copyValsShfl      201 modules/core/include/opencv2/core/cuda/detail/reduce_key_val.hpp         __device__ __forceinline__ void copyValsShfl(V& val, unsigned int delta, int width)
copyValsShfl      211 modules/core/include/opencv2/core/cuda/detail/reduce_key_val.hpp         __device__ __forceinline__ void copyValsShfl(const thrust::tuple<VR0, VR1, VR2, VR3, VR4, VR5, VR6, VR7, VR8, VR9>& val,