projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 926e1fa) | patch
[mlir][Vector] Fix 0-D tensor vectorization in Linalg
authorDiego Caballero <diegocaballero@google.com>
Fri, 16 Jun 2023 23:21:24 +0000 (23:21 +0000)
committerDiego Caballero <diegocaballero@google.com>
Fri, 16 Jun 2023 23:45:03 +0000 (23:45 +0000)
commit3aeb27d69a16e7d8aa3fe684c33d506cdda97b78
treef6006dd4e8fc4e7cb66068e0e931c1f69c7e9883tree | snapshot
parent926e1faabc6f6fd4c2fc208fc416c80eff3c05a5commit | diff
[mlir][Vector] Fix 0-D tensor vectorization in Linalg

It looks like scalable vector support broke vectorization for 0-D
tensors and we didn't have any test coverting that case. This patch
provides a fix and a test.

Differential Revision: https://reviews.llvm.org/D153181
mlir/lib/Dialect/Linalg/Transforms/Vectorization.cpp diff | blob | history
mlir/test/Dialect/Linalg/vectorization.mlir diff | blob | history
Domain: System / Toolchain;