-
Notifications
You must be signed in to change notification settings - Fork 559
[ET-VK] De vectorise conv2d pw shader to improve perf. #11108
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[ET-VK] De vectorise conv2d pw shader to improve perf. #11108
Conversation
This diff optimizes the performance of the `conv2d_pw` shader by de-vectorizing its implementation. * The original vectorized implementation of the `conv2d_pw` shader has been replaced with a de-vectorized approach to improve performance. * The `sum` array has been redefined to hold `float` values instead of `vec4` to accommodate the de-vectorized computation. These changes seem to allow shader compiler to better optimize operations within the shader hence improving perf. Differential Revision: [D75307267](https://our.internmc.facebook.com/intern/diff/D75307267/) [ghstack-poisoned]
This diff optimizes the performance of the `conv2d_pw` shader by de-vectorizing its implementation. * The original vectorized implementation of the `conv2d_pw` shader has been replaced with a de-vectorized approach to improve performance. * The `sum` array has been redefined to hold `float` values instead of `vec4` to accommodate the de-vectorized computation. These changes seem to allow shader compiler to better optimize operations within the shader hence improving perf. Differential Revision: [D75307267](https://our.internmc.facebook.com/intern/diff/D75307267/) ghstack-source-id: 285942441 Pull Request resolved: #11108
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11108
Note: Links to docs will display an error until the docs builds have been completed. ✅ You can merge normally! (2 Unrelated Failures)As of commit a57f7bf with merge base 380eb5f ( BROKEN TRUNK - The following jobs failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This pull request was exported from Phabricator. Differential Revision: D75307267 |
This diff optimizes the performance of the `conv2d_pw` shader by de-vectorizing its implementation. * The original vectorized implementation of the `conv2d_pw` shader has been replaced with a de-vectorized approach to improve performance. * The `sum` array has been redefined to hold `float` values instead of `vec4` to accommodate the de-vectorized computation. These changes seem to allow shader compiler to better optimize operations within the shader hence improving perf. Differential Revision: [D75307267](https://our.internmc.facebook.com/intern/diff/D75307267/) [ghstack-poisoned]
This pull request was exported from Phabricator. Differential Revision: D75307267 |
This diff optimizes the performance of the `conv2d_pw` shader by de-vectorizing its implementation. * The original vectorized implementation of the `conv2d_pw` shader has been replaced with a de-vectorized approach to improve performance. * The `sum` array has been redefined to hold `float` values instead of `vec4` to accommodate the de-vectorized computation. These changes seem to allow shader compiler to better optimize operations within the shader hence improving perf. Differential Revision: [D75307267](https://our.internmc.facebook.com/intern/diff/D75307267/) [ghstack-poisoned]
This pull request was exported from Phabricator. Differential Revision: D75307267 |
This diff optimizes the performance of the `conv2d_pw` shader by de-vectorizing its implementation. * The original vectorized implementation of the `conv2d_pw` shader has been replaced with a de-vectorized approach to improve performance. * The `sum` array has been redefined to hold `float` values instead of `vec4` to accommodate the de-vectorized computation. These changes seem to allow shader compiler to better optimize operations within the shader hence improving perf. Differential Revision: [D75307267](https://our.internmc.facebook.com/intern/diff/D75307267/) [ghstack-poisoned]
This pull request was exported from Phabricator. Differential Revision: D75307267 |
This diff optimizes the performance of the `conv2d_pw` shader by de-vectorizing its implementation. * The original vectorized implementation of the `conv2d_pw` shader has been replaced with a de-vectorized approach to improve performance. * The `sum` array has been redefined to hold `float` values instead of `vec4` to accommodate the de-vectorized computation. These changes seem to allow shader compiler to better optimize operations within the shader hence improving perf. Differential Revision: [D75307267](https://our.internmc.facebook.com/intern/diff/D75307267/) [ghstack-poisoned]
This pull request was exported from Phabricator. Differential Revision: D75307267 |
This diff optimizes the performance of the `conv2d_pw` shader by de-vectorizing its implementation. * The original vectorized implementation of the `conv2d_pw` shader has been replaced with a de-vectorized approach to improve performance. * The `sum` array has been redefined to hold `float` values instead of `vec4` to accommodate the de-vectorized computation. These changes seem to allow shader compiler to better optimize operations within the shader hence improving perf. Differential Revision: [D75307267](https://our.internmc.facebook.com/intern/diff/D75307267/) [ghstack-poisoned]
This pull request was exported from Phabricator. Differential Revision: D75307267 |
This diff optimizes the performance of the `conv2d_pw` shader by de-vectorizing its implementation. * The original vectorized implementation of the `conv2d_pw` shader has been replaced with a de-vectorized approach to improve performance. * The `sum` array has been redefined to hold `float` values instead of `vec4` to accommodate the de-vectorized computation. These changes seem to allow shader compiler to better optimize operations within the shader hence improving perf. Differential Revision: [D75307267](https://our.internmc.facebook.com/intern/diff/D75307267/) [ghstack-poisoned]
This pull request was exported from Phabricator. Differential Revision: D75307267 |
cecc15d
into
gh/trivedivivek/89/base
This PR was created by the merge bot to help merge the original PR into the main branch. ghstack PR number: #11108 by @trivedivivek ^ Please use this as the source of truth for the PR details, comments, and reviews ghstack PR base: https://github.com/pytorch/executorch/tree/gh/trivedivivek/89/base ghstack PR head: https://github.com/pytorch/executorch/tree/gh/trivedivivek/89/head Merge bot PR base: https://github.com/pytorch/executorch/tree/main Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/trivedivivek/89/orig @diff-train-skip-merge Co-authored-by: Vivek Trivedi <[email protected]>
Stack from ghstack (oldest at bottom):
This diff optimizes the performance of the
conv2d_pw
shader by de-vectorizing its implementation.conv2d_pw
shader has been replaced with a de-vectorized approach to improve performance.sum
array has been redefined to holdfloat
values instead ofvec4
to accommodate the de-vectorized computation.These changes seem to allow shader compiler to better optimize operations within the shader hence improving perf.
Differential Revision: D75307267