[Mlir-commits] [mlir] [mlir][linalg][nfc] Clean-up leftover code post #149156 (PR #151334)
llvmlistbot at llvm.org
llvmlistbot at llvm.org
Wed Jul 30 06:31:18 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-mlir
Author: Andrzej WarzyĆski (banach-space)
<details>
<summary>Changes</summary>
In https://github.com/llvm/llvm-project/pull/149156, I ensured that we
no longer generate spurious `tensor.empty` ops when vectorizing
`linalg.unpack`.
This follow-up removes leftover code that is now redundant but was
missed in the original PR and in #<!-- -->150602 that was also meant to clean-up
left-over code.
Note, this is removing code to compute "write-vector-sizes". Instead,
these are fully inferred from previous Ops.
---
Full diff: https://github.com/llvm/llvm-project/pull/151334.diff
1 Files Affected:
- (modified) mlir/lib/Dialect/Linalg/Transforms/Vectorization.cpp (-6)
``````````diff
diff --git a/mlir/lib/Dialect/Linalg/Transforms/Vectorization.cpp b/mlir/lib/Dialect/Linalg/Transforms/Vectorization.cpp
index 793eec732aa03..ea68b1ad572c3 100644
--- a/mlir/lib/Dialect/Linalg/Transforms/Vectorization.cpp
+++ b/mlir/lib/Dialect/Linalg/Transforms/Vectorization.cpp
@@ -1946,12 +1946,6 @@ vectorizeAsTensorUnpackOp(RewriterBase &rewriter, linalg::UnPackOp unpackOp,
vector::ShapeCastOp shapeCastOp = vector::ShapeCastOp::create(
rewriter, loc, vecCollapsedType, transposeOp->getResult(0));
- // writeVectorSizes had to match the shapecast shape for dynamic sizes,
- // otherwise the validator complains that the mask size is invalid.
- SmallVector<int64_t> writeVectorSizes(
- unpackOp.getDestType().hasStaticShape()
- ? vectorSizes
- : shapeCastOp.getResultVectorType().getShape());
Operation *write = createWriteOrMaskedWrite(
rewriter, loc, shapeCastOp.getResult(), unpackOp.getDest(),
/*writeIndices=*/{}, useInBoundsInsteadOfMasking);
``````````
</details>
https://github.com/llvm/llvm-project/pull/151334
More information about the Mlir-commits
mailing list