diff options
| author | Benjamin Kramer <benny.kra@googlemail.com> | 2022-01-13 13:12:50 +0100 |
|---|---|---|
| committer | Benjamin Kramer <benny.kra@googlemail.com> | 2022-01-26 11:38:41 +0100 |
| commit | 0776f6e04d8c3823c31b8fa6fa7d1376a7009af1 (patch) | |
| tree | 1554add4c3c85d960c09502e41607305433b461f /llvm/lib/TextAPI/Architecture.cpp | |
| parent | 188d28f73cc7b7891c182a85fdb6e274123b5b69 (diff) | |
| download | llvm-0776f6e04d8c3823c31b8fa6fa7d1376a7009af1.zip llvm-0776f6e04d8c3823c31b8fa6fa7d1376a7009af1.tar.gz llvm-0776f6e04d8c3823c31b8fa6fa7d1376a7009af1.tar.bz2 | |
[LSV] Vectorize loads of vectors by turning it into a larger vector
Use shufflevector to do the subvector extracts. This allows a lot more
load merging on AMDGPU and also on NVPTX when <2 x half> is involved.
Differential Revision: https://reviews.llvm.org/D117219
Diffstat (limited to 'llvm/lib/TextAPI/Architecture.cpp')
0 files changed, 0 insertions, 0 deletions