projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 8723280) | patch
[mlir] [VectorOps] [integration_test] Sparse matrix times vector (jagged SAXPY version)
authoraartbik <ajcbik@google.com>
Wed, 29 Jul 2020 20:25:31 +0000 (13:25 -0700)
committeraartbik <ajcbik@google.com>
Wed, 29 Jul 2020 20:25:56 +0000 (13:25 -0700)
commit4f92ad508fcc543541be18fb766ab428d08e46e3
treed22736db010d780546cfc538a05c69bb09536927tree | snapshot
parent8723280b68b1e5ed97a699466720b36a32a9e406commit | diff
[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
mlir/integration_test/Dialect/Vector/CPU/test-sparse-saxpy-jagged-matvec.mlir [new file with mode: 0644] blob
Domain: System / Toolchain;