[all-commits] [llvm/llvm-project] 72d5ac: [mlir] Use affine dim instead of symbol in SCFToGP...

[Tres via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: 72d5ac90b9282cd17c8608a756ebb49c19ad4e04
      https://github.com/llvm/llvm-project/commit/72d5ac90b9282cd17c8608a756ebb49c19ad4e04
  Author: Tres Popp <tpopp at google.com>
  Date:   2020-10-20 (Tue, 20 Oct 2020)

  Changed paths:
    M mlir/lib/Conversion/SCFToGPU/SCFToGPU.cpp
    M mlir/test/Conversion/SCFToGPU/parallel_loop.mlir

  Log Message:
  -----------
  [mlir] Use affine dim instead of symbol in SCFToGPU lowering.

This still satisfies the constraints required by the affine dialect and
gives more flexibility in what iteration bounds can be used when
loewring to the GPU dialect.

Differential Revision: https://reviews.llvm.org/D89782