[all-commits] [llvm/llvm-project] 847048: [mlir][Vector] Fix bug in vector xfer op flattenin...

[Diego Caballero via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 847048f497bcdfcfe52f36cba49f07bdbd63cd24
      https://github.com/llvm/llvm-project/commit/847048f497bcdfcfe52f36cba49f07bdbd63cd24
  Author: Diego Caballero <diegocaballero at google.com>
  Date:   2024-02-22 (Thu, 22 Feb 2024)

  Changed paths:
    M mlir/include/mlir/Dialect/Utils/IndexingUtils.h
    M mlir/lib/Dialect/Utils/IndexingUtils.cpp
    M mlir/lib/Dialect/Vector/Transforms/VectorTransferOpTransforms.cpp
    M mlir/test/Dialect/Vector/vector-transfer-flatten.mlir

  Log Message:
  -----------
  [mlir][Vector] Fix bug in vector xfer op flattening transformation (#81964)

It looks like the affine map generated to compute the indices of the
collapsed dimensions used the wrong dim size. For indices `[idx0][idx1]`
we computed the collapsed index as `idx0*size0 + idx1` instead of
`idx0*size1 + idx1`. This led to correctness issues in convolution tests
when enabling this transformation internally.



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications