[GPUHeuristics] Fix RDNA4 conv heuristic seeds to resolve regressions#23841
Merged
yzhang93 merged 1 commit intoiree-org:mainfrom Mar 20, 2026
Merged
[GPUHeuristics] Fix RDNA4 conv heuristic seeds to resolve regressions#23841yzhang93 merged 1 commit intoiree-org:mainfrom
yzhang93 merged 1 commit intoiree-org:mainfrom
Conversation
yzhang93
requested review from
Groverkss,
Max191,
krzysz00,
kuhar,
nirvedhmeshram and
qedawkins
as code owners
yzhang93
force-pushed
the
rdna4-improve-conv-seeds
branch
2 times, most recently
from
a35e384 to
f5759b8
Compare
After the previous RDNA4 seed tuning commit, several medium/large-sized convolution shapes showed significant regressions. To fix the issue, increase conv subgroupCount seed from 4 to 8. This change will bring back the performance upto 2x faster, while not introduce new regressions. Also update the convolution tests to use IGEMM path with use_igemm=true. Signed-off-by: yzhang93 <zhyuhang88@gmail.com>
yzhang93
force-pushed
the
rdna4-improve-conv-seeds
branch
from
f5759b8 to
a666b6b
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
After the previous RDNA4 seed tuning commit, several medium/large-sized convolution shapes showed significant regressions. To fix the issue, increase conv subgroupCount seed from 4 to 8. This change will bring back the performance upto 2x faster, while not introduce new regressions.
Also update the convolution tests to use IGEMM path with use_igemm=true.