library ieee;
use ieee.std_logic_1164.all;
use ieee.numeric_std.all;

package tipos is
constant bandas : positive := 4;
type vector32 is array (0 to bandas-1) of signed (31 downto 0);
end package tipos;

library IEEE;
use IEEE.std_logic_1164.all;
use IEEE.numeric_std.all;
library work; use work.tipos.all;

package propios is
--function declaration.
function module (a : vector32; bands: natural) return unsigned;
end propios;   --end of package.

package body propios is  --start of package body
--definition of function
--based on: https://en.m.wikipedia.org/wiki/Methods_of_computing_square_roots#Binary_numeral_system_.28base_2.29
function module (a : vector32; bands: natural) return unsigned is --To adapt it to a diferent number of bits in the input vector:
--substitute the 71 for the needed number. Number of bits in each element of the vector *2 + power of two that can represent the maximum
--number of bands, or fields. In this case, 32bit numbers, maximum number of bands, 256, so 2^8. 32*2+8=72.
variable sum : unsigned(71 downto 0):= (others => '0');
variable b : unsigned(71 downto 0):=(0=>'0', 70 => '1', others => '0');
variable a_unsig: unsigned(31 downto 0):=(others =>'0');--for this vector use the same length as the input vector, 32bit in my case.
variable result: unsigned (71 downto 0):= (others => '0');
begin

for i in 0 to bands-1 loop--Sum of all the elements squared
    a_unsig:=unsigned(a(i));
    sum:=sum + (a_unsig * a_unsig);
end loop;


--Square root of sum
while b>sum loop--Do any needed changes here. You only have to change the 71's
    b:='0'&'0'& b(71 downto 2);
end loop;

while (b/=0) loop
    if (sum>=result+b) then
        sum:=sum - (result + b);
        result:=('0'& result(71 downto 1))+b;
    else
        result:='0'& result(71 downto 1);
    end if;
    b:='0' & '0' & b(71 downto 2);
end loop;

return result(35 downto 0);--sqrt(2^72)=2^36. Use half of the bits you put in place of 71
end module;


end propios;  --end of the package body

library ieee;
use ieee.std_logic_1164.all;
use ieee.numeric_std.all;
library work;
use work.propios.all;
use work.tipos.all;

ENTITY test IS

END test;
Architecture simple of test is
signal a:vector32;
signal c: unsigned(35 downto 0);
signal b: natural:= 4;
begin
a(0)<="00000000110010011010011100000000";
a(1)<="00000000110010011010011100000000";
a(2)<="00000000110010011010011100000000";
a(3)<="00000000110010011010011100000000";


process
begin
wait for 200ps;
c<= module (a , b);
wait;
end process;


end simple;