[all-commits] [llvm/llvm-project] 831041: [mlir][vector] Cleanup VectorUnroll and create a g...

[Chris via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 831041be797b099b4e3805db368bacb1d1abab5d
      https://github.com/llvm/llvm-project/commit/831041be797b099b4e3805db368bacb1d1abab5d
  Author: Christopher Bate <cbate at nvidia.com>
  Date:   2023-09-14 (Thu, 14 Sep 2023)

  Changed paths:
    M mlir/include/mlir/Dialect/Utils/IndexingUtils.h
    M mlir/include/mlir/IR/AffineExpr.h
    M mlir/lib/Dialect/Utils/IndexingUtils.cpp
    M mlir/lib/Dialect/Vector/Transforms/VectorUnroll.cpp
    M mlir/lib/IR/AffineExpr.cpp
    M mlir/unittests/Dialect/Utils/CMakeLists.txt
    A mlir/unittests/Dialect/Utils/IndexingUtilsTest.cpp

  Log Message:
  -----------
  [mlir][vector] Cleanup VectorUnroll and create a generic tile iteration utility

This change refactors some of the utilities used to unroll larger vector
computations into smaller vector computations. In fact, the indexing
computations used here are rather generic and are useful in other dialects or
downstream projects. Therefore, a utility for iterating over all possible tile
offsets for a particular pair of static (shape, tiled shape) is introduced in
IndexingUtils and replaces the existing computations in the vector unrolling
transformations. This builds off of the refactoring of IndexingUtils introduced
in 203fad476b7e.

Reviewed By: nicolasvasilache

Differential Revision: https://reviews.llvm.org/D150000