[Mlir-commits] [llvm] [mlir] [mlir][tensor] Fold linalg transpose with tensor pack (PR #74206)
llvmlistbot at llvm.org
llvmlistbot at llvm.org
Fri Dec 8 10:40:53 PST 2023
github-actions[bot] wrote:
<!--LLVM CODE FORMAT COMMENT: {clang-format}-->
:warning: C/C++ code formatter, clang-format found issues in your code. :warning:
<details>
<summary>
You can test this locally with the following command:
</summary>
``````````bash
git-clang-format --diff bd382032f6df9529197a391ed80e9ab8c59915f1 1fd838bf1f02c9c4e058ed20021695c08e82b9d2 -- mlir/lib/Dialect/Tensor/Transforms/FoldIntoPackAndUnpackPatterns.cpp
``````````
</details>
<details>
<summary>
View the diff from clang-format here.
</summary>
``````````diff
diff --git a/mlir/lib/Dialect/Tensor/Transforms/FoldIntoPackAndUnpackPatterns.cpp b/mlir/lib/Dialect/Tensor/Transforms/FoldIntoPackAndUnpackPatterns.cpp
index d3186a0873..5f1e6e0980 100644
--- a/mlir/lib/Dialect/Tensor/Transforms/FoldIntoPackAndUnpackPatterns.cpp
+++ b/mlir/lib/Dialect/Tensor/Transforms/FoldIntoPackAndUnpackPatterns.cpp
@@ -241,14 +241,14 @@ struct FoldConsumerPackWithProducerLinalgTransposeOp
Value output = packOp.createDestinationTensor(
rewriter, packOp.getLoc(), transposeOp.getOperand(0),
- newPackInnerTilesArrayRef,
+ newPackInnerTilesArrayRef,
static_cast<ArrayRef<int64_t>>(newPackInnerDimsPosVec),
static_cast<ArrayRef<int64_t>>(newPackOuterDimsPermVec));
output.dump();
rewriter.replaceOpWithNewOp<PackOp>(
- packOp, transposeOp.getOperand(0), output,
+ packOp, transposeOp.getOperand(0), output,
static_cast<ArrayRef<int64_t>>(newPackInnerDimsPosVec),
newPackInnerTilesArrayRef, packOp.getPaddingValue(),
static_cast<ArrayRef<int64_t>>(newPackOuterDimsPermVec));
``````````
</details>
https://github.com/llvm/llvm-project/pull/74206
More information about the Mlir-commits
mailing list