diff options
| author | Guozhi Wei <carrot@google.com> | 2016-12-12 22:09:02 +0000 |
|---|---|---|
| committer | Guozhi Wei <carrot@google.com> | 2016-12-12 22:09:02 +0000 |
| commit | 1fd553c9345ff9f1f32b1256bae0f2d63ec3ae38 (patch) | |
| tree | bc1eee5191bd4080607547efdd097a04e8df213c /llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp | |
| parent | 44bde896a5f88f0d4e283ff4b5ab3a04df32848d (diff) | |
| download | bcm5719-llvm-1fd553c9345ff9f1f32b1256bae0f2d63ec3ae38.tar.gz bcm5719-llvm-1fd553c9345ff9f1f32b1256bae0f2d63ec3ae38.zip | |
[PPC] Prefer direct move on power8 if load 1 or 2 bytes to VSR
Power8 has MTVSRWZ but no LXSIBZX/LXSIHZX, so move 1 or 2 bytes to VSR through MTVSRWZ is much faster than store the extended value into stack and load it with LXSIWZX.
This patch fixes pr31144.
Differential Revision: https://reviews.llvm.org/D27287
llvm-svn: 289473
Diffstat (limited to 'llvm/lib/Target/AMDGPU/AMDGPUCodeGenPrepare.cpp')
0 files changed, 0 insertions, 0 deletions
