CUDA PROGRAM TO ADD VECTOR

#include <stdio.h>

/* vector elements */
#define N 512

/* definition of an function executed on GPU */
__global__ void vecAdd(int *A, int *B,int *C)
{
    int i = threadIdx.x;

    C[i] = A[i] + B[i];
}

/* prints contents */
void Print(const int *A, int size)
{
    for(int i=0;i<size;i++)
    {
        printf("\t%d", A[i]);
    }
    printf("\n");
}

/* an entry point */
int main(int argc, char *argv[])
{
    int A[N], B[N], C[N],i;
    int *devA,*devB,*devC;

    /* device memory allocations */
    cudaMalloc((void**)&devA, N*sizeof(int));
    cudaMalloc((void**)&devB, N*sizeof(int));
    cudaMalloc((void**)&devC, N*sizeof(int));

    /* setting initialize values */
    for(i=0;i<N;i++)
    {
        A[i]=i;
        B[i]=i;
    }
    for(i=0;i<N;i++)
    {
        C[i]=0;
    }
    printf("\nVecotr A is:\n");
    Print( A, N);
    printf("\nVector B is:\n");
    Print(B, N);

    /* data copying from host to device */
    cudaMemcpy(devA, A, N*sizeof(int), cudaMemcpyHostToDevice);
    cudaMemcpy(devB, B, N*sizeof(int), cudaMemcpyHostToDevice);
    cudaMemcpy(devC, C, N*sizeof(int), cudaMemcpyHostToDevice);

    /* execution on GPU */
    vecAdd<<<1, N>>>(devA, devB, devC);

    /* data copying from device to host */
    cudaMemcpy(C, devC, N*sizeof(int), cudaMemcpyDeviceToHost);
    printf("\nVector A+B is\n\n");
    Print(C, N);

    /* freeing device memory */
    cudaFree((void**)&devA);
    cudaFree((void**)&devB);
    cudaFree((void**)&devC);

    return 0;
}