Tweak KleidiAI's FP16 matmul algorithm #4416
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
Summary: Hoist memory loads from the outer loop Intention is to prevent these loads from displacing cache lines, as they may contain matrix data. Similarly, the loads are likely to inccur in cache misses after the first iteration. Executing the inner loop will probably fill the cache with matrix data. Benchmarks repeatedly show a throughput improvement of around 1%. before: P1854747253 after: P1854747141 Differential Revision: D77459967
✅ Deploy Preview for pytorch-fbgemm-docs ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
|
This pull request was exported from Phabricator. Differential Revision: D77459967 |
|
This pull request has been merged in db4f7a3. |
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Outdated suggestions cannot be applied.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:
Hoist memory loads from the outer loop
Intention is to prevent these loads from displacing cache lines, as they may contain matrix data.
Similarly, the loads are likely to inccur in cache misses after the first iteration. Executing the inner loop will probably fill the cache with matrix data.
Benchmarks repeatedly show a throughput improvement of around 1%.
before:
P1854747253
after:
P1854747141
Differential Revision: D77459967