diff options
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | 2017-09-20 05:01:53 +0000 |
|---|---|---|
| committer | Matt Arsenault <Matthew.Arsenault@amd.com> | 2017-09-20 05:01:53 +0000 |
| commit | b81495dccb2977e8861fa40e0b38657b46f148e6 (patch) | |
| tree | 5b9cc193b82458716f81e05376caf19c023f973f /clang/lib/Sema/SemaDeclObjC.cpp | |
| parent | e08ccfe3a116e4c0907fed266788d05681cb5db2 (diff) | |
| download | bcm5719-llvm-b81495dccb2977e8861fa40e0b38657b46f148e6.tar.gz bcm5719-llvm-b81495dccb2977e8861fa40e0b38657b46f148e6.zip | |
AMDGPU: Match load d16 hi instructions
Also starts selecting global loads for constant address
in some cases. Some end up selecting to mubuf still, which
requires investigation.
We still get sub-optimal regalloc and extra waitcnts inserted
due to not really tracking the liveness of the separate register
halves.
llvm-svn: 313716
Diffstat (limited to 'clang/lib/Sema/SemaDeclObjC.cpp')
0 files changed, 0 insertions, 0 deletions
