[fix]: Resolve perf regression of fused_ar_rms on MI300 and MI355 - #1616
Merged
Merged
Conversation
Signed-off-by: root <root@hjbog-srdc-24.amd.com>
valarLip
approved these changes
Dec 14, 2025
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
Fix the performance regression of fused_allreduce_rmsnorm on MI300 and MI355.
Technical Details
Split the cross-device reads and writes within a single persistent into two separate persistent to avoid bandwidth contention on XMGI.
Test Plan
case (256, 16384), run with AITER_LOG_MORE=1
Test Result
The performance of fused_allreduce_rmsnorm on MI300 and MI355 is no longer worse than that of the separated operators, although the optimization effect is not as significant as on MI308.
Submission Checklist