Skip to content

Conversation

@nirvedhmeshram
Copy link
Contributor

@nirvedhmeshram nirvedhmeshram commented Dec 12, 2024

Missed committing clang-fomat in #19903

@llvmbot
Copy link
Member

llvmbot commented Dec 12, 2024

@llvm/pr-subscribers-backend-risc-v
@llvm/pr-subscribers-mlir-tensor

@llvm/pr-subscribers-mlir

Author: Nirvedh Meshram (nirvedhmeshram)

Changes

Missed commiting clang-fomrat in 119039


Full diff: https://github.com/llvm/llvm-project/pull/119727.diff

1 Files Affected:

  • (modified) mlir/lib/Dialect/Tensor/IR/TensorTilingInterfaceImpl.cpp (+7-1)
diff --git a/mlir/lib/Dialect/Tensor/IR/TensorTilingInterfaceImpl.cpp b/mlir/lib/Dialect/Tensor/IR/TensorTilingInterfaceImpl.cpp
index 3caf93b1408df4..6e63cf068bce57 100644
--- a/mlir/lib/Dialect/Tensor/IR/TensorTilingInterfaceImpl.cpp
+++ b/mlir/lib/Dialect/Tensor/IR/TensorTilingInterfaceImpl.cpp
@@ -822,7 +822,13 @@ FailureOr<TilingResult> tensor::bubbleUpPadSlice(OpBuilder &b,
     // the source tensor. (Similar to newOffset.)
     // srcSize - newOffset represents how much length we have available
     // and length - newLow represents how much length we want at most.
-    // Note that there are many ways to order this indexing math to compute newLength, but we want to make sure that the final affine.min ops in the sequence are bounding the index to as small a value as possible. If ValueBoundsOpInterface is used, this calcuation will get upper bounds from the affine.min ops, so we want to use the smallest known value to set the bound at the end of the computation sequence. In this case, the index will be upper bounded by length - newLow.
+    // Note that there are many ways to order this indexing math to compute
+    // newLength, but we want to make sure that the final affine.min ops in the
+    // sequence are bounding the index to as small a value as possible. If
+    // ValueBoundsOpInterface is used, this calcuation will get upper bounds
+    // from the affine.min ops, so we want to use the smallest known value to
+    // set the bound at the end of the computation sequence. In this case, the
+    // index will be upper bounded by length - newLow.
     OpFoldResult newLength = min(sub(srcSize, newOffset), sub(length, newLow));
     // Optimization: If low = 0, then newLow = 0. then newLength >= 0 assuming
     // length >= 0.

@nirvedhmeshram nirvedhmeshram merged commit 7740010 into llvm:main Dec 12, 2024
5 of 6 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants