projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: b76014a) | patch
[mlir][linalg] Add vectorization for linalg on tensor ops
authorThomas Raoux <thomasraoux@google.com>
Tue, 29 Dec 2020 07:55:15 +0000 (23:55 -0800)
committerThomas Raoux <thomasraoux@google.com>
Tue, 29 Dec 2020 17:02:23 +0000 (09:02 -0800)
commitcf216670a0bd1f2ce561a315e00649740f117e1c
treea98d3627f09cf75db3c12febe694d9fbfdae11d6tree | snapshot
parentb76014a4f15ad9f3151862fcc6c6ab2f0f505199commit | diff
[mlir][linalg] Add vectorization for linalg on tensor ops

Support vectorization of linalg ops using tensor inputs/outputs.

Differential Revision: https://reviews.llvm.org/D93890
mlir/lib/Dialect/Linalg/Transforms/Vectorization.cpp diff | blob | history
mlir/lib/Dialect/Vector/VectorOps.cpp diff | blob | history
mlir/test/Dialect/Linalg/vectorization.mlir diff | blob | history
Domain: System / Toolchain;