Skip to content

[ET-VK] Remove the use of shared memory in conv2d pw to improve perf. #11183

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

Merged
merged 3 commits into from
May 28, 2025

Conversation

pytorchbot
Copy link
Collaborator

This PR was created by the merge bot to help merge the original PR into the main branch.
ghstack PR number: #11110 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/90/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/trivedivivek/90/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/trivedivivek/89/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/trivedivivek/90/orig
@diff-train-skip-merge

Pull Request resolved: #11108

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.
ghstack-source-id: 286652100
@exported-using-ghexport

Differential Revision: [D75307267](https://our.internmc.facebook.com/intern/diff/D75307267/)
Pull Request resolved: #11110

This diff removes the use of shared memory in the conv2d pw (pointwise) operation to improve performance.
ghstack-source-id: 286652103

Differential Revision: [D75316188](https://our.internmc.facebook.com/intern/diff/D75316188/)
@pytorchbot pytorchbot requested a review from SS-JIA as a code owner May 28, 2025 15:53
Copy link

pytorch-bot bot commented May 28, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/11183

Note: Links to docs will display an error until the docs builds have been completed.

❌ 1 New Failure, 2 Pending, 2 Unrelated Failures

As of commit 4746119 with merge base 18e5eca (image):

NEW FAILURE - The following job has failed:

FLAKY - The following job failed but was likely due to flakiness present on trunk:

BROKEN TRUNK - The following job failed but was 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.

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label May 28, 2025
@trivedivivek trivedivivek added the release notes: vulkan Changes to the Vulkan backend delegate label May 28, 2025
Base automatically changed from gh/trivedivivek/89/orig to main May 28, 2025 17:20
@trivedivivek trivedivivek merged commit b4b48e7 into main May 28, 2025
93 of 96 checks passed
@trivedivivek trivedivivek deleted the gh/trivedivivek/90/orig branch May 28, 2025 18:51
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. release notes: vulkan Changes to the Vulkan backend delegate
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants