1 #ifndef HeterogeneousTest_CUDAKernel_interface_DeviceAdditionKernel_h 2 #define HeterogeneousTest_CUDAKernel_interface_DeviceAdditionKernel_h 6 #include <cuda_runtime.h> 11 const float* __restrict__ in2,
12 float* __restrict__
out,
16 const double* __restrict__ in2,
17 double* __restrict__
out,
22 #endif // HeterogeneousTest_CUDAKernel_interface_DeviceAdditionKernel_h
__global__ void kernel_add_vectors_d(const double *__restrict__ in1, const double *__restrict__ in2, double *__restrict__ out, size_t size)
__global__ void kernel_add_vectors_f(const float *__restrict__ in1, const float *__restrict__ in2, float *__restrict__ out, size_t size)