__global__ void vecadd_kernel(int n, float *a, float *b, float *c)
{
  int i = blockDim.x * blockIdx.x + threadIdx.x;

  if ( i < n ) c[i] = a[i] + b[i];
}
extern "C" void vecadd(int n ,float *a, float *b, float *c)
{
  dim3 griddim, blockdim;

  blockdim = dim3(128,1,1);
  griddim = dim3(n/blockdim.x,1,1);

  vecadd_kernel<<<griddim,blockdim>>>(n,a,b,c);
}