[all-commits] [llvm/llvm-project] 77d2c8: [MLIR][GPU] Add GPU ops nvvm.mma.sync, nvvm.mma.ld...

[Chris via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 77d2c815f50b20d18f1207e4f442e2cf8eb8cec0
      https://github.com/llvm/llvm-project/commit/77d2c815f50b20d18f1207e4f442e2cf8eb8cec0
  Author: Christopher Bate <cbate at nvidia.com>
  Date:   2022-04-13 (Wed, 13 Apr 2022)

  Changed paths:
    M mlir/include/mlir/Dialect/GPU/GPUOps.td
    M mlir/lib/Conversion/GPUToNVVM/LowerGpuOpsToNVVMOps.cpp
    M mlir/test/Conversion/GPUToNVVM/gpu-to-nvvm.mlir
    A mlir/test/Conversion/GPUToNVVM/mma-sync-to-nvvm.mlir

  Log Message:
  -----------
  [MLIR][GPU] Add GPU ops nvvm.mma.sync, nvvm.mma.ldmatrix, lane_id

This change adds three new operations to the GPU dialect: gpu.mma.sync,
gpu.mma.ldmatrix, and gpu.lane_id. The former two are meant to target
the lower level nvvm.mma.sync and nvvm.ldmatrix instructions, respectively.
Lowerings are added for the new GPU operations for conversion to
NVVM.

Reviewed By: ThomasRaoux

Differential Revision: https://reviews.llvm.org/D123647