SqrtE

;===============================================================
sqrtE:
;===============================================================
;Input:
;     E is the value to find the square root of
;Outputs:
;     A is E-D^2
;     B is 0
;     D is the result
;     E is not changed
;     HL is not changed
;Destroys:
;     C=2D+1 if D is even, 2D-1 if D is odd

        xor a               ;1      4         4
        ld d,a              ;1      4         4
        ld c,a              ;1      4         4
        ld b,4              ;2      7         7
sqrtELoop:
        rlc d               ;2      8        32
        ld c,d              ;1      4        16
        scf                 ;1      4        16
        rl c                ;2      8        32

        rlc e               ;2      8        32
        rla                 ;1      4        16
        rlc e               ;2      8        32
        rla                 ;1      4        16

        cp c                ;1      4        16
        jr c,$+4            ;4    12|15      48+3x
          inc d             ;--    --        --
          sub c             ;--    --        --
        djnz sqrtELoop      ;2    13|8       47
        ret                 ;1     10        10
;===============================================================
;Size  : 25 bytes
;Speed : 332+3x cycles
;   x is the number of set bits in the result. This will not
;   exceed 4, so the range for cycles is 332 to 344. To put this
;   into perspective, under the slowest conditions (4 set bits
;   in the result at 6MHz), this can execute over 18000 times
;   in a second.
;===============================================================