[all-commits] [llvm/llvm-project] 378f18: [mlir][sparse] enhance sparse reduction support

[Aart Bik via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 378f1885e3536ddf93e780f25a84ad493140ff42
      https://github.com/llvm/llvm-project/commit/378f1885e3536ddf93e780f25a84ad493140ff42
  Author: Aart Bik <ajcbik at google.com>
  Date:   2023-06-01 (Thu, 01 Jun 2023)

  Changed paths:
    M mlir/include/mlir/Dialect/SparseTensor/IR/SparseTensorOps.td
    M mlir/lib/Dialect/SparseTensor/Transforms/Sparsification.cpp
    M mlir/test/Dialect/SparseTensor/vectorize_reduction.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_reductions.mlir
    M mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_reductions_prod.mlir

  Log Message:
  -----------
  [mlir][sparse] enhance sparse reduction support

Formerly, we accepted and/prod reductions as a standard
reduction but these change the semantics after sparsification
by not looking at implicit zeros. Therefore, we only accept
standard reductions that are insensitive to implicit vs.
explicit zeros, and leave the more complex reductions to
the sparse_tensor.reduce custom reduction implementation.

Reviewed By: Peiming

Differential Revision: https://reviews.llvm.org/D151929