Code: [Select]

// Multiply a times b
temp = 0
repeat for each bit in a
temp <<= 1
if (high bit of a set)
temp += b
a <<= 1
return temp
if a and b are 2 bytes, temp is 4 bytes, and you loop 16 times.

Spoiler For for code:

stolen from Axe
p_MulFull:
   ; Input in hl, result in cahl
   ld   c,h
   ld   a,l
   ld   hl,0   ;11
   ld   b,16   ;7
__MulFullNext:
   add   hl,hl   ;11
   rla      ;4
   rl   c   ;8
   jr   nc,__MulFullSkip   ;12/7
   add   hl,de   ;11
   adc   a,0   ;7
   jr   nc,__MulFullSkip
   inc   c
__MulFullSkip:
   djnz   __MulFullNext
   ret
__MulFullEnd:

Code: [Select]

// Sqrt a
temp = high byte of a
a <<= 8
b = 0
repeat for every 2 bits in a
test = b << 8 + 0x40
b <<= 1
if (temp >= test)
temp -= test
set low bit of b
temp += high 2 bits of a
a <<= 2
return b
If a is 4 bytes, then b and temp are 2 bytes, and you loop 16 times.

Spoiler For code:

stole my own routine from axe (and modified it)
p_Sqrt88:
   ; input in hlde, result in de
   ld   b,16
   ld   a,h
   ld   c,l
   push   de ; ld ixh,d
   pop   ix ; ld ixl,e
   ld   de,0
   ld   h,d
   ld   l,e
__Sqrt88Loop:
   sub   $40
   sbc   hl,de
   jr   nc,__Sqrt88Skip
   add   a,$40
   adc   hl,de
__Sqrt88Skip:
   ccf
   rl   e
   rl   d
   add   ix,ix
   rl   c
   rla
   adc   hl,hl
   add   ix,ix
   rl   c
   rla
   adc    hl,hl
   djnz   __Sqrt88Loop
   ret
__Sqrt88End:

Quote from: jacobly on December 11, 2011, 02:06:55 pm

Code: [Select]

// Multiply a times b
temp = 0
repeat for each bit in a
temp <<= 1
if (high bit of a set)
temp += b
a <<= 1
return temp
if a and b are 2 bytes, temp is 4 bytes, and you loop 16 times.

Spoiler For for code:

stolen from Axe
p_MulFull:
   ; Input in hl and de, result in cahl
   ld   c,h
   ld   a,l
   ld   hl,0   ;11
   ld   b,16   ;7
__MulFullNext:
   add   hl,hl   ;11
   rla      ;4
   rl   c   ;8
   jr   nc,__MulFullSkip   ;12/7
   add   hl,de   ;11
   adc   a,0   ;7
   jr   nc,__MulFullSkip
   inc   c
__MulFullSkip:
   djnz   __MulFullNext
   ret
__MulFullEnd:

Code: [Select]

// Sqrt a
temp = high byte of a
a <<= 8
b = 0
repeat for every 2 bits in a
test = b << 8 + 0x40
b <<= 1
if (temp >= test)
temp -= test
set low bit of b
temp += high 2 bits of a
a <<= 2
return b
If a is 4 bytes, then b and temp are 2 bytes, and you loop 16 times.

Spoiler For code:

stole my own routine from axe (and modified it)
p_Sqrt88:
   ; input in hlde, result in de
   ld   b,16
   ld   a,h
   ld   c,l
   push   de ; ld ixh,d
   pop   ix ; ld ixl,e
   ld   de,0
   ld   h,d
   ld   l,e
__Sqrt88Loop:
   sub   $40
   sbc   hl,de
   jr   nc,__Sqrt88Skip
   add   a,$40
   adc   hl,de
__Sqrt88Skip:
   ccf
   rl   e
   rl   d
   add   ix,ix
   rl   c
   rla
   adc   hl,hl
   add   ix,ix
   rl   c
   rla
   adc    hl,hl
   djnz   __Sqrt88Loop
   ret
__Sqrt88End:

Kool. Thanks. But, shouldn't the first one have two inputs?

I do have a 24-bit floating-point multiplication routine

saved 2 bytes, 1149 cycles saved by using iy too (and in a way compatible with TIOS, imagine that)

Code: [Select]

; hldebc = hlc * bde
ld (iy+asm_Flag1),b
xor a
ld ix,0
ld b,24
Loop:
add ix,ix
rla
rl c
adc hl,hl
jr nc,Next
add ix,de
adc a,(iy+asm_Flag1)
rl c
jr nc,Next
inc hl
Next:
djnz Loop
ld e,a
ld d,c
push ix ; ld c,ixl
pop bc ; ld b,ixh


That's strange. My test program must not have been working right, because when I went back and changed it a bit, it suddenly started telling me that the second routine doesn't work.
Anyway, my new test program seems to agree with this change.

Code: [Select]

; hldebc = hlc * bde
ld (iy+asm_Flag1),b
xor a
ld ix,0
ld b,24
Loop:
add ix,ix
rla
rl c
adc hl,hl
jr nc,Next
add ix,de
adc a,(iy+asm_Flag1)
jr nc,Next
inc c
jr nz,Next
inc hl
Next:
djnz Loop
ld e,a
ld d,c
push ix ; ld c,ixl
pop bc ; ld b,ixh