[all-commits] [llvm/llvm-project] 708185: [mlir][NVGPU] Add support for structured sparsity ...

[Chris via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 708185f03ff480b3481132802b7b63461564f0ab
      https://github.com/llvm/llvm-project/commit/708185f03ff480b3481132802b7b63461564f0ab
  Author: Christopher Bate <cbate at nvidia.com>
  Date:   2022-11-07 (Mon, 07 Nov 2022)

  Changed paths:
    M mlir/include/mlir/Dialect/NVGPU/IR/NVGPU.td
    M mlir/lib/Conversion/NVGPUToNVVM/NVGPUToNVVM.cpp
    M mlir/lib/Dialect/NVGPU/IR/NVGPUDialect.cpp
    M mlir/test/Conversion/NVGPUToNVVM/nvgpu-to-nvvm.mlir
    M mlir/test/Dialect/NVGPU/roundtrip.mlir

  Log Message:
  -----------
  [mlir][NVGPU] Add support for structured sparsity MMA variants

This change adds a new NVGPU operation that targets the PTX `mma.sp.sync`
instruction variants. A lowering to NVVM is provided using inline
assembly.

Reviewed By: ThomasRaoux, manishucsd

Differential Revision: https://reviews.llvm.org/D137202