[all-commits] [llvm/llvm-project] 7db25f: [WIP] Add support for MMA conversion for 1-D vecto...

[Nicolas Vasilache via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 7db25f78db807da171f23bcbaff258c5677901d1
      https://github.com/llvm/llvm-project/commit/7db25f78db807da171f23bcbaff258c5677901d1
  Author: Nicolas Vasilache <nicolas.vasilache at gmail.com>
  Date:   2022-12-01 (Thu, 01 Dec 2022)

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

  Log Message:
  -----------
  [WIP] Add support for MMA conversion for 1-D vector.transfer followed by a broadcast to 2-D

Differential Revision: https://reviews.llvm.org/D139040


  Commit: 3a6ae0f8f5daf159db654ea00fb9369bc138bb80
      https://github.com/llvm/llvm-project/commit/3a6ae0f8f5daf159db654ea00fb9369bc138bb80
  Author: Nicolas Vasilache <nicolas.vasilache at gmail.com>
  Date:   2022-12-01 (Thu, 01 Dec 2022)

  Changed paths:
    M mlir/lib/Dialect/Linalg/Transforms/Vectorization.cpp

  Log Message:
  -----------
  [mlir][Linalg][NFC] Improve debugging during vectorization

Make more systematic use of `notifyMatchFailure`.


Compare: https://github.com/llvm/llvm-project/compare/a043fcf92fa3...3a6ae0f8f5da