[codegen][gpu] Removing zero slice check from gpu_apply_tiling_level #20120
+3
−3
Conversation
This file contains 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
Signed-off-by: jerryyin <[email protected]>
qedawkins
approved these changes
Feb 27, 2025
nirvedhmeshram
approved these changes
Feb 27, 2025
|
MI300 machine is failing with I'll leave this PR a bit longer till merge. Hopefully wait till when CI on MI300 machine is fixed to get a round of model level regression coverage there. |
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Outdated suggestions cannot be applied.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.
This PR flipped the switch for
allow-zero-sliceoption, which means zero slice will be tolerated for igemm that requires a padding. The dynamic if condition check is unnecessary because we compute the K loop bound in a reasonable fashion and zero slice situation shouldn't happen. The motivation of the PR is performance benefit to remove an unnecessary conditional from padded gemm global loading.