[all-commits] [llvm/llvm-project] c55b41: [mlir][AMDGPU] Define amdgpu.mfma operator

[Krzysztof Drewniak via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: c55b41d5199d2394dd6cdb8f52180d8b81d809d4
      https://github.com/llvm/llvm-project/commit/c55b41d5199d2394dd6cdb8f52180d8b81d809d4
  Author: Krzysztof Drewniak <Krzysztof.Drewniak at amd.com>
  Date:   2022-08-31 (Wed, 31 Aug 2022)

  Changed paths:
    M mlir/include/mlir/Dialect/AMDGPU/AMDGPU.td
    M mlir/include/mlir/Dialect/AMDGPU/AMDGPUDialect.h
    M mlir/include/mlir/Dialect/AMDGPU/CMakeLists.txt
    M mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp
    M mlir/lib/Dialect/AMDGPU/IR/AMDGPUDialect.cpp
    M mlir/lib/Dialect/AMDGPU/IR/CMakeLists.txt
    A mlir/test/Conversion/AMDGPUToROCDL/mfma.mlir
    A mlir/test/Dialect/AMDGPU/invalid.mlir
    M mlir/test/Dialect/AMDGPU/ops.mlir

  Log Message:
  -----------
  [mlir][AMDGPU] Define amdgpu.mfma operator

The amdgpu.mfma operator is a wrapper around the Matrix Fused Multiply
Add (MFMA) instructions on some AMD GPUs (the CDNA-based MI-* cards).

This interface allows for selecting the operation to be performed by
specifying the dimensions of the multiplication to be performed and
any additional attributes (such as whether to use reduced-precision
floating-point math) that are needed to select the relevant mfma
instruction and set its parameters.

Reviewed By: ThomasRaoux, nirvedhmeshram

Differential Revision: https://reviews.llvm.org/D132956