[all-commits] [llvm/llvm-project] 4f92ad: [mlir] [VectorOps] [integration_test] Sparse matri...

[Aart Bik via All-commits]

  Branch: refs/heads/master
  Home:   https://github.com/llvm/llvm-project
  Commit: 4f92ad508fcc543541be18fb766ab428d08e46e3
      https://github.com/llvm/llvm-project/commit/4f92ad508fcc543541be18fb766ab428d08e46e3
  Author: aartbik <ajcbik at google.com>
  Date:   2020-07-29 (Wed, 29 Jul 2020)

  Changed paths:
    A mlir/integration_test/Dialect/Vector/CPU/test-sparse-saxpy-jagged-matvec.mlir

  Log Message:
  -----------
  [mlir] [VectorOps] [integration_test] Sparse matrix times vector (jagged SAXPY version)

Transposed jagged diagonal storage yields longer vector lengths. Also, in
contrast with naive SAXPY (one gather/scatter), this only performs one gather.

Reviewed By: reidtatge

Differential Revision: https://reviews.llvm.org/D84699