[all-commits] [llvm/llvm-project] cca3f3: [MLIR] Add affine.parallel folder and normalizer

Frank Laub via All-commits all-commits at lists.llvm.org
Thu Aug 20 15:24:12 PDT 2020


  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: cca3f3dd2681877cae3dc601779e268ed2341fa3
      https://github.com/llvm/llvm-project/commit/cca3f3dd2681877cae3dc601779e268ed2341fa3
  Author: Frank Laub <frank.laub at intel.com>
  Date:   2020-08-20 (Thu, 20 Aug 2020)

  Changed paths:
    M mlir/include/mlir/Dialect/Affine/IR/AffineOps.td
    M mlir/include/mlir/Dialect/Affine/IR/AffineValueMap.h
    M mlir/include/mlir/Dialect/Affine/Passes.h
    M mlir/include/mlir/Dialect/Affine/Passes.td
    M mlir/include/mlir/Dialect/Affine/Utils.h
    M mlir/lib/Dialect/Affine/IR/AffineOps.cpp
    A mlir/lib/Dialect/Affine/Transforms/AffineParallelNormalize.cpp
    M mlir/lib/Dialect/Affine/Transforms/CMakeLists.txt
    A mlir/test/Dialect/Affine/affine-parallel-normalize.mlir
    M mlir/test/Dialect/Affine/canonicalize.mlir

  Log Message:
  -----------
  [MLIR] Add affine.parallel folder and normalizer

Add a folder to the affine.parallel op so that loop bounds expressions are canonicalized.

Additionally, a new AffineParallelNormalizePass is added to adjust affine.parallel ops so that the lower bound is always 0 and the upper bound always represents a range with a step size of 1.

Differential Revision: https://reviews.llvm.org/D84998




More information about the All-commits mailing list