[all-commits] [llvm/llvm-project] db3932: [mlir][NVGPU][transform] Add `create_async_groups`...

[Matthias Springer via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: db393288ff9b07d2c13b2be6a61f91ba180cb601
      https://github.com/llvm/llvm-project/commit/db393288ff9b07d2c13b2be6a61f91ba180cb601
  Author: Matthias Springer <me at m-sp.org>
  Date:   2023-07-18 (Tue, 18 Jul 2023)

  Changed paths:
    M mlir/include/mlir/Dialect/NVGPU/TransformOps/NVGPUTransformOps.td
    M mlir/include/mlir/Dialect/NVGPU/Transforms/Transforms.h
    M mlir/include/mlir/Dialect/NVGPU/Transforms/Utils.h
    M mlir/include/mlir/Dialect/Vector/IR/VectorOps.td
    M mlir/lib/Dialect/NVGPU/TransformOps/CMakeLists.txt
    M mlir/lib/Dialect/NVGPU/TransformOps/NVGPUTransformOps.cpp
    M mlir/lib/Dialect/NVGPU/Transforms/CMakeLists.txt
    A mlir/lib/Dialect/NVGPU/Transforms/CreateAsyncGroups.cpp
    M mlir/lib/Dialect/NVGPU/Transforms/Utils.cpp
    A mlir/test/Dialect/NVGPU/transform-create-async-groups.mlir
    M utils/bazel/llvm-project-overlay/mlir/BUILD.bazel

  Log Message:
  -----------
  [mlir][NVGPU][transform] Add `create_async_groups` transform op

This transform looks for suitable vector transfers from global memory to shared memory and converts them to async device copies.

Differential Revision: https://reviews.llvm.org/D155569