CUDA sample for curand_kernel

curand_sample.cu

#include <stdio.h>
#include <cuda.h>
#include <curand_kernel.h>

__global__ void
func(void){
  int id = blockIdx.x * blockDim.x + threadIdx.x;
  curandState s;
  curand_init(0,id,0,&s);
  for(int i=0;i<4;i++){
    printf("%d %f\n",id,curand_uniform_double(&s));
  }
}

int
main(void){
  cudaSetDeviceFlags(cudaDeviceMapHost);
  int const n_thread = 2;
  int const n_block = 2;
  func<<<n_block,n_thread>>>();
  printf("Version = %d\n",CUDA_VERSION);
  cudaThreadSynchronize();
}