[all-commits] [llvm/llvm-project] 15ea23: [mlir][NVGPU] Support N-D masks in transform.nvgpu...

[Matthias Springer via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 15ea2306a41ad52a73e03f51497d115733b8b9d3
      https://github.com/llvm/llvm-project/commit/15ea2306a41ad52a73e03f51497d115733b8b9d3
  Author: Matthias Springer <me at m-sp.org>
  Date:   2023-08-08 (Tue, 08 Aug 2023)

  Changed paths:
    M mlir/lib/Dialect/NVGPU/Transforms/CreateAsyncGroups.cpp
    M mlir/test/Dialect/NVGPU/transform-create-async-groups.mlir

  Log Message:
  -----------
  [mlir][NVGPU] Support N-D masks in transform.nvgpu.create_async_groups

Support IR that is generated by the vector-to-scf lowering of N-D vector transfers with a mask. (Until now only 1-D and 2-D transfers were supported.) Only transfers that were fully unrolled are supported.

Differential Revision: https://reviews.llvm.org/D157286