diff options
| author | Alexey Bataev <a.bataev@hotmail.com> | 2018-12-10 16:50:36 +0000 |
|---|---|---|
| committer | Alexey Bataev <a.bataev@hotmail.com> | 2018-12-10 16:50:36 +0000 |
| commit | e90d5a507452b782029b2cacce364785c3af9fdd (patch) | |
| tree | 5caf928910a681784a6df21c7cb074ad6460684d /libomptarget/deviceRTLs | |
| parent | a23f780b1ae886c793d74375c10dab887a30d9eb (diff) | |
[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
git-svn-id: https://llvm.org/svn/llvm-project/openmp/trunk@348772 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'libomptarget/deviceRTLs')
| -rw-r--r-- | libomptarget/deviceRTLs/nvptx/src/reduction.cu | 5 |
1 files changed, 0 insertions, 5 deletions
diff --git a/libomptarget/deviceRTLs/nvptx/src/reduction.cu b/libomptarget/deviceRTLs/nvptx/src/reduction.cu index 2546302..c0d22df 100644 --- a/libomptarget/deviceRTLs/nvptx/src/reduction.cu +++ b/libomptarget/deviceRTLs/nvptx/src/reduction.cu @@ -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, |