[all-commits] [llvm/llvm-project] e79692: [mlir][VectorToGPU] Support more cases in conversi...

[Thomas via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: e7969240dce5e064f11abd44d7553ba9e9f27210
      https://github.com/llvm/llvm-project/commit/e7969240dce5e064f11abd44d7553ba9e9f27210
  Author: Thomas Raoux <thomasraoux at google.com>
  Date:   2021-11-11 (Thu, 11 Nov 2021)

  Changed paths:
    M mlir/include/mlir/Dialect/GPU/GPUOps.td
    M mlir/lib/Conversion/GPUToNVVM/WmmaOpsToNvvm.cpp
    M mlir/lib/Conversion/VectorToGPU/VectorToGPU.cpp
    M mlir/test/Conversion/VectorToGPU/vector-to-mma-ops.mlir

  Log Message:
  -----------
  [mlir][VectorToGPU] Support more cases in conversion to MMA ops

Support load with broadcast, elementwise divf op and remove the
hardcoded restriction on the vector size. Picking the right size should
be enfored by user and will fail conversion to llvm/spirv if it is not
supported.

Differential Revision: https://reviews.llvm.org/D113618