[all-commits] [llvm/llvm-project] 98dcd9: [mlir][vector] Hoist uniform scalar loop code afte...

[Quinn Dawkins via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 98dcd98a1a2b4e556db3eb738ec1a13131b753e7
      https://github.com/llvm/llvm-project/commit/98dcd98a1a2b4e556db3eb738ec1a13131b753e7
  Author: Quinn Dawkins <quinn.dawkins at gmail.com>
  Date:   2023-11-06 (Mon, 06 Nov 2023)

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

  Log Message:
  -----------
  [mlir][vector] Hoist uniform scalar loop code after scf.for distribution (#71422)

After propagation of `vector.warp_execute_on_lane_0` through `scf.for`,
uniform operations like those on the loop iterators can now be hoisted
out of the inner warp op.