maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[OPENMP][NVPTX]Revert __kmpc_shuffle_int64 to its original form. 

Summary:
Use the original shuffle implementation for __kmpc_shuffle_int64 since
default implementation uses the same implementation.

Reviewers: gtbercea

Subscribers: guansong, caomhin, openmp-commits

Differential Revision: https://reviews.llvm.org/D55514

llvm-svn: 348772
This commit is contained in:
Alexey Bataev 2018-12-10 16:50:36 +00:00
parent e448351b77
commit 9056f1116d
1 changed files with 0 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
openmp/libomptarget/deviceRTLs/nvptx/src/reduction.cu
View File

@ -76,17 +76,12 @@ EXTERN int32_t __kmpc_shuffle_int32(int32_t val, int16_t delta, int16_t size) {
}
EXTERN int64_t __kmpc_shuffle_int64(int64_t val, int16_t delta, int16_t size) {
#if defined(CUDART_VERSION) && CUDART_VERSION >= 9000
return __SHFL_DOWN_SYNC(0xFFFFFFFFFFFFFFFFLL, (long long)val, (unsigned)delta,
(int)size);
#else
int lo, hi;
asm volatile("mov.b64 {%0,%1}, %2;" : "=r"(lo), "=r"(hi) : "l"(val));
hi = __SHFL_DOWN_SYNC(0xFFFFFFFF, hi, delta, size);
lo = __SHFL_DOWN_SYNC(0xFFFFFFFF, lo, delta, size);
asm volatile("mov.b64 %0, {%1,%2};" : "=l"(val) : "r"(lo), "r"(hi));
return val;
#endif
}
static INLINE void gpu_regular_warp_reduce(void *reduce_data,