[all-commits] [llvm/llvm-project] 50000a: [mlir] Use affine.apply when distributing to proce...

[Lei Zhang via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 50000abe3cb25f45ec0f293a66a81499726943de
      https://github.com/llvm/llvm-project/commit/50000abe3cb25f45ec0f293a66a81499726943de
  Author: Lei Zhang <antiagainst at google.com>
  Date:   2021-03-09 (Tue, 09 Mar 2021)

  Changed paths:
    M mlir/lib/Transforms/Utils/LoopUtils.cpp
    M mlir/test/Dialect/Linalg/tile-and-distribute.mlir
    M mlir/test/Transforms/parametric-mapping.mlir
    M mlir/test/lib/Transforms/TestGpuMemoryPromotion.cpp
    M mlir/test/lib/Transforms/TestLoopMapping.cpp

  Log Message:
  -----------
  [mlir] Use affine.apply when distributing to processors

This makes it easy to compose the distribution computation with
other affine computations.

Reviewed By: mravishankar

Differential Revision: https://reviews.llvm.org/D98171