[all-commits] [llvm/llvm-project] df49a9: [mlir][vector] Root the transfer write distributio...

[Quinn Dawkins via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: df49a97ab2e952d1588d9e7784987d982ebf3365
      https://github.com/llvm/llvm-project/commit/df49a97ab2e952d1588d9e7784987d982ebf3365
  Author: Quinn Dawkins <quinn.dawkins at gmail.com>
  Date:   2023-11-10 (Fri, 10 Nov 2023)

  Changed paths:
    M mlir/include/mlir/Dialect/Vector/Transforms/VectorDistribution.h
    M mlir/lib/Dialect/Vector/Transforms/VectorDistribute.cpp
    M mlir/test/Dialect/Vector/vector-warp-distribute.mlir
    M mlir/test/lib/Dialect/Vector/TestVectorTransforms.cpp

  Log Message:
  -----------
  [mlir][vector] Root the transfer write distribution pattern on the warp op (#71868)

Currently when there is a mix of transfer read ops and transfer write
ops that need to be distributed, because the pattern for write
distribution is rooted on the transfer write, it is hard to guarantee
that the write gets distributed after the read when the two aren't
directly connected by SSA. This is likely still relatively unsafe when
there are undistributable ops, but structurally these patterns are a bit
difficult to work with. For now pattern benefits give fairly good
guarantees for happy paths.