fatal error lnk1104 无法打开exe

#include "cuda_runtime.h"
#include "device_launch_parameters.h"
#include<iostream>
#include <stdio.h>
using namespace std;


const int N = 2048;


__global__ void kernel(int* a, int* b, int* c)
{
const int tid = blockDim.x*blockIdx.x + threadIdx.x;
c[tid] = a[tid] + b[tid];
}


int main(void)
{
int *a_h, *a_d, *b_h, *b_d, *c_h, *c_d;


a_h = (int*)malloc(N*sizeof(int));
b_h = (int*)malloc(N*sizeof(int));
c_h = (int*)malloc(N*sizeof(int));


cudaMalloc((void**)&a_d, N*sizeof(int));
cudaMalloc((void**)&b_d, N*sizeof(int));
cudaMalloc((void**)&c_d, N*sizeof(int));


for (int i = 0; i < N; i++)
{
a_h[i] = i;
b_h[i] = 2 * i;
}


const int nStream = 4;
int size = N*sizeof(int) / nStream;
int offset;
cudaStream_t stream[nStream];
for (int i = 0; i < nStream; i++)
{
cudaStreamCreate(&stream[i]);
}
for (int i = 0; i < nStream; i++)
{
offset = i*N / nStream;
cudaMemcpyAsync(a_d + offset, a_h + offset, size, cudaMemcpyHostToDevice, stream[i]);
cudaMemcpyAsync(b_d + offset, b_h + offset, size, cudaMemcpyHostToDevice, stream[i]);
}
for (int i = 0; i < nStream; i++)
{
offset = i*N / nStream;
kernel << <2, N / (2 * nStream), 0, stream[i] >> >(a_d + offset, b_d + offset, c_d + offset);
}
//cudaThreadSynchronize();
for (int i = 0; i < nStream; i++)
{
offset = i*N / nStream;
cudaMemcpyAsync(c_h + offset, c_d + offset, size, cudaMemcpyDeviceToHost, stream[i]);
}

for (int i = 0; i < N; i++)
{
if (c_h[i] % 3 != 0)
cout << c_h[i] << "  ";
}






free(a_h);
free(b_h);
free(c_h);
cudaFree(a_d);
cudaFree(b_d);
cudaFree(c_d);
return 0;

}

在红色的代码中，如果没有N*这个符号，那么它将会申请不到内存，整个程序就将会被挂起，那么你将会第一次可以编译通过并且运行，但是第二次就会报出fatal error lnk1104 无法打开exe 这样的错误，这样，我们需要每次进入资源监视器里面，将挂起的程序结束进程，才可以继续编译，但是结果都是错误的，就这么一个N*的错误，就会导致程序挂起来。