[all-commits] [llvm/llvm-project] fa13c3: [mlir][nvgpu] Fix `transposeB` in `nvgpu.warpgroup...

[Guray Ozen via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: fa13c3eea7fbc34310f2fb602aa7f0983d5a0ea4
      https://github.com/llvm/llvm-project/commit/fa13c3eea7fbc34310f2fb602aa7f0983d5a0ea4
  Author: Guray Ozen <guray.ozen at gmail.com>
  Date:   2024-01-25 (Thu, 25 Jan 2024)

  Changed paths:
    M mlir/lib/Conversion/NVGPUToNVVM/NVGPUToNVVM.cpp
    M mlir/test/Conversion/NVGPUToNVVM/nvgpu-to-nvvm.mlir

  Log Message:
  -----------
  [mlir][nvgpu] Fix `transposeB` in `nvgpu.warpgroup.mma` (#79271)

The #76150 fixed meaning of `transposeB` in NVVM dialect which was
initially implemented with opposite meaning.

This PR fixes the lowering of `nvgpu.warpgroup.mma` to NVVM dialect.

This will fix two integration tests:
gemm_f32_f16_f16_128x128x128.mlir
gemm_pred_f32_f16_f16_128x128x128.mlir