[all-commits] [llvm/llvm-project] dbddd4: [mlir][VectorToGPU] Support transposed+broadcasted...

[Lei Zhang via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: dbddd4f6a41ad32de9888b88a96023575a334618
      https://github.com/llvm/llvm-project/commit/dbddd4f6a41ad32de9888b88a96023575a334618
  Author: Lei Zhang <antiagainst at google.com>
  Date:   2022-12-15 (Thu, 15 Dec 2022)

  Changed paths:
    M mlir/lib/Conversion/VectorToGPU/VectorToGPU.cpp
    M mlir/test/Conversion/VectorToGPU/vector-to-mma-ops.mlir

  Log Message:
  -----------
  [mlir][VectorToGPU] Support transposed+broadcasted 1D MMA load

This is now possible with transpose semantics on subgroup MMA
load ops.

Reviewed By: ThomasRaoux

Differential Revision: https://reviews.llvm.org/D139655