#include "stdio.h"


__global__ void add_arrays_gpu( float *in1, float *in2, float *out, int Ntot)
{
  int idx=blockIdx.x*blockDim.x+threadIdx.x;
  if (idx < Ntot)
    out[idx]=in1[idx]+in2[idx];
}


int main(void)
{
  int N=10000, M=100000;
  float **x = (float**) malloc(N*sizeof(float));
  float **x_d = (float**) malloc(N*sizeof(float));
  int i,j;

  for (i = 0; i < N; i++) {
    x[i] = (float*) malloc(M*sizeof(float));
    cudaMalloc ((void **) &x_d[i], sizeof(float)*M);
    for (j = 0; j < M; j++) {
      x[i][j] = (float) j;
    }
    cudaMemcpy(x_d[i], x[i], sizeof(float)*M, cudaMemcpyHostToDevice);
  }


  /* Compute the execution configuration */
//  int block_size=256;
 // dim3 dimBlock(block_size);
  //dim3 dimGrid ( (N/dimBlock.x) + (!(N%dimBlock.x)?0:1) );

  /** Add arrays a and b, store result in c */
 // add_arrays_gpu<<<dimGrid,dimBlock>>>(a_d, b_d, c_d, N);

  /* Copy data from deveice memory to host memory */
  //cudaMemcpy(c, c_d, sizeof(float)*N, cudaMemcpyDeviceToHost);

  /* Print c */
/*for(i=0; i<N; i++)
    printf(" c[%d]=%f\n",i,c[i]);*/

  /* Free the memory */
//  free(a); free(b); free(c);
//  cudaFree(a_d); cudaFree(b_d);cudaFree(c_d);
}