[all-commits] [llvm/llvm-project] cb82d3: [mlir][sparse][vectorization] optimize reduction c...

[Aart Bik via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: cb82d375a8060bd3af83b64d7d2c94f4a59d4b97
      https://github.com/llvm/llvm-project/commit/cb82d375a8060bd3af83b64d7d2c94f4a59d4b97
  Author: Aart Bik <ajcbik at google.com>
  Date:   2022-11-26 (Sat, 26 Nov 2022)

  Changed paths:
    M mlir/lib/Dialect/SparseTensor/Transforms/SparseVectorization.cpp
    A mlir/test/Dialect/SparseTensor/sparse_vector_chain.mlir

  Log Message:
  -----------
  [mlir][sparse][vectorization] optimize reduction chains

A few more dots on the i's of the sparse vectorizer.
Also makes reduction matching less brittle.

Reviewed By: qcolombet

Differential Revision: https://reviews.llvm.org/D138513