[mlir][nvvm] Fix the verifier of wgmma.mma_async wrt transposed layouts

[shubaoyu2]

the WGMMA expect layouts for A/B are row/col, the transposed version should be col/row. when checking other datatypes cannot use transposed layout, it should reject col-major for A and row-major for B

[github-actions]

Thank you for submitting a Pull Request (PR) to the LLVM Project!

This PR will be automatically labeled and the relevant teams will be
notified.

If you wish to, you can add reviewers by using the "Reviewers" section on this page.

If this is not working for you, it is probably because you do not have write
permissions for the repository. In which case you can instead tag reviewers by
name in a comment by using @ followed by their GitHub username.

If you have received no comments on your PR for a week, you can request a review
by "ping"ing the PR by adding a comment “Ping”. The common courtesy "ping" rate
is once a week. Please remember that you are asking for valuable time from other developers.

If you have further questions, they may be answered by the LLVM GitHub User Guide.

You can also ask questions in a comment on this PR, on the LLVM Discord or on the forums.

[llvmbot]

@llvm/pr-subscribers-mlir-llvm

@llvm/pr-subscribers-mlir

Author: bangyu shen (shubaoyu2)

Changes

the WGMMA expect layouts for A/B are row/col, the transposed version should be col/row. when checking other datatypes cannot use transposed layout, it should reject col-major for A and row-major for B

---

Full diff: https://github.com/llvm/llvm-project/pull/97538.diff

1 Files Affected:

• (modified) mlir/lib/Dialect/LLVMIR/IR/NVVMDialect.cpp (+1-1)

diff --git a/mlir/lib/Dialect/LLVMIR/IR/NVVMDialect.cpp b/mlir/lib/Dialect/LLVMIR/IR/NVVMDialect.cpp
index 036a9a15af838..48f44165ccc58 100644
--- a/mlir/lib/Dialect/LLVMIR/IR/NVVMDialect.cpp
+++ b/mlir/lib/Dialect/LLVMIR/IR/NVVMDialect.cpp
@@ -880,7 +880,7 @@ LogicalResult NVVM::WgmmaMmaAsyncOp::verify() {
   // Check transpose (only available for f16/bf16)
   if ((typeA != WGMMATypes::f16 && typeA != WGMMATypes::bf16) &&
       (getLayoutA() == mlir::NVVM::MMALayout::col ||
-       getLayoutB() == mlir::NVVM::MMALayout::col)) {
+       getLayoutB() == mlir::NVVM::MMALayout::row)) {
     return emitOpError()
            << "given layouts layout_a = " << stringifyMMALayout(getLayoutA())
            << " and layout_b = " << stringifyMMALayout(getLayoutB())

[grypp]

Looks good. Let's add comments in the code.

For the title, we use [mlir][nvvm] prefix

[grypp]

Awesome thanks for working on this

[grypp]

I will merge it once the buildkite is done

[github-actions]

✅ With the latest revision this PR passed the C/C++ code formatter.

[grypp]

@shubaoyu2 you need to run clang-format on your code. The buildkite fails here

[github-actions]

@shubaoyu2 Congratulations on having your first Pull Request (PR) merged into the LLVM Project!

Your changes will be combined with recent changes from other authors, then tested
by our build bots. If there is a problem with a build, you may receive a report in an email or a comment on this PR.

Please check whether problems have been caused by your change specifically, as
the builds can include changes from many authors. It is not uncommon for your
change to be included in a build that fails due to someone else's changes, or
infrastructure issues.

How to do this, and the rest of the post-merge process, is covered in detail here.

If your change does cause a problem, it may be reverted, or you can revert it yourself.
This is a normal part of LLVM development. You can fix your changes and open a new PR to merge them again.

If you don't get any reports, no action is required from you. Your changes are working as expected, well done!