用CUDA在GPU熵对任意矢量长度求和

#define N (30*1024)
__global__ void add(int *a, int *b, int *c)
{

#include "cuda_runtime.h"
#include "cublas_v2.h"
#include "time.h"
#include <iostream>
using namespace std;
int tid =threadIdx.x+ blockIdx.x*blockDim.x;
while (tid < N)
{
c[tid] = a[tid] + b[tid];
tid += blockDim.x*gridDim.x;//gridDim线程格中每一维线程块数量，blockDim.x每个线程块的线程数量
}
}
int main(void)
{
int a[N],b[N],c[N];
int *dev_a, *dev_b, *dev_c;
cudaMalloc((void**)&dev_a,