[all-commits] [llvm/llvm-project] 5da213: [mlir][sparse] generalize reduction support in spa...

[Aart Bik via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 5da21338bcd0fe377fc788b1b24cf055ab1977af
      https://github.com/llvm/llvm-project/commit/5da21338bcd0fe377fc788b1b24cf055ab1977af
  Author: Aart Bik <ajcbik at google.com>
  Date:   2021-09-22 (Wed, 22 Sep 2021)

  Changed paths:
    M mlir/lib/Dialect/SparseTensor/Transforms/Sparsification.cpp
    M mlir/test/Dialect/SparseTensor/sparse_vector.mlir
    A mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_reductions.mlir

  Log Message:
  -----------
  [mlir][sparse] generalize reduction support in sparse compiler

Now not just SUM, but also PRODUCT, AND, OR, XOR. The reductions
MIN and MAX are still to be done (also depends on recognizing
these operations in cmp-select constructs).

Reviewed By: bixia

Differential Revision: https://reviews.llvm.org/D110203