Split loops to work around loop vectorizer weakness #3406
Closed
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
✅ Deploy Preview for pytorch-fbgemm-docs ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
|
This pull request was exported from Phabricator. Differential Revision: D65574038 |
Summary: X-link: facebookresearch/FBGEMM#494 I noticed LLVM loop vectorization making bad calls for loops with trip-counts that are not a multiple of the preferred vector size. This can be worked around by manually splitting into two loops with the first one processing in multiples of the preferred block size and a separate loop for the remainder. Reviewed By: helloguo Differential Revision: D65574038
MatzeB
force-pushed
the
export-D65574038
branch
from
25e2508 to
c3460f5
Compare
|
This pull request was exported from Phabricator. Differential Revision: D65574038 |
|
This pull request has been merged in f110630. |
q10
pushed a commit
to q10/FBGEMM
that referenced
this pull request
Apr 10, 2025
Summary: X-link: pytorch#3406 Pull Request resolved: facebookresearch/FBGEMM#494 I noticed LLVM loop vectorization making bad calls for loops with trip-counts that are not a multiple of the preferred vector size. This can be worked around by manually splitting into two loops with the first one processing in multiples of the preferred block size and a separate loop for the remainder. Reviewed By: helloguo Differential Revision: D65574038 fbshipit-source-id: 491c63954b0ceb49eb65c4afb6f1a93706dfa525
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Outdated suggestions cannot be applied.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.
Summary:
I noticed LLVM loop vectorization making bad calls for loops with trip-counts that are not a multiple of the preferred vector size.
This can be worked around by manually splitting into two loops with the first one processing in multiples of the preferred block size and a separate loop for the remainder.
Reviewed By: helloguo
Differential Revision: D65574038