CUDA

cuda_parallel.cu

#include <cstdio>
#include "cuda.h"

__global__
void loop_on_device()
{
    printf("Device(GPU) iteration number %d\n", blockIdx.x * blockDim.x + threadIdx.x);
}

void loop_on_host(int length)
{
  for (int i = 0; i < length; ++i) {
    printf("Host(CPU) iteration number %d\n", i);
  }
}

int main()
{
    int block_size = 3;
    int kernel_size = 4;
    loop_on_device<<<block_size, kernel_size>>>();

    int n = block_size * kernel_size;
    loop_on_host(n);

    cudaDeviceSynchronize();
    return EXIT_SUCCESS;
}