[all-commits] [llvm/llvm-project] fd15e2: [mlir][Linalg] Use rank-reduced versions of subten...

[MaheshRavishankar via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: fd15e2b825f26dd7eac3b4a52aab36c88e52850a
      https://github.com/llvm/llvm-project/commit/fd15e2b825f26dd7eac3b4a52aab36c88e52850a
  Author: MaheshRavishankar <ravishankarm at google.com>
  Date:   2021-05-03 (Mon, 03 May 2021)

  Changed paths:
    M mlir/include/mlir/Dialect/MemRef/Transforms/Passes.td
    M mlir/lib/Dialect/Linalg/Transforms/DropUnitDims.cpp
    M mlir/lib/Dialect/MemRef/Transforms/CMakeLists.txt
    M mlir/lib/Dialect/MemRef/Transforms/FoldSubViewOps.cpp
    M mlir/test/Dialect/Linalg/drop-unit-extent-dims.mlir
    M mlir/test/Dialect/MemRef/fold-subview-ops.mlir

  Log Message:
  -----------
  [mlir][Linalg] Use rank-reduced versions of subtensor and subtensor insert when possible.

Convert subtensor and subtensor_insert operations to use their
rank-reduced versions to drop unit dimensions.

Differential Revision: https://reviews.llvm.org/D101495