[all-commits] [llvm/llvm-project] 4c3db2: [mlir][linalg] Block pack matmul pass (#89782)

[Adam Siemieniuk via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 4c3db2588e8b38f75744def6e2dd17c556950e46
      https://github.com/llvm/llvm-project/commit/4c3db2588e8b38f75744def6e2dd17c556950e46
  Author: Adam Siemieniuk <adam.siemieniuk at intel.com>
  Date:   2024-05-09 (Thu, 09 May 2024)

  Changed paths:
    M mlir/include/mlir/Dialect/Linalg/Passes.td
    M mlir/include/mlir/Dialect/Linalg/Transforms/Transforms.h
    A mlir/lib/Dialect/Linalg/Transforms/BlockPackMatmul.cpp
    M mlir/lib/Dialect/Linalg/Transforms/CMakeLists.txt
    A mlir/test/Dialect/Linalg/block-pack-matmul-layout.mlir
    A mlir/test/Dialect/Linalg/block-pack-matmul-padding.mlir
    A mlir/test/Dialect/Linalg/block-pack-matmul.mlir

  Log Message:
  -----------
  [mlir][linalg] Block pack matmul pass (#89782)

Pack a matmul MxNxK operation into 4D blocked layout. Any present batch
dimensions remain unchanged and the result is unpacked back to the
original layout.

Matmul block packing splits the operands into major blocks (outer
dimensions) and minor blocks (inner dimensions). The desired block
layout can be controlled through packing options.



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications