Index: libomptarget/deviceRTLs/nvptx/src/reduction.cu
===================================================================
--- libomptarget/deviceRTLs/nvptx/src/reduction.cu
+++ libomptarget/deviceRTLs/nvptx/src/reduction.cu
@@ -76,7 +76,17 @@
 }
 
 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,