CUDA编程学习（四）

利用Block和Thread进行并行加速

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

#define N (2048*2048)
#define THREAD_PER_BLOCK 512

int main()
{
    int *a, *b, *c;            //host copies of a, b, c
    int *d_a, *d_b, *d_c;    //device copies of a, b, c
    int size = N * sizeof(int);
    
    //Alloc space for device copies of a, b, c
    cudaMalloc((void **)&d_a, size);
    cudaMalloc((void **)&d_b, size);
    cudaMalloc((void **)&d_c, size);
    
    //Alloc space for host copies of a, b, c and setup input values
    a = (int *)malloc(size); random_ints(a, N);
    b = (int *)malloc(size); random_ints(b, N);
    c = (int *)malloc(size);
    
    //Copy the data into device
    cudeMemcpy(d_a, a, size, cudaMemcpyHostToDevice);
    cudaMemcpy(d_b, b, size, cudaMemcpyHostToDevice);
    
    //Launch add() kernel on GPU with N blocks
    add<<<N/THREADS_PER_BLOCK,THREADS_PER_BLOCK>>>(d_a, d_b, d_c);
    
    //Copy result back to host
    cudaMemcpy(c, d_c, size, cudaMemcpyDeviceToHost);
    
    //Cleanup
    free(a); free(b); free(c);
    cudeFree(d_a); cudaFree(d_b); cudaFree(d_c);
    return 0;
}

/**** What's the function of random_ints****/
void random_ints(int* a, int N)
{
 int i;
 for (i = 0; i < N; ++i)
 a[i] = rand();
}