#include "cuda_runtime.h"
#include "cublas_v2.h"
#include "time.h"
#include <iostream>
using namespace std;
#define N 10
__global__ void add(int *a, int *b, int *c){
int tid = blockIdx.x;
if (tid < N)
c[tid] = a[tid] + b[tid];
}
int main(void)
{
int a[N],b[N],c[N];
int *dev_a, *dev_b, *dev_c;
cudaMalloc((void**)&dev_a, N*sizeof(int));
cudaMalloc((void**)&dev_b, N*sizeof(int));
cudaMalloc((void**)&dev_c, N*sizeof(int));