[all-commits] [llvm/llvm-project] d77f48: [mlir][gpu] Relax restriction on mma load/store op

[Thomas via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: d77f4836401e492fa4aee549d6f677b6ab336a81
      https://github.com/llvm/llvm-project/commit/d77f4836401e492fa4aee549d6f677b6ab336a81
  Author: Thomas Raoux <thomasraoux at google.com>
  Date:   2022-03-25 (Fri, 25 Mar 2022)

  Changed paths:
    M mlir/lib/Conversion/VectorToGPU/VectorToGPU.cpp
    M mlir/lib/Dialect/GPU/IR/GPUDialect.cpp
    M mlir/test/Conversion/VectorToGPU/vector-to-mma-ops.mlir
    M mlir/test/Dialect/GPU/invalid.mlir
    M mlir/test/Dialect/GPU/ops.mlir

  Log Message:
  -----------
  [mlir][gpu] Relax restriction on mma load/store op

Those ops can support more complex layout as long as the most inner
dimension is contiguous.

Differential Revision: https://reviews.llvm.org/D122452