__kernel void matrix_mult(__global int * a, __global int * b, __global int * c, int n)
{
   int row = get_global_id(0);
   int col = get_global_id(1);

   if (row >= n || col >= n)
      return;

   int sum = 0;

   for (int k = 0; k < n; ++k)
      sum += a[row * n + k] * b[k * n + col];

   c[row * n + col] = sum;
}