Cuda C bloki/watki razem

#include <stdio.h>

#define N 1024

__global__ void dodawanie(int *a, int *b, int *c)
{
    int indeks = threadIdx.x + blockIdx.x * blockDim.x;
    while (indeks < N) {
        c[indeks] = a[indeks] + b[indeks];
        indeks += blockDim.x * gridDim.x;
    }
}

__global__ void funkcja(int *a, int *b, int *c)
{
    int indeks = threadIdx.x;
    if (indeks < N) {
        c[indeks]= a[indeks] + b[indeks];
    }
}

int main(void)
{
    int *a, *b, *c;
    cudaMallocManaged(&a, N*sizeof(int));
    cudaMallocManaged(&b, N*sizeof(int));
    cudaMallocManaged(&c, N*sizeof(int));


    for (int i = 0; i<N; i++) {
        a[i] = 2 *i;
        b[i] = 2 *i;
    }
    dodawanie<<<16,16>>>(a, b, c);
    cudaDeviceSynchronize();
    /*for (int i = 0; i< N; i++) {
        printf("%d + %d = %d\n", a[i], b[i], c[i]);
    }*/
    printf("%d + %d = %d\n", a[N-1], b[N-1], c[N-1]);
    cudaFree(a);
    cudaFree(b);
    cudaFree(c);
    return 0;
}