Как использовать GPU-вычисления в Microsoft Visual C++?

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35

#include 

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

int main()
{
    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));
    for (int i = 0; i < N; i++)
    {
        a[i] = i;
        b[i] = i * i;
        c[i] = 0;
    }
    cudaMemcpy(dev_a, a, N * sizeof(int), cudaMemcpyHostToDevice);
    cudaMemcpy(dev_b, b, N * sizeof(int), cudaMemcpyHostToDevice);
    add<<>>(dev_a, dev_b, dev_c);
    cudaMemcpy(c, dev_c, N * sizeof(int), cudaMemcpyDeviceToHost);
    for (int i = 0; i < N; i++)
    {
        printf("%d + %d = %d
", a[i], b[i], c[i]);
    }
    cudaFree(dev_a);
    cudaFree(dev_b);
    cudaFree(dev_c);
    return 0;
}