[all-commits] [llvm/llvm-project] 650669: Revert "[mlir][Transform] Add support for mma.sync...

[Mehdi Amini via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 6506692fe619ef8a1f7c6ea829d9a9eceb31622d
      https://github.com/llvm/llvm-project/commit/6506692fe619ef8a1f7c6ea829d9a9eceb31622d
  Author: Mehdi Amini <joker.eph at gmail.com>
  Date:   2023-06-27 (Tue, 27 Jun 2023)

  Changed paths:
    M mlir/include/mlir/Dialect/NVGPU/CMakeLists.txt
    R mlir/include/mlir/Dialect/NVGPU/TransformOps/CMakeLists.txt
    R mlir/include/mlir/Dialect/NVGPU/TransformOps/NVGPUTransformOps.h
    R mlir/include/mlir/Dialect/NVGPU/TransformOps/NVGPUTransformOps.td
    M mlir/include/mlir/InitAllDialects.h
    M mlir/lib/Dialect/NVGPU/CMakeLists.txt
    R mlir/lib/Dialect/NVGPU/TransformOps/CMakeLists.txt
    R mlir/lib/Dialect/NVGPU/TransformOps/NVGPUTransformOps.cpp
    R mlir/test/Dialect/NVGPU/transform-matmul-to-nvvm.mlir
    R mlir/test/Integration/GPU/CUDA/TensorCore/transform-mma-sync-matmul-f16-f16-accum.mlir
    R mlir/test/Integration/GPU/CUDA/TensorCore/transform-mma-sync-matmul-f32.mlir
    M utils/bazel/llvm-project-overlay/mlir/BUILD.bazel

  Log Message:
  -----------
  Revert "[mlir][Transform] Add support for mma.sync m16n8k16 f16 rewrite." and "[mlir][Transform] Introduce nvgpu transform extensions"

This reverts commit 40deed40ae77ba22f7c72693903752ab6bfeb4e7.
and commit 1660f2174d59bc2fd04131dab9ab0b43178bf665.

The buildbot is broken, the two tests aren't passing.