[all-commits] [llvm/llvm-project] 70c2e0: [mlir][nvgpu] Add nvgpu.tma.async.load and nvgpu.t...

[Guray Ozen via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 70c2e0618a0f3c09ed7149d88b4987b932eb6705
      https://github.com/llvm/llvm-project/commit/70c2e0618a0f3c09ed7149d88b4987b932eb6705
  Author: Guray Ozen <guray.ozen at gmail.com>
  Date:   2023-07-21 (Fri, 21 Jul 2023)

  Changed paths:
    M mlir/include/mlir/Dialect/NVGPU/IR/CMakeLists.txt
    M mlir/include/mlir/Dialect/NVGPU/IR/NVGPU.td
    M mlir/include/mlir/Dialect/NVGPU/IR/NVGPUDialect.h
    M mlir/lib/Conversion/NVGPUToNVVM/NVGPUToNVVM.cpp
    M mlir/lib/Dialect/NVGPU/IR/CMakeLists.txt
    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.load and nvgpu.tma.descriptor

This work adds `nvgpu.tma.async.load` Op that requests tma load asyncronusly using mbarrier object.

It also creates nvgpu.tma.descriptor type. The type is supposed be created by `cuTensorMapEncodeTiled` cuda drivers api.

Reviewed By: nicolasvasilache

Differential Revision: https://reviews.llvm.org/D155453