CUDA编程学习（三）

我们知道一个grid包含多个block，而一个block又包含多个thread，下面将是如何进行下thread中的并行。

/**** Splot a block into parallel threads****/

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

#define N 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<<<1,N>>>(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();
}

重点语句变化: grid下的 add<<<1,1>>>(d_a, d_b, d_c)  到block下的 add<<<N,1>>>(d_a, d_b, d_c); 最后到 thread下   add<<<1,N>>>(d_a, d_b, d_c);