[all-commits] [llvm/llvm-project] 717124: [mlir] Add vectorize_nd_extract attribute to the m...
Andrzej WarzyĆski via All-commits
all-commits at lists.llvm.org
Wed Feb 15 00:47:59 PST 2023
Branch: refs/heads/main
Home: https://github.com/llvm/llvm-project
Commit: 71712440bbb26b8e1789372024c3a14428b68eae
https://github.com/llvm/llvm-project/commit/71712440bbb26b8e1789372024c3a14428b68eae
Author: Andrzej Warzynski <andrzej.warzynski at gmail.com>
Date: 2023-02-15 (Wed, 15 Feb 2023)
Changed paths:
M mlir/include/mlir/Dialect/Linalg/TransformOps/LinalgTransformOps.td
M mlir/lib/Dialect/Linalg/TransformOps/LinalgTransformOps.cpp
A mlir/test/Dialect/Linalg/vectorization-unsupported.mlir
Log Message:
-----------
[mlir] Add vectorize_nd_extract attribute to the masked_vectorize Op
This patch simply adds `vectorize_nd_extract` (that's currently only
used for the `vectorize` Op) to `masked_vectorize`. A test is added to
verify that it works as expected - it prevents the masked vectorisation
of `tensor.extract`, which is currently not supported.
Differential Revision: https://reviews.llvm.org/D142634
More information about the All-commits
mailing list