#include <stdio.h>

#define NUM_BLOCKS 2
#define BLOCK_WIDTH 16

__global__ void hello()
{
  printf("Hello world! I'm thread %d in block %d\n", threadIdx.x, blockIdx.x);
}

int main()
{

  // launch the kernel
  hello<<<NUM_BLOCKS, BLOCK_WIDTH>>>();

  // force the printf()s to flush
  cudaDeviceSynchronize();

  printf("That's all!\n");

  return 0;

}