visual c++ - seperate the cuda host code in .cpp file -

main.cpp

#include<iostream> #include "cuda.h"   using namespace std; void cuda_calculation();   int main() {     cuda_calculation();     return 0; } 

cu.h

void call(int , int ,float*  , int  ); 

cuda.cpp

#include <stdio.h> #include <cuda.h> #include "cu.h"     void cuda_calculation() {   float *a_h, *a_d;  // pointer host & device arrays   const int n = 10;  // number of elements in arrays   size_t size = n * sizeof(float);   a_h = (float *)malloc(size);        // allocate array on host   cudamalloc((void **) &a_d, size);   // allocate array on device   // initialize host array , copy cuda device   (int i=0; i<n; i++) a_h[i] = (float)i;   cudamemcpy(a_d, a_h, size, cudamemcpyhosttodevice);   // calculation on device:   int block_size = 4;   int n_blocks = n/block_size + (n%block_size == 0 ? 0:1);   void call(n_blocks, block_size,&a_d, n);   /*square_array <<< n_blocks, block_size >>> (a_d, n);*/   // retrieve result device , store in host array   cudamemcpy(a_h, a_d, sizeof(float)*n, cudamemcpydevicetohost);   // print results   (int i=0; i<n; i++) printf("%d %f\n", i, a_h[i]);   // cleanup   free(a_h); cudafree(a_d); } 

cu.cu

#include <stdio.h> #include "cu.h" #include <cuda.h>  // kernel executes on cuda device __global__ void square_array(float *a, int n) {   int idx = blockidx.x * blockdim.x + threadidx.x;   if (idx<n) a[idx] = a[idx] * a[idx]; }   //}   void call(int a,int b,float* c,int d) { square_array <<< 3,4 >>> (c,d); } 

i tried seperate kernal code , host code in cpp file, following error prevails:

error    'cudamemcpy': identifier not found , other cuda related identifier not identified.  how use cuda related identifier in cpp file , call kernal functions 

there errors: void cuda_calculation(); needs visible main.cpp through header file (cu.h).

also make sure compile .cu files nvcc , not standard c++ file. use cuda compilation rules make process easy (installed default part of cuda toolkit)