tile_y", "sp", [-1, 2, 8, 2]], ["tile_x", "sp", [-1, 6, 16, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.22391676902770996, 1690203701.5742157], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1315902637, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 32, 5, 4]], ["tile_x", "sp", [-1, 5, 32, 3]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.16378021240234375, 1690203701.5742228], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 951356269, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 8]], ["tile_y", "sp", [-1, 4, 16, 1]], ["tile_x", "sp", [-1, 4, 20, 2]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.2377183437347412, 1690203701.5742295], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1991465910, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 2]], ["tile_y", "sp", [-1, 1, 32, 4]], ["tile_x", "sp", [-1, 8, 10, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.21460247039794922, 1690203701.5742354], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5577854886, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 20, 4, 8]], ["tile_x", "sp", [-1, 2, 5, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.16616201400756836, 1690203701.574242], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 32976562, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 5, 1, 32]], ["tile_x", "sp", [-1, 4, 2, 30]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.18088912963867188, 1690203701.5742478], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1078579568, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 32]], ["tile_y", "sp", [-1, 10, 8, 4]], ["tile_x", "sp", [-1, 6, 1, 20]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.25606489181518555, 1690203701.5742545], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4898200314, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 2]], ["tile_y", "sp", [-1, 2, 16, 1]], ["tile_x", "sp", [-1, 12, 8, 5]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.16034173965454102, 1690203701.5742602], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2512537388, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 2, 2, 40]], ["tile_x", "sp", [-1, 2, 2, 5]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.12470602989196777, 1690203701.5742662], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4712337022, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 16, 2, 4]], ["tile_x", "sp", [-1, 8, 1, 4]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.37828946113586426, 1690203701.5742729], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1911102681, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 2]], ["tile_y", "sp", [-1, 4, 40, 2]], ["tile_x", "sp", [-1, 4, 5, 24]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.13967156410217285, 1690203701.5742786], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2730158660, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 16, 2, 2]], ["tile_x", "sp", [-1, 24, 4, 5]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.12822175025939941, 1690203701.5742855], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1100459321, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 1]], ["tile_y", "sp", [-1, 64, 10, 1]], ["tile_x", "sp", [-1, 30, 2, 4]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.19108104705810547, 1690203701.5742924], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 216540113, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 2]], ["tile_y", "sp", [-1, 8, 1, 5]], ["tile_x", "sp", [-1, 3, 1, 160]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.1352846622467041, 1690203701.5742984], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4270515613, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 2, 4, 5]], ["tile_x", "sp", [-1, 2, 240, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.3255295753479004, 1690203701.5743043], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2034918059, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 64]], ["tile_y", "sp", [-1, 5, 64, 1]], ["tile_x", "sp", [-1, 3, 16, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.163163423538208, 1690203701.5743098], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1490056180, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 16]], ["tile_x", "sp", [-1, 20, 2, 2]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.12677693367004395, 1690203701.574316], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3932971659, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 10, 1, 64]], ["tile_x", "sp", [-1, 12, 2, 20]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.47336840629577637, 1690203701.5743215], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 80971659, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 10, 2, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0023719018127962084], 0, 3.1478171348571777, 1690203845.5575678], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 284872081, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 2, 1, 24]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.010772380860215054], 0, 2.728550434112549, 1690203847.800649], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 536860990, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 4, 1, 1]], ["tile_x", "sp", [-1, 2, 2, 20]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.004864074703883494], 0, 3.457854747772217, 1690203849.9886515], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 522596619, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 4, 3, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0022659104276018097], 0, 2.5404512882232666, 1690203852.1713953], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 506218969, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 20, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.002712906170731707], 0, 2.4656739234924316, 1690203854.2896435], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 587632779, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 4, 4, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0023143280802292265], 0, 4.112615585327148, 1690203858.022464], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 561876384, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 2]], ["tile_y", "sp", [-1, 1, 2, 4]], ["tile_x", "sp", [-1, 12, 2, 5]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.1897014282], 0, 5.228897333145142, 1690203861.2532768], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 551506059, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 4, 4, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0024011056282973622], 0, 2.6363699436187744, 1690203863.361769], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1097953943, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 10, 4, 3]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0025956118860103626], 0, 2.8302183151245117, 1690203865.4669175], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1799441307, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 4, 15]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0020294498319838056], 0, 2.6200783252716064, 1690203867.6133678], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2307968401, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 2, 1, 24]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.007659543564885497], 0, 3.0727977752685547, 1690203869.7720218], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1032071065, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 6, 4, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.003754915958801498], 0, 4.498722553253174, 1690203871.889257], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1278523031, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 5, 4, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0023658878676122933], 0, 5.175894737243652, 1690203874.0474603], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1526080859, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 12, 2, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.003064988626911315], 0, 3.004687786102295, 1690203876.1775851], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1537845145, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 6, 4, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0018615275361781073], 0, 2.5705835819244385, 1690203878.292592], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1273321753, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 24, 2, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0021149995243128963], 0, 3.4349498748779297, 1690203880.4694142], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2584723872, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 1, 2, 5]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0030199948945783127], 0, 2.730855703353882, 1690203882.6316094], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1517606038, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 4, 2, 1]], ["tile_x", "sp", [-1, 10, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0027167163197831974], 0, 2.847161293029785, 1690203884.7773], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2073254419, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 4, 4, 3]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.003255771386363636], 0, 2.7778866291046143, 1690203886.9515796], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2290071191, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 5, 4, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0021536767573333334], 0, 4.56650447845459, 1690203890.682285], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2545692939, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 4, 3, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0020453614764826176], 0, 2.5602540969848633, 1690203892.8148823], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2586988704, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 2]], ["tile_y", "sp", [-1, 1, 2, 4]], ["tile_x", "sp", [-1, 10, 1, 6]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.01786871015789474], 0, 4.209167957305908, 1690203895.1986775], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3586150539, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 4, 4, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0024010122213967314], 0, 4.217372417449951, 1690203898.9695697], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3296160191, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 4, 1, 1]], ["tile_x", "sp", [-1, 6, 2, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.002579529907216495], 0, 2.6765899658203125, 1690203901.109135], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2303765201, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 1]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 10, 1, 12]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.26000117180000004], 0, 5.043959379196167, 1690203905.0925326], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1518709296, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 2]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 16, 2, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.002531760994936709], 0, 3.0829286575317383, 1690203907.1963124], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3632445963, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 1]], ["tile_y", "sp", [-1, 1, 2, 4]], ["tile_x", "sp", [-1, 2, 2, 5]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0020918703065976713], 0, 4.056085109710693, 1690203910.908558], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1542019609, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 2, 1, 5]], ["tile_x", "sp", [-1, 3, 4, 8]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.008904323336283188], 0, 3.088834047317505, 1690203913.178229], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3625793163, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 1]], ["tile_y", "sp", [-1, 1, 2, 4]], ["tile_x", "sp", [-1, 2, 1, 3]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.002713844195121951], 0, 2.6595005989074707, 1690203915.3243394], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 17999638, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 10, 20, 8]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.38323163986206055, 1690203917.755601], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4686828, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 2]], ["tile_x", "sp", [-1, 50, 6, 8]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203927.411235], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2950642, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 32, 75, 4]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.8453783988952637, 1690203927.4112747], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4235904, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 2]], ["tile_x", "sp", [-1, 192, 5, 20]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 3.263719081878662, 1690203927.4112844], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 20962137, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 8, 1]], ["tile_x", "sp", [-1, 20, 4, 60]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 1.0199594497680664, 1690203927.4112942], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3104422, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 24, 5, 16]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 3.4849987030029297, 1690203927.4113023], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 22742359, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 2]], ["tile_x", "sp", [-1, 25, 4, 1]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.023339984255813958], 0, 8.98780083656311, 1690203931.9554875], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3986788, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 8]], ["tile_x", "sp", [-1, 192, 50, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 1.3097054958343506, 1690203927.4113116], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1985733, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 4]], ["tile_x", "sp", [-1, 4, 80, 15]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 1.2243642807006836, 1690203927.4113195], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 15807507, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 4]], ["tile_x", "sp", [-1, 4, 10, 10]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0334386861], 0, 7.353148937225342, 1690203934.465962], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5217979, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 8]], ["tile_x", "sp", [-1, 4, 8, 6]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203927.5420508], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14201718, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 64, 1, 1]], ["tile_x", "sp", [-1, 3, 40, 16]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 1.2523670196533203, 1690203927.5420647], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14561838, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 1]], ["tile_x", "sp", [-1, 160, 1, 4]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 1.421684980392456, 1690203927.542073], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7491145, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 1]], ["tile_x", "sp", [-1, 240, 8, 10]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.7761938571929932, 1690203927.5420833], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 15429810, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 1]], ["tile_x", "sp", [-1, 6, 25, 64]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 1.3823537826538086, 1690203927.5420916], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5237335, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 1]], ["tile_x", "sp", [-1, 25, 4, 8]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203927.8441682], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 21238340, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 2]], ["tile_x", "sp", [-1, 16, 25, 4]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.9337828159332275, 1690203927.844189], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 18300554, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 4]], ["tile_x", "sp", [-1, 15, 2, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0013982791145251397], 0, 7.0292627811431885, 1690203936.6905942], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3155883, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 1]], ["tile_x", "sp", [-1, 128, 6, 25]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 1.3557848930358887, 1690203927.8441994], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 16616093, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 4]], ["tile_x", "sp", [-1, 2, 20, 480]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 1.3625109195709229, 1690203927.8442066], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 10986603, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 16]], ["tile_x", "sp", [-1, 1, 64, 60]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.8268752098083496, 1690203927.8442175], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 11344003, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 4]], ["tile_x", "sp", [-1, 50, 12, 8]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 2.678607225418091, 1690203927.844225], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3650649, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 1]], ["tile_x", "sp", [-1, 3, 1, 16]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.01566955184375], 0, 6.72495436668396, 1690203939.0455618], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 16615383, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 1]], ["tile_x", "sp", [-1, 4, 5, 480]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 1.2670929431915283, 1690203927.8442345], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 21038375, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 8]], ["tile_x", "sp", [-1, 2, 8, 300]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 1.316737174987793, 1690203927.8442419], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 11653949, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 2]], ["tile_x", "sp", [-1, 12, 4, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203927.9385836], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 17739703, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 16]], ["tile_x", "sp", [-1, 1, 5, 3840]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 2.4731740951538086, 1690203927.9385958], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8704919, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 64]], ["tile_x", "sp", [-1, 1, 128, 25]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.01654045329508197], 0, 11.612834930419922, 1690203941.3742654], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5954268, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 2, 1]], ["tile_x", "sp", [-1, 2, 25, 32]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 1.179703712463379, 1690203927.9386058], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1455905, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 4, 1]], ["tile_x", "sp", [-1, 5, 1, 20]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203928.1304028], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 22757531, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 64]], ["tile_x", "sp", [-1, 4, 15, 1]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0021989331582417584], 0, 8.254377365112305, 1690203943.5137346], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7026416, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 8]], ["tile_x", "sp", [-1, 2, 10, 24]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 1.2761471271514893, 1690203928.1304176], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 17578445, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 4, 1]], ["tile_x", "sp", [-1, 64, 2, 30]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.830451488494873, 1690203928.1304255], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 13049720, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 8]], ["tile_x", "sp", [-1, 2, 960, 10]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 1.1098525524139404, 1690203928.130432], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3082346, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 4]], ["tile_x", "sp", [-1, 5, 64, 12]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 1.4168503284454346, 1690203928.1304393], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 17038310, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 1]], ["tile_x", "sp", [-1, 25, 6, 32]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.9790740013122559, 1690203928.1304502], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 19516508, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 2]], ["tile_x", "sp", [-1, 40, 120, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203928.2533345], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 10904383, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 2, 4, 24]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203928.2533894], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3719745, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 4]], ["tile_x", "sp", [-1, 160, 4, 30]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.8346195220947266, 1690203928.2534018], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 13692342, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 64, 1, 1]], ["tile_x", "sp", [-1, 16, 24, 25]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 1.2155425548553467, 1690203928.25341], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 13529330, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 2, 2]], ["tile_x", "sp", [-1, 4, 2, 6]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.1295054809], 0, 6.790611505508423, 1690203946.2189465], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14859752, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 8]], ["tile_x", "sp", [-1, 2, 48, 50]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.8414969444274902, 1690203928.25342], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 9898345, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 2]], ["tile_x", "sp", [-1, 1, 10, 80]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203928.4669747], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 11367602, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 4]], ["tile_x", "sp", [-1, 160, 4, 10]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.9199962615966797, 1690203928.4669876], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 13401923, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 4]], ["tile_x", "sp", [-1, 60, 20, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 1.0800583362579346, 1690203928.4669952], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 10137349, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 4]], ["tile_x", "sp", [-1, 320, 5, 4]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.9557485580444336, 1690203928.4670026], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2364784, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 1]], ["tile_x", "sp", [-1, 100, 1, 4]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.1055267822], 0, 5.894375562667847, 1690203948.5421097], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2121004, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 1]], ["tile_x", "sp", [-1, 6, 5, 64]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 2.3191657066345215, 1690203928.467011], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 22839829, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 4]], ["tile_x", "sp", [-1, 12, 80, 2]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 1.1199345588684082, 1690203928.467018], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 11188594, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 2]], ["tile_x", "sp", [-1, 320, 30, 2]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 1.2290501594543457, 1690203928.467026], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8519871, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 1]], ["tile_x", "sp", [-1, 20, 12, 5]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.05988442452941176], 0, 7.346264600753784, 1690203951.3608336], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4947777, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 1]], ["tile_x", "sp", [-1, 10, 10, 192]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 2.144606113433838, 1690203928.4670346], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8099972, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 1]], ["tile_x", "sp", [-1, 25, 16, 16]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.01991667982352941], 0, 6.233179569244385, 1690203953.7191648], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 21726514, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 32]], ["tile_x", "sp", [-1, 1, 50, 2]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008381514170124482], 0, 12.611525297164917, 1690203957.4721239], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2443254, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 2]], ["tile_x", "sp", [-1, 8, 4, 6]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.1013021667], 0, 6.295753479003906, 1690203959.6690495], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 432533, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 4, 1]], ["tile_x", "sp", [-1, 10, 4, 48]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0398980336923077], 0, 6.369119882583618, 1690203962.2324078], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1028956, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 2]], ["tile_x", "sp", [-1, 10, 12, 80]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 2.6297848224639893, 1690203928.4670477], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 13408239, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 16]], ["tile_x", "sp", [-1, 6, 40, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.018507440727272728], 0, 6.036693811416626, 1690203964.6188688], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 20780023, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 1]], ["tile_x", "sp", [-1, 2, 100, 8]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203928.7685964], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3397054, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 1]], ["tile_x", "sp", [-1, 240, 1, 2]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 1.1151840686798096, 1690203928.7686121], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 10558379, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 64]], ["tile_x", "sp", [-1, 384, 10, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.9383676052093506, 1690203928.7686205], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 16032831, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 1]], ["tile_x", "sp", [-1, 1, 30, 160]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.018121234339285718], 0, 6.071003675460815, 1690203966.9406679], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4964054, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 16]], ["tile_x", "sp", [-1, 1, 5, 320]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690203928.9033163], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 9116238, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 4]], ["tile_x", "sp", [-1, 20, 3, 8]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0873352355625], 0, 9.977842330932617, 1690203970.3853242], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 18017579, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 64]], ["tile_x", "sp", [-1, 5, 3, 10]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.09436077112499999], 0, 12.504730224609375, 1690203974.0955944], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 12794405, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 4, 50, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203929.14925], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 20787291, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 4]], ["tile_x", "sp", [-1, 5, 2, 10]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203929.149305], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 10425115, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 1, 96, 50]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.803804874420166, 1690203929.1493177], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4299538, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 32]], ["tile_x", "sp", [-1, 160, 3, 40]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.7609090805053711, 1690203929.1493256], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4423693, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 1, 5, 768]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.05316198405263158], 0, 5.900546073913574, 1690203976.8390114], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 18168585, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 4]], ["tile_x", "sp", [-1, 3, 40, 40]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 2.430830955505371, 1690203929.1493347], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4160770, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 32]], ["tile_x", "sp", [-1, 2, 5, 10]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.03015348544117647], 0, 5.317461013793945, 1690203979.2781312], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 15005795, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 32, 30, 1]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.909482479095459, 1690203929.149346], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14304375, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 1]], ["tile_x", "sp", [-1, 2, 24, 50]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.6655604839324951, 1690203929.149355], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 18454550, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 1]], ["tile_x", "sp", [-1, 80, 6, 4]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.7095482349395752, 1690203929.1493618], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4708863, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 16]], ["tile_x", "sp", [-1, 320, 1, 10]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 4, 5.246528625488281, 1690203980.4643338], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 19808125, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 30, 4, 32]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203929.1494164], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1928621, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 8]], ["tile_x", "sp", [-1, 8, 60, 8]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.6912434101104736, 1690203929.1494253], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 21293647, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 8]], ["tile_x", "sp", [-1, 100, 4, 6]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.6526296138763428, 1690203929.1494331], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8007069, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 8, 1]], ["tile_x", "sp", [-1, 5, 3, 8]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.002557559117647059], 0, 5.430736780166626, 1690203982.596654], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4257903, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 64, 1]], ["tile_x", "sp", [-1, 16, 50, 24]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.5642392635345459, 1690203929.149441], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 18233174, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 4]], ["tile_x", "sp", [-1, 40, 4, 120]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.6953771114349365, 1690203929.1494477], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 19685523, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 8, 6, 10]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690203929.6109438], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 11032498, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 1]], ["tile_x", "sp", [-1, 2, 25, 128]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.7504231929779053, 1690203929.6109562], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 9732637, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 4]], ["tile_x", "sp", [-1, 40, 20, 12]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.7402112483978271, 1690203929.6109626], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 15790862, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 2, 2]], ["tile_x", "sp", [-1, 12, 100, 8]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.021029738104166668], 0, 8.09395170211792, 1690203984.9963765], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2574437, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 1, 1]], ["tile_x", "sp", [-1, 12, 8, 20]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.6330013275146484, 1690203929.6109717], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 17149231, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 12, 8, 200]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.45790600776672363, 1690203929.6109784], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 227648, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 64, 5, 6]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.05446542836842106], 0, 12.53564977645874, 1690203987.754775], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1729520, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 2]], ["tile_x", "sp", [-1, 2, 1920, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 2.1506760120391846, 1690203929.6109886], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 10861970, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 1]], ["tile_x", "sp", [-1, 200, 2, 16]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.5132863521575928, 1690203929.610995], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 17585980, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 16]], ["tile_x", "sp", [-1, 10, 1, 32]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.5707180175000001], 0, 11.164587020874023, 1690203995.1491718], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 18667025, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 2]], ["tile_x", "sp", [-1, 2, 5, 24]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.010278013265306123], 0, 6.178500413894653, 1690203997.430014], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 18873366, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 16]], ["tile_x", "sp", [-1, 40, 10, 1]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.5040733814239502, 1690203929.611006], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7393061, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 4]], ["tile_x", "sp", [-1, 5, 480, 4]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.4643216133117676, 1690203929.6110125], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4672336, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 1]], ["tile_x", "sp", [-1, 1, 128, 6]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0011786449198250728], 0, 6.728673696517944, 1690204001.1911578], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14466056, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 32]], ["tile_x", "sp", [-1, 1, 120, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690204611.2622895], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 18346856, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 32]], ["tile_x", "sp", [-1, 1, 120, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008353190475792988], 0, 5.249743938446045, 1690204614.132676], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6704456, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 32]], ["tile_x", "sp", [-1, 1, 120, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0008392824924753502], 0, 6.856178283691406, 1690204617.8906896], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2823656, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 32]], ["tile_x", "sp", [-1, 1, 120, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0008391241873378308], 0, 12.112749814987183, 1690204621.630048], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 18334931, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 64]], ["tile_x", "sp", [-1, 1, 40, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0010734933127079175], 0, 7.2527031898498535, 1690204625.4016144], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14454131, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 64]], ["tile_x", "sp", [-1, 1, 40, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0011343064070294783], 0, 5.452108383178711, 1690204627.5579453], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 17877965, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 16]], ["tile_x", "sp", [-1, 1, 40, 3]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690204611.3919177], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14586175, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 16]], ["tile_x", "sp", [-1, 1, 30, 4]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0007928357782139353], 0, 6.674868822097778, 1690204631.3347082], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 18466975, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 16]], ["tile_x", "sp", [-1, 1, 30, 4]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0007954596325627152], 0, 9.01478099822998, 1690204635.1079261], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14641281, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 32]], ["tile_x", "sp", [-1, 1, 5, 6]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.051464038049999994], 0, 5.917036056518555, 1690204637.816271], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 18522081, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 32]], ["tile_x", "sp", [-1, 1, 5, 6]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.05139527585], 0, 5.8173956871032715, 1690204640.5525177], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 22227656, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 32]], ["tile_x", "sp", [-1, 1, 120, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690204612.1083143], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 17419075, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 16]], ["tile_x", "sp", [-1, 1, 25, 6]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690204612.1083748], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 13538275, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 16]], ["tile_x", "sp", [-1, 1, 25, 6]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0009999797051915946], 0, 6.75117564201355, 1690204644.3233638], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 21299875, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 16]], ["tile_x", "sp", [-1, 1, 25, 6]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0009556740472813238], 0, 8.135387420654297, 1690204648.0602064], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 18522082, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 32]], ["tile_x", "sp", [-1, 1, 5, 6]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.00269041158], 0, 6.798553943634033, 1690204651.8305888], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14641282, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 32]], ["tile_x", "sp", [-1, 1, 5, 6]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.002796480997206704], 0, 7.110642671585083, 1690204654.0087], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 21792199, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 16]], ["tile_x", "sp", [-1, 1, 25, 4]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008380203481865285], 0, 7.792502164840698, 1690204657.7448843], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14030599, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 16]], ["tile_x", "sp", [-1, 1, 25, 4]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008656314139410188], 0, 6.540404319763184, 1690204661.4729729], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 17973475, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 16]], ["tile_x", "sp", [-1, 1, 25, 6]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0009332949872979215], 0, 6.707431077957153, 1690204665.2522154], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 17911399, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 16]], ["tile_x", "sp", [-1, 1, 25, 4]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008567491935312831], 0, 6.643444061279297, 1690204668.980945], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 21793374, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 16]], ["tile_x", "sp", [-1, 1, 30, 4]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.000872456296976242], 0, 11.933238983154297, 1690204672.7213216], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14031774, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 16]], ["tile_x", "sp", [-1, 1, 30, 4]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0009179107944954129], 0, 5.032041311264038, 1690204674.8913894], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6692531, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 64]], ["tile_x", "sp", [-1, 1, 40, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690204612.1084564], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2811731, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 64]], ["tile_x", "sp", [-1, 1, 40, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0011339797487719297], 0, 6.988130807876587, 1690204678.670259], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14031773, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 16]], ["tile_x", "sp", [-1, 1, 30, 4]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008688662046834345], 0, 4.896111488342285, 1690204680.7931879], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 17912573, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 16]], ["tile_x", "sp", [-1, 1, 30, 4]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008087974121892542], 0, 5.097336053848267, 1690204682.9548988], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 18466965, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 8]], ["tile_x", "sp", [-1, 1, 30, 4]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008456371101766191], 0, 5.162396192550659, 1690204685.079542], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [64, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14586165, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 8]], ["tile_x", "sp", [-1, 1, 30, 4]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0009672339580587178], 0, 6.426357984542847, 1690204688.8234613], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1413621644, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 2, 5, 1]], ["tile_x", "sp", [-1, 2, 6, 8]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.02008350708], 0, 3.2763121128082275, 1690204703.3773077], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3486559397, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 32, 5, 2]], ["tile_x", "sp", [-1, 1, 1, 12]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03980231285095215, 1690204692.4307435], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3376976661, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 16, 4, 5]], ["tile_x", "sp", [-1, 3, 1, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690204701.1556382], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2525258482, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 2]], ["tile_y", "sp", [-1, 1, 2, 8]], ["tile_x", "sp", [-1, 1, 30, 16]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04029059410095215, 1690204701.1556616], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1579528097, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 4, 80, 1]], ["tile_x", "sp", [-1, 6, 8, 5]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04730343818664551, 1690204701.1556711], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2089697992, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 2]], ["tile_y", "sp", [-1, 2, 8, 10]], ["tile_x", "sp", [-1, 2, 1, 12]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.036353349685668945, 1690204701.1556787], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 609473931, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 5, 2, 32]], ["tile_x", "sp", [-1, 1, 10, 2]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04433441162109375, 1690204701.1556857], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1586170516, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 2]], ["tile_y", "sp", [-1, 4, 8, 2]], ["tile_x", "sp", [-1, 24, 1, 20]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03623676300048828, 1690204701.155693], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2508412684, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 2, 4, 40]], ["tile_x", "sp", [-1, 6, 16, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03101181983947754, 1690204701.1557002], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3129364157, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 1, 5, 16]], ["tile_x", "sp", [-1, 2, 1, 40]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03686404228210449, 1690204701.1557076], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2889205771, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 2, 10, 2]], ["tile_x", "sp", [-1, 1, 1, 60]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.010017771600000001], 0, 6.005634069442749, 1690204705.4011614], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2856047307, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 1, 1, 16]], ["tile_x", "sp", [-1, 12, 8, 5]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03154253959655762, 1690204701.155716], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2802955231, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 32]], ["tile_y", "sp", [-1, 1, 1, 8]], ["tile_x", "sp", [-1, 8, 2, 3]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.3123481689], 0, 9.53931999206543, 1690204709.8026373], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3376887819, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 16, 2, 2]], ["tile_x", "sp", [-1, 1, 480, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03836941719055176, 1690204701.1557255], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1858301242, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 4, 1, 2]], ["tile_x", "sp", [-1, 4, 20, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.027659291837837833], 0, 3.964223623275757, 1690204712.0778441], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2181388904, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 2, 16, 20]], ["tile_x", "sp", [-1, 24, 4, 5]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03164553642272949, 1690204701.155736], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2720850031, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 4]], ["tile_y", "sp", [-1, 32, 5, 1]], ["tile_x", "sp", [-1, 1, 8, 60]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0370638370513916, 1690204701.1557426], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 634009026, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 1, 4, 8]], ["tile_x", "sp", [-1, 8, 15, 2]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04867982864379883, 1690204701.1557512], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1099444562, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 2, 1, 80]], ["tile_x", "sp", [-1, 4, 20, 6]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.07449722290039062, 1690204701.1557577], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2269645384, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 8]], ["tile_y", "sp", [-1, 5, 128, 1]], ["tile_x", "sp", [-1, 4, 2, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04058980941772461, 1690204701.1557639], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 350559665, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 20, 4, 8]], ["tile_x", "sp", [-1, 24, 2, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03194880485534668, 1690204701.15577], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2798854653, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 80, 2, 1]], ["tile_x", "sp", [-1, 1, 480, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.06437134742736816, 1690204701.1557777], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1258427014, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 16]], ["tile_y", "sp", [-1, 4, 8, 4]], ["tile_x", "sp", [-1, 120, 2, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03538036346435547, 1690204701.1557837], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2651996776, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 1, 32, 5]], ["tile_x", "sp", [-1, 10, 8, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.08362817764282227, 1690204701.155791], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 382084138, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 20, 2, 4]], ["tile_x", "sp", [-1, 6, 2, 20]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.036763668060302734, 1690204701.1557975], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 911495699, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 1, 10, 16]], ["tile_x", "sp", [-1, 1, 10, 16]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04383707046508789, 1690204701.1558044], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2181119546, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 8, 2, 20]], ["tile_x", "sp", [-1, 8, 3, 5]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04188179969787598, 1690204701.1558113], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 205980427, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 1, 2, 80]], ["tile_x", "sp", [-1, 8, 2, 5]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03975272178649902, 1690204701.1558173], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2758662138, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 8]], ["tile_y", "sp", [-1, 2, 5, 16]], ["tile_x", "sp", [-1, 16, 1, 5]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04433608055114746, 1690204701.1558237], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 476929096, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 10, 32]], ["tile_x", "sp", [-1, 16, 1, 15]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.031610965728759766, 1690204701.1558306], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 662681367, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 8, 8, 2]], ["tile_x", "sp", [-1, 4, 15, 4]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.07745218276977539, 1690204701.1558375], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2143908680, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 2]], ["tile_y", "sp", [-1, 1, 20, 4]], ["tile_x", "sp", [-1, 32, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03378868103027344, 1690204701.1558437], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3136053540, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 2, 5, 8]], ["tile_x", "sp", [-1, 1, 480, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.054061174392700195, 1690204701.15585], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 413273304, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 2]], ["tile_y", "sp", [-1, 4, 16, 10]], ["tile_x", "sp", [-1, 6, 20, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.12020111083984375, 1690204701.1558564], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2257475613, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 2]], ["tile_y", "sp", [-1, 4, 5, 4]], ["tile_x", "sp", [-1, 12, 2, 10]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.10787391662597656, 1690204701.1558628], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3196524649, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 20, 8, 2]], ["tile_x", "sp", [-1, 16, 1, 10]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05153322219848633, 1690204701.1558697], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3420310330, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 1]], ["tile_y", "sp", [-1, 1, 20, 8]], ["tile_x", "sp", [-1, 20, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05609869956970215, 1690204701.155877], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3442858723, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 32, 1, 5]], ["tile_x", "sp", [-1, 2, 6, 40]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0486905574798584, 1690204701.1558843], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1524204621, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 5, 2, 1]], ["tile_x", "sp", [-1, 48, 5, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690204701.2845736], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2086975789, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 4, 5, 4]], ["tile_x", "sp", [-1, 1, 80, 6]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03647661209106445, 1690204701.2845855], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2559164212, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 16, 3, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.20679689939999996], 0, 3.9141476154327393, 1690204715.3279114], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2626335333, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 1, 8, 40]], ["tile_x", "sp", [-1, 80, 2, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03598928451538086, 1690204701.2845948], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3840487734, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 8, 4, 2]], ["tile_x", "sp", [-1, 15, 2, 4]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.07156872749328613, 1690204701.2846026], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1710586318, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 10, 2, 32]], ["tile_x", "sp", [-1, 160, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04691648483276367, 1690204701.2846107], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3361561866, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 2]], ["tile_y", "sp", [-1, 1, 8, 1]], ["tile_x", "sp", [-1, 2, 6, 5]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.054337263107299805, 1690204701.2846177], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3332544476, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 4]], ["tile_y", "sp", [-1, 2, 16, 5]], ["tile_x", "sp", [-1, 16, 1, 3]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.053926944732666016, 1690204701.2846243], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2027670896, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 8]], ["tile_y", "sp", [-1, 2, 40, 1]], ["tile_x", "sp", [-1, 10, 48, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0668191909790039, 1690204701.2846308], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3254073349, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 80, 2, 2]], ["tile_x", "sp", [-1, 6, 8, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.06389999389648438, 1690204701.2846377], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2270480923, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 40, 4, 2]], ["tile_x", "sp", [-1, 15, 4, 2]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.07868003845214844, 1690204701.284645], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2325946052, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 2, 4, 10]], ["tile_x", "sp", [-1, 2, 6, 5]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03425025939941406, 1690204701.2846515], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3058774558, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 2, 40, 8]], ["tile_x", "sp", [-1, 2, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.004523353918918919], 0, 3.514011859893799, 1690204717.3737597], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2530827146, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 8]], ["tile_y", "sp", [-1, 10, 4, 16]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.2793421875], 0, 6.035579681396484, 1690204721.378549], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 316573970, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 4, 5, 2]], ["tile_x", "sp", [-1, 32, 15, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04285597801208496, 1690204701.2846618], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1849704625, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 20, 1, 4]], ["tile_x", "sp", [-1, 8, 1, 15]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03182578086853027, 1690204701.2846682], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2620218884, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 4, 40, 2]], ["tile_x", "sp", [-1, 4, 10, 12]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05613851547241211, 1690204701.284675], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 402439800, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 10]], ["tile_x", "sp", [-1, 3, 20, 8]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03307747840881348, 1690204701.2846818], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 90830305, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 128, 5, 1]], ["tile_x", "sp", [-1, 40, 1, 12]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03277945518493652, 1690204701.2846897], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2219635079, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 4]], ["tile_y", "sp", [-1, 16, 1, 10]], ["tile_x", "sp", [-1, 8, 20, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04071760177612305, 1690204701.284696], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2181890208, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 4, 20, 4]], ["tile_x", "sp", [-1, 6, 16, 5]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04345822334289551, 1690204701.2847025], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2051771899, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 2, 5, 16]], ["tile_x", "sp", [-1, 10, 48, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.041864633560180664, 1690204701.28471], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2799318276, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 4, 5, 2]], ["tile_x", "sp", [-1, 60, 1, 2]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.09501957893371582, 1690204701.2847176], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2461922228, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 1, 32, 2]], ["tile_x", "sp", [-1, 12, 1, 2]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04795670509338379, 1690204701.2847245], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 745748012, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 4]], ["tile_y", "sp", [-1, 1, 64, 5]], ["tile_x", "sp", [-1, 4, 1, 60]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.05081462860107422, 1690204701.2847314], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3239750895, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 2]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 8, 15, 4]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.1004941463470459, 1690204701.2847383], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1274764113, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 4, 2, 2]], ["tile_x", "sp", [-1, 3, 5, 32]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04550886154174805, 1690204701.2847445], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3873708144, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 16, 20, 1]], ["tile_x", "sp", [-1, 1, 5, 16]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.21387863159179688, 1690204701.2847514], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1969043144, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 4, 5, 1]], ["tile_x", "sp", [-1, 2, 12, 10]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04716038703918457, 1690204701.2847576], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2416973001, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 10, 16, 1]], ["tile_x", "sp", [-1, 2, 60, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.17110204696655273, 1690204701.2847636], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 770875091, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 1, 80, 2]], ["tile_x", "sp", [-1, 8, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04914689064025879, 1690204701.28477], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2016343293, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 20, 1, 16]], ["tile_x", "sp", [-1, 8, 1, 10]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03476572036743164, 1690204701.2847757], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2152789734, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 40]], ["tile_x", "sp", [-1, 40, 2, 3]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0330510139465332, 1690204701.2847822], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 476642533, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 10, 1, 2]], ["tile_x", "sp", [-1, 1, 10, 12]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.035025835037231445, 1690204701.284789], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1920145451, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 2, 1, 160]], ["tile_x", "sp", [-1, 1, 2, 10]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04272770881652832, 1690204701.284796], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2278026367, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 4, 1, 1]], ["tile_x", "sp", [-1, 1, 12, 5]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0030315736696969694], 0, 2.1976022720336914, 1690204723.388643], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2659207993, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 32]], ["tile_x", "sp", [-1, 4, 10, 3]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03890109062194824, 1690204701.2848046], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3825354739, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 4, 5, 2]], ["tile_x", "sp", [-1, 3, 2, 16]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05810689926147461, 1690204701.2848108], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1359956533, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 1]], ["tile_y", "sp", [-1, 20, 1, 8]], ["tile_x", "sp", [-1, 4, 3, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690204701.3942354], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2128478883, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 5, 8, 4]], ["tile_x", "sp", [-1, 1, 2, 3]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.035141944885253906, 1690204701.3942475], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3961438938, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 80]], ["tile_x", "sp", [-1, 30, 4, 4]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.14481878280639648, 1690204701.3942552], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2014392097, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 1, 40, 1]], ["tile_x", "sp", [-1, 10, 8, 6]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.038236141204833984, 1690204701.3942618], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 161453726, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 1, 5, 4]], ["tile_x", "sp", [-1, 5, 12, 8]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.19271159172058105, 1690204701.3942678], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1602992797, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 8, 16, 1]], ["tile_x", "sp", [-1, 1, 3, 5]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.12659835815429688, 1690204701.3942745], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3147439618, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 8]], ["tile_y", "sp", [-1, 64, 1, 2]], ["tile_x", "sp", [-1, 3, 4, 8]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.045030832290649414, 1690204701.3942814], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2767300607, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 2, 32, 1]], ["tile_x", "sp", [-1, 4, 5, 24]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.040099382400512695, 1690204701.3942876], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1249549460, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 2, 160, 1]], ["tile_x", "sp", [-1, 2, 12, 20]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.043572187423706055, 1690204701.394294], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4034138355, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 2, 2, 5]], ["tile_x", "sp", [-1, 5, 8, 4]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.041533470153808594, 1690204701.3943005], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2233978858, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 1, 10, 2]], ["tile_x", "sp", [-1, 2, 12, 10]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.024277820404761907], 0, 2.6774659156799316, 1690204725.6427205], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1835868958, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 2, 40, 8]], ["tile_x", "sp", [-1, 30, 1, 2]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03210163116455078, 1690204701.3943088], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 854454321, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 8, 4, 10]], ["tile_x", "sp", [-1, 6, 4, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.06350874900817871, 1690204701.3943157], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 678947350, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 10, 4, 4]], ["tile_x", "sp", [-1, 10, 48, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.061532020568847656, 1690204701.394324], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 445152879, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 2]], ["tile_y", "sp", [-1, 1, 16, 10]], ["tile_x", "sp", [-1, 2, 5, 4]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04039335250854492, 1690204701.3943324], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2402367571, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 5, 4, 16]], ["tile_x", "sp", [-1, 2, 6, 10]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04988884925842285, 1690204701.3943393], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2363461925, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 10, 1, 4]], ["tile_x", "sp", [-1, 4, 12, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.04207824958333333], 0, 4.727717638015747, 1690204728.04333], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2957354447, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 80, 1, 8]], ["tile_x", "sp", [-1, 1, 10, 12]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.038533926010131836, 1690204701.3943465], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 464754536, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 5, 1, 128]], ["tile_x", "sp", [-1, 1, 8, 2]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03414416313171387, 1690204701.3943524], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1622955001, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 2, 4, 16]], ["tile_x", "sp", [-1, 80, 2, 3]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03683614730834961, 1690204701.394359], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 21917972, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 1, 2, 30]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0016107767439613528], 0, 2.7039713859558105, 1690204796.3038216], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 696283412, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 1, 2, 30]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0015254540777439023], 0, 3.035181760787964, 1690204798.2365186], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 60508597, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 1, 15, 4]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.003963843300395256], 0, 2.7403016090393066, 1690204800.2377791], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 716416544, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 1, 6, 10]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0036112966479820625], 0, 4.437196969985962, 1690204803.7859223], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 887739848, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 1, 2, 20]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0012242665963581184], 0, 4.3682990074157715, 1690204807.32544], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 60508609, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 1, 15, 4]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0016990854872665536], 0, 2.744021415710449, 1690204809.2941697], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 371350607, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 1, 10, 1]], ["tile_x", "sp", [-1, 1, 20, 3]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0016004302284345047], 0, 2.7126717567443848, 1690204811.2272882], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1045726993, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 2, 1, 5]], ["tile_x", "sp", [-1, 1, 20, 3]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.002072902513457557], 0, 2.7741053104400635, 1690204813.1507666], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1195545124, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 1, 10, 1]], ["tile_x", "sp", [-1, 1, 10, 6]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0016433972380952382], 0, 2.8207590579986572, 1690204815.1137288], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1725025730, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 8]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 2, 4, 6]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0013605498107653491], 0, 4.319261789321899, 1690204818.6638231], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1063104937, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 4, 15, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0012139808196844478], 0, 4.153335809707642, 1690204822.1942263], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1699742362, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 1]], ["tile_y", "sp", [-1, 1, 5, 4]], ["tile_x", "sp", [-1, 2, 6, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.024642609365853663], 0, 4.891531467437744, 1690204824.4189434], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 179572697, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 6, 2, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.043595196260869565], 0, 4.582446336746216, 1690204826.8041244], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 519870709, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 2]], ["tile_y", "sp", [-1, 2, 2, 4]], ["tile_x", "sp", [-1, 1, 12, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.1491559448], 0, 4.654576301574707, 1690204829.3508983], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1047067465, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 2, 1, 4]], ["tile_x", "sp", [-1, 3, 4, 4]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00281599712605042], 0, 3.0117242336273193, 1690204831.3321404], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2202669017, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 6, 2, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.04359902552173913], 0, 3.393911361694336, 1690204833.7163584], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2873652138, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 10]], ["tile_x", "sp", [-1, 2, 12, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.035855030571428574], 0, 4.915304899215698, 1690204836.0231442], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2205784311, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 2]], ["tile_y", "sp", [-1, 2, 2, 4]], ["tile_x", "sp", [-1, 1, 12, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.002210221514348786], 0, 2.5222368240356445, 1690204837.9982123], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2705060778, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 10]], ["tile_x", "sp", [-1, 2, 12, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.03488817517241379], 0, 5.598031520843506, 1690204840.3069668], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2199551411, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 1, 2, 5]], ["tile_x", "sp", [-1, 1, 16, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008136823073868148], 0, 3.16198468208313, 1690204842.2459462], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2555886523, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 4, 10, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0009710131208372979], 0, 3.003194808959961, 1690204844.2203126], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1530562334, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 1, 4, 5]], ["tile_x", "sp", [-1, 4, 2, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.036714900392857144], 0, 4.500416278839111, 1690204846.5853155], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1868601589, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 2]], ["tile_y", "sp", [-1, 2, 2, 4]], ["tile_x", "sp", [-1, 1, 12, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.02758393156756757], 0, 4.436069011688232, 1690204848.8376708], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2870649820, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 5, 1, 1]], ["tile_x", "sp", [-1, 1, 60, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.001022791917721519], 0, 4.415510416030884, 1690204852.4193354], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2203669682, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 16]], ["tile_x", "sp", [-1, 1, 8, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00191742603686088], 0, 4.177974700927734, 1690204855.9538722], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 204087703, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 1, 2, 5]], ["tile_x", "sp", [-1, 2, 4, 4]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0018183837872727273], 0, 2.5378990173339844, 1690204857.8796065], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2206540202, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 1, 2, 5]], ["tile_x", "sp", [-1, 4, 2, 6]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.024719209975609755], 0, 4.964152097702026, 1690204860.1173089], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 709884760, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 2]], ["tile_y", "sp", [-1, 2, 1, 4]], ["tile_x", "sp", [-1, 3, 4, 4]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.045228345782608696], 0, 6.49230694770813, 1690204862.5739164], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1040229337, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 5, 1, 1]], ["tile_x", "sp", [-1, 1, 60, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0009947403905289053], 0, 4.0893754959106445, 1690204866.1023178], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14971575, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 2]], ["tile_x", "sp", [-1, 4, 6, 10]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0009668079784560143], 0, 8.521702527999878, 1690204884.14621], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7553683, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 1200, 1, 8]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.34417104721069336, 1690204873.2247224], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8886432, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 1]], ["tile_x", "sp", [-1, 80, 10, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690204878.1007335], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3384104, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 2]], ["tile_x", "sp", [-1, 50, 8, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.02399687992857143], 0, 7.688365697860718, 1690204886.393798], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 12249120, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 1]], ["tile_x", "sp", [-1, 16, 4, 2]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006290622244389028], 0, 10.073886632919312, 1690204888.3252435], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2949100, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 2]], ["tile_x", "sp", [-1, 25, 1, 768]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.41411733627319336, 1690204878.1007667], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5629382, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 4]], ["tile_x", "sp", [-1, 160, 4, 3]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690204878.1631727], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6563106, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 1]], ["tile_x", "sp", [-1, 40, 4, 40]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.4183194637298584, 1690204878.1631927], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 11538723, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 2]], ["tile_x", "sp", [-1, 1, 1920, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 2.8676648139953613, 1690204878.163202], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4710849, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 1]], ["tile_x", "sp", [-1, 2, 150, 32]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.4711284637451172, 1690204878.1632147], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3184667, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 1]], ["tile_x", "sp", [-1, 5, 40, 16]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.012737497063291138], 0, 6.139891147613525, 1690204890.4477475], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8739469, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 16]], ["tile_x", "sp", [-1, 8, 10, 20]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690204878.2580156], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 13903953, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 8]], ["tile_x", "sp", [-1, 24, 50, 16]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.5693008899688721, 1690204878.2580287], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 12672108, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 4, 6, 4]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690204878.3814595], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8550761, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 1]], ["tile_x", "sp", [-1, 480, 2, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690204878.38153], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 11380091, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 8]], ["tile_x", "sp", [-1, 16, 1, 50]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690204878.3995943], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 319726, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 1, 4, 96]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.041747072833333336], 0, 6.363297700881958, 1690204892.8983312], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8165785, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 5, 120, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008280917930327868], 0, 11.301197528839111, 1690204896.4421875], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 13221602, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 1]], ["tile_x", "sp", [-1, 1, 60, 40]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0012676533406593407], 0, 6.848459959030151, 1690204899.99196], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3874390, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 8, 100, 8]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.930274248123169, 1690204880.7267792], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2704933, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 32, 50, 4]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.009796049357575758], 0, 7.2553160190582275, 1690204903.6775947], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 41340, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 1]], ["tile_x", "sp", [-1, 8, 480, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 1.0136311054229736, 1690204880.7267945], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8453756, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 16]], ["tile_x", "sp", [-1, 64, 1, 100]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.5788915157318115, 1690204880.7268047], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8177159, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 4]], ["tile_x", "sp", [-1, 16, 1, 2]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.2599145507], 0, 8.409034729003906, 1690204907.4797692], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1945887, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 32]], ["tile_x", "sp", [-1, 60, 1, 4]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 4, 15.055038928985596, 1690204917.711152], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6255660, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 1]], ["tile_x", "sp", [-1, 1, 50, 192]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.9745385646820068, 1690204880.7268195], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 10782948, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 480, 20, 2]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.5720932483673096, 1690204880.7268295], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3229532, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 1]], ["tile_x", "sp", [-1, 20, 15, 32]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.4017784595489502, 1690204880.7268395], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 12613077, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 2]], ["tile_x", "sp", [-1, 96, 1, 2]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.4651522636413574, 1690204880.7268486], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14676064, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 2]], ["tile_x", "sp", [-1, 2, 4, 30]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.007254053086956522], 0, 8.028663158416748, 1690204919.775839], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6168786, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 8]], ["tile_x", "sp", [-1, 16, 4, 25]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690204880.7269413], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4739655, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 4]], ["tile_x", "sp", [-1, 25, 3, 64]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.4508204460144043, 1690204880.7269564], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 9849181, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 1]], ["tile_x", "sp", [-1, 1, 15, 20]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690204880.7270105], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4340949, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 16]], ["tile_x", "sp", [-1, 2, 100, 32]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.4285576343536377, 1690204880.7270215], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 332046, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 25, 6, 128]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.39857959747314453, 1690204880.7270312], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14552644, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 8, 20, 5]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 2.1040451526641846, 1690204880.7270386], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 9996138, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 5, 12, 1]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0016359954706477733], 0, 6.724677085876465, 1690204923.4212985], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 12014346, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 8]], ["tile_x", "sp", [-1, 48, 5, 10]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.3431580066680908, 1690204880.727048], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5959817, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 1]], ["tile_x", "sp", [-1, 32, 1, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.002374813710900474], 0, 5.615669012069702, 1690204925.358312], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2627968, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 6, 400, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0017906364171029665], 0, 5.1300950050354, 1690204927.375609], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7229011, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 4, 50, 12]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 2.0752458572387695, 1690204880.7270582], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 12527685, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 4]], ["tile_x", "sp", [-1, 3, 2, 128]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.36778736114501953, 1690204880.727068], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 11699586, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 2, 1]], ["tile_x", "sp", [-1, 1, 32, 20]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690204880.72712], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2021646, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 8]], ["tile_x", "sp", [-1, 2, 25, 8]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.5380094051361084, 1690204880.7271297], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4985247, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 1]], ["tile_x", "sp", [-1, 5, 480, 8]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 1.570526123046875, 1690204880.7271369], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 12062720, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 4]], ["tile_x", "sp", [-1, 20, 4, 20]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.3884546756744385, 1690204880.727146], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 557249, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 8]], ["tile_x", "sp", [-1, 5, 6, 10]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.012751223784810127], 0, 5.584728479385376, 1690204929.5319808], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 9881557, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 30, 10, 32]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.47451305389404297, 1690204880.7271569], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2777616, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 1]], ["tile_x", "sp", [-1, 10, 12, 10]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0013477396691729325], 0, 7.0732502937316895, 1690204933.073718], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14823465, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 4]], ["tile_x", "sp", [-1, 32, 300, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.6045074462890625, 1690204880.7271652], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5675032, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 8]], ["tile_x", "sp", [-1, 120, 4, 5]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0722978591875], 0, 9.99843716621399, 1690204936.0111642], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1364621, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 1]], ["tile_x", "sp", [-1, 32, 6, 25]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.438920259475708, 1690204880.7271748], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1450506, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 8]], ["tile_x", "sp", [-1, 5, 10, 192]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.49033260345458984, 1690204880.7271833], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14587474, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 2]], ["tile_x", "sp", [-1, 1, 24, 8]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0007105501921723835], 0, 7.273041009902954, 1690204939.6208954], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2291976, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 1]], ["tile_x", "sp", [-1, 32, 100, 2]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 1.713038444519043, 1690204880.7271914], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3966470, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 8]], ["tile_x", "sp", [-1, 60, 5, 32]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.48719096183776855, 1690204880.7271981], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6836579, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 64, 2, 10]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 1.6277081966400146, 1690204880.7272043], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5715961, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 4]], ["tile_x", "sp", [-1, 30, 16, 8]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690204880.727255], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4247603, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 1]], ["tile_x", "sp", [-1, 80, 1, 10]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.6076033115386963, 1690204880.727263], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 12507274, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 2, 1]], ["tile_x", "sp", [-1, 2, 32, 75]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 2.2821264266967773, 1690204880.7272718], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 10502451, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 160, 10, 6]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690204880.7273183], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 9086657, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 4]], ["tile_x", "sp", [-1, 4, 1, 16]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.06940255731249999], 0, 8.429605960845947, 1690204942.5596967], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2092477, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 4]], ["tile_x", "sp", [-1, 8, 120, 20]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.4078550338745117, 1690204880.7273288], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6243715, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 8]], ["tile_x", "sp", [-1, 1, 160, 120]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.4245011806488037, 1690204880.7273357], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5163055, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 2]], ["tile_x", "sp", [-1, 2, 4, 480]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.6164309978485107, 1690204880.7273424], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 10293145, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 1]], ["tile_x", "sp", [-1, 12, 4, 80]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 2.252366542816162, 1690204880.7273483], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 13102279, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 1]], ["tile_x", "sp", [-1, 12, 5, 8]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0012963585260625501], 0, 6.8732805252075195, 1690204946.1647658], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3422756, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 1, 1280, 3]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 2.203105926513672, 1690204880.7273564], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14879412, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 4]], ["tile_x", "sp", [-1, 4, 320, 3]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 1.7936952114105225, 1690204880.727363], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 12942503, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 100, 3, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0026045865989583333], 0, 5.646790504455566, 1690204948.135987], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14073926, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 32, 50, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.6114897727966309, 1690204880.7273712], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 9331307, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 100, 32, 3]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.5898830890655518, 1690204880.7273784], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 10960691, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 2]], ["tile_x", "sp", [-1, 10, 32, 20]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.684852123260498, 1690204880.727385], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3144295, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 2, 6, 10]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0016744766787564766], 0, 6.551853895187378, 1690204951.7080164], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2467794, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 4]], ["tile_x", "sp", [-1, 10, 20, 24]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.7015631198883057, 1690204880.7273953], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 15242570, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 4]], ["tile_x", "sp", [-1, 16, 16, 3]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.7226133346557617, 1690204880.7274044], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 11441679, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 4]], ["tile_x", "sp", [-1, 3, 20, 320]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.6837003231048584, 1690204880.7274103], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6892547, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 8, 15, 20]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.7107620239257812, 1690204880.7274172], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7594456, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 1]], ["tile_x", "sp", [-1, 16, 5, 12]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.6986386775970459, 1690204880.7274241], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2316765, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 4]], ["tile_x", "sp", [-1, 1, 2, 4]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0008319320547263683], 0, 7.5952699184417725, 1690204953.6884959], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3473305, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 1]], ["tile_x", "sp", [-1, 1, 640, 5]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 1.7447168827056885, 1690204880.7274332], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1121909, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 1, 1]], ["tile_x", "sp", [-1, 4, 8, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.000997411371375694], 0, 6.473447799682617, 1690204957.2090604], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 933128, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 4, 32, 10]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.001769931228522337], 0, 4.951073884963989, 1690204959.1746702], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 13820665, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 5, 192, 5]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.5283756256103516, 1690204880.7274444], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14652978, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 1]], ["tile_x", "sp", [-1, 6, 10, 20]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.6227061748504639, 1690204880.7274501], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7207998, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 1]], ["tile_x", "sp", [-1, 10, 4, 10]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.6539425849914551, 1690204880.727457], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 13519903, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 8]], ["tile_x", "sp", [-1, 2, 40, 15]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.010449482593750002], 0, 7.790083646774292, 1690204961.2374797], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5592418, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 2]], ["tile_x", "sp", [-1, 8, 2, 2]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0008069482685971042], 0, 6.613845109939575, 1690204964.761992], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1949899, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 2]], ["tile_x", "sp", [-1, 80, 3, 4]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.6542506217956543, 1690204880.7274673], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 12081843, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 128, 3, 25]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.7154273986816406, 1690204880.7274752], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4916032, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 1]], ["tile_x", "sp", [-1, 10, 16, 4]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.5834052562713623, 1690204880.7274816], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 9222170, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 2]], ["tile_x", "sp", [-1, 6, 2, 320]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.6828622817993164, 1690204880.727488], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6416674, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 4, 8, 5]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0012125468733572282], 0, 11.356318473815918, 1690204966.7290223], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7296526, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 10, 30, 32]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.6140601634979248, 1690204880.7274957], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8726691, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 4, 20, 16]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0018979286034155598], 0, 5.100951671600342, 1690204968.6934836], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 9512816, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 4]], ["tile_x", "sp", [-1, 40, 15, 32]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.400390625, 1690204880.7275033], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1167409, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 4, 10, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006038012982248521], 0, 4.835658073425293, 1690205544.6621902], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8930521, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 4, 12, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690205542.484861], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8929009, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 4, 10, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690205542.48767], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1168921, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 4, 12, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690205542.5363588], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6343321, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 4, 12, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005662613123966943], 0, 5.031182289123535, 1690205546.6402662], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6341809, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 4, 10, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.000598375844716871], 0, 5.06753396987915, 1690205548.560458], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14104921, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 4, 12, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005663024427942794], 0, 5.895242929458618, 1690205550.5343392], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14103409, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 4, 10, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.000596870933022714], 0, 5.860000371932983, 1690205552.4693463], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1126921, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 5, 15, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006438990860215054], 0, 4.679726839065552, 1690205554.3894548], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8888521, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 5, 15, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006440081790668348], 0, 4.607478141784668, 1690205556.3472066], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8927385, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 5, 8, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005940035303030304], 0, 7.023147344589233, 1690205558.2954314], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14062921, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 5, 15, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006512508963531671], 0, 7.595192909240723, 1690205560.2448466], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6301321, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 5, 15, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006516207925973197], 0, 4.853403568267822, 1690205562.2006752], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14101785, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 5, 8, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.000578817871533673], 0, 6.384926080703735, 1690205564.1158276], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1125745, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 5, 12, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.000626566357011635], 0, 4.806633472442627, 1690205566.0700488], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8887345, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 5, 12, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006268298945432251], 0, 4.913240671157837, 1690205568.0603757], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14067119, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 2]], ["tile_x", "sp", [-1, 4, 24, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005339703968911917], 0, 10.789515018463135, 1690205570.0479932], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6305519, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 2]], ["tile_x", "sp", [-1, 4, 24, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005388308478488983], 0, 4.88634729385376, 1690205571.986915], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6304007, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 2]], ["tile_x", "sp", [-1, 4, 20, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690205542.8496141], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14065607, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 2]], ["tile_x", "sp", [-1, 4, 20, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690205542.8737137], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 11516209, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 4, 10, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690205542.8738348], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 11517721, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 4, 12, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005727873092324805], 0, 9.699033737182617, 1690205573.9776354], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3756121, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 4, 12, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.000572673001112966], 0, 6.671585559844971, 1690205575.9285977], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3754609, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 4, 10, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006020802631578947], 0, 6.6892266273498535, 1690205577.8820946], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1165785, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 5, 8, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005955659200700117], 0, 4.6670098304748535, 1690205579.852533], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6300145, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 5, 12, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006157732812687015], 0, 4.76341986656189, 1690205581.7994115], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 14061745, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 5, 12, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006163488628983765], 0, 5.209785461425781, 1690205583.7440243], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8885553, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 4, 10, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006718868195637805], 0, 4.672528266906738, 1690205585.7282062], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 640, 480], "float32"], ["TENSOR", [32, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1123953, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 4, 10, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006725989154557464], 0, 4.6084184646606445, 1690205587.664456], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1252649593, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 1, 8, 4]], ["tile_x", "sp", [-1, 6, 1, 2]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03130030632019043, 1690205589.9755416], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1527418332, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 1, 64, 10]], ["tile_x", "sp", [-1, 20, 3, 4]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.07685089111328125, 1690205590.0361733], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 289323191, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 10, 1, 8]], ["tile_x", "sp", [-1, 12, 1, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.30292214349999996], 0, 7.019723892211914, 1690205598.7286227], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2156553245, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 10, 2, 2]], ["tile_x", "sp", [-1, 4, 4, 2]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05629396438598633, 1690205593.1417394], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 33637706, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 40, 1, 2]], ["tile_x", "sp", [-1, 2, 2, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.030028498029411765], 0, 4.718052387237549, 1690205600.758419], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1337553941, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 4, 5, 2]], ["tile_x", "sp", [-1, 12, 1, 20]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04015231132507324, 1690205593.1417549], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 594831140, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 8, 1, 8]], ["tile_x", "sp", [-1, 8, 15, 4]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04192519187927246, 1690205593.1417632], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 525957914, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 32, 1, 1]], ["tile_x", "sp", [-1, 6, 2, 40]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.028425931930541992, 1690205593.1417718], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 745278499, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 1, 20, 16]], ["tile_x", "sp", [-1, 5, 12, 4]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.0373837947845459, 1690205593.1417797], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1159966625, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 4, 2, 8]], ["tile_x", "sp", [-1, 40, 3, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.040544986724853516, 1690205593.1417887], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 493284069, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 2]], ["tile_y", "sp", [-1, 5, 16, 1]], ["tile_x", "sp", [-1, 20, 1, 12]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.0967245101928711, 1690205593.1417966], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1921215677, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 16, 4, 1]], ["tile_x", "sp", [-1, 4, 5, 6]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.06479573249816895, 1690205593.1418042], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 121376962, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 1, 40, 16]], ["tile_x", "sp", [-1, 1, 4, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00118042161459854], 0, 3.7268781661987305, 1690205604.0439444], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 127331853, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 80, 2, 2]], ["tile_x", "sp", [-1, 15, 2, 4]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.035855770111083984, 1690205593.1418157], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2084646033, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 10, 4, 1]], ["tile_x", "sp", [-1, 24, 5, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.23488497734069824, 1690205593.1418238], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1927798326, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 1, 20, 32]], ["tile_x", "sp", [-1, 6, 4, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.32966089248657227, 1690205593.1418314], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1772219246, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 2]], ["tile_y", "sp", [-1, 20, 1, 2]], ["tile_x", "sp", [-1, 1, 3, 10]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.04561491809090909], 0, 6.951888084411621, 1690205606.201393], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 627922192, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 5, 8, 2]], ["tile_x", "sp", [-1, 2, 1, 10]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03284811973571777, 1690205594.8911521], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 711095520, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 8, 8, 1]], ["tile_x", "sp", [-1, 8, 2, 2]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.14230918884277344, 1690205594.8911684], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1032678958, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 160]], ["tile_x", "sp", [-1, 1, 1, 6]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.07298246762499999], 0, 3.2455224990844727, 1690205608.8361344], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1932010450, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 20, 1, 8]], ["tile_x", "sp", [-1, 3, 40, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04719424247741699, 1690205594.8911808], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2139163302, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 8, 16, 1]], ["tile_x", "sp", [-1, 6, 8, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.09146690368652344, 1690205594.8911898], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1472175307, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 2]], ["tile_y", "sp", [-1, 5, 8, 4]], ["tile_x", "sp", [-1, 8, 1, 15]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.038892507553100586, 1690205594.8911984], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 453571333, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 16, 4, 2]], ["tile_x", "sp", [-1, 4, 12, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.041036064440000006], 0, 3.9497480392456055, 1690205610.9967012], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 300636551, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 640, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 80]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.0416872501373291, 1690205594.8912098], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 503304326, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 2]], ["tile_y", "sp", [-1, 4, 16, 5]], ["tile_x", "sp", [-1, 4, 1, 4]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.040911197662353516, 1690205594.8912177], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 351567031, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 2, 1, 8]], ["tile_x", "sp", [-1, 4, 60, 2]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.039055824279785156, 1690205594.8912258], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 762339418, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 2, 16, 2]], ["tile_x", "sp", [-1, 1, 16, 6]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03854990005493164, 1690205594.8912334], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 413269227, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 2, 20, 2]], ["tile_x", "sp", [-1, 5, 2, 4]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.22532296180725098, 1690205594.8912416], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1773304078, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 4, 10, 16]], ["tile_x", "sp", [-1, 2, 2, 15]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05087637901306152, 1690205594.8912492], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1070409076, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 4, 1, 20]], ["tile_x", "sp", [-1, 5, 8, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.033008575439453125, 1690205594.8912568], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 776182560, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 32, 10, 2]], ["tile_x", "sp", [-1, 1, 4, 5]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.19999265670776367, 1690205594.8912644], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1022745072, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 8, 10, 8]], ["tile_x", "sp", [-1, 2, 3, 40]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.1842026710510254, 1690205594.891273], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 491241434, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 2]], ["tile_y", "sp", [-1, 64, 2, 5]], ["tile_x", "sp", [-1, 16, 5, 6]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.036478519439697266, 1690205594.8912804], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 817257450, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 80, 2, 2]], ["tile_x", "sp", [-1, 10, 6, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.042104482650756836, 1690205594.8912873], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1707596010, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 16, 1, 8]], ["tile_x", "sp", [-1, 10, 1, 4]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.059186458587646484, 1690205594.8912945], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1082833186, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 1, 20, 2]], ["tile_x", "sp", [-1, 6, 1, 40]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03652024269104004, 1690205594.8913019], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 988819653, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 64, 5, 2]], ["tile_x", "sp", [-1, 4, 5, 8]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04172325134277344, 1690205594.8913083], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 667006214, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 4, 16, 10]], ["tile_x", "sp", [-1, 8, 10, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04718160629272461, 1690205594.8913155], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1473290538, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 32]], ["tile_x", "sp", [-1, 6, 4, 20]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04026436805725098, 1690205594.8913233], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3035806, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 2, 1, 10]], ["tile_x", "sp", [-1, 5, 96, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.010451018645833332], 0, 2.314164400100708, 1690205612.7523355], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 136679015, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 20, 4, 8]], ["tile_x", "sp", [-1, 120, 4, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.030208349227905273, 1690205594.8913336], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2688436, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 128, 1, 1]], ["tile_x", "sp", [-1, 15, 32, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03551006317138672, 1690205594.8913412], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1637014315, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 20, 8, 2]], ["tile_x", "sp", [-1, 2, 8, 10]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.053319692611694336, 1690205594.8913493], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1650537403, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 2]], ["tile_y", "sp", [-1, 40, 2, 2]], ["tile_x", "sp", [-1, 1, 40, 6]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.043729543685913086, 1690205594.8913567], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1509176599, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 10, 1, 64]], ["tile_x", "sp", [-1, 16, 3, 2]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04464554786682129, 1690205594.8913634], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 463713030, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 4, 2, 80]], ["tile_x", "sp", [-1, 2, 2, 15]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03441262245178223, 1690205594.8913696], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1163925494, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 4, 15, 2]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03363823890686035, 1690205594.891377], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 348863593, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 2, 20, 8]], ["tile_x", "sp", [-1, 1, 32, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04191899299621582, 1690205594.8913834], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 730064346, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 5, 128, 1]], ["tile_x", "sp", [-1, 15, 8, 4]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.05817675590515137, 1690205594.8913908], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 143567146, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 8, 5, 8]], ["tile_x", "sp", [-1, 6, 1, 5]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04717278480529785, 1690205594.8913987], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 32723908, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 8, 4, 20]], ["tile_x", "sp", [-1, 8, 30, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04419350624084473, 1690205594.891405], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 401345170, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 8, 16, 5]], ["tile_x", "sp", [-1, 15, 1, 8]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04169583320617676, 1690205594.8914182], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 276160733, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 2]], ["tile_y", "sp", [-1, 64, 10, 1]], ["tile_x", "sp", [-1, 1, 40, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.13004016876220703, 1690205594.8914254], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2138729516, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 2]], ["tile_y", "sp", [-1, 20, 8, 2]], ["tile_x", "sp", [-1, 2, 5, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.10287284851074219, 1690205594.8914328], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 217158301, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 2, 40, 3]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0008824360332787781], 0, 3.5686287879943848, 1690205616.017707], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 749482934, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 32, 4, 1]], ["tile_x", "sp", [-1, 1, 10, 12]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.036130428314208984, 1690205594.8914425], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1349618332, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 160, 1, 4]], ["tile_x", "sp", [-1, 6, 1, 8]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.09764504432678223, 1690205594.8914495], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 84302341, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 1, 2, 320]], ["tile_x", "sp", [-1, 1, 48, 5]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03411674499511719, 1690205594.891456], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 285449338, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 640, 1, 1]], ["tile_x", "sp", [-1, 4, 1, 60]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.031673431396484375, 1690205594.8914635], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1396618695, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 2, 4, 1]], ["tile_x", "sp", [-1, 5, 4, 12]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0010813318194594595], 0, 2.6263039112091064, 1690205617.7029169], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 991967748, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 2]], ["tile_y", "sp", [-1, 1, 80, 8]], ["tile_x", "sp", [-1, 2, 5, 24]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.041527509689331055, 1690205594.891473], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1298808950, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 80, 2, 1]], ["tile_x", "sp", [-1, 16, 5, 2]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03772258758544922, 1690205594.8914807], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1030297083, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 2]], ["tile_y", "sp", [-1, 8, 80, 1]], ["tile_x", "sp", [-1, 30, 1, 4]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.06631302833557129, 1690205594.8914878], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2007294372, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 5, 8, 16]], ["tile_x", "sp", [-1, 6, 40, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.08306241035461426, 1690205594.891495], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1269533617, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 4]], ["tile_x", "sp", [-1, 2, 24, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0011911009285714284], 0, 2.032175064086914, 1690205619.3230224], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1383582914, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 1, 10, 1]], ["tile_x", "sp", [-1, 2, 4, 30]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.000683521730743013], 0, 2.0525074005126953, 1690205620.9537668], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1228923102, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 2]], ["tile_y", "sp", [-1, 2, 40, 1]], ["tile_x", "sp", [-1, 2, 10, 6]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.1440885066986084, 1690205594.8915057], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1816984584, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 1, 4, 20]], ["tile_x", "sp", [-1, 4, 15, 8]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.051261186599731445, 1690205594.891513], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1892453739, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 64, 2, 1]], ["tile_x", "sp", [-1, 16, 1, 10]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03588128089904785, 1690205594.8915203], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1530019471, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 2, 16, 5]], ["tile_x", "sp", [-1, 8, 10, 6]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04018831253051758, 1690205594.891527], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 46398483, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 4, 10, 16]], ["tile_x", "sp", [-1, 2, 5, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03879737854003906, 1690205594.8915339], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1706281772, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 2, 80, 2]], ["tile_x", "sp", [-1, 1, 60, 2]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05572056770324707, 1690205594.891541], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1368068105, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 80, 1, 8]], ["tile_x", "sp", [-1, 1, 1, 24]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.027471542358398438, 1690205594.8915493], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 284550347, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 1, 40, 4]], ["tile_x", "sp", [-1, 1, 20, 24]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.037941694259643555, 1690205594.8915575], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 137393697, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 5, 64, 1]], ["tile_x", "sp", [-1, 24, 10, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.040047645568847656, 1690205594.8915648], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1488004850, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 2, 2, 10]], ["tile_x", "sp", [-1, 2, 1, 20]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.016931037383333333], 0, 4.932952642440796, 1690205622.838328], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1374554332, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 16, 1, 10]], ["tile_x", "sp", [-1, 2, 12, 2]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03146791458129883, 1690205594.8915737], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 122608911, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 8, 16, 1]], ["tile_x", "sp", [-1, 1, 16, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0007843502066957787], 0, 3.6765387058258057, 1690205626.118842], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 762544772, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 8, 4, 5]], ["tile_x", "sp", [-1, 5, 1, 8]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04633831977844238, 1690205594.8915837], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1853113439, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 5, 32, 2]], ["tile_x", "sp", [-1, 3, 8, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05348038673400879, 1690205594.8915904], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 948658002, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 1, 8, 10]], ["tile_x", "sp", [-1, 96, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.047456979751586914, 1690205594.891597], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1896558136, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 16, 20, 2]], ["tile_x", "sp", [-1, 3, 1, 160]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03555917739868164, 1690205594.8916044], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 719131470, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 80, 2, 4]], ["tile_x", "sp", [-1, 2, 2, 12]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.12419462203979492, 1690205594.8916116], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 266192984, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 1, 40, 16]], ["tile_x", "sp", [-1, 3, 4, 8]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03492164611816406, 1690205594.8916187], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 544318975, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 5, 1, 64]], ["tile_x", "sp", [-1, 8, 20, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.036151885986328125, 1690205594.8916256], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 342101386, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 10, 32, 1]], ["tile_x", "sp", [-1, 3, 2, 10]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.06362271308898926, 1690205594.891632], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1789905522, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 2, 1, 320]], ["tile_x", "sp", [-1, 8, 1, 30]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0653541088104248, 1690205594.8916388], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1515680254, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 6, 5, 8]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.15740489959716797, 1690205594.8916452], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1561085277, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 4, 8, 10]], ["tile_x", "sp", [-1, 4, 15, 8]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05666065216064453, 1690205594.891652], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1951804732, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 1, 8, 20]], ["tile_x", "sp", [-1, 20, 1, 8]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04844784736633301, 1690205594.8916595], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2034832462, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 160]], ["tile_x", "sp", [-1, 15, 32, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.050943613052368164, 1690205594.8916664], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 629533124, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 1, 128, 1]], ["tile_x", "sp", [-1, 2, 1, 16]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03254580497741699, 1690205594.8916721], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 558984156, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 32]], ["tile_x", "sp", [-1, 8, 12, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.026978142973684213], 0, 3.3490257263183594, 1690205628.1063926], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 334709654, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 1, 64, 1]], ["tile_x", "sp", [-1, 3, 2, 2]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.039052486419677734, 1690205594.89168], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1281523686, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 2, 32, 1]], ["tile_x", "sp", [-1, 10, 12, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05750226974487305, 1690205594.8916872], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 821376300, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 3, 4, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0009467321855549031], 0, 4.237460613250732, 1690205789.5559437], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 96389102, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 2, 8, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0008955773715308864], 0, 1.960669755935669, 1690205791.1921704], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 457656302, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 2, 8, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0008071333549675488], 0, 3.598353147506714, 1690205794.443677], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 460092300, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 2, 4, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0009817657614858261], 0, 2.2217695713043213, 1690205796.1060877], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1537863012, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 2, 5, 4]], ["tile_x", "sp", [-1, 2, 24, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008669790037573806], 0, 9.13062047958374, 1690205799.3379412], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 460109100, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 3, 4, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0008493751717436975], 0, 8.085580825805664, 1690205802.6030242], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 457658052, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 2, 2, 5]], ["tile_x", "sp", [-1, 2, 8, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005234320087378641], 0, 3.7857608795166016, 1690205805.8791924], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 911810702, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 2, 6, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00041052705776081425], 0, 5.543251991271973, 1690205809.1320648], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 96390852, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 2, 2, 5]], ["tile_x", "sp", [-1, 2, 8, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005983354974093264], 0, 5.455385446548462, 1690205812.3972564], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1541459652, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 2, 2, 5]], ["tile_x", "sp", [-1, 2, 8, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005924834840047393], 0, 2.6410841941833496, 1690205814.0652077], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1182626702, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 2, 4, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0017906926015625], 0, 4.41172981262207, 1690205817.3114626], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1905161102, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 2, 4, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0007619018840169732], 0, 4.332148313522339, 1690205820.5586925], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 98825102, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 2, 4, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0017944309955207167], 0, 3.6747500896453857, 1690205823.820984], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1995612302, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 2, 6, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00037448839717134244], 0, 4.788263320922852, 1690205827.0661645], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 818923502, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 2, 8, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0008071087086359968], 0, 3.6063883304595947, 1690205828.6825485], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1899017827, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 1, 2, 16]], ["tile_x", "sp", [-1, 3, 20, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.001199903309352518], 0, 4.455275297164917, 1690205830.3539746], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 98825100, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 2, 4, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0010180753289340103], 0, 2.3866488933563232, 1690205832.0055187], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 905512662, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 1, 4, 5]], ["tile_x", "sp", [-1, 2, 20, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0009372718753514525], 0, 2.02803635597229, 1690205833.6344595], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 98841900, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 3, 4, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006623358623514952], 0, 4.08405327796936, 1690205836.9342277], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1182626700, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 2, 4, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0010183796839443743], 0, 4.033380031585693, 1690205840.1839433], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 817595567, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 2, 1, 4]], ["tile_x", "sp", [-1, 2, 12, 2]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003162458735745183], 0, 5.321635723114014, 1690205843.4145668], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1902726852, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 2, 2, 5]], ["tile_x", "sp", [-1, 2, 8, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0004112084116441164], 0, 3.279097557067871, 1690205845.0835793], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1273077902, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 2, 6, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006128121013282733], 0, 3.7720978260040283, 1690205848.3145812], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1543893900, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 2, 4, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006312954018032143], 0, 4.385523557662964, 1690205851.551324], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 189276302, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 2, 6, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006127919032258064], 0, 3.723850965499878, 1690205854.8179612], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 815216227, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 1, 2, 16]], ["tile_x", "sp", [-1, 3, 20, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0021840118281461433], 0, 4.365782976150513, 1690205858.0838258], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1182643500, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 3, 4, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006622028902089308], 0, 3.846386432647705, 1690205861.3315675], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 818925252, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 2, 2, 5]], ["tile_x", "sp", [-1, 2, 8, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00048244516084250833], 0, 2.371307134628296, 1690205862.9894924], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1905177900, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 3, 4, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00037904009741784037], 0, 6.4028215408325195, 1690205866.2460358], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5285452, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 8]], ["tile_x", "sp", [-1, 3, 16, 100]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.7079677581787109, 1690205869.2375026], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7424061, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 160, 3, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690205878.3864303], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4117104, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 2, 3, 64]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.3456380367279053, 1690205878.386458], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4188950, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 1]], ["tile_x", "sp", [-1, 150, 2, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.006245929217391305], 0, 5.808786630630493, 1690205883.3214028], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6969613, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 4]], ["tile_x", "sp", [-1, 3, 20, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00032187141980474196], 0, 7.348954439163208, 1690205886.6215956], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1460075, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 3, 64, 4]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003910190483558994], 0, 5.235680341720581, 1690205888.2963514], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6422946, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 4]], ["tile_x", "sp", [-1, 3, 128, 50]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.5331130027770996, 1690205878.3864732], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5795061, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 6, 80, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.00030930845304374423], 0, 4.443539381027222, 1690205889.9357564], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1402090, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 24, 32, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690205878.4722097], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6235086, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 1]], ["tile_x", "sp", [-1, 2, 2, 1600]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.7285361289978027, 1690205878.472221], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6645573, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 2]], ["tile_x", "sp", [-1, 12, 20, 40]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.5260226726531982, 1690205878.4722285], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5408080, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 1, 8, 6]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0003347305008242664], 0, 7.09496545791626, 1690205891.6210816], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6078432, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 2]], ["tile_x", "sp", [-1, 2, 40, 4]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0003143498802022559], 0, 8.45915675163269, 1690205894.8701317], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3064497, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 1]], ["tile_x", "sp", [-1, 200, 1, 4]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690205878.7973216], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7460501, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 16, 12, 4]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690205878.7973747], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7804169, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 20, 10, 48]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.5360078811645508, 1690205878.7973874], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1784977, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 1]], ["tile_x", "sp", [-1, 40, 3, 32]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.003946757547911548], 0, 10.87174916267395, 1690205898.176188], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5597704, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 1]], ["tile_x", "sp", [-1, 8, 5, 3]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0003576545586864877], 0, 12.194320678710938, 1690205901.4485898], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1295779, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 40, 15, 16]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 2.1477484703063965, 1690205881.6801448], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4378135, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 10, 3, 320]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.019876643156862744], 0, 4.809794664382935, 1690205903.3183613], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6880704, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 16, 25, 48]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 1.9484994411468506, 1690205881.6801572], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2041318, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 1]], ["tile_x", "sp", [-1, 64, 2, 75]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.49211812019348145, 1690205881.6801646], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7930316, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 25, 192, 4]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.4296383857727051, 1690205881.6801715], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7886270, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1600, 3, 2]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.3756401538848877, 1690205881.6801784], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5740443, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 2]], ["tile_x", "sp", [-1, 2, 5, 80]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0033898689347368425], 0, 7.89055609703064, 1690205906.6655452], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3236388, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 1]], ["tile_x", "sp", [-1, 30, 2, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.001347078181695828], 0, 5.507333993911743, 1690205908.36841], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3300597, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 4]], ["tile_x", "sp", [-1, 800, 6, 4]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 1.0452027320861816, 1690205881.6801884], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7362543, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 1]], ["tile_x", "sp", [-1, 48, 1, 100]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.009336803287037036], 0, 10.308157444000244, 1690205910.1271534], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7271286, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 12, 50, 8]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005723404687943262], 0, 7.465768098831177, 1690205913.4049902], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2453720, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 1]], ["tile_x", "sp", [-1, 1, 120, 16]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 3.465205669403076, 1690205881.6801996], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6844902, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 24, 2, 20]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.34482765197753906, 1690205881.6802068], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5534302, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 8]], ["tile_x", "sp", [-1, 10, 1, 384]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.42456793785095215, 1690205881.6802154], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 80429, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 16]], ["tile_x", "sp", [-1, 640, 2, 5]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690205881.6803007], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7192377, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 2]], ["tile_x", "sp", [-1, 1200, 2, 2]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0406910156], 0, 5.3578572273254395, 1690205915.5635433], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3798122, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 4]], ["tile_x", "sp", [-1, 600, 2, 8]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 1.2095880508422852, 1690205881.6803124], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 630663, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 8]], ["tile_x", "sp", [-1, 4, 5, 32]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.003974696567460317], 0, 5.434548616409302, 1690205917.3342264], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7882318, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 1]], ["tile_x", "sp", [-1, 1, 19200, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 3.184251546859741, 1690205881.680321], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3274337, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 2]], ["tile_x", "sp", [-1, 480, 20, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.4513990879058838, 1690205881.6803272], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1321931, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 150, 1, 32]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.39474010467529297, 1690205881.6803336], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7365444, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 40, 1, 120]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.020160163560000003], 0, 5.882571220397949, 1690205919.2190459], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8082613, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 4]], ["tile_x", "sp", [-1, 5, 1, 1280]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 3.7127747535705566, 1690205881.680341], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3356258, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 1]], ["tile_x", "sp", [-1, 8, 60, 10]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.5578422546386719, 1690205881.680347], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3145715, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 1, 50, 16]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0004542615886983413], 0, 12.76448655128479, 1690205922.52074], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6558237, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 1]], ["tile_x", "sp", [-1, 1, 128, 5]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.00032657328082607814], 0, 6.2950921058654785, 1690205925.7524984], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1436075, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 1, 800, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.00030675397593664334], 0, 4.403780460357666, 1690205927.3956275], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5813144, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 4]], ["tile_x", "sp", [-1, 1, 15, 2]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002886161749354746], 0, 4.845161437988281, 1690205929.0650997], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3396105, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 3, 128, 25]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 3.7356696128845215, 1690205881.680359], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4695136, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 4]], ["tile_x", "sp", [-1, 1, 100, 4]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002695733998399573], 0, 4.779040575027466, 1690205930.6879454], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1927080, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 320, 1, 5]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690205881.6804135], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5404826, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 2]], ["tile_x", "sp", [-1, 1, 640, 5]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 1.556903600692749, 1690205881.6804218], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3820792, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 2]], ["tile_x", "sp", [-1, 40, 1, 12]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.08422835537500001], 0, 6.681857109069824, 1690205933.58144], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7886132, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 1]], ["tile_x", "sp", [-1, 320, 3, 2]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.36692214012145996, 1690205881.680431], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2115532, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 4]], ["tile_x", "sp", [-1, 1, 10, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.00032293184850434224], 0, 5.0133867263793945, 1690205935.2484407], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3398459, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 4]], ["tile_x", "sp", [-1, 20, 8, 30]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.38301825523376465, 1690205881.6804407], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1238784, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 4]], ["tile_x", "sp", [-1, 30, 8, 5]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.3615705966949463, 1690205881.6804483], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2135122, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 2]], ["tile_x", "sp", [-1, 16, 20, 3]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0020437446122448977], 0, 6.818480491638184, 1690205938.4830127], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 69222, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 4]], ["tile_x", "sp", [-1, 80, 15, 4]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00554719467403315], 0, 6.896155118942261, 1690205940.191785], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3951054, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 8, 240, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.47974324226379395, 1690205881.6804569], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6662313, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 4]], ["tile_x", "sp", [-1, 2, 128, 75]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.43248677253723145, 1690205881.6804636], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1014109, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 4, 120, 5]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.4207944869995117, 1690205881.680474], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3500703, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 1]], ["tile_x", "sp", [-1, 10, 8, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0004317873115806365], 0, 6.880019903182983, 1690205943.4933894], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7987055, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 2, 16, 15]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0004442965822616408], 0, 5.9355034828186035, 1690205945.1116056], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 546913, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 1]], ["tile_x", "sp", [-1, 16, 12, 5]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.005914515594117647], 0, 5.6800453662872314, 1690205946.7922287], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 234905, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 32, 3, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006021307065176909], 0, 6.077512979507446, 1690205950.0972135], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6098679, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 16]], ["tile_x", "sp", [-1, 40, 1, 6]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.1533652954], 0, 7.784957408905029, 1690205952.414801], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8013638, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 1]], ["tile_x", "sp", [-1, 96, 4, 25]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.3526573181152344, 1690205881.6804879], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3152317, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 1]], ["tile_x", "sp", [-1, 48, 10, 20]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 1.4943194389343262, 1690205881.680498], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3922174, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 1]], ["tile_x", "sp", [-1, 25, 1, 768]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.5878584384918213, 1690205881.6805046], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3942576, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 160, 30, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.5302560329437256, 1690205881.6805103], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1785200, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 3, 4, 32]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.009944023504950496], 0, 5.840139150619507, 1690205954.208744], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 150584, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 1]], ["tile_x", "sp", [-1, 8, 20, 20]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006519793123486683], 0, 6.221222639083862, 1690205957.5234451], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5511984, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 1]], ["tile_x", "sp", [-1, 1, 120, 80]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.4834709167480469, 1690205881.6805205], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6315579, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 1]], ["tile_x", "sp", [-1, 30, 1, 5]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.07422815699999999], 0, 6.176009178161621, 1690205960.146885], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7918497, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 4]], ["tile_x", "sp", [-1, 40, 4, 4]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690205881.6805747], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 537126, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 1, 100, 4]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003055735945622946], 0, 5.162817478179932, 1690205961.8092752], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8229325, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 1, 400, 16]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.34223127365112305, 1690205881.6805842], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7659990, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 30, 10, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005265487837980011], 0, 5.402324438095093, 1690205963.4680974], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3601512, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 1]], ["tile_x", "sp", [-1, 25, 2, 16]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.002125853685601057], 0, 11.09988021850586, 1690205966.7181559], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 500986, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 8]], ["tile_x", "sp", [-1, 12, 16, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.000311557429563875], 0, 12.491564989089966, 1690205969.9619367], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 930446, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 30, 5, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.000768278040893961], 0, 6.704368591308594, 1690205973.2402513], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7625702, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 1]], ["tile_x", "sp", [-1, 96, 2, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.009423123538011696], 0, 10.130089521408081, 1690205976.5989227], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2964682, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 1]], ["tile_x", "sp", [-1, 1, 150, 64]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0026073519375000003], 0, 4.498153448104858, 1690205978.2538905], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5155192, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 1]], ["tile_x", "sp", [-1, 50, 48, 4]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.34062743186950684, 1690205881.6805983], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1384977, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 4]], ["tile_x", "sp", [-1, 2, 2, 2400]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.5973849296569824, 1690205881.6806045], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7086446, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 8]], ["tile_x", "sp", [-1, 40, 20, 24]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.379497766494751, 1690205881.6806116], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3064060, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 40, 1, 4]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690205881.6806622], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1174621, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 2]], ["tile_x", "sp", [-1, 2, 75, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002652046888479747], 0, 4.583178281784058, 1690205979.9259005], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3658858, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 4]], ["tile_x", "sp", [-1, 1, 16, 75]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0014169352138420585], 0, 8.664431810379028, 1690205983.1534038], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 392715, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 2, 64, 25]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005672531956445381], 0, 6.226334810256958, 1690205986.414036], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7087872, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 6, 1, 25]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0016307566427850655], 0, 6.919011831283569, 1690205989.7114203], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6146310, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 5, 12, 16]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0007527084114114115], 0, 5.3652167320251465, 1690205991.3515913], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 376929, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 1]], ["tile_x", "sp", [-1, 30, 2, 20]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.002631314690671031], 0, 6.197208404541016, 1690205994.6297238], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7481213, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 8]], ["tile_x", "sp", [-1, 10, 64, 5]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 1.2750508785247803, 1690205881.6806824], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6108500, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 32, 3, 8]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.011016181021978023], 0, 5.742903470993042, 1690205996.426079], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 8175198, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 1]], ["tile_x", "sp", [-1, 32, 120, 5]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.6329083442687988, 1690205881.6806912], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4026583, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 1]], ["tile_x", "sp", [-1, 1, 640, 6]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.5908417701721191, 1690205881.6806974], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4667170, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 1, 150, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002847112481118881], 0, 7.254254579544067, 1690206746.4878795], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6053170, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 1, 150, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002847441176634992], 0, 7.326757192611694, 1690206748.3647954], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1895170, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 1, 150, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002848842343575419], 0, 6.873460531234741, 1690206750.1100404], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 509170, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 1, 150, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00028524251960784314], 0, 10.054570198059082, 1690206751.8835285], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4887562, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 2, 10, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00029566621428571427], 0, 7.229558229446411, 1690206753.6802397], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6273562, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 2, 10, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002951336735345328], 0, 6.85806941986084, 1690206755.403059], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7439170, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 1, 150, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00028743466732172933], 0, 7.3378005027771, 1690206757.1950684], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2115562, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 2, 10, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690206743.9878745], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 729562, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 2, 10, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00029622997775826754], 0, 7.3497655391693115, 1690206759.0266175], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 478540, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 1, 40, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003023043292094146], 0, 8.08405327796936, 1690206760.964603], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3281170, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 1, 150, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690206743.9881248], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6051070, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 2, 75, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690206744.110522], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4665070, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 2, 75, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00029182254491188174], 0, 10.198265075683594, 1690206762.8972812], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7437070, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 2, 75, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.000290858914471821], 0, 8.115826845169067, 1690206764.6897724], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7659562, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 2, 10, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690206744.3640692], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 507070, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 2, 75, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690206744.3641744], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1893070, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 2, 75, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690206744.3642712], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3279070, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 2, 75, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690206744.5868597], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 479380, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 1, 48, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1690206744.5869627], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3501562, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 2, 10, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002947981210801394], 0, 9.237863302230835, 1690206766.7514782], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4636540, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 1, 40, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0003025025039180229], 0, 6.907062530517578, 1690206768.6143243], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4665350, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 2, 80, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002856337401003904], 0, 6.886552572250366, 1690206770.4329908], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6051350, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 2, 80, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.00028569515551839464], 0, 6.703636884689331, 1690206772.169723], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7437350, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 2, 80, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1690206744.5870793], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1864540, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 1, 40, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003030904440096327], 0, 7.108915328979492, 1690206774.1795504], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1893350, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 2, 80, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.00028567200195203565], 0, 6.858614206314087, 1690206775.969178], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 507350, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 2, 80, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00028567509977641135], 0, 7.3304479122161865, 1690206777.9093325], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3279350, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 2, 80, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00028651209857182865], 0, 7.490677356719971, 1690206779.934879], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_80 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 640, 480], "float32"], ["TENSOR", [16, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4637380, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 1, 48, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002915814258566081], 0, 6.764335870742798, 1690206781.6788685], "version": 0.2, "tvm_version": "0.11.dev0"} diff --git a/l40_squeezenet_tuned/README.md b/l40_squeezenet_tuned/README.md new file mode 100644 index 0000000..34745f7 --- /dev/null +++ b/l40_squeezenet_tuned/README.md @@ -0,0 +1,8 @@ +This is a model from + +https://github.com/onnx/models/tree/main/vision/classification/squeezenet + + +It is designed to run on embedded devices, but it's a good benchmark for a "fast" GPU, where we want to see fast inferences with reasonably sized inputs. The weights are small, hence probably not a good candidate if the load/unload times are critical. + +Warning: the compilation with TVM 0.6 throw an out of resources errors. diff --git a/l40_squeezenet_tuned/compile_tuned.sh b/l40_squeezenet_tuned/compile_tuned.sh new file mode 100755 index 0000000..28be2ea --- /dev/null +++ b/l40_squeezenet_tuned/compile_tuned.sh @@ -0,0 +1,12 @@ +#!/bin/bash +TUNING=$(ls tuning* --sort=time -1 | head -n1) + +set -x +python3 -m tvm.driver.tvmc compile \ + --target cuda + --target-cuda-arch sm_89 \ + --output model.tar \ + --tuning-records $TUNING \ + squeezenet1.1-7.onnx $@ \ + +tar -xvf model.tar diff --git a/l40_squeezenet_tuned/download.sh b/l40_squeezenet_tuned/download.sh new file mode 100755 index 0000000..fea6fa3 --- /dev/null +++ b/l40_squeezenet_tuned/download.sh @@ -0,0 +1,7 @@ +#!/bin/bash +#wget https://github.com/onnx/models/blob/main/vision/classification/squeezenet/model/squeezenet1.0-12-int8.onnx +wget https://github.com/onnx/models/raw/main/vision/classification/squeezenet/model/squeezenet1.1-7.onnx +#wget https://github.com/onnx/models/raw/main/vision/classification/squeezenet/model/squeezenet1.0-12-int8.tar.gz +#wget https://github.com/onnx/models/raw/main/vision/classification/squeezenet/model/squeezenet1.1-7.tar.gz +#tar xvzf squeezenet1.0-12-int8.tar.gz +#tar xvzf squeezenet1.1-7.tar.gz diff --git a/l40_squeezenet_tuned/metadata.json b/l40_squeezenet_tuned/metadata.json new file mode 100644 index 0000000..5bfe528 --- /dev/null +++ b/l40_squeezenet_tuned/metadata.json @@ -0,0 +1,16 @@ +{ + "load_time": 1000000000, + "exec_time": [1000000,2000000,4000000,8000000], + "weights_size": 100000000, + "workspace_size": 500000000, + "input_name" : "input", + "output_name" : "output", + "input_shape": [1,3,224,224], + "output_shape": [1,1000], + "input_type": "FP32", + "output_type": "FP32", + "device": "CUDA", + "model" : "a100", + "architecture" : "CUDA_80" + +} diff --git a/l40_squeezenet_tuned/model2.tar b/l40_squeezenet_tuned/model2.tar new file mode 100644 index 0000000..dded694 Binary files /dev/null and b/l40_squeezenet_tuned/model2.tar differ diff --git a/l40_squeezenet_tuned/tune.sh b/l40_squeezenet_tuned/tune.sh new file mode 100755 index 0000000..a03e4ba --- /dev/null +++ b/l40_squeezenet_tuned/tune.sh @@ -0,0 +1,12 @@ +#!/bin/bash +source ../../scripts/activate_venv.sh + + + + +set -x +python3 -m -m tvm.driver.tvmc tune \ + --target "cuda" \ + --target-cuda-arch 'sm_89' \ + --output tuning.$(date --iso-8601=minutes).json \ + squeezenet1.1-7.onnx $@ \ diff --git a/l40_squeezenet_tuned/tuning.2023-07-04T21:17+02:00.json b/l40_squeezenet_tuned/tuning.2023-07-04T21:17+02:00.json new file mode 100644 index 0000000..c2158fa --- /dev/null +++ b/l40_squeezenet_tuned/tuning.2023-07-04T21:17+02:00.json @@ -0,0 +1,990 @@ +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 654927, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 3, 37, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.20193052291870117, 1688498232.5541954], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 919106, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 4]], ["tile_y", "sp", [-1, 3, 1, 37]], ["tile_x", "sp", [-1, 1, 37, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.13970398902893066, 1688498232.554215], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 683602, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 37, 1, 3]], ["tile_x", "sp", [-1, 1, 1, 37]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.2006978988647461, 1688498232.6051571], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 448066, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 1, 37, 1]], ["tile_x", "sp", [-1, 3, 1, 37]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.12331771850585938, 1688498232.6051726], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 779682, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 16]], ["tile_y", "sp", [-1, 3, 1, 1]], ["tile_x", "sp", [-1, 1, 3, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1.8558616119880874e-05], 0, 3.756706476211548, 1688498245.5951643], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 274941, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 1, 1, 37]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.000746845901107011], 0, 3.932429552078247, 1688498246.9839747], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 676096, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 3, 37, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.1712310970696107e-05], 0, 3.2483012676239014, 1688498249.8293145], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 300972, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 111]], ["tile_x", "sp", [-1, 1, 1, 111]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.19741201400756836, 1688498234.8360877], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 492035, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 3, 1, 1]], ["tile_x", "sp", [-1, 1, 3, 37]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00011208707720716327], 0, 4.719771385192871, 1688498252.7747285], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 335836, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 1, 3, 37]], ["tile_x", "sp", [-1, 1, 1, 3]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005372089477711243], 0, 3.6238317489624023, 1688498255.7718322], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 653331, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 3, 1, 1]], ["tile_x", "sp", [-1, 1, 37, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[7.205313786916527e-06], 0, 3.1426734924316406, 1688498258.563], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 421581, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 8]], ["tile_y", "sp", [-1, 37, 1, 3]], ["tile_x", "sp", [-1, 1, 1, 3]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.017018671576271186], 0, 8.162474632263184, 1688498260.0927522], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 980331, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 1, 37, 1]], ["tile_x", "sp", [-1, 1, 1, 3]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.772565048206978e-05], 0, 4.825537443161011, 1688498263.062176], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 293918, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 1, 37, 3]], ["tile_x", "sp", [-1, 37, 1, 3]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.12137675285339355, 1688498239.0655603], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 526178, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 1, 111, 1]], ["tile_x", "sp", [-1, 3, 37, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.12246894836425781, 1688498239.0655732], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 103471, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 111]], ["tile_x", "sp", [-1, 1, 1, 37]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.1177067756652832, 1688498239.0655813], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 529380, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 1]], ["tile_y", "sp", [-1, 1, 3, 37]], ["tile_x", "sp", [-1, 1, 1, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0014734457871559633], 0, 3.5653297901153564, 1688498266.0215259], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 495302, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 2]], ["tile_y", "sp", [-1, 1, 111, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[2.4597490302356466e-05], 0, 4.586925268173218, 1688498268.932281], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 142900, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 37, 3, 1]], ["tile_x", "sp", [-1, 37, 1, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.12026834487915039, 1688498239.065595], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 563090, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 2]], ["tile_y", "sp", [-1, 1, 1, 111]], ["tile_x", "sp", [-1, 37, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.11997866630554199, 1688498239.0656025], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 845794, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 32]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 37, 3, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688498242.3004296], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 90590, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 2]], ["tile_y", "sp", [-1, 1, 37, 1]], ["tile_x", "sp", [-1, 111, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.11998343467712402, 1688498242.3004525], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 848417, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 1]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 3, 37, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1.0724751167555411e-05], 0, 3.884934186935425, 1688498271.8191824], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 255808, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 37, 3, 1]], ["tile_x", "sp", [-1, 1, 3, 37]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.12046432495117188, 1688498242.3004642], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 83512, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 37, 1, 1]], ["tile_x", "sp", [-1, 1, 3, 37]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.12111067771911621, 1688498242.300471], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 668826, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 37, 1, 3]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002373051892526795], 0, 4.019995927810669, 1688498274.7628555], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 790671, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 1, 1, 37]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[2.927991716085307e-05], 0, 4.045037269592285, 1688498277.6568491], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 790766, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 37, 3, 1]], ["tile_x", "sp", [-1, 1, 1, 37]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.11942386627197266, 1688498242.300482], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 76298, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 1]], ["tile_y", "sp", [-1, 1, 1, 37]], ["tile_x", "sp", [-1, 1, 111, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.12029767036437988, 1688498242.300491], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1006677, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 3, 1, 37]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00026513761907883955], 0, 10.693426132202148, 1688498280.6432536], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 705364, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 3, 1, 37]], ["tile_x", "sp", [-1, 1, 1, 37]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.12140750885009766, 1688498242.3005013], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 69462, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 16]], ["tile_y", "sp", [-1, 37, 1, 3]], ["tile_x", "sp", [-1, 111, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.1689283847808838, 1688498242.300511], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 124451, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 1, 1, 37]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0009671184013539652], 0, 2.77351975440979, 1688498281.9942715], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 660459, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 1, 37, 1]], ["tile_x", "sp", [-1, 1, 37, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.19925475120544434, 1688498242.3005204], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 204654, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 1, 111, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1.9255013491576784e-05], 0, 3.4273130893707275, 1688498284.9301043], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 309098, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 4]], ["tile_y", "sp", [-1, 1, 1, 111]], ["tile_x", "sp", [-1, 37, 3, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.16754722595214844, 1688498242.300531], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 266640, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_y", "sp", [-1, 1, 37, 1]], ["tile_x", "sp", [-1, 1, 37, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.12284350395202637, 1688498242.3005378], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 190547, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 1, 1, 37]], ["tile_x", "sp", [-1, 3, 1, 37]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.17036223411560059, 1688498242.300545], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 495645, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 37]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[6.239975154987052e-05], 0, 4.536658525466919, 1688498287.8754647], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 431599, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 37, 1, 1]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.005938563958579882], 0, 3.6606080532073975, 1688498289.2723825], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 815199, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 1, 111, 1]], ["tile_x", "sp", [-1, 1, 3, 37]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.12856769561767578, 1688498242.300555], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 943072, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 1, 37, 3]], ["tile_x", "sp", [-1, 3, 1, 37]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.1212160587310791, 1688498242.3005621], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 695431, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 16]], ["tile_y", "sp", [-1, 1, 37, 1]], ["tile_x", "sp", [-1, 37, 3, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.12395739555358887, 1688498242.300569], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 179269, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 1, 37, 1]], ["tile_x", "sp", [-1, 37, 3, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.12181949615478516, 1688498242.3005764], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 3, 224, 224], "float32"], ["TENSOR", [64, 3, 3, 3], "float32"], [2, 2], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 105942, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 3, 1, 37]], ["tile_x", "sp", [-1, 1, 3, 37]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.11983799934387207, 1688498242.3005853], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 196323, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 1, 5, 11]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00020785029457161546], 0, 3.604884386062622, 1688498298.5645204], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 9128, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[8.009079029063996e-06], 0, 3.1074483394622803, 1688498301.347601], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 96569, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 1, 1, 11]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00033948550179438463], 0, 4.1305835247039795, 1688498304.3075051], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 170752, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 2]], ["tile_y", "sp", [-1, 1, 5, 11]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.160998787001671e-05], 0, 3.8346803188323975, 1688498307.1377125], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7727, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 11]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0068286743135593225], 0, 4.742257356643677, 1688498310.1379325], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 144724, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 1, 11, 1]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.5045124596242426e-05], 0, 3.610399007797241, 1688498313.067188], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 354586, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 5]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0010579859593442622], 0, 7.194362640380859, 1688498316.0065646], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 359603, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 11, 1, 1]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[8.089682598864378e-05], 0, 5.8730998039245605, 1688498318.9363127], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 375056, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 1, 11, 5]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.028489351272583008, 1688498294.3462224], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 357619, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 1, 5, 11]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.9992019668607705e-05], 0, 4.007643938064575, 1688498321.8857412], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 166453, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 5]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.000983051799265606], 0, 5.822930335998535, 1688498324.8135028], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 309838, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 2]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 1, 1, 5]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1.0373603050137888e-05], 0, 5.839989185333252, 1688498327.6480398], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 14205, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 1, 1, 5]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00010138495994962217], 0, 3.5595550537109375, 1688498330.6053808], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 348674, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 11, 1, 5]], ["tile_x", "sp", [-1, 1, 5, 11]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0503239631652832, 1688498294.3462467], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 162256, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 1, 11, 5]], ["tile_x", "sp", [-1, 5, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[2.4730760501139658e-05], 0, 3.969635248184204, 1688498333.4948416], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 233116, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[9.41568065710234e-06], 0, 3.2064695358276367, 1688498336.2923527], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 361068, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 11]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[9.635145625949701e-06], 0, 5.088453054428101, 1688498339.1912086], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 297659, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 2]], ["tile_y", "sp", [-1, 1, 55, 1]], ["tile_x", "sp", [-1, 55, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02556014060974121, 1688498294.346261], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 208736, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 1, 11, 5]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.0758480932026399e-05], 0, 3.149923086166382, 1688498342.0133636], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 79971, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 11]], ["tile_x", "sp", [-1, 1, 5, 11]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.004217022750656168], 0, 5.048353910446167, 1688498344.979161], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 34890, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 1, 5, 11]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.0879525418152625e-05], 0, 3.281175374984741, 1688498347.9037201], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 207446, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00015340941682509505], 0, 3.553595542907715, 1688498350.8297992], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 99229, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 5, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.005687665201413427], 0, 4.056858539581299, 1688498353.8201725], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 84325, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 1, 11, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[5.530889636489775e-06], 0, 3.1497740745544434, 1688498356.6241527], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 36650, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 5, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.4087703663841834e-05], 0, 3.2988789081573486, 1688498359.4647849], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 315576, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 1, 55, 1]], ["tile_x", "sp", [-1, 55, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[7.934233333333333e-05], 0, 3.8075907230377197, 1688498362.3870237], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 190886, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005212465713822194], 0, 3.7431628704071045, 1688498365.358505], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 21724, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 11]], ["tile_x", "sp", [-1, 1, 11, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[8.297520263984026e-06], 0, 3.1413118839263916, 1688498368.1482468], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 275860, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 1, 1, 11]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[2.6929007130907924e-05], 0, 4.195104122161865, 1688498371.0471044], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 120795, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 11, 5]], ["tile_x", "sp", [-1, 5, 11, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.025555133819580078, 1688498294.346286], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 30102, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 11]], ["tile_x", "sp", [-1, 11, 5, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006182875342518178], 0, 3.677489757537842, 1688498374.023138], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 259988, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[7.433707086015585e-06], 0, 3.0622940063476562, 1688498376.802521], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 150677, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 5, 1, 1]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0011302232606232295], 0, 7.823357820510864, 1688498379.7009528], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 98547, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 55]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.022757291793823242, 1688498295.0306978], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 250464, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.022034645080566406, 1688498295.0307055], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 273554, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 1, 55, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.028304576873779297, 1688498295.0307133], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 334326, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 11, 5, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[9.564845233491102e-06], 0, 3.380577564239502, 1688498382.5825262], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 167858, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 11, 5]], ["tile_x", "sp", [-1, 1, 11, 5]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.0272982120513916, 1688498295.0307248], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 163061, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 11, 1, 1]], ["tile_x", "sp", [-1, 55, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.03646519032142857], 0, 7.449803590774536, 1688498384.328542], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 231377, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 11, 1, 1]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00723764133632287], 0, 6.869408369064331, 1688498387.3562746], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 115202, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 1, 11, 5]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.027642011642456055, 1688498295.8125348], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 153456, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.4062354314574833e-05], 0, 3.378880262374878, 1688498390.2705097], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 275155, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 1, 11, 5]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[6.234226042192782e-05], 0, 4.180060625076294, 1688498393.2306826], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 163636, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[2.1741631594056295e-05], 0, 3.8397560119628906, 1688498396.1239202], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 55, 55], "float32"], ["TENSOR", [16, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 112265, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 1, 55, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.12122201919555664, 1688498295.8125467], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 362892, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 5, 11]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[4.123855236290273e-05], 0, 2.965224266052246, 1688498409.2654734], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 288035, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 64]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 1, 11, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[3.860302421962031e-06], 0, 3.6972222328186035, 1688498411.9944894], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 472576, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0030865890076628355], 0, 7.421973466873169, 1688498414.9670768], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13252, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 1, 1, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0007888720309072782], 0, 4.8970255851745605, 1688498417.9659653], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 628751, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 1]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 55, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.023580551147460938, 1688498401.4079058], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 618047, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 4]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 1, 11, 5]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04384446144104004, 1688498401.4079213], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 92074, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 1, 55, 1]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[4.884579672752643e-06], 0, 2.9677460193634033, 1688498420.6938207], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 71636, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 11, 5, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[8.317475906366593e-06], 0, 3.147853374481201, 1688498423.4830256], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 384357, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 55]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.024011611938476562, 1688498401.4079332], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 544129, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.0282785392245266e-05], 0, 3.7068867683410645, 1688498426.37159], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 245614, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 32]], ["tile_y", "sp", [-1, 1, 11, 5]], ["tile_x", "sp", [-1, 1, 11, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.393502005085812e-05], 0, 3.2728052139282227, 1688498429.2286787], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 560426, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 4]], ["tile_y", "sp", [-1, 1, 1, 55]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.9705929376832292e-05], 0, 5.020293235778809, 1688498432.105836], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 137554, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 1, 11, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1.0668290668744531e-05], 0, 3.303649425506592, 1688498434.9850543], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 147476, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 1, 11, 5]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005274009880873594], 0, 4.721071004867554, 1688498437.8891308], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 340638, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001083789321931183], 0, 3.5385870933532715, 1688498440.8154178], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 294094, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 11, 1, 5]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.05494499206542969, 1688498401.4079516], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 475093, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 8]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 5, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[2.0598913992782793e-05], 0, 3.769571542739868, 1688498443.7465386], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 507827, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 1, 1, 5]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00017216676380728556], 0, 5.084853410720825, 1688498446.6678448], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 382726, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 11]], ["tile_x", "sp", [-1, 1, 1, 11]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.4976263245331738e-05], 0, 3.297346830368042, 1688498449.532872], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 263472, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[3.879217358021148e-06], 0, 2.9907279014587402, 1688498452.247678], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 117128, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 11, 1, 1]], ["tile_x", "sp", [-1, 5, 11, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0032936259522821578], 0, 10.356953382492065, 1688498455.1734018], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 187424, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 1, 11, 5]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04147052764892578, 1688498404.4018953], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 108598, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 11]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[2.5526895681255427e-05], 0, 3.435798406600952, 1688498458.070467], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 372465, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 11, 1, 1]], ["tile_x", "sp", [-1, 11, 5, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00014743663707498836], 0, 4.972824573516846, 1688498460.996772], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 131803, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 5, 1, 1]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1.8640924212621474e-05], 0, 3.290131092071533, 1688498463.887678], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 533581, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[5.7655163010118405e-06], 0, 3.7458600997924805, 1688498466.6170878], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 597971, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 4]], ["tile_y", "sp", [-1, 1, 5, 11]], ["tile_x", "sp", [-1, 1, 1, 11]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00020619394628422423], 0, 10.090957403182983, 1688498469.5401633], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 255630, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 1, 5, 11]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00017814246443190618], 0, 7.310332775115967, 1688498472.4723053], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 397885, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 55, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[2.7834179509508093e-06], 0, 2.8010470867156982, 1688498475.0127778], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 153028, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 5, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.003805222817966903], 0, 4.942160606384277, 1688498478.0259113], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 268483, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 11]], ["tile_x", "sp", [-1, 5, 11, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[9.349152817568224e-06], 0, 3.398221015930176, 1688498480.8383322], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 442267, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 5, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1.7226642880740004e-05], 0, 3.1790225505828857, 1688498483.687547], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 498600, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 4]], ["tile_y", "sp", [-1, 1, 1, 55]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0012024844740796395], 0, 3.933156967163086, 1688498486.655059], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 539545, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 5, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.5878563323990976e-05], 0, 3.8553028106689453, 1688498489.5356858], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 128478, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005037211942423283], 0, 6.719749689102173, 1688498492.458031], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 545234, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 11, 1, 5]], ["tile_x", "sp", [-1, 11, 5, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688498406.8966389], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 566418, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 1, 1]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 11, 5, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688498406.8967054], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 394590, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 11, 5, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[9.55818653625551e-05], 0, 4.740500450134277, 1688498495.386671], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 229646, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 11, 1, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.008657000139784946], 0, 5.584510803222656, 1688498498.4391708], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 427380, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 8]], ["tile_y", "sp", [-1, 1, 1, 55]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02227163314819336, 1688498406.8967285], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 246388, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 5, 11, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[9.148498310195722e-05], 0, 5.045528411865234, 1688498501.4646962], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 293312, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 11, 1, 5]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.023918867111206055, 1688498406.8967416], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 41789, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 2]], ["tile_y", "sp", [-1, 5, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.000448795692177351], 0, 3.3474481105804443, 1688498504.4288642], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 122826, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 1, 11, 1]], ["tile_x", "sp", [-1, 1, 11, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[8.23302744560101e-06], 0, 3.1020779609680176, 1688498507.2228093], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 118340, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 55, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[3.678225798612254e-06], 0, 2.9379465579986572, 1688498509.9022326], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2355385, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 1, 55, 1]], ["tile_x", "sp", [-1, 1, 55, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05724000930786133, 1688498510.7501466], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 515509, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.004993884945273632], 0, 2.195068359375, 1688498521.9765003], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2251181, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 55]], ["tile_x", "sp", [-1, 11, 1, 5]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03272390365600586, 1688498511.647268], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 804149, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 1]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 1, 11, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[5.8275912136925697e-05], 0, 3.945467948913574, 1688498524.8951347], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1460945, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0016493018517382413], 0, 3.701859951019287, 1688498527.8512251], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 72226, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 8]], ["tile_y", "sp", [-1, 1, 11, 5]], ["tile_x", "sp", [-1, 11, 5, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.06804132461547852, 1688498511.8232298], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 959962, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 11, 1, 5]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0007473931331786543], 0, 5.975722551345825, 1688498530.8296914], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 440550, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 11]], ["tile_x", "sp", [-1, 5, 11, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003505905723584291], 0, 3.8741328716278076, 1688498533.770918], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 574295, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 1, 11, 5]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[2.3403160465973604e-05], 0, 3.5422329902648926, 1688498536.6695316], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 722333, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 1]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 1, 1, 5]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003999604104218362], 0, 4.649348258972168, 1688498539.6489677], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 72739, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 16]], ["tile_y", "sp", [-1, 5, 1, 1]], ["tile_x", "sp", [-1, 1, 11, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.6718663024409803e-05], 0, 3.379319667816162, 1688498542.5580778], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1112752, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 55]], ["tile_x", "sp", [-1, 1, 11, 5]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.003668227197802198], 0, 3.171776533126831, 1688498543.9394894], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1771708, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 1, 11, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005674385766654917], 0, 7.924063444137573, 1688498546.9261978], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 853902, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 2]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 1, 11, 5]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.051308631896972656, 1688498515.738708], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1631864, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 32]], ["tile_y", "sp", [-1, 11, 1, 1]], ["tile_x", "sp", [-1, 1, 5, 11]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.034539944344827586], 0, 2.6831347942352295, 1688498548.6472135], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1978184, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688498520.718845], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1791246, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 11]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[5.3976306472209155e-05], 0, 7.434755802154541, 1688498551.570705], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1956429, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 8]], ["tile_y", "sp", [-1, 11, 1, 5]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0728191985625], 0, 3.2678515911102295, 1688498553.930556], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 439520, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 5, 11, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[3.258448322670604e-05], 0, 3.762192487716675, 1688498556.911249], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1575487, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 8]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.01024698], 0, 2.692213773727417, 1688498558.3849819], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1935226, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 2]], ["tile_y", "sp", [-1, 1, 5, 11]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05424308776855469, 1688498520.7188706], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 42779, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.01846486149090909], 0, 3.2054250240325928, 1688498559.9761379], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 779692, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 11, 1, 1]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00011678621957255343], 0, 4.641635894775391, 1688498562.8327777], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2515396, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688498520.718935], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2385515, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 64]], ["tile_y", "sp", [-1, 1, 5, 11]], ["tile_x", "sp", [-1, 1, 5, 11]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.008170812585365854], 0, 5.994490623474121, 1688498564.261299], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 590712, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_y", "sp", [-1, 1, 55, 1]], ["tile_x", "sp", [-1, 5, 11, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.0432889461517334, 1688498520.7189457], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1692898, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 1, 11, 5]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[2.4273098894255594e-05], 0, 3.4401092529296875, 1688498567.2219071], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2229201, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 11, 1, 5]], ["tile_x", "sp", [-1, 11, 1, 5]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.09411025047302246, 1688498520.7189548], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2189431, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008182769197562215], 0, 5.960327386856079, 1688498570.165938], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 356945, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 1, 1, 5]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00015132274207465765], 0, 3.668302059173584, 1688498573.0977364], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1843240, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 1, 11, 5]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[4.171686558272632e-05], 0, 4.269984245300293, 1688498576.0530307], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1600132, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 1, 11, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[3.543647768302138e-05], 0, 3.3712522983551025, 1688498578.9539082], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 271958, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 11, 1, 5]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.12179899215698242, 1688498520.7189665], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2233042, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 8]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.08741950988769531, 1688498520.7189732], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1513327, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 55]], ["tile_x", "sp", [-1, 11, 5, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.03537760975862069], 0, 3.5322012901306152, 1688498580.7177432], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 194398, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 11, 1, 5]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.259180264915885e-05], 0, 3.7238144874572754, 1688498583.7022402], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2053478, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 5, 11]], ["tile_x", "sp", [-1, 5, 11, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[6.654088551798352e-05], 0, 4.426049709320068, 1688498586.6359637], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 703739, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 1, 11, 5]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[7.123920757730359e-05], 0, 3.9007396697998047, 1688498589.5534115], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1777750, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 1, 11, 5]], ["tile_x", "sp", [-1, 11, 1, 5]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688498520.7325354], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1867499, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 1]], ["tile_y", "sp", [-1, 1, 55, 1]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.002168734463203463], 0, 3.3009133338928223, 1688498590.9427314], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1543671, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 1, 1, 11]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0012247118103186647], 0, 4.304276943206787, 1688498593.8937361], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1558804, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 5, 11, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0785379409790039, 1688498520.7325468], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 396059, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 64]], ["tile_y", "sp", [-1, 11, 1, 5]], ["tile_x", "sp", [-1, 1, 11, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.003222073569131833], 0, 2.2589330673217773, 1688498595.2610497], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2315744, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 11, 5]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[8.45351048304766e-05], 0, 6.939215898513794, 1688498598.1789348], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2541863, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 55, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.3558930351721583e-05], 0, 6.396589517593384, 1688498601.0756269], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 403684, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 8]], ["tile_x", "sp", [-1, 28, 1, 14]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00861825535042735], 0, 5.2602550983428955, 1688498609.715724], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 761816, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 1]], ["tile_x", "sp", [-1, 2, 1, 56]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.320184180565265e-05], 0, 5.801947593688965, 1688498612.6607885], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 395242, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 1]], ["tile_x", "sp", [-1, 28, 1, 4]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[2.408313352790389e-05], 0, 4.89197564125061, 1688498615.497375], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 88204, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00013517645038746632], 0, 4.064581394195557, 1688498618.4286842], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 305649, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 4]], ["tile_x", "sp", [-1, 1, 49, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[9.266056379168799e-06], 0, 4.272900581359863, 1688498621.3048308], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 483470, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 4]], ["tile_x", "sp", [-1, 28, 1, 4]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.004351301108695652], 0, 3.4286136627197266, 1688498622.67396], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 614941, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 4]], ["tile_x", "sp", [-1, 7, 1, 56]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.00012856221676924308], 0, 5.269036531448364, 1688498625.6006937], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 634333, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 4]], ["tile_x", "sp", [-1, 14, 2, 7]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.00029285044863076637], 0, 5.776642322540283, 1688498628.545695], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 506046, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 2]], ["tile_x", "sp", [-1, 1, 56, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[8.192564902119128e-06], 0, 3.7613344192504883, 1688498631.2448368], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 270061, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 4, 28, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1.201406050989839e-05], 0, 4.034353733062744, 1688498634.0846477], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 528496, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 4]], ["tile_x", "sp", [-1, 2, 1, 196]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.007648646694656488], 0, 3.0372238159179688, 1688498635.537208], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 388628, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 2]], ["tile_x", "sp", [-1, 7, 56, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[9.0120518184119e-06], 0, 4.105790853500366, 1688498638.3966014], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 178001, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 1, 1]], ["tile_x", "sp", [-1, 8, 2, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[4.135983165105478e-05], 0, 4.252705335617065, 1688498641.2889557], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 529840, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 4]], ["tile_x", "sp", [-1, 28, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0050101008606965175], 0, 3.626131296157837, 1688498642.723663], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 144012, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 2]], ["tile_x", "sp", [-1, 4, 4, 49]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.45954108238220215, 1688498605.7800791], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 283697, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 2]], ["tile_x", "sp", [-1, 4, 28, 7]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.3997211456298828, 1688498605.7800956], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 756959, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 14, 2, 14]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00024083294400127633], 0, 9.218077898025513, 1688498645.4858963], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 760166, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 4]], ["tile_x", "sp", [-1, 4, 7, 28]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00026952466737853713], 0, 8.92261266708374, 1688498648.2741978], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 238508, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 2]], ["tile_x", "sp", [-1, 7, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1.4889472910148825e-05], 0, 4.903910398483276, 1688498651.1081357], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 441522, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 1]], ["tile_x", "sp", [-1, 16, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.5215786107618688e-05], 0, 3.8209335803985596, 1688498653.9489474], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 88479, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 64, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.4526411748355414e-05], 0, 3.9337964057922363, 1688498656.845793], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 574084, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 2, 98, 4]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.4020206928253174, 1688498608.4208305], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 630676, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 1]], ["tile_x", "sp", [-1, 196, 1, 4]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.011692958408759124], 0, 4.964645147323608, 1688498659.9364283], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 226947, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 4]], ["tile_x", "sp", [-1, 4, 1, 14]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[4.952028853462317e-05], 0, 2.7997400760650635, 1688498661.3250105], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 521039, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 8]], ["tile_x", "sp", [-1, 7, 1, 14]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00015781627563262425], 0, 4.623074769973755, 1688498664.1783733], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 206520, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 2]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[2.5019265817355807e-05], 0, 4.3196797370910645, 1688498667.0824783], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 361830, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 2]], ["tile_x", "sp", [-1, 28, 2, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0001663888451926056], 0, 5.609241008758545, 1688498670.0082607], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 51804, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 4]], ["tile_x", "sp", [-1, 14, 4, 14]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003937301280175567], 0, 5.850648880004883, 1688498672.9511554], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 469252, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 1, 8, 98]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[3.263853090699018e-05], 0, 4.030440807342529, 1688498675.8887863], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 653800, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 2]], ["tile_x", "sp", [-1, 7, 112, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1.2271070154730646e-05], 0, 3.970503091812134, 1688498678.6791432], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 549701, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 1, 1]], ["tile_x", "sp", [-1, 1, 14, 8]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00011149842170897285], 0, 5.1167073249816895, 1688498681.455054], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 519441, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 8]], ["tile_x", "sp", [-1, 7, 1, 8]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006993318566433566], 0, 2.7298545837402344, 1688498682.825766], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 739408, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 2]], ["tile_x", "sp", [-1, 1, 14, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.1933874047079838e-05], 0, 3.8073461055755615, 1688498685.5669663], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 262333, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 7, 2, 56]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0004045225931544146], 0, 2.908998966217041, 1688498686.9316702], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 371796, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 2, 1]], ["tile_x", "sp", [-1, 2, 28, 7]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[6.696487932834885e-05], 0, 4.562165260314941, 1688498689.8970342], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 667164, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 2]], ["tile_x", "sp", [-1, 7, 7, 8]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[7.942262756014096e-05], 0, 4.92458701133728, 1688498692.7270682], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 359828, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 4]], ["tile_x", "sp", [-1, 7, 112, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.0563373981572617e-05], 0, 4.075164556503296, 1688498695.5498412], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 668997, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 8, 1]], ["tile_x", "sp", [-1, 2, 4, 14]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[2.695627333016724e-05], 0, 4.2140724658966064, 1688498698.4731987], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 574533, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 4]], ["tile_x", "sp", [-1, 7, 1, 7]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0007774858393983503], 0, 4.866721153259277, 1688498701.4078739], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 459739, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 1]], ["tile_x", "sp", [-1, 1, 16, 7]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.4127673346873483e-05], 0, 3.8594017028808594, 1688498704.2694423], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 712237, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 1]], ["tile_x", "sp", [-1, 2, 98, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1.2650561985157851e-05], 0, 3.8784945011138916, 1688498707.1323893], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 282676, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 1]], ["tile_x", "sp", [-1, 1, 8, 7]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1.8550944494546853e-05], 0, 3.961005449295044, 1688498709.9441285], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 98938, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 8]], ["tile_x", "sp", [-1, 49, 8, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002920219100940666], 0, 4.699483633041382, 1688498712.890079], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 800588, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 8]], ["tile_x", "sp", [-1, 4, 98, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[8.722131396319867e-06], 0, 3.906714677810669, 1688498715.7587411], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 16, 55, 55], "float32"], ["TENSOR", [64, 16, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 58264, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 4]], ["tile_x", "sp", [-1, 1, 2, 196]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.001366473430412371], 0, 4.0596442222595215, 1688498718.6698258], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 342720, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[2.784848705376818e-05], 0, 2.281390428543091, 1688498730.6613843], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 273756, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 2]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 1, 55, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.024573326110839844, 1688498720.4894187], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 414842, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 11]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.014835029561645e-05], 0, 6.931919813156128, 1688498733.4991302], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 263213, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 11, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[4.8829253820737955e-06], 0, 3.0046956539154053, 1688498736.221513], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 151923, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 2]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[7.546452206537542e-05], 0, 3.431384563446045, 1688498739.1851778], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 214946, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.036031484603881836, 1688498723.6231673], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 217252, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 55]], ["tile_x", "sp", [-1, 55, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.01618261914516129], 0, 2.658848762512207, 1688498740.713469], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 303867, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 1, 5, 11]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00693111655862069], 0, 3.310091257095337, 1688498742.169966], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3835, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 5, 1, 11]], ["tile_x", "sp", [-1, 1, 11, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00023788686334120422], 0, 3.4020657539367676, 1688498745.1435716], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 321856, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 1, 11, 5]], ["tile_x", "sp", [-1, 1, 5, 11]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.06138896942138672, 1688498723.6231863], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13570, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 1, 55, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00013577310033641716], 0, 3.3839194774627686, 1688498748.0799158], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 164217, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 11, 5, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688498729.439188], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 32636, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 1, 5, 1]], ["tile_x", "sp", [-1, 11, 1, 5]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00042482704809461235], 0, 3.467489004135132, 1688498751.0460577], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 252875, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 55, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0014771238966026588], 0, 2.0229835510253906, 1688498752.4248774], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 105705, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 11]], ["tile_x", "sp", [-1, 1, 1, 11]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[5.916690942909761e-05], 0, 4.230804443359375, 1688498755.3467627], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 12655, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 1, 1, 5]], ["tile_x", "sp", [-1, 1, 11, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.599540124144356e-05], 0, 3.1205241680145264, 1688498758.2217815], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 65236, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04159140586853027, 1688498729.4392228], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 385956, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 5, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688498729.4421704], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 80674, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[7.182453339886511e-05], 0, 3.233731508255005, 1688498761.190636], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 384440, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 55, 1]], ["tile_x", "sp", [-1, 1, 5, 11]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00021179216006775352], 0, 1.7069640159606934, 1688498762.506814], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 305453, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 5, 11, 1]], ["tile_x", "sp", [-1, 5, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[4.137312405227067e-05], 0, 3.7273406982421875, 1688498765.4257019], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 252915, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 11, 1, 5]], ["tile_x", "sp", [-1, 55, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.022361278533935547, 1688498729.4421883], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 368448, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 55]], ["tile_x", "sp", [-1, 5, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0037106697862068967], 0, 4.432180881500244, 1688498768.4449677], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4763, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 1, 55, 1]], ["tile_x", "sp", [-1, 1, 55, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.021625041961669922, 1688498729.4421983], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 188394, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 1, 11, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[8.758622792827687e-06], 0, 3.1679344177246094, 1688498771.2567272], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 28582, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 55, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[3.094738447982028e-05], 0, 3.372443199157715, 1688498774.1716182], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 12560, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 1, 11, 1]], ["tile_x", "sp", [-1, 1, 11, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.4403939525749733e-05], 0, 3.1342055797576904, 1688498777.0789447], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 413306, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.7507810813622805e-05], 0, 6.478366851806641, 1688498779.9670749], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 305958, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 2]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008975217001114827], 0, 5.316107273101807, 1688498782.9068537], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 262842, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 11, 5, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05991172790527344, 1688498729.4422133], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 360472, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 1, 11, 5]], ["tile_x", "sp", [-1, 55, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0020534299885496183], 0, 10.470453262329102, 1688498785.912212], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 337787, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 1, 11, 5]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04268908500671387, 1688498729.442222], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 304125, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 5, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 55]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0012283599152671757], 0, 4.374558925628662, 1688498788.8472571], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 82716, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 1, 11, 5]], ["tile_x", "sp", [-1, 55, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0011283329539427775], 0, 4.18805456161499, 1688498791.7897718], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 63569, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 1, 55, 1]], ["tile_x", "sp", [-1, 5, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.12064123153686523, 1688498729.442233], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 22379, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 55]], ["tile_x", "sp", [-1, 5, 11, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006168175631438382], 0, 3.6938633918762207, 1688498794.7812471], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 64071, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 2]], ["tile_y", "sp", [-1, 1, 11, 1]], ["tile_x", "sp", [-1, 11, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.027840852737426758, 1688498729.4422414], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 423399, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 5, 1, 1]], ["tile_x", "sp", [-1, 1, 5, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.5807642460461187e-05], 0, 10.871247291564941, 1688498797.6471949], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 10751, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 55, 1, 1]], ["tile_x", "sp", [-1, 55, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.005675267176056338], 0, 3.737914562225342, 1688498800.6535373], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 61254, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 1, 11, 1]], ["tile_x", "sp", [-1, 5, 1, 11]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.023736953735351562, 1688498729.4422505], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 284783, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 2]], ["tile_y", "sp", [-1, 1, 55, 1]], ["tile_x", "sp", [-1, 1, 1, 11]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.1839449405670166, 1688498729.4422572], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 30307, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 5, 1, 1]], ["tile_x", "sp", [-1, 1, 11, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[4.829487007755667e-05], 0, 3.361032009124756, 1688498803.6190145], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 114737, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 1, 5, 11]], ["tile_x", "sp", [-1, 1, 1, 11]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0013360296074380166], 0, 3.8268516063690186, 1688498806.5703413], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 161910, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 11, 1, 1]], ["tile_x", "sp", [-1, 5, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[8.240543058050609e-05], 0, 3.5193819999694824, 1688498809.4981177], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 55, 55], "float32"], ["TENSOR", [16, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 156436, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 2]], ["tile_y", "sp", [-1, 11, 5, 1]], ["tile_x", "sp", [-1, 5, 11, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.000774652353617633], 0, 6.532885789871216, 1688498812.483152], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 330122, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 1, 9, 3]], ["tile_x", "sp", [-1, 3, 3, 3]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.024089574813842773, 1688498813.228529], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 816818, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 9, 3, 1]], ["tile_x", "sp", [-1, 1, 27, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[3.880700612423447e-05], 0, 3.7474822998046875, 1688498826.0249462], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 804925, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 1, 3, 3]], ["tile_x", "sp", [-1, 1, 3, 9]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[5.980170825257193e-05], 0, 4.804867267608643, 1688498828.9354432], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3641, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 3, 3, 1]], ["tile_x", "sp", [-1, 27, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[8.51298186440678e-05], 0, 3.454282283782959, 1688498831.8483906], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 860201, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 3, 9, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[8.069280281342418e-06], 0, 4.083980083465576, 1688498834.6906753], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 125547, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 3, 1, 1]], ["tile_x", "sp", [-1, 9, 1, 3]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006155933146239022], 0, 3.8703861236572266, 1688498837.6306634], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 466275, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 9, 3, 1]], ["tile_x", "sp", [-1, 1, 1, 9]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[3.7226559192491756e-05], 0, 3.5416784286499023, 1688498840.552087], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 612438, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 9]], ["tile_x", "sp", [-1, 9, 3, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008395356859074364], 0, 3.664611339569092, 1688498843.5347736], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 963201, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[4.5860815481651375e-05], 0, 3.7707016468048096, 1688498846.4412], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 942111, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 27, 1, 1]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.000618383383306962], 0, 6.965534925460815, 1688498849.3078063], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 141126, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 9, 3, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[3.111548817955308e-05], 0, 3.234304189682007, 1688498852.2367082], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1041870, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 1, 1, 3]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.1650191458115241e-05], 0, 6.229884386062622, 1688498855.0596945], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 980505, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 1, 27, 1]], ["tile_x", "sp", [-1, 1, 9, 3]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.1397730347631248e-05], 0, 4.545963764190674, 1688498857.952147], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 752099, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 3, 1, 3]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[2.0145519322749708e-05], 0, 3.469590425491333, 1688498860.8747966], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 820022, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 27, 1, 1]], ["tile_x", "sp", [-1, 9, 1, 3]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688498823.228122], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 70204, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 1, 3, 3]], ["tile_x", "sp", [-1, 9, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00021178123679035005], 0, 3.4061334133148193, 1688498863.8065202], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 506498, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 9, 1, 3]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[2.510965449424869e-05], 0, 3.846216917037964, 1688498866.6923642], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 269259, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 3, 9, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1.2886114583076227e-05], 0, 3.4598910808563232, 1688498869.5828857], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 31291, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 1, 3, 9]], ["tile_x", "sp", [-1, 1, 9, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.122911868865594e-05], 0, 3.2362990379333496, 1688498872.4850652], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 398788, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 3, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 9]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[2.9239366222515874e-05], 0, 3.3186957836151123, 1688498875.382037], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 698947, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 3, 1, 1]], ["tile_x", "sp", [-1, 1, 3, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[9.132343894385553e-06], 0, 3.2649600505828857, 1688498878.2511938], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 422568, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 8]], ["tile_y", "sp", [-1, 3, 3, 1]], ["tile_x", "sp", [-1, 3, 1, 9]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.01021823368367347], 0, 4.276169061660767, 1688498879.6808789], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 822710, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 3, 1, 3]], ["tile_x", "sp", [-1, 3, 3, 3]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005246659912109376], 0, 8.217999935150146, 1688498882.6268651], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 131136, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 3, 1, 1]], ["tile_x", "sp", [-1, 3, 1, 9]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.000464955424364896], 0, 3.912717580795288, 1688498885.5970907], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 297020, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 27, 1, 1]], ["tile_x", "sp", [-1, 3, 3, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0065532178627450985], 0, 2.387773275375366, 1688498886.997599], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 669965, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 27, 1, 1]], ["tile_x", "sp", [-1, 1, 3, 9]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02320075035095215, 1688498823.228166], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 985459, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 3, 1, 9]], ["tile_x", "sp", [-1, 1, 1, 27]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688498823.2390234], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1043143, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 2]], ["tile_y", "sp", [-1, 1, 9, 1]], ["tile_x", "sp", [-1, 3, 1, 3]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.0182165546655433e-05], 0, 4.122369766235352, 1688498889.822388], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 248756, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 9, 1, 1]], ["tile_x", "sp", [-1, 9, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0026094386019417477], 0, 5.895251035690308, 1688498892.8191833], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 612835, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 27, 1, 1]], ["tile_x", "sp", [-1, 1, 9, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[8.918956356378555e-05], 0, 3.399470090866089, 1688498895.7565482], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 51483, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 27]], ["tile_x", "sp", [-1, 3, 3, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[9.045216011014948e-05], 0, 3.4833688735961914, 1688498898.6813226], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 35265, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 1, 27, 1]], ["tile_x", "sp", [-1, 3, 1, 3]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[3.026280645528764e-05], 0, 3.392127513885498, 1688498901.6138954], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 269139, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 9, 3, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[2.0759275860713723e-05], 0, 3.6007328033447266, 1688498904.4933305], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1013226, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 1, 3, 3]], ["tile_x", "sp", [-1, 1, 3, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[4.814923788324978e-06], 0, 3.544910430908203, 1688498907.1762426], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1035326, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 16]], ["tile_y", "sp", [-1, 1, 9, 1]], ["tile_x", "sp", [-1, 1, 3, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[8.42559221139716e-06], 0, 6.6301186084747314, 1688498910.0624435], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 960888, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 1, 3, 9]], ["tile_x", "sp", [-1, 3, 1, 9]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0018725336693735499], 0, 11.201998949050903, 1688498913.0137622], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 706355, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 1, 3, 3]], ["tile_x", "sp", [-1, 1, 1, 3]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[4.2475771982392876e-05], 0, 3.2749648094177246, 1688498915.9239092], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 556296, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 8]], ["tile_y", "sp", [-1, 1, 3, 3]], ["tile_x", "sp", [-1, 1, 1, 9]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008967281761111111], 0, 3.7223010063171387, 1688498918.9228764], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 380182, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 16]], ["tile_y", "sp", [-1, 3, 9, 1]], ["tile_x", "sp", [-1, 1, 1, 27]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0022220644702627937], 0, 5.737394094467163, 1688498921.8795877], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 309208, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 2]], ["tile_y", "sp", [-1, 3, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 9]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[3.500520173863537e-05], 0, 4.042525053024292, 1688498924.7837346], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 881697, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 1, 9, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[5.0750477808118055e-06], 0, 3.8906750679016113, 1688498927.5657725], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 965633, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 27, 1, 1]], ["tile_x", "sp", [-1, 9, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688498823.2469087], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 35280, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 3, 1, 3]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[6.239784479470714e-05], 0, 3.3268513679504395, 1688498930.4805532], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 823351, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 4]], ["tile_y", "sp", [-1, 9, 1, 1]], ["tile_x", "sp", [-1, 1, 9, 3]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008072049939969986], 0, 8.637540817260742, 1688498933.4342518], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 128, 27, 27], "float32"], ["TENSOR", [32, 128, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 83941, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 1, 3, 9]], ["tile_x", "sp", [-1, 3, 3, 3]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0016547011934493349], 0, 3.988628625869751, 1688498936.425498], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1497785, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 3, 1, 1]], ["tile_x", "sp", [-1, 1, 3, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[6.746713819913612e-06], 0, 3.827080011367798, 1688498949.8707817], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 655710, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 1, 3, 3]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[7.328587630105623e-06], 0, 3.3303089141845703, 1688498952.6481812], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 96776, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 9, 3, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[9.762807512182773e-06], 0, 3.444783926010132, 1688498955.4532452], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 769067, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 16]], ["tile_y", "sp", [-1, 3, 9, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[6.6359154748752166e-06], 0, 3.6143555641174316, 1688498958.2646663], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 779956, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 4]], ["tile_y", "sp", [-1, 1, 1, 27]], ["tile_x", "sp", [-1, 1, 3, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.3725228831812917e-05], 0, 3.689671754837036, 1688498961.0260441], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 180070, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 9, 3]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[3.4378730928615366e-06], 0, 3.020836114883423, 1688498963.5348885], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 908462, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 2]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 1, 3, 9]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[2.3594717782834368e-05], 0, 3.441972017288208, 1688498966.4679885], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1008314, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 4]], ["tile_y", "sp", [-1, 9, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00012536752969008754], 0, 4.148961067199707, 1688498969.3552783], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 630427, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 4]], ["tile_y", "sp", [-1, 1, 3, 3]], ["tile_x", "sp", [-1, 9, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00017548375013875015], 0, 5.004651784896851, 1688498972.2347565], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1265912, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 32, 1]], ["tile_y", "sp", [-1, 1, 27, 1]], ["tile_x", "sp", [-1, 1, 9, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.026213645935058594, 1688498939.4008317], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1137081, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 4]], ["tile_y", "sp", [-1, 1, 9, 3]], ["tile_x", "sp", [-1, 1, 3, 3]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[2.385034851734637e-05], 0, 3.580078601837158, 1688498975.1681714], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1573213, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 1, 9, 3]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.87020020583721e-05], 0, 5.603041887283325, 1688498978.0248988], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 771904, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 9, 1, 3]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[7.603633814011041e-05], 0, 6.427893877029419, 1688498980.927062], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 609681, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 3, 3, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.1971774834487774e-05], 0, 3.4637250900268555, 1688498983.8087647], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1250373, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 27]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005176848031037827], 0, 7.267003297805786, 1688498986.7301133], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1638748, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 9]], ["tile_x", "sp", [-1, 9, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.429571273786145e-05], 0, 5.0362632274627686, 1688498989.6537182], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1325693, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 2]], ["tile_y", "sp", [-1, 1, 9, 1]], ["tile_x", "sp", [-1, 9, 1, 3]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688498947.1971183], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 305538, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 9, 3, 1]], ["tile_x", "sp", [-1, 1, 9, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1.0427137408932955e-05], 0, 3.5064830780029297, 1688498992.5213637], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1024133, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 2]], ["tile_y", "sp", [-1, 3, 3, 3]], ["tile_x", "sp", [-1, 9, 3, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005176114523580365], 0, 6.080695390701294, 1688498995.4557335], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1299381, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 3, 9, 1]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[7.122464631610499e-06], 0, 3.669105291366577, 1688498998.2277179], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1138077, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 64]], ["tile_y", "sp", [-1, 27, 1, 1]], ["tile_x", "sp", [-1, 3, 3, 3]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.022463560104370117, 1688498947.1971462], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1110546, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 3, 3, 3]], ["tile_x", "sp", [-1, 9, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00029853688739996283], 0, 5.93231463432312, 1688499001.1859603], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1456051, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 8]], ["tile_y", "sp", [-1, 1, 3, 3]], ["tile_x", "sp", [-1, 9, 3, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.598071987540686e-05], 0, 4.9226768016815186, 1688499004.0942452], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 622138, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 1, 1, 27]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.099499009483667e-05], 0, 3.340970516204834, 1688499006.93465], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1591715, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 128, 1]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 27, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03744029998779297, 1688498947.1971622], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1560321, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 4]], ["tile_y", "sp", [-1, 9, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 3]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[4.8611486919089344e-05], 0, 5.150338888168335, 1688499009.879225], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 740628, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 16]], ["tile_y", "sp", [-1, 3, 1, 3]], ["tile_x", "sp", [-1, 3, 9, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00038527480153220016], 0, 4.84408974647522, 1688499012.821367], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1374610, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 1, 9, 3]], ["tile_x", "sp", [-1, 9, 1, 3]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[8.084934766823482e-05], 0, 4.338970899581909, 1688499015.6893177], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1521800, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 4]], ["tile_y", "sp", [-1, 3, 1, 1]], ["tile_x", "sp", [-1, 3, 3, 3]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.6824709996385056e-05], 0, 4.199309349060059, 1688499018.6022284], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1478732, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 8]], ["tile_y", "sp", [-1, 9, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 9]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0018773813732394366], 0, 9.488425016403198, 1688499021.5345523], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 88475, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 128, 1]], ["tile_y", "sp", [-1, 3, 1, 9]], ["tile_x", "sp", [-1, 1, 1, 9]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03174567222595215, 1688498947.1971776], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 716720, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 4]], ["tile_y", "sp", [-1, 9, 1, 3]], ["tile_x", "sp", [-1, 1, 3, 9]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.006566731366013071], 0, 5.6599695682525635, 1688499022.9371362], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 862838, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 1, 1, 27]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00032149079987797436], 0, 4.387691974639893, 1688499025.8600924], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1515550, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 1, 27, 1]], ["tile_x", "sp", [-1, 3, 1, 3]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[8.232162624061971e-06], 0, 4.572756290435791, 1688499028.6520102], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1719617, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 1, 1, 9]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[9.897908391873932e-06], 0, 4.527090787887573, 1688499031.5036576], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1120872, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 9, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[7.494025654569149e-06], 0, 3.347531795501709, 1688499034.3124597], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1099622, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 2]], ["tile_y", "sp", [-1, 27, 1, 1]], ["tile_x", "sp", [-1, 1, 3, 9]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0444188117980957, 1688498947.197195], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1251924, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 4]], ["tile_y", "sp", [-1, 9, 1, 3]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[5.299771423390154e-05], 0, 4.720308780670166, 1688499037.2446897], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1594233, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 64, 1]], ["tile_y", "sp", [-1, 3, 3, 1]], ["tile_x", "sp", [-1, 1, 3, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.1648745313680124e-06], 0, 3.3198070526123047, 1688499040.0050159], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 238859, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 1, 1, 27]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[5.410850869964928e-05], 0, 3.790682554244995, 1688499042.935028], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 144958, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 64]], ["tile_y", "sp", [-1, 1, 9, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.6272648725729164e-05], 0, 3.447601556777954, 1688499045.8147802], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1637757, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 64]], ["tile_y", "sp", [-1, 1, 9, 1]], ["tile_x", "sp", [-1, 9, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688498947.2216878], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1300788, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 16]], ["tile_y", "sp", [-1, 1, 1, 27]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.005650742221830986], 0, 6.646816968917847, 1688499048.7975886], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 612768, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 2]], ["tile_y", "sp", [-1, 9, 3, 1]], ["tile_x", "sp", [-1, 1, 9, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.005740532814946619], 0, 10.89551568031311, 1688499051.83822], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1554596, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 64]], ["tile_y", "sp", [-1, 3, 3, 3]], ["tile_x", "sp", [-1, 1, 9, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[8.287465179995443e-05], 0, 6.143901348114014, 1688499054.5171456], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1652588, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 4]], ["tile_y", "sp", [-1, 3, 1, 3]], ["tile_x", "sp", [-1, 3, 9, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0031822170944881887], 0, 6.6510539054870605, 1688499068.1599839], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4527452, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 8]], ["tile_y", "sp", [-1, 3, 9, 1]], ["tile_x", "sp", [-1, 9, 3, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05436539649963379, 1688499059.0556593], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4109194, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 64, 1]], ["tile_y", "sp", [-1, 27, 1, 1]], ["tile_x", "sp", [-1, 9, 1, 3]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.003979576956349207], 0, 5.20444393157959, 1688499069.5301938], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 486974, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 2, 1]], ["tile_y", "sp", [-1, 1, 3, 9]], ["tile_x", "sp", [-1, 9, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.008178287658536584], 0, 5.9094603061676025, 1688499070.9604795], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5887813, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 1]], ["tile_y", "sp", [-1, 3, 3, 1]], ["tile_x", "sp", [-1, 1, 3, 3]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00014489572177858438], 0, 6.324972629547119, 1688499073.9068916], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4147357, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 3, 1, 1]], ["tile_x", "sp", [-1, 3, 9, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00014085812759825328], 0, 3.5303690433502197, 1688499076.832159], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 963135, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 9, 3, 1]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[9.933866522837947e-05], 0, 3.449599027633667, 1688499079.7603815], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6599560, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 9]], ["tile_x", "sp", [-1, 1, 27, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688499065.264828], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5748266, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 9, 1, 1]], ["tile_x", "sp", [-1, 1, 9, 3]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04539942741394043, 1688499065.264853], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1177032, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 3, 9, 1]], ["tile_x", "sp", [-1, 1, 1, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00018234529227816664], 0, 3.6535110473632812, 1688499082.7346027], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5569227, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[3.363127276558977e-05], 0, 3.654909372329712, 1688499085.6301103], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1726889, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 1, 1, 27]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.028158903121948242, 1688499065.264868], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 381196, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 4]], ["tile_y", "sp", [-1, 1, 1, 9]], ["tile_x", "sp", [-1, 1, 3, 9]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.010400831082474226], 0, 3.1602816581726074, 1688499087.0725815], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6383311, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 1]], ["tile_y", "sp", [-1, 3, 3, 3]], ["tile_x", "sp", [-1, 1, 1, 27]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0010554098022193211], 0, 7.606241703033447, 1688499090.0578258], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2294970, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 1, 1, 9]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00010515487993474714], 0, 4.6524269580841064, 1688499092.986494], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 592891, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 9, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[4.5267125492846684e-05], 0, 3.3870089054107666, 1688499095.9016101], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2367536, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 1, 27, 1]], ["tile_x", "sp", [-1, 9, 3, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0004583461273036575], 0, 3.8464090824127197, 1688499098.8746681], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2548043, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 4]], ["tile_y", "sp", [-1, 1, 3, 3]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[5.566243133589504e-05], 0, 3.468761444091797, 1688499101.7871258], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6140851, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 8]], ["tile_y", "sp", [-1, 1, 3, 3]], ["tile_x", "sp", [-1, 1, 3, 9]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008241984045407636], 0, 8.367708206176758, 1688499104.6963613], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6066319, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 9, 1, 3]], ["tile_x", "sp", [-1, 1, 9, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[7.631082926482438e-05], 0, 4.756598234176636, 1688499107.656519], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6868808, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 9, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[8.922953401341687e-05], 0, 7.344872951507568, 1688499110.5757957], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6852088, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 9, 3]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688499065.2763348], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6776266, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 16]], ["tile_y", "sp", [-1, 3, 9, 1]], ["tile_x", "sp", [-1, 27, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.057268381118774414, 1688499065.2763467], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6058753, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 4]], ["tile_y", "sp", [-1, 1, 27, 1]], ["tile_x", "sp", [-1, 1, 3, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[6.904901853679468e-05], 0, 3.6611807346343994, 1688499113.4945984], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5730034, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 64, 1]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 1, 9, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03845548629760742, 1688499065.276357], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2004528, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 2]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 1, 9, 3]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.07473635673522949, 1688499065.2763643], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5196864, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 1, 9, 1]], ["tile_x", "sp", [-1, 3, 3, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[4.886366471841705e-05], 0, 3.514462471008301, 1688499116.4470694], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3092911, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 1]], ["tile_y", "sp", [-1, 3, 3, 3]], ["tile_x", "sp", [-1, 3, 9, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04798483848571777, 1688499065.276374], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5918434, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 64, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 9, 3, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.9869874374777543e-05], 0, 4.816344499588013, 1688499119.3482845], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5954947, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 4]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.6822184391141305e-05], 0, 6.873956680297852, 1688499122.274657], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 5856609, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 3, 3, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[4.307916751842487e-05], 0, 3.9551098346710205, 1688499125.2236252], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 4909372, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 2]], ["tile_y", "sp", [-1, 3, 1, 3]], ["tile_x", "sp", [-1, 3, 3, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0004692240579667929], 0, 5.352571487426758, 1688499128.1482835], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1954456, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 9, 1]], ["tile_x", "sp", [-1, 3, 3, 3]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[4.438793158507513e-05], 0, 4.103819847106934, 1688499131.0670927], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6511391, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 3, 1, 1]], ["tile_x", "sp", [-1, 1, 3, 3]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.8360126282655475e-05], 0, 4.901809453964233, 1688499134.0041306], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 888567, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 8]], ["tile_y", "sp", [-1, 1, 3, 1]], ["tile_x", "sp", [-1, 1, 1, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[8.991903861413803e-05], 0, 3.5355920791625977, 1688499136.927535], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 996138, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 3, 1, 1]], ["tile_x", "sp", [-1, 1, 9, 3]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[4.5046423960797576e-05], 0, 3.5811851024627686, 1688499139.835631], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 763814, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 2, 1]], ["tile_y", "sp", [-1, 3, 3, 1]], ["tile_x", "sp", [-1, 1, 3, 9]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.002966242517431193], 0, 4.206174373626709, 1688499142.8382735], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6320335, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 1, 27, 1]], ["tile_x", "sp", [-1, 1, 3, 3]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.6686802167338706e-05], 0, 5.456488847732544, 1688499145.742171], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3537881, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 2]], ["tile_y", "sp", [-1, 9, 1, 1]], ["tile_x", "sp", [-1, 3, 3, 3]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.01970983168627451], 0, 7.96697473526001, 1688499147.2812028], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2502088, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 9, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.037880111111111114], 0, 6.070165157318115, 1688499149.0871851], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2503629, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 4]], ["tile_y", "sp", [-1, 27, 1, 1]], ["tile_x", "sp", [-1, 27, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02716660499572754, 1688499065.2764044], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2045814, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 2]], ["tile_y", "sp", [-1, 3, 9, 1]], ["tile_x", "sp", [-1, 9, 1, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0001084473280587166], 0, 3.6977944374084473, 1688499152.020712], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6890537, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 3, 1, 1]], ["tile_x", "sp", [-1, 3, 1, 3]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688499065.3094451], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 2354681, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 2]], ["tile_y", "sp", [-1, 9, 1, 1]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.05787090383333334], 0, 9.528036832809448, 1688499154.0188363], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1575335, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 8]], ["tile_y", "sp", [-1, 1, 9, 1]], ["tile_x", "sp", [-1, 1, 1, 9]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0001109299486332025], 0, 3.6985833644866943, 1688499156.9863546], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 244353, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 64, 1]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.6280034882871602e-05], 0, 3.6768672466278076, 1688499171.427284], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 12585, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 16]], ["tile_x", "sp", [-1, 14, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00024639336839651953], 0, 4.251142501831055, 1688499174.3106756], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 225827, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 16]], ["tile_x", "sp", [-1, 14, 1, 14]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006267693803799923], 0, 4.95903205871582, 1688499177.2969131], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 239405, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 1, 1]], ["tile_x", "sp", [-1, 1, 4, 49]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00045526938322507766], 0, 4.064167737960815, 1688499180.2272978], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 102010, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 1]], ["tile_x", "sp", [-1, 7, 14, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1.1973844478645018e-05], 0, 3.833209753036499, 1688499182.9853268], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 322907, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 16]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002269197528930285], 0, 4.926818609237671, 1688499185.944896], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 376331, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 1]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[7.049391359649123e-05], 0, 4.913292407989502, 1688499188.8542032], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 12044, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00012192111951737745], 0, 3.72550106048584, 1688499191.7750826], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 31764, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 4]], ["tile_x", "sp", [-1, 14, 1, 7]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[8.645083020794154e-05], 0, 4.426450490951538, 1688499194.759959], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 412407, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 8]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[7.537962654408298e-05], 0, 6.175908327102661, 1688499197.6584606], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 340326, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 64, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 2]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[8.5384467596521e-05], 0, 5.813752174377441, 1688499200.5812137], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 291822, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 16]], ["tile_x", "sp", [-1, 2, 49, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1.411274722756439e-05], 0, 4.227441072463989, 1688499203.4833956], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 210562, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 4]], ["tile_x", "sp", [-1, 1, 1, 4]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.2824789682833518e-05], 0, 4.0996034145355225, 1688499206.3253682], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 391428, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 16]], ["tile_x", "sp", [-1, 2, 1, 7]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00016923787384284176], 0, 6.327537298202515, 1688499209.1910298], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 188963, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 16, 4]], ["tile_x", "sp", [-1, 4, 7, 7]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[2.8268875194924864e-05], 0, 4.329652309417725, 1688499212.1242268], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 236889, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 1]], ["tile_x", "sp", [-1, 4, 7, 7]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.9572620294190976e-05], 0, 4.012479782104492, 1688499214.9897645], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 102384, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 8, 1]], ["tile_x", "sp", [-1, 1, 98, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1.5381069070373587e-05], 0, 3.793076753616333, 1688499217.8242688], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 151164, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 4]], ["tile_x", "sp", [-1, 1, 49, 4]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.35588741302490234, 1688499161.290313], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 426768, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 2, 2]], ["tile_x", "sp", [-1, 49, 1, 4]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0031821467301587298], 0, 3.247303009033203, 1688499219.2255545], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 180985, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 8, 1]], ["tile_x", "sp", [-1, 196, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0011465495652482269], 0, 4.4695844650268555, 1688499222.2293522], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 297345, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 16]], ["tile_x", "sp", [-1, 1, 28, 7]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[2.0191252409807984e-05], 0, 4.274721622467041, 1688499225.115139], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 281633, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 32]], ["tile_x", "sp", [-1, 2, 7, 2]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[2.202832490984782e-05], 0, 4.099359750747681, 1688499228.032421], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 76910, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 32]], ["tile_x", "sp", [-1, 49, 1, 2]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0035028664013015184], 0, 4.425229549407959, 1688499231.0014439], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 153745, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 8, 1]], ["tile_x", "sp", [-1, 14, 1, 14]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0007710876464694657], 0, 4.967207193374634, 1688499233.963636], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 284853, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 8]], ["tile_x", "sp", [-1, 2, 7, 7]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001975434819173716], 0, 4.433079957962036, 1688499236.9313602], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 188659, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 4, 1]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.593595385305116e-05], 0, 4.275925159454346, 1688499239.7759752], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 101864, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 16]], ["tile_x", "sp", [-1, 14, 7, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0001487442762696214], 0, 4.323513746261597, 1688499242.716113], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 127061, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 16]], ["tile_x", "sp", [-1, 7, 7, 4]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0001440282114265246], 0, 4.323272705078125, 1688499245.6771376], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 347020, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 16]], ["tile_x", "sp", [-1, 2, 1, 49]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0009228905493119266], 0, 4.818004846572876, 1688499248.6066706], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 57570, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 8]], ["tile_x", "sp", [-1, 2, 1, 14]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.2792225206162405e-05], 0, 4.166660308837891, 1688499251.4898427], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 360800, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 8, 4]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.261810326514555e-05], 0, 5.468294858932495, 1688499254.4454467], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 328289, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 1, 8]], ["tile_x", "sp", [-1, 1, 196, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1.4981237283208992e-05], 0, 4.610965728759766, 1688499257.266509], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 283097, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 1]], ["tile_x", "sp", [-1, 1, 49, 4]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.0428833809472231e-05], 0, 3.728299856185913, 1688499260.0771763], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 71801, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 1, 2]], ["tile_x", "sp", [-1, 1, 2, 98]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0015332291831119545], 0, 4.2322282791137695, 1688499263.0697155], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 26329, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 2]], ["tile_x", "sp", [-1, 2, 7, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[9.813691749404866e-06], 0, 3.9036755561828613, 1688499265.8770106], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 306403, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 1, 98, 2]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[9.763679001061068e-06], 0, 3.789243698120117, 1688499268.6632814], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 58507, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 4]], ["tile_x", "sp", [-1, 1, 1, 28]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.001351903244952894], 0, 3.432853937149048, 1688499270.0446854], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 359825, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 4]], ["tile_x", "sp", [-1, 1, 2, 98]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002173525318480044], 0, 5.180606365203857, 1688499272.9420967], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 306796, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 4]], ["tile_x", "sp", [-1, 49, 1, 4]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0003821818899952584], 0, 5.875415563583374, 1688499275.8959846], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 236056, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 4, 1]], ["tile_x", "sp", [-1, 2, 2, 7]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.7270135722938004e-05], 0, 3.945072650909424, 1688499278.794544], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 29111, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 4]], ["tile_x", "sp", [-1, 1, 2, 2]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.294803871070595e-05], 0, 3.8729448318481445, 1688499281.6683652], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 314406, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 64, 1, 1]], ["tile_x", "sp", [-1, 4, 7, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[3.090045979333385e-05], 0, 4.7650065422058105, 1688499284.5526469], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 189324, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 4]], ["tile_x", "sp", [-1, 1, 28, 7]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[2.324664101133494e-05], 0, 3.6809353828430176, 1688499287.464678], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 328852, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 2]], ["tile_x", "sp", [-1, 49, 1, 2]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0010157275942211056], 0, 5.208635568618774, 1688499290.416335], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 32, 27, 27], "float32"], ["TENSOR", [128, 32, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 422632, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 32]], ["tile_x", "sp", [-1, 7, 7, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688499168.7231107], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 472805, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 9, 1, 1]], ["tile_x", "sp", [-1, 9, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.05395719826315789], 0, 5.720716714859009, 1688499298.0081856], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 676892, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 1, 9, 1]], ["tile_x", "sp", [-1, 1, 3, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.3643072550851972e-05], 0, 3.12467622756958, 1688499300.8524437], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 378992, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 1, 9, 1]], ["tile_x", "sp", [-1, 1, 3, 9]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.027113676071166992, 1688499295.0549283], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 550909, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 3, 1, 9]], ["tile_x", "sp", [-1, 3, 1, 3]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.024977445602416992, 1688499295.054945], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 732921, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 9, 1]], ["tile_x", "sp", [-1, 3, 3, 3]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[8.864153377374071e-05], 0, 3.3884053230285645, 1688499303.818925], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 141083, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 27]], ["tile_x", "sp", [-1, 3, 3, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.026320219039916992, 1688499295.0549555], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 743756, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 3, 1, 1]], ["tile_x", "sp", [-1, 1, 3, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[9.091608283647536e-06], 0, 3.162811279296875, 1688499306.6409528], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 778575, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 27, 1, 1]], ["tile_x", "sp", [-1, 1, 9, 3]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.025539159774780273, 1688499295.054965], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 987152, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 1, 9, 1]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1.1221262182650361e-05], 0, 7.813694953918457, 1688499309.494882], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 960947, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 1, 1, 27]], ["tile_x", "sp", [-1, 3, 1, 9]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02566218376159668, 1688499296.2033813], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 252370, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 9, 3, 1]], ["tile_x", "sp", [-1, 3, 3, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[6.99412998826036e-05], 0, 3.6757357120513916, 1688499312.4599683], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 627945, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 1, 3, 3]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[2.8373998072495582e-05], 0, 3.2590672969818115, 1688499315.3459797], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 179076, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 4]], ["tile_y", "sp", [-1, 3, 1, 9]], ["tile_x", "sp", [-1, 1, 1, 27]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.039865732192993164, 1688499296.2033935], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 271464, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 2]], ["tile_y", "sp", [-1, 1, 9, 1]], ["tile_x", "sp", [-1, 9, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[3.464165814592758e-05], 0, 3.3301188945770264, 1688499318.2503383], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 995000, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 8]], ["tile_y", "sp", [-1, 1, 9, 1]], ["tile_x", "sp", [-1, 3, 9, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02584528923034668, 1688499296.2034037], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 341815, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 27, 1, 1]], ["tile_x", "sp", [-1, 3, 3, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02473759651184082, 1688499296.2034123], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 481298, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 3, 3, 3]], ["tile_x", "sp", [-1, 1, 27, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[7.349138158556088e-05], 0, 3.415797472000122, 1688499321.2241364], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 574353, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 9]], ["tile_x", "sp", [-1, 9, 1, 3]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.028841018676757812, 1688499296.2034214], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 720345, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 27, 1, 1]], ["tile_x", "sp", [-1, 27, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.022321462631225586, 1688499296.2034287], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 391059, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 27, 1, 1]], ["tile_x", "sp", [-1, 1, 27, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.038175106048583984, 1688499296.2034364], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 575313, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 1, 3, 3]], ["tile_x", "sp", [-1, 1, 3, 3]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02485823631286621, 1688499296.2034445], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1199083, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 9, 1, 3]], ["tile_x", "sp", [-1, 1, 1, 3]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.024734020233154297, 1688499296.2034514], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1197822, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 1, 27, 1]], ["tile_x", "sp", [-1, 1, 27, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.041527748107910156, 1688499296.2034597], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 384927, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 4]], ["tile_y", "sp", [-1, 1, 3, 3]], ["tile_x", "sp", [-1, 27, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.039092302322387695, 1688499296.2034662], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 988241, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 1, 9, 1]], ["tile_x", "sp", [-1, 9, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03135180473327637, 1688499296.2034724], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 239197, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 3, 1, 3]], ["tile_x", "sp", [-1, 1, 3, 3]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[9.935911915498178e-05], 0, 3.295966625213623, 1688499324.1499271], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 21485, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 27, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 27]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.016447823934426228], 0, 2.471219778060913, 1688499325.6577735], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 670123, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 9, 3, 1]], ["tile_x", "sp", [-1, 1, 3, 9]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005928907573421439], 0, 3.8145980834960938, 1688499328.6470876], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 676163, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 3, 3, 3]], ["tile_x", "sp", [-1, 27, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0010853011771812082], 0, 4.1567702293396, 1688499331.595891], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 154237, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 3, 3, 3]], ["tile_x", "sp", [-1, 3, 1, 9]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.045569419860839844, 1688499296.2034853], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 306847, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 27]], ["tile_x", "sp", [-1, 1, 3, 3]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0038296581090047394], 0, 5.227415561676025, 1688499334.590291], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 221767, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 3, 9]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[4.9934819803829985e-05], 0, 3.1822705268859863, 1688499337.5480406], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 549603, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 3, 3, 3]], ["tile_x", "sp", [-1, 1, 1, 3]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[3.568579242130589e-05], 0, 3.4542839527130127, 1688499340.4547315], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 368509, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 27, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[2.083102088246083e-05], 0, 3.437701940536499, 1688499343.346488], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 54280, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 1, 27, 1]], ["tile_x", "sp", [-1, 3, 9, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.028294801712036133, 1688499296.2034967], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 318804, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 9, 1, 3]], ["tile_x", "sp", [-1, 1, 3, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.001329841418930041], 0, 4.188397169113159, 1688499346.3392613], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 122428, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 9, 3, 1]], ["tile_x", "sp", [-1, 1, 27, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02693009376525879, 1688499296.2035072], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1025362, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 3]], ["tile_x", "sp", [-1, 1, 9, 3]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.6301076995765234e-05], 0, 3.293016195297241, 1688499349.2548149], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1053476, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 9, 1, 3]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002669613313100657], 0, 4.8830461502075195, 1688499352.1520054], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 753613, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 3, 1, 9]], ["tile_x", "sp", [-1, 9, 1, 3]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04134535789489746, 1688499296.203516], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1196976, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 2]], ["tile_y", "sp", [-1, 3, 3, 3]], ["tile_x", "sp", [-1, 3, 9, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05081367492675781, 1688499296.2035222], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 143506, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 2]], ["tile_y", "sp", [-1, 9, 1, 1]], ["tile_x", "sp", [-1, 3, 9, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.16640305519104004, 1688499296.2035294], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 19166, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 9, 1, 1]], ["tile_x", "sp", [-1, 3, 1, 9]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.004166027894329897], 0, 5.441715717315674, 1688499355.185166], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 772673, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 3, 1, 9]], ["tile_x", "sp", [-1, 1, 27, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02698206901550293, 1688499296.203537], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 27, 27], "float32"], ["TENSOR", [32, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 874721, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 3, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[5.183869889939644e-05], 0, 3.2401955127716064, 1688499358.0995934], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 76602, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 3, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00016605806838749487], 0, 3.2892098426818848, 1688499371.6367009], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 52292, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 12, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006008648512458162], 0, 6.444376230239868, 1688499374.5712068], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1142, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 3, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[4.811331696415179e-05], 0, 3.186873197555542, 1688499377.4975755], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 48933, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 12, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.002493750029776675], 0, 3.0528736114501953, 1688499378.8917465], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4804, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 48, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.4345829213008847e-05], 0, 3.090540885925293, 1688499381.7362778], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 8669, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 12]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.021093523645833334], 0, 3.3369979858398438, 1688499383.2967236], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 48764, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 48, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.6358386042118592e-05], 0, 3.1911699771881104, 1688499386.2147212], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 111415, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 6]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.8477090414234976e-05], 0, 4.564825534820557, 1688499389.1075563], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 72274, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[3.413064080209241e-05], 0, 4.095264196395874, 1688499392.0309095], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 113245, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 3, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.3034091217646034e-05], 0, 4.173675537109375, 1688499394.9108715], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 82595, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 3, 16]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0037062122481481487], 0, 3.316844940185547, 1688499396.266894], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 25409, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 6, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688499368.8351457], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 48819, "code_hash": null, "entity": [["tile_f", "sp", [-1, 6, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0002546171072555205], 0, 3.7117183208465576, 1688499399.202044], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 71445, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[3.784249055263532e-05], 0, 3.2842857837677, 1688499402.126877], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 78591, "code_hash": null, "entity": [["tile_f", "sp", [-1, 12, 1, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00020080929590439437], 0, 4.19588565826416, 1688499405.054163], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 77231, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.023505210876464844, 1688499368.8351777], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 99962, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 1, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03075242042541504, 1688499368.8351858], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 74513, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.6836353565927955e-05], 0, 3.656352996826172, 1688499407.911658], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 33062, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 3, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00015249933180340407], 0, 4.955145359039307, 1688499410.8472276], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 83087, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 6, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[2.955915701177125e-05], 0, 3.1914174556732178, 1688499413.7350311], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 120772, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 1, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.026876449584960938, 1688499368.8351986], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 68278, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.003793136825757576], 0, 2.6255853176116943, 1688499415.0875397], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 40336, "code_hash": null, "entity": [["tile_f", "sp", [-1, 12, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[5.534763627897351e-05], 0, 3.289440631866455, 1688499418.0392685], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 55933, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 12, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.023747920989990234, 1688499368.8352082], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 8834, "code_hash": null, "entity": [["tile_f", "sp", [-1, 6, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0018162074218222724], 0, 3.451572895050049, 1688499420.9889722], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 35816, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 6]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.022545337677001953, 1688499368.835216], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 5793, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.569018031437609e-05], 0, 3.184276819229126, 1688499423.887229], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 97257, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04953575134277344, 1688499368.835225], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13100, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 3]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0008728586886486485], 0, 4.184720277786255, 1688499426.8762345], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 57369, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 6]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03513646125793457, 1688499368.8352349], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 20424, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 3, 8]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[7.740328738396422e-05], 0, 3.2272071838378906, 1688499429.7963798], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 19880, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03598165512084961, 1688499368.835245], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 112482, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 3, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[6.845571676448073e-05], 0, 5.158675193786621, 1688499432.730925], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 49819, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[7.369332467353953e-05], 0, 3.817397117614746, 1688499435.695321], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 94264, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 48, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1.5413484264592656e-05], 0, 3.495824098587036, 1688499438.5683289], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 112948, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 6]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[5.0538537665523855e-05], 0, 4.504544734954834, 1688499441.489683], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 100459, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 3]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.025889158248901367, 1688499368.8352597], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 9945, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.004394657600877192], 0, 2.328132152557373, 1688499442.9017394], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 94383, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1.177379168248857e-05], 0, 3.600893259048462, 1688499445.7220466], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 21554, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 1, 16]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0011302256862745098], 0, 3.5447232723236084, 1688499448.6704795], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 33545, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 3]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0015986948733926803], 0, 5.674821376800537, 1688499451.665308], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 70522, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 3, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.005119738831632652], 0, 3.1792726516723633, 1688499453.0485706], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 16695, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.023870229721069336, 1688499368.835274], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 20004, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 3, 8]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.024613618850708008, 1688499368.8352807], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 256, 13, 13], "float32"], ["TENSOR", [48, 256, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 64687, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[7.034661153627498e-05], 0, 3.342266798019409, 1688499455.9824152], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 289678, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 6, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.440241669513828e-05], 0, 3.714354991912842, 1688499469.4702873], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2935, "code_hash": null, "entity": [["tile_f", "sp", [-1, 12, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.4528514600080756e-05], 0, 3.225019693374634, 1688499472.342786], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 71346, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[7.491154312455572e-06], 0, 3.3176748752593994, 1688499475.113651], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 121859, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 6]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[9.819888772862478e-06], 0, 3.5257105827331543, 1688499477.990594], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 207923, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 12]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[5.3359830188052365e-05], 0, 3.4765379428863525, 1688499480.900316], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 238137, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[9.53637512661375e-06], 0, 3.5744290351867676, 1688499483.7287862], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 270704, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 6]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688499466.7695696], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 257950, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 6]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00028386857657816076], 0, 6.8756725788116455, 1688499486.7090566], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 36732, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 3, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0004439449351545253], 0, 4.670576810836792, 1688499489.6339498], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 254901, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 12, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[2.0131450770874675e-05], 0, 3.5138590335845947, 1688499492.5140567], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 208572, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00014220078514306025], 0, 3.6871821880340576, 1688499495.4658926], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 106688, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00044000270876712327], 0, 5.737613201141357, 1688499498.3971882], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 181768, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 48]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00039723638608221896], 0, 3.5389111042022705, 1688499501.3201358], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 174474, "code_hash": null, "entity": [["tile_f", "sp", [-1, 12, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.002838772507067138], 0, 5.447259187698364, 1688499504.3092172], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 258895, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[4.708648214314533e-06], 0, 3.2763094902038574, 1688499506.991027], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 262854, "code_hash": null, "entity": [["tile_f", "sp", [-1, 12, 2, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[4.513183033256881e-05], 0, 4.685910224914551, 1688499509.854482], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 121249, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[7.881298248546365e-06], 0, 3.323972225189209, 1688499512.7278874], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 282327, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.178423044208961e-06], 0, 3.2532382011413574, 1688499515.3135633], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 66639, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 3, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0036354697274774772], 0, 5.573288202285767, 1688499518.2768092], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 145944, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 6, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[5.01473330784144e-06], 0, 3.163952350616455, 1688499521.0644526], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 67466, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[5.699789889138235e-06], 0, 3.306922674179077, 1688499523.847715], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 209705, "code_hash": null, "entity": [["tile_f", "sp", [-1, 24, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.4910585169395607e-05], 0, 3.3251540660858154, 1688499526.7276297], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 10756, "code_hash": null, "entity": [["tile_f", "sp", [-1, 6, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.0953263920307972e-05], 0, 3.330803632736206, 1688499529.6428945], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 44367, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[9.331737970840223e-06], 0, 3.3908517360687256, 1688499532.4727647], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 234296, "code_hash": null, "entity": [["tile_f", "sp", [-1, 24, 2, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00036001571130083127], 0, 10.121753454208374, 1688499535.4128084], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 52773, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0007951887376237625], 0, 4.095702171325684, 1688499538.3870158], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 270665, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00041373221278826], 0, 6.139235019683838, 1688499541.2600164], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 30637, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 12, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.05803296530787e-05], 0, 3.404782772064209, 1688499544.142421], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 204593, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 24]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[2.518690085913643e-05], 0, 4.347780227661133, 1688499547.0736737], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 18433, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 16]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.000291492147219193], 0, 3.6880688667297363, 1688499549.9865277], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 210911, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 6]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.9515370352087473e-05], 0, 3.344954490661621, 1688499552.8602426], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 270720, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 6]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0005302064011838212], 0, 7.958112001419067, 1688499555.8345282], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 223265, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 3]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[3.1303006705046614e-06], 0, 3.1955459117889404, 1688499558.4457939], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 39212, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 6]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.325439837681061e-05], 0, 3.4771273136138916, 1688499561.291615], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 191051, "code_hash": null, "entity": [["tile_f", "sp", [-1, 12, 4, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.2953016150818312e-05], 0, 3.352144956588745, 1688499564.190343], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 218397, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 96]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0009558662835909631], 0, 3.3485209941864014, 1688499567.1225197], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 161598, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 32]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[2.0373807559386925e-05], 0, 3.192596912384033, 1688499570.0161839], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 253937, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 3, 8]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0002959036674053555], 0, 6.239242076873779, 1688499572.9910846], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 158911, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 2, 32]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.8959340442328624e-05], 0, 3.8858964443206787, 1688499575.8824437], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 285803, "code_hash": null, "entity": [["tile_f", "sp", [-1, 12, 4, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[9.667891524793003e-06], 0, 3.5055012702941895, 1688499578.7280383], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7384, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 48]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0024081372541106126], 0, 6.26181173324585, 1688499581.7682614], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 149804, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 12]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0011696105590643276], 0, 4.925503730773926, 1688499583.1288984], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 108288, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[5.291267693987057e-06], 0, 3.144148588180542, 1688499585.8659356], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 107628, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 3, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.4285606304738123e-05], 0, 3.7938318252563477, 1688499588.7602227], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 47089, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[3.7768853628467783e-06], 0, 3.0851645469665527, 1688499591.4892116], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 138306, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 8, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[8.971628179995545e-05], 0, 3.418567657470703, 1688499605.0673692], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 467418, "code_hash": null, "entity": [["tile_f", "sp", [-1, 48, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.017395429931034483], 0, 10.499579429626465, 1688499606.6053581], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 21432, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 6, 8]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00865677247413793], 0, 4.215434789657593, 1688499608.0718796], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 935670, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0007109537721073471], 0, 3.9052045345306396, 1688499611.0619745], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 338700, "code_hash": null, "entity": [["tile_f", "sp", [-1, 96, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0017333960034662042], 0, 2.130197525024414, 1688499612.411389], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1139570, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 3, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688499602.242361], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 212259, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03026866912841797, 1688499602.2423875], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1021329, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 6]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05030035972595215, 1688499602.2423964], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 559266, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 3]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[7.910166437481582e-05], 0, 4.735246658325195, 1688499615.3354714], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 303597, "code_hash": null, "entity": [["tile_f", "sp", [-1, 6, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.01227647362195122], 0, 3.1383585929870605, 1688499616.8425722], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1174720, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.934695400553828e-05], 0, 5.976500988006592, 1688499619.7385907], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 760256, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 6]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00455949485], 0, 2.606226921081543, 1688499621.1113214], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 423880, "code_hash": null, "entity": [["tile_f", "sp", [-1, 48, 1, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.028191804885864258, 1688499602.2424166], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1233554, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 2, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688499602.258199], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 796925, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 12, 8]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.028244733810424805, 1688499602.2582119], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 573660, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 3, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[4.370411856963613e-05], 0, 3.640562057495117, 1688499624.0766554], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 25573, "code_hash": null, "entity": [["tile_f", "sp", [-1, 6, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[9.044160946446616e-05], 0, 3.4992401599884033, 1688499627.0012145], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 396314, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 3]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[5.932648714164483e-05], 0, 3.48457670211792, 1688499629.9173071], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 774048, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 6]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.002944828167647059], 0, 2.5885043144226074, 1688499631.3136737], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1247044, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 3]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.001956215699386503], 0, 12.379249811172485, 1688499634.2402196], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 225241, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 6, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0001068801697588126], 0, 3.47210431098938, 1688499637.1871989], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 487913, "code_hash": null, "entity": [["tile_f", "sp", [-1, 24, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005169990196901227], 0, 3.8930509090423584, 1688499640.147926], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 683428, "code_hash": null, "entity": [["tile_f", "sp", [-1, 6, 1, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.8065139383039897e-05], 0, 3.303419351577759, 1688499643.019878], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1082564, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 24]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.010907481315217392], 0, 5.135489463806152, 1688499644.4774363], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 666936, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 24]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00036722500886363633], 0, 3.420872926712036, 1688499647.4497485], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1139012, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 24]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.010643597531914894], 0, 5.716704607009888, 1688499648.8933887], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 293633, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 24]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00560769294972067], 0, 2.973747730255127, 1688499650.2802272], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 831, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 3]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00022602056311223063], 0, 3.4671616554260254, 1688499653.2498457], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 408698, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 6, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00019088435528493732], 0, 3.3244073390960693, 1688499656.182095], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 699092, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 12, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[8.122086751618123e-05], 0, 3.311448812484741, 1688499659.1001089], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 640981, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 6]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.028780698776245117, 1688499602.2582424], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 663211, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 12]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.007009287153846154], 0, 4.683927297592163, 1688499660.5446472], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 386312, "code_hash": null, "entity": [["tile_f", "sp", [-1, 24, 1, 8]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 4, 12.423407793045044, 1688499670.830458], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 579995, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 12, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[4.9193731422244096e-05], 0, 3.3847267627716064, 1688499673.7527955], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 848615, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.027953386306762695, 1688499602.258254], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 177148, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 48, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0001918612644184938], 0, 4.338457107543945, 1688499676.7317517], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 792410, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 6, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[9.329067584451643e-05], 0, 3.6892178058624268, 1688499679.6574292], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 871607, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[7.631708341223252e-05], 0, 3.7628061771392822, 1688499682.5869932], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 502328, "code_hash": null, "entity": [["tile_f", "sp", [-1, 24, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.1574397827], 0, 5.788278102874756, 1688499684.6741624], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 1119256, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00011612974186113513], 0, 5.448279619216919, 1688499687.604717], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 506042, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 3, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.359458196141451e-05], 0, 3.360097646713257, 1688499690.4333365], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 247704, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[4.8698157668172315e-05], 0, 3.422852039337158, 1688499693.3955798], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 874834, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 6]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00012209905608537693], 0, 4.205679416656494, 1688499696.3231254], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 473680, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 3, 8]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00012797196642857145], 0, 4.196190595626831, 1688499699.248517], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 499706, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 32, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.001575500680314961], 0, 3.708923578262329, 1688499700.6304207], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 105325, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 3]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.5046937712235339e-05], 0, 3.964810848236084, 1688499712.0379007], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 73558, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 2, 24]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0001400302668122668], 0, 4.796494722366333, 1688499714.8842058], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 126666, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 3, 1, 64]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.000965681843373494], 0, 4.302879333496094, 1688499717.8148873], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 37150, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 4]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[6.152024576984917e-05], 0, 4.0960493087768555, 1688499720.727612], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 169680, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 49, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.908301845807949e-05], 0, 4.424813985824585, 1688499723.6366546], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 46617, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 8]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1.2310308247074796e-05], 0, 4.097602844238281, 1688499726.5100362], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 198220, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 3, 1, 32]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 24]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.019178325833333332], 0, 8.837610483169556, 1688499729.6475432], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 44022, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 12, 1, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[3.041848187152386e-05], 0, 4.488941192626953, 1688499732.5829616], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 167034, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 48, 4, 1]], ["tile_x", "sp", [-1, 7, 1, 7]], ["tile_rc", "sp", [-1, 48]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006168829796623177], 0, 10.766507625579834, 1688499735.518536], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 25637, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 2]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.639878382887347e-05], 0, 4.181064128875732, 1688499738.424042], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 64584, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 1]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 48]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1.3148403434460044e-05], 0, 4.270563364028931, 1688499741.2834628], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 115051, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 24, 2]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 6]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.5098127433196799e-05], 0, 4.7132086753845215, 1688499744.1021402], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 12290, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 3, 4]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.7848822030076884e-05], 0, 4.136003732681274, 1688499746.9775786], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 169067, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 12, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.0925586720915231e-05], 0, 4.308435440063477, 1688499749.8292584], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 68102, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 2, 6]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.024958000171875], 0, 10.852463245391846, 1688499753.020811], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 153632, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 3, 64, 1]], ["tile_x", "sp", [-1, 7, 1, 7]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[2.6734117012712577e-05], 0, 4.086318492889404, 1688499755.9204912], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 24798, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 24, 8]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[9.16795946910657e-06], 0, 4.070906639099121, 1688499758.7632368], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 556, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 6]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[3.670090105738441e-05], 0, 3.9305155277252197, 1688499761.6585543], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 132586, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 6, 4, 4]], ["tile_x", "sp", [-1, 7, 7, 1]], ["tile_rc", "sp", [-1, 48]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[2.6914050391804336e-05], 0, 4.191600561141968, 1688499764.5382564], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 16468, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 6, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 6]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[9.06632540140718e-05], 0, 3.089193344116211, 1688499765.911513], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 181549, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 3, 2]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 6]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[4.474640374161861e-05], 0, 4.462681531906128, 1688499768.846435], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 94919, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 8, 3]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 24]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00033487158120721846], 0, 5.51003360748291, 1688499771.7888565], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 113391, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 2, 3]], ["tile_x", "sp", [-1, 7, 1, 7]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0021340839428950864], 0, 5.283048868179321, 1688499774.7824333], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 153286, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 24, 1]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1.2023822867687004e-05], 0, 3.8922693729400635, 1688499777.1890872], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 71768, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 3, 4, 4]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[9.091759716915308e-06], 0, 3.9973347187042236, 1688499779.7154293], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 100051, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 8]], ["tile_x", "sp", [-1, 7, 1, 7]], ["tile_rc", "sp", [-1, 48]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00019324355399804973], 0, 6.072427034378052, 1688499782.6437547], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 178226, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 96, 2]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.3265301767112925e-05], 0, 3.903432846069336, 1688499785.313837], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 199267, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 48]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.138408085382154e-05], 0, 4.773867607116699, 1688499787.8843756], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 44667, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 32]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.008319393195876289], 0, 4.50461745262146, 1688499790.9574351], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 60400, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 3, 8]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005461781851599727], 0, 4.390216588973999, 1688499793.8929622], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 96571, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 24, 2]], ["tile_x", "sp", [-1, 7, 1, 7]], ["tile_rc", "sp", [-1, 24]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.5011754219147188e-05], 0, 4.699623346328735, 1688499796.7510083], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 92952, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 3, 16, 4]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.7356851216826342e-05], 0, 4.598992347717285, 1688499799.678691], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 67416, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 3, 16, 4]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.6318312002673292e-05], 0, 5.034823656082153, 1688499802.6420472], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 53292, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 6, 4]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1.0220763086021863e-05], 0, 3.9570140838623047, 1688499805.452642], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 61526, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 24]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[9.243553535521792e-06], 0, 4.136254549026489, 1688499808.3432636], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 21111, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 12]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 12]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00435127217027027], 0, 5.003943204879761, 1688499811.322918], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 125532, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 6, 4]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[9.645894390010619e-06], 0, 3.867147207260132, 1688499813.7287736], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 162507, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 48, 4]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 24]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[8.59343797580751e-06], 0, 3.600708246231079, 1688499815.9955962], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 170928, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 6]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.1995471150781003e-05], 0, 4.035113334655762, 1688499818.8815196], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 133689, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 3, 16]], ["tile_x", "sp", [-1, 7, 1, 7]], ["tile_rc", "sp", [-1, 48]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0004451602162236988], 0, 4.419908761978149, 1688499821.8261304], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 145216, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 3, 16, 1]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[2.862694509148424e-05], 0, 4.217147588729858, 1688499824.7661612], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 148352, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 4]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 6]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[3.0651219928428505e-05], 0, 4.452928066253662, 1688499827.6499693], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 78857, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 6]], ["tile_x", "sp", [-1, 7, 7, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.699676655513357e-05], 0, 4.268702268600464, 1688499830.5497985], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 26329, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 6, 2]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.109444629192591e-05], 0, 3.6728484630584717, 1688499833.4194384], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 48, 13, 13], "float32"], ["TENSOR", [192, 48, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 144302, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 2, 3]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.001343768080334728], 0, 5.5374908447265625, 1688499836.3473952], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 23791, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 12]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005253313370201691], 0, 3.4682650566101074, 1688499846.6017525], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 112681, "code_hash": null, "entity": [["tile_f", "sp", [-1, 6, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0030736051428571433], 0, 4.132934331893921, 1688499849.613792], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 103805, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 4, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 192]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.0857384204864502, 1688499838.3006647], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 14420, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00037512484702878366], 0, 3.7609386444091797, 1688499852.5547218], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 127336, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 3]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0026762295481283426], 0, 3.7691919803619385, 1688499853.8845088], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 112983, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0031689916677215195], 0, 2.3143134117126465, 1688499855.2806578], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11346, "code_hash": null, "entity": [["tile_f", "sp", [-1, 12, 1, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[8.01442092225041e-05], 0, 3.5954530239105225, 1688499858.2307227], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 78252, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 12]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[8.160728987123593e-05], 0, 3.3693439960479736, 1688499861.1469114], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 70581, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 3, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 384]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.023757219314575195, 1688499839.6221218], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 73819, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 12, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00122897376146789], 0, 4.084346294403076, 1688499864.1134539], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 128825, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[8.197530868069769e-06], 0, 3.13484787940979, 1688499866.9524474], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 58908, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 6]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00019113515121373594], 0, 3.669574499130249, 1688499869.8804207], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 163184, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 3]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0021700158763557484], 0, 4.49689507484436, 1688499871.2644634], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 209793, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 12, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03185629844665527, 1688499840.2998064], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 146547, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 12, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[7.539128128512552e-05], 0, 3.2745587825775146, 1688499874.1804187], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 156348, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 6]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[5.580157255323576e-05], 0, 3.4990196228027344, 1688499877.1047099], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 148466, "code_hash": null, "entity": [["tile_f", "sp", [-1, 6, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[7.763988364233294e-05], 0, 3.8257529735565186, 1688499880.0598106], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 199753, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 6]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.804048433504573e-05], 0, 3.910076856613159, 1688499882.9069886], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 160032, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.003267780587878788], 0, 6.08174729347229, 1688499885.900954], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 189335, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 2, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.634465030896355e-05], 0, 3.2197535037994385, 1688499888.8210857], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 63687, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 12]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 96]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03923320770263672, 1688499840.2998283], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 94025, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 3]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.005605965212290502], 0, 7.9787757396698, 1688499890.1966946], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 82222, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 24, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[6.097491470487888e-05], 0, 3.1857481002807617, 1688499893.1070933], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 130928, "code_hash": null, "entity": [["tile_f", "sp", [-1, 12, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.004172543841666667], 0, 3.134488344192505, 1688499894.5194597], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 80287, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 6, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005125253135324015], 0, 4.42027473449707, 1688499897.4460716], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 146566, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 6, 8]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[7.524547953353315e-05], 0, 3.4885330200195312, 1688499900.3681092], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 71098, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 384]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.022216796875, 1688499843.7990744], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 155833, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[4.773472474438847e-05], 0, 3.60908842086792, 1688499903.3238742], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 129986, "code_hash": null, "entity": [["tile_f", "sp", [-1, 6, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[4.459052332154493e-05], 0, 3.17053484916687, 1688499906.236357], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 138972, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 192]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[5.2067218657852954e-05], 0, 3.3746376037597656, 1688499909.14935], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 124831, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00014571659866341552], 0, 3.287360429763794, 1688499912.118027], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 213207, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 12]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 384]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.520562553620017e-05], 0, 6.488680362701416, 1688499914.9705956], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 25654, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0009634261811175337], 0, 2.031771659851074, 1688499916.3118644], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 117475, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.003433679030821918], 0, 2.4067864418029785, 1688499917.7040129], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 185958, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 12, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.901733138535166e-05], 0, 3.133502721786499, 1688499920.5786734], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 140692, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 12]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 192]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001111752360488377], 0, 3.304253578186035, 1688499923.5098927], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 183779, "code_hash": null, "entity": [["tile_f", "sp", [-1, 6, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[6.982970403334346e-05], 0, 3.393643856048584, 1688499926.464463], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 100938, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 24]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00013082382847870184], 0, 3.2600061893463135, 1688499929.3895838], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 192730, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[4.374593030949256e-05], 0, 3.2156848907470703, 1688499932.3036056], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 194781, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0026448914664484453], 0, 6.190227746963501, 1688499935.3042614], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 95247, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.0214362126726913e-05], 0, 3.3694002628326416, 1688499938.1268032], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 105474, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 384]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[4.1034435843543345e-05], 0, 3.407107353210449, 1688499941.0471032], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 173247, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 6, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.039759159088134766, 1688499843.7991076], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 4152, "code_hash": null, "entity": [["tile_f", "sp", [-1, 3, 1, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.008144662747967478], 0, 2.81103777885437, 1688499942.4964666], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [48, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 117782, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 24, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[6.143745682834538e-05], 0, 3.270836353302002, 1688499945.4274065], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 109418, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[8.081330991217063e-05], 0, 3.429130792617798, 1688499955.529301], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 108613, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0013154200528885274], 0, 4.17743182182312, 1688499958.5181346], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 104335, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0258333683013916, 1688499947.4349868], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 17002, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 96]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03121018409729004, 1688499947.4350019], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 108710, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[7.752571897124693e-05], 0, 3.221501350402832, 1688499961.4341052], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 126495, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 192]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0008041524320557492], 0, 4.312144756317139, 1688499964.3944442], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 111449, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00010735895255231242], 0, 4.05315899848938, 1688499967.3595982], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 25704, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1.716782045392696e-05], 0, 3.0861270427703857, 1688499970.225064], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 40146, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 16]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.0370020866394043, 1688499947.6009157], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 114734, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00601042019760479], 0, 7.877457857131958, 1688499971.6361353], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 115856, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.089988832898928e-05], 0, 3.725266218185425, 1688499974.5799258], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 42294, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 384]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04735732078552246, 1688499952.7187319], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 50526, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[8.802149278215222e-05], 0, 3.7848362922668457, 1688499977.5033805], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 111713, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 16]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00012889893221964673], 0, 4.36072564125061, 1688499980.4218228], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 63664, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 16]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 384]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.0814063549041748, 1688499952.7187479], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 34578, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[4.972792318427092e-05], 0, 3.5841739177703857, 1688499983.3737102], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 60458, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 96]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03271985054016113, 1688499952.7187583], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 67050, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[5.224421950426127e-05], 0, 3.1628987789154053, 1688499986.3010232], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 45540, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00034339066460422447], 0, 3.677182197570801, 1688499989.2185116], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 111318, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00011882624559852671], 0, 4.109629154205322, 1688499992.1914759], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 35710, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 48]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[6.304024252751987e-05], 0, 4.005198240280151, 1688499995.1282637], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 42627, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 384]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.022551774978637695, 1688499952.7187738], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 104958, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 192]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.029667377471923828, 1688499952.7187808], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 33714, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00014975029975863348], 0, 4.219593524932861, 1688499998.0490906], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 124600, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 96]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02949666976928711, 1688499952.7187889], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 107858, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00010731446348127415], 0, 3.2555992603302, 1688500001.0037696], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 79705, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[9.196089063123682e-05], 0, 3.347512722015381, 1688500003.943416], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 60137, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 16]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 96]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04128313064575195, 1688499952.7187989], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 46730, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 32, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 3]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[3.8170899145829354e-05], 0, 3.188401460647583, 1688500006.846699], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 41722, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 384]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[3.179823083801991e-05], 0, 3.2737557888031006, 1688500009.8018498], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 119315, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[6.378198285782311e-05], 0, 4.9523091316223145, 1688500012.7292497], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 55010, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00020910375854479542], 0, 3.7249934673309326, 1688500015.6567254], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 8155, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.6213232507433104e-05], 0, 3.192965269088745, 1688500018.580169], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 23377, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[9.193908497291132e-05], 0, 3.1945059299468994, 1688500021.4987984], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 111809, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006769540577494692], 0, 4.766178607940674, 1688500024.3989298], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11775, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[3.513566189388616e-05], 0, 3.379598617553711, 1688500027.3553069], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 6583, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 6]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00012310191838455054], 0, 3.4676947593688965, 1688500030.2704902], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 106055, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 192]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.026957273483276367, 1688499952.718822], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 68667, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[2.9923241245356314e-05], 0, 3.15340256690979, 1688500033.143367], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 34167, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[6.896538160427807e-05], 0, 3.311737060546875, 1688500036.1247866], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 8341, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 32, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 12]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.8919119075658526e-05], 0, 3.660676956176758, 1688500038.9808407], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 102044, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 8]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[8.00191479304677e-05], 0, 5.506258249282837, 1688500041.8900807], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 11754, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 16]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 24]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0013379136647350995], 0, 3.4334921836853027, 1688500044.891986], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 82791, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02694225311279297, 1688499952.718837], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 384, 13, 13], "float32"], ["TENSOR", [64, 384, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 103381, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 96]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02770686149597168, 1688499952.7188437], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 5713, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[6.161473271106467e-06], 0, 2.985595464706421, 1688500058.2527075], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7438, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0014089575468066492], 0, 4.189814805984497, 1688500061.1868205], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 100103, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 8]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.000802579764324863], 0, 6.0015788078308105, 1688500064.116994], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 46374, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[9.821864945256629e-06], 0, 3.877277135848999, 1688500066.9891667], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 14285, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.4129698456063412e-05], 0, 3.297962188720703, 1688500069.8502216], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 82761, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688500055.6382773], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 54865, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006083511618431074], 0, 5.661772966384888, 1688500072.7568994], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 28510, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[2.055577875658424e-05], 0, 3.665095090866089, 1688500075.691272], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 104306, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[3.143220921781409e-06], 0, 3.0453011989593506, 1688500078.242966], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 3726, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.772651390991179e-05], 0, 3.5072553157806396, 1688500081.1351576], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 22737, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 16]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00039823168012884043], 0, 3.5092270374298096, 1688500084.0989099], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 24278, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0016611668255933952], 0, 3.6372451782226562, 1688500087.0387626], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1797, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 32]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[2.7179731575273666e-05], 0, 3.2567243576049805, 1688500089.9324439], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 26699, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 16]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0031135879593810444], 0, 4.263184070587158, 1688500092.9380157], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 50095, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0014726355147058824], 0, 5.8304383754730225, 1688500094.275025], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 2893, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.2374832896912354e-05], 0, 3.1562039852142334, 1688500097.1205025], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 39176, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[7.389426671261199e-05], 0, 3.589160919189453, 1688500100.096519], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 62452, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[4.878183025901718e-06], 0, 3.0716629028320312, 1688500102.850362], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 63750, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[6.206063942938613e-06], 0, 3.071359157562256, 1688500105.6432135], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 60241, "code_hash": null, "entity": [["tile_f", "sp", [-1, 128, 2, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688500055.6402125], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 59083, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[2.3161107566776332e-05], 0, 3.456702470779419, 1688500108.579128], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 49763, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.003952247412776413], 0, 8.340228796005249, 1688500111.5448854], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 74741, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 128]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.001161299568231047], 0, 3.434267997741699, 1688500114.5337093], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 34108, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 8]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003232031885542169], 0, 4.219427108764648, 1688500117.4995959], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 108140, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03860020637512207, 1688500055.6402423], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 20975, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006220408552123552], 0, 3.5583813190460205, 1688500120.4254673], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 10252, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 4, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0008787481432461873], 0, 3.8138985633850098, 1688500123.384107], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 34409, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1.8185311536778088e-05], 0, 4.568842887878418, 1688500126.2918613], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 63848, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 64]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.6398028771004806e-05], 0, 3.210681438446045, 1688500129.1576958], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 60518, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 8]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[5.6993787850864756e-05], 0, 3.354098320007324, 1688500132.0833087], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 73773, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00013569943784199725], 0, 3.579986333847046, 1688500135.0037315], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 75492, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 1, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688500055.6567545], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 45096, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 1, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.01245757157364341], 0, 11.772417783737183, 1688500138.0580091], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 48678, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0013592431967769294], 0, 6.097264051437378, 1688500141.0055604], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 73753, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 128]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03271341323852539, 1688500055.6567717], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 77347, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1.7155525053066997e-05], 0, 3.380362033843994, 1688500143.9044957], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 22169, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 2, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.010915261304347824], 0, 8.040947437286377, 1688500145.3212702], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 45360, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 32]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.563844401002713e-05], 0, 3.6614489555358887, 1688500148.0884218], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 51232, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.609810005536417e-05], 0, 3.9068033695220947, 1688500150.983767], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 54122, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[5.123923961056365e-06], 0, 3.2007484436035156, 1688500153.6728892], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 12923, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[8.110417186869652e-06], 0, 3.212822437286377, 1688500156.5616183], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 110503, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 8]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0635983943939209, 1688500055.6567907], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 27740, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[4.234097005496425e-06], 0, 3.001598358154297, 1688500159.2678053], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 42528, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 8]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0007739494987916869], 0, 5.069399833679199, 1688500162.1794415], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 20759, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 16]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0407585986], 0, 3.24784255027771, 1688500164.001046], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 68487, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.004821907629807692], 0, 2.4987127780914307, 1688500176.0579367], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 323355, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.004843950497584542], 0, 6.565008640289307, 1688500177.4294798], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 187303, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 8, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.016960581627118644], 0, 2.9831748008728027, 1688500178.9384491], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 132983, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 64]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.037059280925925926], 0, 5.7856409549713135, 1688500180.7387795], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 252114, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 64]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03119373321533203, 1688500170.0721402], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 337690, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 8, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00010273418868044515], 0, 3.9864068031311035, 1688500183.7070765], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 152652, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.015133741686567165], 0, 5.729036331176758, 1688500185.2075415], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 213727, "code_hash": null, "entity": [["tile_f", "sp", [-1, 128, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03445148468017578, 1688500170.0721693], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 258110, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.048452138900756836, 1688500170.0721843], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 47486, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.022106290065217395], 0, 4.363563776016235, 1688500186.8300705], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 123531, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0015078673115060805], 0, 4.220163822174072, 1688500189.795328], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 124808, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003173706365599843], 0, 3.8752341270446777, 1688500192.7304263], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 121111, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[3.664222900062016e-05], 0, 3.685922145843506, 1688500195.6648445], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 327841, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 32]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0676417350769043, 1688500170.072208], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 162968, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0057476003333333334], 0, 5.107159376144409, 1688500197.0541885], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 316045, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 8, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0018476398081180812], 0, 3.083261013031006, 1688500198.3889906], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 414193, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 128, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.07745742797851562, 1688500170.0722263], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 209142, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.2266109863], 0, 12.245445489883423, 1688500201.2440314], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 42766, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[5.720093490112239e-05], 0, 3.7187352180480957, 1688500204.1766446], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 154215, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 16, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00047181105985401463], 0, 4.253648519515991, 1688500207.1302977], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 207112, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 32, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0021826615991285404], 0, 3.481504201889038, 1688500208.5209816], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 196763, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[5.589617982243184e-05], 0, 4.212954998016357, 1688500211.436714], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 437959, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688500174.8010337], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 127913, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 32, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.05586600303649902, 1688500174.8010538], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 139736, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 32]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.010323788350515464], 0, 10.842858791351318, 1688500212.8706563], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 273330, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00017974032049426696], 0, 3.5435752868652344, 1688500215.8459916], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 251223, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03481006622314453, 1688500174.8010662], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7001, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03851604461669922, 1688500174.8010728], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 401587, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 16]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03483271598815918, 1688500174.8010795], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 347817, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 128]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04675889015197754, 1688500174.8010862], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 222427, "code_hash": null, "entity": [["tile_f", "sp", [-1, 128, 1, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.014106537281690142], 0, 4.839421987533569, 1688500217.3189876], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 216335, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.01360356345945946], 0, 5.426243305206299, 1688500218.7947342], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 45710, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 6, 10, 1688500174.8068883], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 345155, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 16]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0017653100174863387], 0, 8.336342573165894, 1688500221.8135328], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 236664, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[5.4814321964389456e-05], 0, 3.566619396209717, 1688500224.733796], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 109118, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.06297111511230469, 1688500174.8069012], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 23774, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00026304465452771906], 0, 3.5888454914093018, 1688500227.6711462], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 336070, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00012581545816764135], 0, 4.285701274871826, 1688500230.6709929], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 400514, "code_hash": null, "entity": [["tile_f", "sp", [-1, 64, 2, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.0722048282623291, 1688500174.8069127], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 436250, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 64]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.004973946403940887], 0, 10.65053415298462, 1688500232.0691197], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 396816, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 64]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 3]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.02599355687179487], 0, 3.1266376972198486, 1688500233.706662], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 116719, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 3]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0027221270033726814], 0, 4.877391815185547, 1688500236.7107656], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 152580, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00017144149537774944], 0, 3.666530132293701, 1688500239.63954], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 308996, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.00021234925009867123], 0, 6.383876323699951, 1688500242.5760748], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 372669, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[6.145158392263292e-05], 0, 3.382798910140991, 1688500245.5285637], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 30273, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 64, 2]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.0364989876280702e-05], 0, 3.833811044692993, 1688500258.935002], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 51750, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 16, 4]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1.2095361532485266e-05], 0, 4.007847309112549, 1688500261.7423096], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 68122, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 16]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688500256.251299], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 13108, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 16, 2]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[8.883119226727143e-05], 0, 4.886237144470215, 1688500264.6613219], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 18675, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 1]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1.2913570477868422e-05], 0, 3.91413950920105, 1688500267.529253], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 30438, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 64, 2]], ["tile_x", "sp", [-1, 7, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.3084656870280024e-05], 0, 4.047465562820435, 1688500270.3932254], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 50561, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 2]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1.2173093504516311e-05], 0, 3.7457563877105713, 1688500273.2301192], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 21324, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 64, 1]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1.5090667024860594e-05], 0, 4.43035101890564, 1688500276.1168718], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 33985, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 64]], ["tile_x", "sp", [-1, 1, 49, 1]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.3214545249938965, 1688500256.2513406], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 12819, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 1, 8]], ["tile_x", "sp", [-1, 7, 1, 7]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.063411903375], 0, 3.967737913131714, 1688500278.1585398], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 50258, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 4, 4]], ["tile_x", "sp", [-1, 7, 7, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.00021062606867627785], 0, 5.149721384048462, 1688500281.1435716], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 3496, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 16, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.3481275599700473e-05], 0, 3.8699817657470703, 1688500284.034779], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 52388, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 4]], ["tile_x", "sp", [-1, 7, 1, 7]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.004504732698198198], 0, 3.7756402492523193, 1688500285.4241924], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 7189, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 4, 4]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[9.375293211903256e-06], 0, 3.7758677005767822, 1688500288.2072573], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 26668, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 4]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.204400975169091e-05], 0, 3.943084478378296, 1688500291.0872025], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 55807, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 32, 1]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[1.3038779547884782e-05], 0, 3.8650999069213867, 1688500293.9334762], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 27817, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 4]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[3.410576333912596e-05], 0, 4.226423263549805, 1688500296.8247554], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 18533, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 2]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[3.847639103458227e-05], 0, 4.288269758224487, 1688500299.7770321], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 62858, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 64]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00010982087011392319], 0, 6.218486785888672, 1688500302.700719], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 20623, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 128]], ["tile_x", "sp", [-1, 7, 7, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005049950834117278], 0, 4.077629566192627, 1688500305.6406984], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 19862, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 4, 2]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[5.6392763751063225e-05], 0, 3.9466617107391357, 1688500308.6005187], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 33680, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 4, 1]], ["tile_x", "sp", [-1, 7, 7, 1]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.1656029236110587e-05], 0, 4.287675619125366, 1688500311.4273689], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 12651, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 8]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[4.495738241561063e-05], 0, 4.382038593292236, 1688500314.379937], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 47611, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 4]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[2.721602493036926e-05], 0, 4.239719390869141, 1688500317.318629], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 52616, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 32]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.00048733884491654024], 0, 5.350194215774536, 1688500320.2465515], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 31486, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 16]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[9.925050070817167e-05], 0, 8.144112586975098, 1688500323.1889026], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 63663, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 16]], ["tile_x", "sp", [-1, 1, 49, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.0336076274779346e-05], 0, 6.673764944076538, 1688500326.1099105], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 65776, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 4]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.3539279975722895e-05], 0, 4.288797855377197, 1688500328.9686668], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 6067, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 16, 8]], ["tile_x", "sp", [-1, 1, 1, 7]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1.5972961521400497e-05], 0, 3.9636647701263428, 1688500331.7996097], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 62838, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 16]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0001150009701364578], 0, 10.260205268859863, 1688500334.7629342], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 38499, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 2, 2]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1.5600718006919585e-05], 0, 3.831536054611206, 1688500337.6136498], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 13442, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 32, 2]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[2.0175335025186998e-05], 0, 4.039684057235718, 1688500340.5010028], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 67846, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 16, 1]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1.2677144096561222e-05], 0, 5.1779749393463135, 1688500343.393073], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 29979, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 32, 1, 8]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.011359160084507042], 0, 5.031686544418335, 1688500346.472081], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 38321, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 64, 1]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[2.611687836703799e-05], 0, 4.012376546859741, 1688500349.3597965], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 57531, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 8]], ["tile_x", "sp", [-1, 1, 7, 7]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[3.97435008332297e-05], 0, 4.24284815788269, 1688500352.297541], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 41980, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 16, 8, 2]], ["tile_x", "sp", [-1, 7, 7, 1]], ["tile_rc", "sp", [-1, 16]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[4.019271694178538e-05], 0, 4.065429449081421, 1688500355.212876], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 43222, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 4, 1, 64]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0014869779231481482], 0, 4.277347564697266, 1688500358.1479094], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 29274, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 8, 2]], ["tile_x", "sp", [-1, 7, 1, 7]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0006590148351693187], 0, 5.458775281906128, 1688500361.1334739], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 33405, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 32, 2]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.854612210807455e-05], 0, 4.104572534561157, 1688500364.0251577], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 33971, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 2, 1, 32]], ["tile_x", "sp", [-1, 1, 49, 1]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1.2079535987295855e-05], 0, 3.9165396690368652, 1688500366.8464222], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 22011, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 8, 2]], ["tile_x", "sp", [-1, 1, 7, 1]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 0]]}, "result": [[1.040931355088608e-05], 0, 3.832648515701294, 1688500369.7109802], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 57597, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 2, 1]], ["tile_x", "sp", [-1, 1, 1, 49]], ["tile_rc", "sp", [-1, 64]], ["auto_unroll_max_step", "ot", 128], ["unroll_explicit", "ot", 1]]}, "result": [[0.00031148305532906234], 0, 4.01385498046875, 1688500372.6262627], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 28348, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 8, 1, 16]], ["tile_x", "sp", [-1, 7, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0007138239316163411], 0, 7.126375436782837, 1688500375.5549052], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw_winograd.cuda", [["TENSOR", [1, 64, 13, 13], "float32"], ["TENSOR", [256, 64, 3, 3], "float32"], [1, 1], [1, 1, 1, 1], [1, 1], "float32"], {}], "config": {"index": 66479, "code_hash": null, "entity": [["tile_b", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 1, 2, 32]], ["tile_x", "sp", [-1, 49, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006270988754879], 0, 9.864732265472412, 1688500378.531994], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 24845, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.022823333740234375, 1688500379.3054354], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 6380, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 32]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0026885559731182796], 0, 2.2173962593078613, 1688500390.5337296], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 19141, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 8]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[7.121744918483076e-05], 0, 3.5040321350097656, 1688500393.4577446], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 58458, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 16]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688500389.2921696], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 53332, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 16]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.039072275161743164, 1688500389.2921994], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 7677, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.0032403303689320386], 0, 2.2500593662261963, 1688500394.822259], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 69590, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0004763710091391509], 0, 5.164653778076172, 1688500397.792283], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 40905, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 32]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0035162072947368425], 0, 1.7268154621124268, 1688500399.1636834], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 73393, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[4.7071583602513657e-05], 0, 4.094351530075073, 1688500402.0880396], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 75103, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[4.989112519420795e-05], 0, 4.5983734130859375, 1688500405.0513642], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 30934, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[2.636660630391506e-05], 0, 3.905951976776123, 1688500407.9335957], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 57277, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 8]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[9.081200477689109e-05], 0, 3.6613826751708984, 1688500410.866495], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 40525, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00010039650728608794], 0, 3.233609437942505, 1688500413.8227909], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13605, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 32]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.005701806500000001], 0, 1.827282428741455, 1688500415.1998765], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 48971, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 64]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03741455078125, 1688500389.2922266], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 41191, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[7.076521674876846e-05], 0, 3.3371291160583496, 1688500418.1437767], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 13629, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 8, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[5.2452359937299975e-05], 0, 3.2849278450012207, 1688500421.0976841], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 1880, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 1, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.001310035389114541], 0, 4.3590004444122314, 1688500424.058218], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 50618, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.024272680282592773, 1688500389.2922382], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 40014, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00023395774362688297], 0, 3.3081610202789307, 1688500427.0096543], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 33740, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 4]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0001542816891375024], 0, 4.861953020095825, 1688500429.980529], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 45191, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 64]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.00289519699132948], 0, 1.9865868091583252, 1688500431.3456423], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 34200, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.014832143441176471], 0, 6.382049798965454, 1688500432.8408606], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 50913, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.04264569282531738, 1688500389.2922533], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 29675, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[3.856743444278774e-05], 0, 3.3437132835388184, 1688500435.8114219], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 67886, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[2.5885503936111384e-05], 0, 3.2364861965179443, 1688500438.6972253], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 51740, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 32]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02201533317565918, 1688500389.292263], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 25887, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 4, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.0411839485168457, 1688500389.2922714], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 35104, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 1, 16]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.005574519516666666], 0, 4.297640800476074, 1688500440.0784187], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 60929, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688500389.3160665], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 55394, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 2, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0007260661059721599], 0, 4.595272541046143, 1688500443.064609], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 57579, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006855512288747345], 0, 5.627155303955078, 1688500446.0019262], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 36106, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 8]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.04211735725402832, 1688500389.3160808], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 35322, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 4, 2]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0001499264764957265], 0, 6.844813346862793, 1688500449.0289586], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 55843, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 8]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[8.103239000554128e-05], 0, 3.3178043365478516, 1688500451.9860387], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 68204, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 32]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0006197853188961287], 0, 4.2984631061553955, 1688500454.941837], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 65315, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 16, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03076767921447754, 1688500389.316092], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 73769, "code_hash": null, "entity": [["tile_f", "sp", [-1, 16, 4, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.00010288889491178726], 0, 3.8483901023864746, 1688500457.870826], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 25177, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 4]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.026920795440673828, 1688500389.3161006], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 72922, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[7.724496215177714e-05], 0, 4.060246229171753, 1688500460.8290248], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 52703, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 2]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[5.4872589145962205e-05], 0, 3.427543878555298, 1688500463.7429233], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 65595, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 1, 16]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.0009731933299217339], 0, 4.5353474617004395, 1688500466.6946344], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 50160, "code_hash": null, "entity": [["tile_f", "sp", [-1, 32, 2, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.06465840339660645, 1688500389.3161116], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 48615, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 16, 4]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[2.358759089226213e-05], 0, 3.3990352153778076, 1688500469.629295], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [64, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 32004, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003985804972866305], 0, 8.006797552108765, 1688500472.56872], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 84030, "code_hash": null, "entity": [["tile_f", "sp", [-1, 5, 4, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[3.651725510905425e-05], 0, 3.101423740386963, 1688500486.1314137], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 200309, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 10, 20]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.0003927252863050353], 0, 3.407257080078125, 1688500489.07525], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 235931, "code_hash": null, "entity": [["tile_f", "sp", [-1, 10, 4, 25]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.029774904251098633, 1688500473.8873823], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 361776, "code_hash": null, "entity": [["tile_f", "sp", [-1, 25, 5, 4]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.035166263580322266, 1688500473.8873954], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 379710, "code_hash": null, "entity": [["tile_f", "sp", [-1, 250, 1, 2]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.8869938850402832, 1688500474.2049246], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 156499, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1000, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.022931337356567383, 1688500474.2049382], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 373747, "code_hash": null, "entity": [["tile_f", "sp", [-1, 20, 25, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.051309823989868164, 1688500474.2049465], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 77135, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 5, 25]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.000968307509196515], 0, 1.87449049949646, 1688500490.4089067], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 29603, "code_hash": null, "entity": [["tile_f", "sp", [-1, 5, 1, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[6.384536902348874e-05], 0, 3.2738547325134277, 1688500493.3826082], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 75796, "code_hash": null, "entity": [["tile_f", "sp", [-1, 20, 1, 5]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.2659492919], 0, 5.22533106803894, 1688500496.6452122], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 79983, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 2, 125]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 4, 2.8791935443878174, 1688500497.1455545], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 158233, "code_hash": null, "entity": [["tile_f", "sp", [-1, 20, 10, 5]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 16]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02718520164489746, 1688500475.8084102], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 190750, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 50]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02195262908935547, 1688500475.8084219], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 65419, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 5, 5]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.0005003972928483354], 0, 3.3937156200408936, 1688500500.1281543], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 365063, "code_hash": null, "entity": [["tile_f", "sp", [-1, 5, 1, 10]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.003031561278787879], 0, 1.8317079544067383, 1688500501.4919837], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 302239, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 25, 5]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.026947975158691406, 1688500475.808433], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 354424, "code_hash": null, "entity": [["tile_f", "sp", [-1, 100, 2, 1]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 32]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 6, 10, 1688500483.3538733], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 169906, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 5, 20]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.02619338035583496, 1688500483.353893], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 235523, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 25]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[0.003047754366037736], 0, 3.5581867694854736, 1688500504.4767992], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 307415, "code_hash": null, "entity": [["tile_f", "sp", [-1, 25, 4, 5]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.02457427978515625, 1688500483.3539035], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 253935, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 5, 25]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.025398969650268555, 1688500483.3539107], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 111617, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.03342628479003906, 1688500483.3539183], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 46020, "code_hash": null, "entity": [["tile_f", "sp", [-1, 10, 2, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.00017374729198493813], 0, 3.3047077655792236, 1688500507.4618464], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 103045, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 50, 5]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.043639183044433594, 1688500483.3539276], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 341095, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 100, 10]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.03298020362854004, 1688500483.3539343], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 63184, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 125]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.022629499435424805, 1688500483.3539417], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 143496, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 1, 20]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.00029773048877342734], 0, 3.63313889503479, 1688500510.3944705], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 189528, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 25]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.032196044921875, 1688500483.3539505], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 153102, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 2, 20]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[0.0003474401460215054], 0, 3.4940145015716553, 1688500513.33694], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 345123, "code_hash": null, "entity": [["tile_f", "sp", [-1, 2, 2, 25]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.0033137690033112586], 0, 4.593374490737915, 1688500514.7416797], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 239673, "code_hash": null, "entity": [["tile_f", "sp", [-1, 20, 25, 1]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.029512882232666016, 1688500483.3539624], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 46845, "code_hash": null, "entity": [["tile_f", "sp", [-1, 50, 5, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.039102792739868164, 1688500483.3539689], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 234596, "code_hash": null, "entity": [["tile_f", "sp", [-1, 20, 1, 5]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.023559093475341797, 1688500483.3539753], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 322328, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 4, 25]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[0.012208403048780488], 0, 3.1730079650878906, 1688500516.2153447], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 379408, "code_hash": null, "entity": [["tile_f", "sp", [-1, 25, 2, 5]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 512]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.05080914497375488, 1688500483.3539848], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 148126, "code_hash": null, "entity": [["tile_f", "sp", [-1, 4, 5, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[4.021837590536578e-05], 0, 3.1921043395996094, 1688500519.1593227], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 72318, "code_hash": null, "entity": [["tile_f", "sp", [-1, 8, 1, 25]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 2]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.018987935754716984], 0, 2.957503080368042, 1688500520.7505884], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 102842, "code_hash": null, "entity": [["tile_f", "sp", [-1, 20, 5, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 64]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[0.00040419045704983723], 0, 3.688307046890259, 1688500523.7049978], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 21027, "code_hash": null, "entity": [["tile_f", "sp", [-1, 25, 8, 5]], ["tile_y", "sp", [-1, 1, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 0], ["unroll_explicit", "ot", 0]]}, "result": [[0.004956720059113301], 0, 3.286017417907715, 1688500525.0953047], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 148114, "code_hash": null, "entity": [["tile_f", "sp", [-1, 5, 2, 2]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[3.840104351058981e-05], 0, 3.2278966903686523, 1688500528.0437171], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 274049, "code_hash": null, "entity": [["tile_f", "sp", [-1, 5, 8, 1]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 13]], ["tile_rc", "sp", [-1, 4]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.003007322018018018], 0, 2.250117301940918, 1688500529.4160752], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 365571, "code_hash": null, "entity": [["tile_f", "sp", [-1, 10, 1, 100]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 128]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 1]]}, "result": [[1000000000.0], 1, 0.027098655700683594, 1688500483.3540008], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 87825, "code_hash": null, "entity": [["tile_f", "sp", [-1, 1, 8, 5]], ["tile_y", "sp", [-1, 1, 1, 13]], ["tile_x", "sp", [-1, 1, 13, 1]], ["tile_rc", "sp", [-1, 8]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 0]]}, "result": [[6.953101079028012e-05], 0, 3.2292566299438477, 1688500532.3705692], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 257108, "code_hash": null, "entity": [["tile_f", "sp", [-1, 10, 5, 20]], ["tile_y", "sp", [-1, 1, 13, 1]], ["tile_x", "sp", [-1, 1, 1, 1]], ["tile_rc", "sp", [-1, 1]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 512], ["unroll_explicit", "ot", 1]]}, "result": [[0.000532918897790966], 0, 3.7259232997894287, 1688500535.381121], "version": 0.2, "tvm_version": "0.11.dev0"} +{"input": ["cuda -keys=cuda,gpu -arch=sm_89 -max_num_threads=1024 -thread_warp_size=32", "conv2d_nchw.cuda", [["TENSOR", [1, 512, 13, 13], "float32"], ["TENSOR", [1000, 512, 1, 1], "float32"], [1, 1], [0, 0, 0, 0], [1, 1], "float32"], {}], "config": {"index": 181503, "code_hash": null, "entity": [["tile_f", "sp", [-1, 5, 2, 20]], ["tile_y", "sp", [-1, 13, 1, 1]], ["tile_x", "sp", [-1, 13, 1, 1]], ["tile_rc", "sp", [-1, 256]], ["tile_ry", "sp", [-1, 1]], ["tile_rx", "sp", [-1, 1]], ["auto_unroll_max_step", "ot", 1500], ["unroll_explicit", "ot", 0]]}, "result": [[1000000000.0], 1, 0.07652401924133301, 1688500483.3540103], "version": 0.2, "tvm_version": "0.11.dev0"}