use reshape to handle flatten

[shivadbhavsar]

Fixes #3579

[codecov]

Codecov Report

Attention: Patch coverage is 53.84615% with 6 lines in your changes missing coverage. Please review.

Project coverage is 92.13%. Comparing base (5388984) to head (c525f49).
Report is 127 commits behind head on develop.

Files with missing lines	Patch %	Lines
src/include/migraphx/op/flatten.hpp	0.00%	6 Missing ⚠️

Additional details and impacted files

@@             Coverage Diff             @@
##           develop    #3584      +/-   ##
===========================================
- Coverage    92.16%   92.13%   -0.03%     
===========================================
  Files          512      512              
  Lines        21412    21424      +12     
===========================================
+ Hits         19735    19740       +5     
- Misses        1677     1684       +7     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

[migraphx-bot]

Test	Batch	Rate new c525f4	Rate old 77ab44	Diff	Compare
torchvision-resnet50	64	3,260.32	3,259.78	0.02%	✅
torchvision-resnet50_fp16	64	6,994.99	6,995.97	-0.01%	✅
torchvision-densenet121	32	2,436.13	2,436.42	-0.01%	✅
torchvision-densenet121_fp16	32	4,039.53	4,071.94	-0.80%	✅
torchvision-inceptionv3	32	1,637.83	1,639.03	-0.07%	✅
torchvision-inceptionv3_fp16	32	2,761.91	2,763.00	-0.04%	✅
cadene-inceptionv4	16	776.46	776.59	-0.02%	✅
cadene-resnext64x4	16	811.38	808.43	0.37%	✅
slim-mobilenet	64	7,533.37	7,532.81	0.01%	✅
slim-nasnetalarge	64	211.52	211.50	0.01%	✅
slim-resnet50v2	64	3,505.66	3,504.45	0.03%	✅
bert-mrpc-onnx	8	1,149.21	1,150.80	-0.14%	✅
bert-mrpc-tf	1	468.22	464.16	0.87%	✅
pytorch-examples-wlang-gru	1	421.34	424.10	-0.65%	✅
pytorch-examples-wlang-lstm	1	389.19	397.87	-2.18%	✅
torchvision-resnet50_1	1	769.94	817.55	-5.82%	🔴
cadene-dpn92_1	1	397.43	436.30	-8.91%	🔴
cadene-resnext101_1	1	384.13	374.14	2.67%	✅
onnx-taau-downsample	1	343.14	343.01	0.04%	✅
dlrm-criteoterabyte	1	33.35	33.36	-0.02%	✅
dlrm-criteoterabyte_fp16	1	52.74	52.73	0.01%	✅
agentmodel	1	7,976.52	8,198.74	-2.71%	✅
unet_fp16	2	58.76	58.86	-0.17%	✅
resnet50v1_fp16	1	946.33	987.67	-4.19%	🔴
resnet50v1_int8	1	1,040.07	991.53	4.89%	🔆
bert_base_cased_fp16	64	1,170.10	1,171.75	-0.14%	✅
bert_large_uncased_fp16	32	363.51	363.44	0.02%	✅
bert_large_fp16	1	199.34	198.74	0.31%	✅
distilgpt2_fp16	16	2,204.35	2,194.99	0.43%	✅
yolov5s	1	542.56	538.41	0.77%	✅
tinyllama	1	43.48	43.41	0.15%	✅
vicuna-fastchat	1	178.89	174.43	2.56%	✅
whisper-tiny-encoder	1	418.09	418.43	-0.08%	✅
whisper-tiny-decoder	1	425.96	426.61	-0.15%	✅

This build is not recommended to merge 🔴

[migraphx-bot]

     ✅ bert-mrpc-onnx: PASSED: MIGraphX meets tolerance

     ✅ bert-mrpc-tf: PASSED: MIGraphX meets tolerance

     ✅ pytorch-examples-wlang-gru: PASSED: MIGraphX meets tolerance

     ✅ pytorch-examples-wlang-lstm: PASSED: MIGraphX meets tolerance

     ✅ torchvision-resnet50_1: PASSED: MIGraphX meets tolerance

     ✅ cadene-dpn92_1: PASSED: MIGraphX meets tolerance

     ✅ cadene-resnext101_1: PASSED: MIGraphX meets tolerance

     ✅ dlrm-criteoterabyte: PASSED: MIGraphX meets tolerance

     ✅ agentmodel: PASSED: MIGraphX meets tolerance

     ✅ unet: PASSED: MIGraphX meets tolerance

     ✅ resnet50v1: PASSED: MIGraphX meets tolerance

     ✅ bert_base_cased_fp16: PASSED: MIGraphX meets tolerance

🔴bert_large_uncased_fp16: FAILED: MIGraphX is not within tolerance - check verbose output

     ✅ bert_large: PASSED: MIGraphX meets tolerance

     ✅ yolov5s: PASSED: MIGraphX meets tolerance

     ✅ tinyllama: PASSED: MIGraphX meets tolerance

     ✅ vicuna-fastchat: PASSED: MIGraphX meets tolerance

     ✅ whisper-tiny-encoder: PASSED: MIGraphX meets tolerance

     ✅ whisper-tiny-decoder: PASSED: MIGraphX meets tolerance

     ✅ distilgpt2_fp16: PASSED: MIGraphX meets tolerance