[all-commits] [llvm/llvm-project] 8dd0d9: [mlir][nvgpu] Add `nvgpu.tma.async.store` (#77811)

[Guray Ozen via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 8dd0d95c7c022c05aa5ab519bab6b537714cd0e9
      https://github.com/llvm/llvm-project/commit/8dd0d95c7c022c05aa5ab519bab6b537714cd0e9
  Author: Guray Ozen <guray.ozen at gmail.com>
  Date:   2024-01-15 (Mon, 15 Jan 2024)

  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

  Log Message:
  -----------
  [mlir][nvgpu] Add `nvgpu.tma.async.store` (#77811)

PR adds `nvgpu.tma.async.store` Op for asynchronous stores using the
Tensor Memory Access (TMA) unit.

It also implements Op lowering to NVVM dialect. The Op currently
performs asynchronous stores of a tile memory region from shared to
global memory for a single CTA.