[all-commits] [llvm/llvm-project] 43531e: [LLVM][NVPTX] Add cp.async.bulk.commit/wait intrin...

[Durgadoss R via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 43531e719636e5960d8592a184e10af885be6869
      https://github.com/llvm/llvm-project/commit/43531e719636e5960d8592a184e10af885be6869
  Author: Durgadoss R <durgadossr at nvidia.com>
  Date:   2024-01-19 (Fri, 19 Jan 2024)

  Changed paths:
    M llvm/include/llvm/IR/IntrinsicsNVVM.td
    M llvm/lib/Target/NVPTX/NVPTXIntrinsics.td
    M llvm/test/CodeGen/NVPTX/intrinsics-sm90.ll

  Log Message:
  -----------
  [LLVM][NVPTX] Add cp.async.bulk.commit/wait intrinsics (#78698)

This patch adds NVVM intrinsics and NVPTX codegen for the bulk variants
of the async-copy commit/wait instructions.
lit tests are added to verify the generated PTX.

PTX Doc link:

https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#data-movement-and-conversion-instructions-cp-async-bulk-commit-group

Signed-off-by: Durgadoss R <durgadossr at nvidia.com>