[all-commits] [llvm/llvm-project] 5205c7: [mlir][gpu] Add support for unsigned integer exten...

[Quinn Dawkins via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 5205c7126b2fea73b283e54c4e1bf409089a8d52
      https://github.com/llvm/llvm-project/commit/5205c7126b2fea73b283e54c4e1bf409089a8d52
  Author: Quinn Dawkins <quinn at nod-labs.com>
  Date:   2023-02-14 (Tue, 14 Feb 2023)

  Changed paths:
    M mlir/lib/Conversion/GPUToNVVM/WmmaOpsToNvvm.cpp
    M mlir/lib/Conversion/VectorToGPU/VectorToGPU.cpp
    M mlir/lib/Dialect/SPIRV/IR/SPIRVOps.cpp
    M mlir/test/Conversion/VectorToGPU/vector-to-mma-ops.mlir
    M mlir/test/Dialect/SPIRV/IR/cooperative-matrix-ops.mlir

  Log Message:
  -----------
  [mlir][gpu] Add support for unsigned integer extend in vector to gpu.subgroup_mma lowering

Unsigned integer types are supported in subgroup mma ops by matching
against arith.extui ops. This allows for subgroup_mma_compute ops with
mixed signedness which requires later conversions to handle this. SPIR-V
cooperative matrix ops support this while the lowering to WMMA does not.

Differential Revision: https://reviews.llvm.org/D143922