Profiler: fix fp32 c-shuffle gemm tuning parameter#194
Merged
Conversation
Contributor
|
@rosenrodt Is KPerBlock =16 optimal? Have you test other KPerBlock, i.e., KPerBlock = 8? |
Contributor
Author
@zjing14 I haven't tried K1=8 but K1=32 is slow for FP32 due to lowered occupancy. It's also just the same K1 value as in DeviceGemmXdl's |
asroy
approved these changes
Apr 21, 2022
Contributor
|
@rosenrodt This PR doesn't seem to be picked up by CI. |
Contributor
Author
@asroy I just manually triggered the CI |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixed oversight in PR #159
FP32 kernel's KPerBlock is changed from 32 to 16 to avoid register spill