[all-commits] [llvm/llvm-project] 4db65e: [mlir][vector] Reorder elementwise(transpose)

[Lei Zhang via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 4db65e279b96e2af9a4ea2c1e2acc40a64de2a0e
      https://github.com/llvm/llvm-project/commit/4db65e279b96e2af9a4ea2c1e2acc40a64de2a0e
  Author: Lei Zhang <antiagainst at google.com>
  Date:   2022-04-15 (Fri, 15 Apr 2022)

  Changed paths:
    M mlir/lib/Dialect/Vector/Transforms/VectorTransforms.cpp
    M mlir/test/Dialect/Vector/vector-reduce-to-contract.mlir

  Log Message:
  -----------
  [mlir][vector] Reorder elementwise(transpose)

Similar to the existing pattern for reodering cast(transpose),
this makes transpose following transpose and increases the chance
of embedding the transposition inside contraction op. Actually
cast ops are just special instances of elementwise ops.

Reviewed By: ThomasRaoux

Differential Revision: https://reviews.llvm.org/D123596