[MLIR][NVGPU-Tests] Fix a failing sm90 test #111731
Merged
Conversation
This file contains hidden or 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
For memref, output_shape is required now. This patch adds it to the assembly format which fixes the failing test. Signed-off-by: Durgadoss R <[email protected]>
Member
|
@llvm/pr-subscribers-mlir @llvm/pr-subscribers-mlir-gpu Author: Durgadoss R (durga4github) ChangesFor memref, output_shape is required now. This patch adds it to the assembly format which fixes the Full diff: https://github.com/llvm/llvm-project/pull/111731.diff 1 Files Affected:
diff --git a/mlir/test/Integration/GPU/CUDA/sm90/tma_load_128x128_stride_noswizzle.mlir b/mlir/test/Integration/GPU/CUDA/sm90/tma_load_128x128_stride_noswizzle.mlir
index 4d415394482029..1f284f250fd839 100644
--- a/mlir/test/Integration/GPU/CUDA/sm90/tma_load_128x128_stride_noswizzle.mlir
+++ b/mlir/test/Integration/GPU/CUDA/sm90/tma_load_128x128_stride_noswizzle.mlir
@@ -57,7 +57,7 @@ module {
%s4 = gpu.memcpy async [%s3] %srcMemref, %srcMemref_host : memref<128x128xf16>, memref<128x128xf16>
%s5 = gpu.memcpy async [%s4] %dstMemref, %dstMemref_host : memref<128x128xf16>, memref<128x128xf16>
- %expand_shape = memref.expand_shape %srcMemref [[0, 1], [2, 3]] : memref<128x128xf16> into memref<2x64x2x64xf16>
+ %expand_shape = memref.expand_shape %srcMemref [[0, 1], [2, 3]] output_shape [2, 64, 2, 64] : memref<128x128xf16> into memref<2x64x2x64xf16>
%transpose = memref.transpose %expand_shape (d0, d1, d2, d3) -> (d0, d2, d1, d3) : memref<2x64x2x64xf16> to memref<2x2x64x64xf16, strided<[8192, 64, 128, 1]>>
%cast = memref.cast %transpose : memref<2x2x64x64xf16, strided<[8192, 64, 128, 1]>> to memref<*xf16>
%24 = nvgpu.tma.create.descriptor %cast box[%c2, %c2, %c64, %c64] : memref<*xf16> -> <tensor = memref<2x2x64x64xf16, 3>, swizzle = none, l2promo = none, oob = zero, interleave = none>
|
Contributor
Author
|
@grypp , Kindly help with review. |
grypp
approved these changes
Oct 9, 2024
DanielCChen
pushed a commit
to DanielCChen/llvm-project
that referenced
this pull request
Oct 16, 2024
The memref.expand_shape explicitly takes an output_shape now. This patch adds it to the Op and fixes the failing test. Signed-off-by: Durgadoss R <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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 memref.expand_shape explicitly takes an output_shape now.
This patch adds it to the Op and fixes the failing test.