[PROTON-DEV] protongpu shared memory buffer conversion pass #6029
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
Jokeren
reviewed
Feb 26, 2025
third_party/proton/dialect/lib/ProtonGPUToLLVM/AllocateProtonSharedMemory.cpp
Show resolved
Hide resolved
Jokeren
reviewed
Feb 27, 2025
| // Compute the proton buffer size in bytes. | ||
| auto memDescTy = | ||
| mlir::cast<triton::gpu::MemDescType>(alloc.getResult().getType()); | ||
| int bufferSizeInBytes = memDescTy.getShape()[0] * 4; |
There was a problem hiding this comment.
Can we use getNumElements? just for generality.
There was a problem hiding this comment.
Sure. You mean a helper function? The shape is an ArrayRef not a RankedTensorType.
There was a problem hiding this comment.
I think memDescTy has a getNumElements method. Correct me if I were wrong.
There was a problem hiding this comment.
I see what you are saying. You are referring to mlir::ShapedType::getNumElements.
Done.
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Outdated suggestions cannot be applied.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.
In this PR, we add the support for proton's internal SMEM profiling buffer conversion. This pass happens after
proton-to-protongpulowering and after the general triton'sshared-memory-allocpass. We basically override thettg.sharedattributes and annotate the shared memory alloc op proton inserted.