diff options
| author | Simon Pilgrim <llvm-dev@redking.me.uk> | 2016-11-05 16:40:20 +0000 |
|---|---|---|
| committer | Simon Pilgrim <llvm-dev@redking.me.uk> | 2016-11-05 16:40:20 +0000 |
| commit | 1af0fc1103591c35cca8048dae9776a6c329ecd1 (patch) | |
| tree | 0ca70076d0c57aaa2d237140f09ab2ef76bf4ad1 /llvm/test | |
| parent | a8d63dc2896a555a5efa19dea312f245fdf10ba2 (diff) | |
| download | bcm5719-llvm-1af0fc1103591c35cca8048dae9776a6c329ecd1.tar.gz bcm5719-llvm-1af0fc1103591c35cca8048dae9776a6c329ecd1.zip | |
[X86][SSE] Reuse zeroable element mask instead of regenerating it. NFCI
We are repeatedly calling computeZeroableShuffleElements in many shuffle lowering calls for the same shuffle mask/inputs.
This is a first step towards reusing the zeroable result, initially just for lowerVectorShuffleAsShift calls.
llvm-svn: 286037
Diffstat (limited to 'llvm/test')
0 files changed, 0 insertions, 0 deletions
