diff options
| author | Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com> | 2017-04-06 16:48:30 +0000 |
|---|---|---|
| committer | Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com> | 2017-04-06 16:48:30 +0000 |
| commit | ea57c38521d46fe4a8ae2d1172d25538a88d4431 (patch) | |
| tree | f8848ebe196295e32e1b209346c5a78196231ed0 /polly/lib/Transform/ScheduleOptimizer.cpp | |
| parent | 3fc1225c1851a2511bade654751e1ed42dda3653 (diff) | |
| download | bcm5719-llvm-ea57c38521d46fe4a8ae2d1172d25538a88d4431.tar.gz bcm5719-llvm-ea57c38521d46fe4a8ae2d1172d25538a88d4431.zip | |
[AMDGPU] Eliminate barrier if workgroup size is not greater than wavefront size
If a workgroup size is known to be not greater than wavefront size
the s_barrier instruction is not needed since all threads are guarantied
to come to the same point at the same time.
Differential Revision: https://reviews.llvm.org/D31731
llvm-svn: 299659
Diffstat (limited to 'polly/lib/Transform/ScheduleOptimizer.cpp')
0 files changed, 0 insertions, 0 deletions
