[ET-VK] Minor improvement to q_linear op shader. #7643
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
## Context The stack of diffs aims to optimize the performance of the Executorch Vulkan backend by making changes to the q_linear, q_8w_linear, and conv2d_pw ops. The changes include reducing the precision of int storage, reducing register usage, improving texture coordinate storage, and reducing shader register pressure. The overall purpose of the diffs is to improve the performance of Executorch on Vulkan-based devices. ## This Diff This diff contains a minor improvement to the q_linear op shader in the Vulkan backend for Executorch. The code changes in the q_8w_linear.glsl file include a change in the input parameter from a 3-element u16vec3 to a 2-element u16vec2, and a change in the loop variable from i to x. The changes were made to improve the performance of the shader. Differential Revision: [D68113154](https://our.internmc.facebook.com/intern/diff/D68113154/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/7643
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 4cb5e1d with merge base c9db811 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
trivedivivek
added a commit
that referenced
this pull request
Jan 14, 2025
## Context The stack of diffs aims to optimize the performance of the Executorch Vulkan backend by making changes to the q_linear, q_8w_linear, and conv2d_pw ops. The changes include reducing the precision of int storage, reducing register usage, improving texture coordinate storage, and reducing shader register pressure. The overall purpose of the diffs is to improve the performance of Executorch on Vulkan-based devices. ## This Diff This diff contains a minor improvement to the q_linear op shader in the Vulkan backend for Executorch. The code changes in the q_8w_linear.glsl file include a change in the input parameter from a 3-element u16vec3 to a 2-element u16vec2, and a change in the loop variable from i to x. The changes were made to improve the performance of the shader. Differential Revision: [D68113154](https://our.internmc.facebook.com/intern/diff/D68113154/) ghstack-source-id: 261204381 Pull Request resolved: #7643
|
This pull request was exported from Phabricator. Differential Revision: D68113154 |
SS-JIA
approved these changes
Jan 22, 2025
trivedivivek
had a problem deploying
to
cherry-pick-bot
GitHub Actions
Failure
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Stack from ghstack (oldest at bottom):
Context
The stack of diffs aims to optimize the performance of the Executorch Vulkan backend by making changes to the q_linear, q_8w_linear, and conv2d_pw ops. The changes include reducing the precision of int storage, reducing register usage, improving texture coordinate storage, and reducing shader register pressure. The overall purpose of the diffs is to improve the performance of Executorch on Vulkan-based devices.
This Diff
This diff contains a minor improvement to the q_linear op shader in the Vulkan backend for Executorch. The code changes in the q_8w_linear.glsl file include a change in the input parameter from a 3-element u16vec3 to a 2-element u16vec2, and a change in the loop variable from i to x. The changes were made to improve the performance of the shader.
Differential Revision: D68113154