[all-commits] [llvm/llvm-project] eb8d6a: [mlir] Specify cuda-runner pass pipeline as comman...

[Christian Sigg via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: eb8d6af5e406f1dafb2f742bc9994ffbc8a6ea76
      https://github.com/llvm/llvm-project/commit/eb8d6af5e406f1dafb2f742bc9994ffbc8a6ea76
  Author: Christian Sigg <csigg at google.com>
  Date:   2021-02-24 (Wed, 24 Feb 2021)

  Changed paths:
    M mlir/lib/Conversion/GPUCommon/ConvertKernelFuncToBlob.cpp
    M mlir/test/mlir-cuda-runner/all-reduce-and.mlir
    M mlir/test/mlir-cuda-runner/all-reduce-max.mlir
    M mlir/test/mlir-cuda-runner/all-reduce-min.mlir
    M mlir/test/mlir-cuda-runner/all-reduce-op.mlir
    M mlir/test/mlir-cuda-runner/all-reduce-or.mlir
    M mlir/test/mlir-cuda-runner/all-reduce-region.mlir
    M mlir/test/mlir-cuda-runner/all-reduce-xor.mlir
    M mlir/test/mlir-cuda-runner/async.mlir
    M mlir/test/mlir-cuda-runner/gpu-to-cubin.mlir
    M mlir/test/mlir-cuda-runner/multiple-all-reduce.mlir
    M mlir/test/mlir-cuda-runner/shuffle.mlir
    M mlir/test/mlir-cuda-runner/two-modules.mlir
    M mlir/tools/mlir-cuda-runner/mlir-cuda-runner.cpp

  Log Message:
  -----------
  [mlir] Specify cuda-runner pass pipeline as command line options.

The cuda-runner registers two pass pipelines for nested passes,
so that we don't have to use verbose textual pass pipeline specification.

Reviewed By: herhut

Differential Revision: https://reviews.llvm.org/D97091