diff options
| author | Sanjay Patel <spatel@rotateright.com> | 2016-03-10 22:35:33 +0000 |
|---|---|---|
| committer | Sanjay Patel <spatel@rotateright.com> | 2016-03-10 22:35:33 +0000 |
| commit | 0181943b89e156f85b77e7e97a2a467ebf0fb736 (patch) | |
| tree | 8a9515318cd2e943f999628340516f1c5af3d9cb /clang/test/CodeGen | |
| parent | 82a827de3ba5a907d72508758269eb075f533322 (diff) | |
| download | bcm5719-llvm-0181943b89e156f85b77e7e97a2a467ebf0fb736.tar.gz bcm5719-llvm-0181943b89e156f85b77e7e97a2a467ebf0fb736.zip | |
[x86] don't use a shuffle when a vselect will do; NFCI
Looking at the IR definition of a masked load made me realize
there was no reason to use a shuffle here, so we don't need
to convert the format of the mask at all.
llvm-svn: 263167
Diffstat (limited to 'clang/test/CodeGen')
0 files changed, 0 insertions, 0 deletions
