http://stackoverflow.com/questions/1100090/looking-for-an-efficient-integer-square-root-algorithm-for-arm-thumb2

int_square_root.c

intmax_t sqroot_imax(intmax_t n, int round)
{
   intmax_t op  = n;
   intmax_t res = 0;
   intmax_t one = 1uL << ((sizeof(intmax_t)*8)-2);

   // "one" starts at the highest power of four <= than the argument.
   while (one > op)
      one >>= 2;

   while (one != 0)
   {
      if (op >= res + one)
      {
         op = op - (res + one);
         res = res +  2 * one;
      };
      res >>= 1;
      one >>= 2;
   };

   // Do arithmetic rounding to nearest integer
   if ((round))
      if (op > res)
         res++;

   return(res);
}


uintmax_t sqroot_uimax(uintmax_t n, int round)
{
   uintmax_t op  = n;
   uintmax_t res = 0;
   uintmax_t one = 1uL << ((sizeof(uintmax_t)*8)-2);

   // "one" starts at the highest power of four <= than the argument.
   while (one > op)
      one >>= 2;

   while (one != 0)
   {
      if (op >= res + one)
      {
         op = op - (res + one);
         res = res +  2 * one;
      };
      res >>= 1;
      one >>= 2;
   };

   // Do arithmetic rounding to nearest integer
   if ((round))
      if (op > res)
         res++;

   return(res);
}