[all-commits] [llvm/llvm-project] edd951: [mlir][VectorToGPU] First step to convert vector o...

[Thomas via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: edd9515bd125634f40ebc2e783d6a127345e7c0d
      https://github.com/llvm/llvm-project/commit/edd9515bd125634f40ebc2e783d6a127345e7c0d
  Author: thomasraoux <thomasraoux at google.com>
  Date:   2021-06-11 (Fri, 11 Jun 2021)

  Changed paths:
    M mlir/include/mlir/Conversion/Passes.h
    M mlir/include/mlir/Conversion/Passes.td
    A mlir/include/mlir/Conversion/VectorToGPU/VectorToGPU.h
    M mlir/lib/Conversion/CMakeLists.txt
    A mlir/lib/Conversion/VectorToGPU/CMakeLists.txt
    A mlir/lib/Conversion/VectorToGPU/VectorToGPU.cpp
    A mlir/test/Conversion/VectorToGPU/vector-to-mma-ops.mlir

  Log Message:
  -----------
  [mlir][VectorToGPU] First step to convert vector ops to GPU MMA ops

This is the first step to convert vector ops to MMA operations in order to
target GPUs tensor core ops. This currently only support simple cases,
transpose and element-wise operation will be added later.

Differential Revision: https://reviews.llvm.org/D102962