From cc6cf64c38f49ad203aa2252c4209e21103f06f6 Mon Sep 17 00:00:00 2001 From: Alexey Bataev Date: Mon, 10 Dec 2018 14:29:05 +0000 Subject: [OPENMP][NVPTX]Enable fast shuffles on 64bit values only if CUDA >= 9. Summary: Shuffle on 64bit data is allowed only for CUDA >= 9.0. Also, fixed the constant for the mask, need one extra L in the end. Reviewers: gtbercea, kkwli0 Subscribers: guansong, caomhin, openmp-commits Differential Revision: https://reviews.llvm.org/D55440 llvm-svn: 348758 --- openmp/libomptarget/deviceRTLs/nvptx/src/reduction.cu | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'openmp') diff --git a/openmp/libomptarget/deviceRTLs/nvptx/src/reduction.cu b/openmp/libomptarget/deviceRTLs/nvptx/src/reduction.cu index a05a6e0..2546302 100644 --- a/openmp/libomptarget/deviceRTLs/nvptx/src/reduction.cu +++ b/openmp/libomptarget/deviceRTLs/nvptx/src/reduction.cu @@ -76,7 +76,17 @@ 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) { - return __SHFL_DOWN_SYNC(0xFFFFFFFFFFFFFFFFL, val, delta, 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, -- cgit v1.1