diff options
| author | Justin Lebar <jlebar@google.com> | 2016-05-31 21:27:13 +0000 |
|---|---|---|
| committer | Justin Lebar <jlebar@google.com> | 2016-05-31 21:27:13 +0000 |
| commit | f179364341ef49440757a481b377627d17db3aaa (patch) | |
| tree | 91f6ce66a817e125e164c2fffc16b171150cb443 /compiler-rt/lib/esan/cache_frag.cpp | |
| parent | 0aeb313e792649aa063e91783e3d8675cfdfd5be (diff) | |
| download | bcm5719-llvm-f179364341ef49440757a481b377627d17db3aaa.tar.gz bcm5719-llvm-f179364341ef49440757a481b377627d17db3aaa.zip | |
[CUDA] Conservatively mark inline asm as convergent.
Summary:
This is particularly important because a some convergent CUDA intrinsics
(e.g. __shfl_down) are implemented in terms of inline asm.
Reviewers: tra
Subscribers: cfe-commits
Differential Revision: http://reviews.llvm.org/D20836
llvm-svn: 271336
Diffstat (limited to 'compiler-rt/lib/esan/cache_frag.cpp')
0 files changed, 0 insertions, 0 deletions
