Minor changes to native layer norm shader op to improve perf. #10585
Conversation
This file contains hidden or 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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10585
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 9f58e6a with merge base 75f1eea ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D73864950 |
trivedivivek
force-pushed
the
export-D73864950
branch
from
b6bc4bf to
286d2a0
Compare
trivedivivek
added a commit
to trivedivivek/executorch
that referenced
this pull request
May 1, 2025
…h#10585) Summary: This diff improves perf by changing native layer norm shader to accumulate result in local variable instead of shared memory, and do a shared memory pass later. Differential Revision: D73864950
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D73864950 |
SS-JIA
approved these changes
May 1, 2025
…h#10585) Summary: This diff improves perf by changing native layer norm shader to accumulate result in local variable instead of shared memory, and do a shared memory pass later. Reviewed By: SS-JIA Differential Revision: D73864950
trivedivivek
force-pushed
the
export-D73864950
branch
from
286d2a0 to
9f58e6a
Compare
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D73864950 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
Summary: This diff improves perf by changing native layer norm shader to accumulate result in local variable instead of shared memory, and do a shared memory pass later.
Differential Revision: D73864950