diff options
| author | Sanjay Patel <spatel@rotateright.com> | 2016-03-09 22:12:08 +0000 |
|---|---|---|
| committer | Sanjay Patel <spatel@rotateright.com> | 2016-03-09 22:12:08 +0000 |
| commit | 4a8dd89128eb563d50ac9dd2c9f8017fc0cfc495 (patch) | |
| tree | 8115ff1605c1384b63da181b674072e71b7e05cf /llvm/test/Transforms/LoopVectorize | |
| parent | eee554d86ed2407623421d3aa3bac1f8e0d9e2ae (diff) | |
| download | bcm5719-llvm-4a8dd89128eb563d50ac9dd2c9f8017fc0cfc495.tar.gz bcm5719-llvm-4a8dd89128eb563d50ac9dd2c9f8017fc0cfc495.zip | |
[x86, AVX] optimize masked loads with constant masks
Instead of a variable-blend instruction, form a blend with immediate because those are always cheaper.
Differential Revision: http://reviews.llvm.org/D17899
llvm-svn: 263067
Diffstat (limited to 'llvm/test/Transforms/LoopVectorize')
0 files changed, 0 insertions, 0 deletions
