diff options
| author | Jakub Lichman <limo@google.com> | 2020-09-08 08:31:52 +0000 |
|---|---|---|
| committer | Jakub Lichman <limo@google.com> | 2020-09-08 08:47:42 +0000 |
| commit | 67b37f571cc27d5684125f694d719b114ad72a18 (patch) | |
| tree | eaa9696bef58da9b64205156679f59e7cefaff87 /clang/lib/Frontend/CompilerInvocation.cpp | |
| parent | 38778e1087b2825e91b07ce4570c70815b49dcdc (diff) | |
| download | llvm-67b37f571cc27d5684125f694d719b114ad72a18.zip llvm-67b37f571cc27d5684125f694d719b114ad72a18.tar.gz llvm-67b37f571cc27d5684125f694d719b114ad72a18.tar.bz2 | |
[mlir] Conv ops vectorization pass
In this commit a new way of convolution ops lowering is introduced.
The conv op vectorization pass lowers linalg convolution ops
into vector contractions. This lowering is possible when conv op
is first tiled by 1 along specific dimensions which transforms
it into dot product between input and kernel subview memory buffers.
This pass converts such conv op into vector contraction and does
all necessary vector transfers that make it work.
Differential Revision: https://reviews.llvm.org/D86619
Diffstat (limited to 'clang/lib/Frontend/CompilerInvocation.cpp')
0 files changed, 0 insertions, 0 deletions