[Codegen][GPU] Finish splitting NV intrinsics from AMD ones #19853
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
The split of `WMMA_*` enums into Nvidia and AMD variants was half finished. This completely splits the handling of each vendor. In the process, because concrete layouts for nvidia intrinsics is unimplemented, the only supported case is opaque layouts via SPIR-V. This required re-introducing `getMNKShape` per enum value rather than inferring it from the layout. This PR is effectively NFC, but unblocks enabling LLVMGPUTileAndFuse by default for matmuls.
bjacob
reviewed
Jan 30, 2025
compiler/src/iree/compiler/Codegen/Dialect/GPU/IR/IREEGPUAttrs.cpp
Outdated
Show resolved
Hide resolved
bjacob
approved these changes
Jan 31, 2025
ita9naiwa
pushed a commit
to ita9naiwa/iree
that referenced
this pull request
Feb 4, 2025
…#19853) The split of `WMMA_*` enums into Nvidia and AMD variants was half finished. This completely splits the handling of each vendor. In the process, because concrete layouts for nvidia intrinsics is unimplemented, the only supported case is opaque layouts via SPIR-V. This required re-introducing `getMNKShape` per enum value rather than inferring it from the layout. This PR is effectively NFC, but unblocks enabling LLVMGPUTileAndFuse by default for matmuls. Signed-off-by: Hyunsung Lee <[email protected]>
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Outdated suggestions cannot be applied.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.
The split of
WMMA_*enums into Nvidia and AMD variants was half finished. This completely splits the handling of each vendor. In the process, because concrete layouts for nvidia intrinsics is unimplemented, the only supported case is opaque layouts via SPIR-V. This required re-introducinggetMNKShapeper enum value rather than inferring it from the layout.This PR is effectively NFC, but unblocks enabling LLVMGPUTileAndFuse by default for matmuls.