diff options
| author | Diego Caballero <diegocaballero@google.com> | 2024-01-31 17:26:50 -0800 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-01-31 17:26:50 -0800 |
| commit | 8ba018d72a67050a9c37065ea2668814ebf513a9 (patch) | |
| tree | 4c4a220fa50caa6cd02166bee7c0c408a249154a /clang/unittests/Format/ConfigParseTest.cpp | |
| parent | 0e8eb445db0cc2552d9d077b527a43c779785cb9 (diff) | |
| download | llvm-8ba018d72a67050a9c37065ea2668814ebf513a9.zip llvm-8ba018d72a67050a9c37065ea2668814ebf513a9.tar.gz llvm-8ba018d72a67050a9c37065ea2668814ebf513a9.tar.bz2 | |
[mlir][Vector] Add support for sub-byte transpose emulation (#80110)
This PR adds patterns to convert a sub-byte vector transpose into a
sequence of instructions that perform the transpose on i8 vector
elements. Whereas this rewrite may not lead to the absolute peak
performance, it should ensure correctness when dealing with sub-byte
transposes.
Diffstat (limited to 'clang/unittests/Format/ConfigParseTest.cpp')
0 files changed, 0 insertions, 0 deletions