Skip to content

[mlir][nvgpu] Remove strict verifiers on warpgroup.generate.descriptor #69935

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

[mlir][nvgpu] Remove strict verifiers on warpgroup.generate.descriptor #69935

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 0 additions & 6 deletions mlir/lib/Dialect/NVGPU/IR/NVGPUDialect.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -375,15 +375,9 @@ LogicalResult WarpgroupGenerateDescriptorOp::verify() {
MemRefType memrefType = getTensor().getType();
MemRefType tensorMapType = getTensorMap().getType().getTensor();

if (memrefType != tensorMapType)
return emitError() << "memref and tensor map type mismatch";
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What's the semantic of unmatched memref/tensor types?

Could you add a test case demonstrating this case?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The issue is similar what we discuss here.


if (!memrefType.hasStaticShape() || !tensorMapType.hasStaticShape())
return emitError() << "supports only static shapes";

if (memrefType.getRank() != 2)
return emitError() << "supports only 2d memref is supported for now";
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Since this is supposed to be used to feed into wgmma operations, why do we need to support more than 2ds?

(Sorry for the dumb questions x).)


if (getTensorMap().getType().getSwizzle() !=
TensorMapSwizzleKind::SWIZZLE_128B) {
return emitError() << "supports only "
Expand Down