int main()

{

/* 0 means unassigned cells */

int grid[N][N] =

{0, 0, 0, 0, 0, 0, 0, 7, 4},

{0, 0, 5, 2, 0, 6, 3, 0, 0} };

/**

int grid[N][N] =

{0, 16, 12, 0, 0, 5, 0, 9, 0, 13, 14, 4, 1, 0, 0, 0} };

/**/

int* d_a;

cudaMalloc((void**)&d_a, N*N * sizeof(int));