replica
/
hanchenye-llvm-project
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[CUDA] Added missing __threadfence_system() function for CUDA9. 

llvm-svn: 325626
This commit is contained in:
Artem Belevich 2018-02-20 21:25:30 +00:00
parent c03c9040aa
commit 4dbea99137
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
clang/lib/Headers/__clang_cuda_device_functions.h
View File

@ -530,6 +530,7 @@ __DEVICE__ int __syncthreads_or(int __a) { return __nvvm_bar0_or(__a); }
__DEVICE__ float __tanf(float __a) { return __nv_fast_tanf(__a); }
__DEVICE__ void __threadfence(void) { __nvvm_membar_gl(); }
__DEVICE__ void __threadfence_block(void) { __nvvm_membar_cta(); };
__DEVICE__ void __threadfence_system(void) { __nvvm_membar_sys(); };
__DEVICE__ void __trap(void) { asm volatile("trap;"); }
__DEVICE__ unsigned int __uAtomicAdd(unsigned int *__p, unsigned int __v) {
return __nvvm_atom_add_gen_i((int *)__p, __v);