| commit | f179364341ef49440757a481b377627d17db3aaa | [log] [tgz] |
|---|---|---|
| author | Justin Lebar <jlebar@google.com> | Tue May 31 21:27:13 2016 +0000 |
| committer | Justin Lebar <jlebar@google.com> | Tue May 31 21:27:13 2016 +0000 |
| tree | 91f6ce66a817e125e164c2fffc16b171150cb443 | |
| parent | 0aeb313e792649aa063e91783e3d8675cfdfd5be [diff] |
[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