Assembly BUG! I am stuck...

geek504 · October 27, 2020

I am in the process of writing support assembly code for my BASIC compiler and am stuck with a particular BUG in the routine (PrDec16) that converts and prints an UNSIGNED INT into a DECIMAL STRING (There is also a routine, PrSgnDec16, that prints SIGNED INT which relies on it).

When you compile and run the program, it seems to work BUT the side-effect of the bug is that when you type RUN again, it just clears the screen (it actually prints out something random before it clears). So if I wrote a larger program, it ends up clearing the screen preventing other things to be printed (or it crashed?).

I spent two full days hungting for this bug but cannot find it! Can anyone see where the mistake is?

Quote

       .org $0801

       .byte $0C, $08
       .byte $0A, $00
       .byte $9E
       .byte $20
       .byte $32, $30, $36, $34
       .byte $00
       .byte $00, $00
       .byte $00, $00 ; Padding so code starts at $0810

CHROUT       = $FFD2
PLOT       = $FFF0
NEWLINE       = $0D
UPPERCASE   = $8E

r0   = $02
r0L   = $02
r0H   = $03
r1   = $04
r1L   = $04
r1H   = $05
r2   = $06
r2L   = $06
r2H   = $07
r3   = $08
r3L   = $08
r3H   = $09
r4   = $0a
r4L   = $0a
r4H   = $0b
r5   = $0c
r5L   = $0c
r5H   = $0d
r6   = $0e
r6L   = $0e
r6H   = $0f
r7   = $10
r7L   = $10
r7H   = $11
r8   = $12
r8L   = $12
r8H   = $13
r9   = $14
r9L   = $14
r9H   = $15
r10   = $16
r10L   = $16
r10H   = $17
r11   = $18
r11L   = $18
r11H   = $19
r12   = $1a
r12L   = $1a
r12H   = $1b
r13   = $1c
r13L   = $1c
r13H   = $1d
r14   = $1e
r14L   = $1e
r14H   = $1f
r15   = $20
r15L   = $20
r15H   = $21

; Loads a 16-bit Word (immediate) to .A (lo-byte) and .X (hi-byte)
;
.macro   LoadWordAX value
   lda #<value
   ldx #>value
.endmacro

; Loads the 16-bit Word value at address to .A (lo-byte) and .X (hi-byte)
;
.macro   LoadAX address
   lda address
   ldx address+1
.endmacro

; Moves the 8-bit Byte from source to dest
;
.macro MoveB source, dest
   lda source
   sta dest
.endmacro

; Moves the 16-bit Word from source (lo,hi) to dest (lo,hi)
;
.macro MoveW source, dest
   MoveB source+0, dest+0
   MoveB source+1, dest+1
.endmacro

; Store the 16-bit Word in AX to address (lo,hi)
;
.macro   StoreAX address
   sta address
   stx address+1
.endmacro

; Store a 16-bit Word (immediate) to address (lo,hi)
;
.macro   StoreImm value, address
   LoadWordAX value
   StoreAX address
.endmacro

; Print a NEWLINE char
;
.macro   PrintNewline
   lda #NEWLINE
   jsr CHROUT
.endmacro

START:
       StoreImm $1234, r0   ; decimal = 4660
       jsr PrHex16       ; input at r0
       PrintNewline
       jsr NEG16       ; input at r0, output at r2
       MoveW r2, r0
       jsr PrHex16       ; prints EDCC (decimal = 60876)
       PrintNewline

       ldy #0           ; pad char, 0=none
       jsr PrSgnDec16       ; ### BUG, prints -4660 OK, but prog corrupted
;       jsr PrDec16       ; ### BUG, prints 60876 OK, but prog corrupted

END:       rts

;-----------------------------------------------------------------
; FUNCTION: 16-bit Binary Negation (two's complement)
; INPUT: r0
;
; OUTPUT: r2 = 0 - r0 = ~r0 + 1
;-----------------------------------------------------------------
NEG16: ; 16 bit Binary Negation: r2 = 0 - r0 = ~r0 + 1 (two's complement)
SEC ;Ensure carry is set
LDA #0 ;Load constant zero
SBC r0L ;... subtract the least significant byte
STA r2L ;... and store the result
LDA #0 ;Load constant zero again
SBC r0H ;... subtract the most significant byte
STA r2H ;... and store the result
RTS

;-----------------------------------------------------------------
; FUNCTION: Print 16-bit decimal number
; INPUT: r0 = value to print, copied to scratch r11
; .Y = pad character
; (e.g. '0' #48 or ' ' #32 or #0 for none)
;-----------------------------------------------------------------
PrSgnDec16:
       phy           ; save .Y = padding char
       lda r0H           ; load MSB
       and #$80       ; check for sign bit of MSB
       beq LL1           ; positive, print normally
       jsr NEG16       ; negative, NEG16 result at r2
       lda #'-'       ; print '-' sign
       jsr CHROUT
       MoveW r2, r0       ; load new positive value
LL1:
       ply           ; restore .Y

;-----------------------------------------------------------------
; FUNCTION: Print 16-bit decimal number
; INPUT: r0 = value to print, copied to scratch r11
; .Y = pad character
; (e.g. '0' #48 or ' ' #32 or #0 for none)
;
; INPUT: at PrDec16Lp1
; Y=(number of digits)*2-2, e.g. 8 for 5 digits
;
; OUTPUT: A,X,Y corrupted
;-----------------------------------------------------------------
PrDec16:
   STY pad           ; Save new padding character
   MoveW r0, r11
   LDY #8           ; Offset to powers of ten
PrDec16Lp1:
   LDX #$FF           ; Start with digit=-1
   SEC
PrDec16Lp2:
   LDA r11L           ; Subtract current tens
   SBC PrDec16Tens+0,Y
STA r11L
LDA r11H
SBC PrDec16Tens+1,Y
STA r11H
INX               ; Loop until <0
BCS PrDec16Lp2
LDA r11L ; Add current tens back in
ADC PrDec16Tens+0,Y
STA r11L
LDA r11H
ADC PrDec16Tens+1,Y
STA r11H
TXA               ; Not zero, print it
BNE PrDec16Digit
LDA pad           ; pad<>0, use it
BNE PrDec16Print
BEQ PrDec16Next
PrDec16Digit:
LDX #48 ; ASC"0", No more zero padding
STX pad
ORA #48 ; ASC"0", Print this digit
PrDec16Print:
JSR CHROUT
PrDec16Next:
DEY               ; Loop for next digit
DEY
BPL PrDec16Lp1
RTS
PrDec16Tens:
.word 1
.word 10
.word 100
.word 1000
.word 10000
pad:   .res 0           ; default 0 = no padding

;-----------------------------------------------------------------
; FUNCTION: Print 8-bit hexadecimal number
; INPUT: .A = value to print
;
; OUTPUT:
;-----------------------------------------------------------------
PrHex8: ; Print value in A in hexadecimal padded with zeros,
PHA ; Save A
LSR A ; Move top nybble to bottom nybble
LSR A
LSR A
LSR A
JSR PrNybble ; Print this nybble
PLA ; Get A back and print bottom nybble
PrNybble:
AND #15 ; Keep bottom four bits
CMP #10 ; If 0-9, jump to print
BCC PrDigit
ADC #6 ; Convert ':' to 'A'
PrDigit:
ADC #48 ; ASC"0"
JSR CHROUT ; Convert to character and print
RTS

;-----------------------------------------------------------------
; FUNCTION: Print 16-bit hexadecimal number
; INPUT: r0 = Word to print
;
; OUTPUT:
;-----------------------------------------------------------------
PrHex16:
   ;pha
   ;txa
lda r0H
jsr PrHex8
lda r0L
   ;pla
jsr PrHex8
rts

C:\dev\src>rm test.prg

C:\dev\src>cl65 -o test.prg -t cx16 -C cx16-asm.cfg test.asm

C:\dev\src>\x16-r38\x16emu.exe -prg test.prg -run

test.asm

Edited October 27, 2020 by geek504

SlithyMatt · October 27, 2020

1 hour ago, Ender said:

I don't think you can declare variables in the middle of your code like that, at least not with cc65, unless you use segments. The "PrDec16Tens" and "pad" declarations should be at the end. From what I can tell, when pad is written to, it's overwriting the first command of PrHex8, changing it from PHA to "BMI $8fd". Therefore, when you PLA later on the stack gets screwed up. If you move those declarations to the end it works.

It's perfectly OK to declare variables in the code segment, as long as it's outside the path of execution, as it appears here. RAM is RAM, and everything has to go somewhere.

But indeed, doing a ".res 0" for "pad" is not ok. You need to allocate the number of bytes you plan on writing there.

Ender · October 27, 2020

I don't think you can declare variables in the middle of your code like that, at least not with cc65, unless you use segments. The "PrDec16Tens" and "pad" declarations should be at the end. From what I can tell, when pad is written to, it's overwriting the first command of PrHex8, changing it from PHA to "BMI $8fd". Therefore, when you PLA later on the stack gets screwed up. If you move those declarations to the end it works.

geek504 · October 27, 2020

1 hour ago, Ender said:

I don't think you can declare variables in the middle of your code like that, at least not with cc65, unless you use segments. The "PrDec16Tens" and "pad" declarations should be at the end. From what I can tell, when pad is written to, it's overwriting the first command of PrHex8, changing it from PHA to "BMI $8fd". Therefore, when you PLA later on the stack gets screwed up. If you move those declarations to the end it works.

Ender, thanks a million for your fresh view on the code analysis! You actually found the spot where the problem was and it was totally off my radar! It is possible to declare variable space within one's code from what I've experienced (one can really make a mess if one really wanted to!) The bug was...

1 hour ago, geek504 said:

PrDec16Tens:
.word 1
.word 10
.word 100
.word 1000
.word 10000
pad: .res 0 ; default 0 = no padding

... pad like you said BUT it was because I was reserving ZERO byte(s) and thus overwriting PrHex8 as you mentioned. It is supposed to be .res 1 and it runs repeatedly without any problems. The ZERO was the remnant of my previous .byte 0 thinking about having a default value for pad, but the routine always write over this space so reserving was more accurate but forgot to change the 0 to 1.

I wasted so much time thinking that I was corrupting .A, .X, .Y, or the many r0-r15 or simply bad assembly code. *sigh*

Edited October 27, 2020 by geek504

SlithyMatt · October 27, 2020

3 minutes ago, geek504 said:

change the 0 to 1

I see you figured this out right as I was typing the same thing! Another thing you can do is change the .res to .byte. You should only use .res if you have some odd number or macro-defined amount of space to reserve. If it's just a byte, use .byte and give it a default load value.

geek504 · October 27, 2020

1 hour ago, SlithyMatt said:

It's perfectly OK to declare variables in the code segment, as long as it's outside the path of execution, as it appears here. RAM is RAM, and everything has to go somewhere.

LOL! As I was reading more webpages on algorithms for integer math and fixed-point math, I came across a text that mentioned that keeping data inside your code is in the realms of "self-modifying code"... woooo... makes us look like uber virus/worm programmers! Not that I ever wrote one during the 80s...

Edited October 27, 2020 by geek504

desertfish · October 27, 2020

well, it only classifies as self-modifying code if the code is modifying actual code

If you keep a byte in between instructions just as a storage byte, it doesn't qualify IMO Now, if you're changing opcodes or (more often) the operand values for certain opcodes, then we're talking

SlithyMatt · October 27, 2020

I see it as no different than having a static variable inside a function in C. If you want to be evil, you can put executable instructions in there and call them, but it's not the greatest idea.

geek504 · October 28, 2020

2 minutes ago, SlithyMatt said:

I see it as no different than having a static variable inside a function in C. If you want to be evil, you can put executable instructions in there and call them, but it's not the greatest idea.

I remember putting a shell code inside a string array...

Ender · October 28, 2020

4 hours ago, geek504 said:

.. pad like you said BUT it was because I was reserving ZERO byte(s) and thus overwriting PrHex8 as you mentioned. It is supposed to be .res 1 and it runs repeatedly without any problems. The ZERO was the remnant of my previous .byte 0 thinking about having a default value for pad, but the routine always write over this space so reserving was more accurate but forgot to change the 0 to 1.

Ah right, I was thinking of .byte when I read it and didn't notice it, the same as you All I knew was that when I stepped through it I could see that that's what was happening so I figured it must be that it was in the middle, based on the coding practices of other stuff I've looked at (I haven't been doing cc65 assembly for long).

Edited October 28, 2020 by Ender

Stefan · October 28, 2020

If I understand your code it's a repeated subtraction method.

I've found some other interesting methods, which have worked nicely.

On converting from binary to decimal:

http://www.6502.org/source/integers/hex2dec-more.htm

On converting from decimal to binary:

https://www.atarimagazines.com/compute/issue17/221_1_A_GENERAL_PURPOSE_BCD-TO-BINARY_ROUTINE.php

geek504 · October 28, 2020

7 hours ago, Stefan said:

If I understand your code it's a repeated subtraction method.

I've found some other interesting methods, which have worked nicely.

Thanks for the links... I am always looking for cool 6502 algorithms to include in my support library!

But, I just wanted to print Hex2Dec for the PRINT function... you're suggesting to first convert hex to BCD and then use BCD to print each digit? Would that be substantially faster than repeated subtraction?

I confess, I never used BCD in my life. Can anyone illuminate the usefulness of BCD?

Stefan · October 28, 2020

I haven't done the math to tell which method is faster.

The methods described in the articles are general and scales well. My gut feeling is that they are more effective when dealing with large numbers (more than 16 bits).

I'm using those functions on 32 bit numbers. First and foremost because of the beauty of the design

SlithyMatt · October 28, 2020

2 hours ago, geek504 said:

Can anyone illuminate the usefulness of BCD?

BCD is generally faster, and a more scalable process. Also, you can have a running counter that stays in BCD all the time, like a score, that can be quickly rendered as text on screen.

geek504 · October 28, 2020

48 minutes ago, SlithyMatt said:

BCD is generally faster, and a more scalable process. Also, you can have a running counter that stays in BCD all the time, like a score, that can be quickly rendered as text on screen.

Faster? A statement like var++ would be a simply matter of using INC and ADC for large numbers. BCD would require checking for the 9 digit and moving to 0 digit instead of A. Of course, 6502 does native BCD and that might be just as fast? BCD also uses more memory but I can see that BCD to string is much easier!

On another topic, does anyone have a handy algorithm to convert a fraction into a floating-point mantissa (binary form), for example:

N=7, D=3 ==> N/D = 7/3 = 2R1

I want to convert R/D (always less than 1) to the fractional part (mantissa) of a floating/fixed point number:

R/D = 1/3 = 0.3333 ==> Result in Binary : 0.01010101

SlithyMatt · October 28, 2020

6 minutes ago, geek504 said:

6502 does native BCD and that might be just as fast?

Yes, that's the point. Native hardware BCD support is what makes it fast. Generating BCD values with binary arithmetic would be a lot slower.

geek504 · October 28, 2020

2 hours ago, geek504 said:

On another topic, does anyone have a handy algorithm to convert a fraction into a floating-point mantissa (binary form), for example:

N=7, D=3 ==> N/D = 7/3 = 2R1

I want to convert R/D (always less than 1) to the fractional part (mantissa) of a floating/fixed point number:

R/D = 1/3 = 0.3333 ==> Result in Binary : 0.01010101

After spending the afternoon going over binary division just for fun, I probably re-invented the wheel. In any case, here is the algorithm in Python form:

Quote

# Q16 factor for mantissa

N = 1
D = 7
Q = []

print("Binary Division: (N) " + "{0:b}".format(N) + "/" + "{0:b}".format(D) + " (D)")

for i in range(16):

N = N<<1

print("Can D=" + "{0:b}".format(D) + " go into N=" + "{0:b}".format(N) + "?")

if D>N:
print("No")
Q.append("0")
else:
print("Yes")
Q.append("1")
N = N - D
if N == 0:
break

print("N={0:b}".format(N))

print("Result: ", *Q)

F = 0.0

for i in range(16):
if Q.pop(0) == '1':
F = F + (1/(2**(i+1)))

print("Fraction: ", F)

Feel free to comment! Now I have to convert this to 6502 assembly

Sample run on 1/7 (which happens to be the remainder of the cheap PI value 22/7 = 3.14):

Quote

Binary Division: (N) 1/111 (D)
Can D=111 go into N=10?
No
N=10
Can D=111 go into N=100?
No
N=100
Can D=111 go into N=1000?
Yes
N=1
Can D=111 go into N=10?
No
N=10
Can D=111 go into N=100?
No
N=100
Can D=111 go into N=1000?
Yes
N=1
Can D=111 go into N=10?
No
N=10
Can D=111 go into N=100?
No
N=100
Can D=111 go into N=1000?
Yes
N=1
Can D=111 go into N=10?
No
N=10
Can D=111 go into N=100?
No
N=100
Can D=111 go into N=1000?
Yes
N=1
Can D=111 go into N=10?
No
N=10
Can D=111 go into N=100?
No
N=100
Can D=111 go into N=1000?
Yes
N=1
Can D=111 go into N=10?
No
N=10
Result: 0 0 1 0 0 1 0 0 1 0 0 1 0 0 1 0
Fraction: 0.142852783203125

Edited October 28, 2020 by geek504

desertfish · October 28, 2020

1 hour ago, geek504 said:

convert a fraction into a floating-point mantissa

Can't you just perform the division using FDIV rom routine?

geek504 · October 28, 2020

10 minutes ago, desertfish said:

Can't you just perform the division using FDIV rom routine?

The compiler is for Integer BASIC using 16-bit SIGNED INTs. After checking Microsoft's implmentation as well as Woz's and third-party, I decided to use 16.16 Fixed-Point since most of the INTEGER part is done. I just have to integrate the 16-bit MANTISSA part into my FP routines. This "integration" might cost a few execution cycles more but it should work well. Considering that fixed-point is faster to compute than floating-point, it's a small sacrifice. GPUs work like this as well, i.e. they use integer math along with fixed-point math with just the fractional part.

When the compiler is done, I'll add the use of the ROM's floating-point math for serious work!

My goal is to have a compiler that produces fast math at the expense of accuracy. It also uses 8-bit sine/cosine tables with 6% error margin. PI will be just 22/7 for fast computations. Let's see what this Frankenstein will look like in the end! In true Woz spirit, it is designed for game creation!

geek504 · October 29, 2020

On 10/28/2020 at 5:57 PM, geek504 said:

After checking Microsoft's implmentation as well as Woz's and third-party, I decided to use 16.16 Fixed-Point since most of the INTEGER part is done.

For those who are curious:

e = exponent, s = sign, m=mantissa, i = integer (used in fixed-point)

Microsoft (5-bytes): eeee.eeee | smmm.mmmm | mmmm.mmmm | mmmm.mmmm | mmmm.mmmm

Woz (4-bytes): seee.eeee | smmm.mmmm | mmmm.mmmm | mmmm.mmmm

Bishop (4-bytes): siii.iiii | mmmm.mmmm | mmmm.mmmm | mmmm.mmmm

My version (4-bytes): siii.iiii | iiii.iiii | mmmm.mmmm | mmmm.mmmm

32-bit float has a 7 significant digits precision

16-bit float has a 3 significant digits precision

16-bit fixed mantissa has a 5 s.d.p. plus the significant digits from the INT

The only major drawback of 16.16 fixed-point: it cannot do very very large or very very small numbers. Use ROM float-math for that!

Bishop's version is very interesting because the INT part is only -128 to +127 only, BUT any number larger than +127 the fractional part starts to become negligible, i.e. ~0.78% error margin. In order to take advantage of that requires constant checking for the INT value to determine when to use the Bishop float or normal 16-bit INT. Bishop's fixed-point was used to generate fast mandelbrots in the Apple ][.

Edited October 29, 2020 by geek504

Assembly BUG! I am stuck...

Question

geek504 44

Share this post

Link to post

Share on other sites

19 answers to this question

Recommended Posts

SlithyMatt 608

Share this post

Link to post

Share on other sites

Ender 64

Share this post

Link to post

Share on other sites

geek504 44

Share this post

Link to post

Share on other sites

SlithyMatt 608

Share this post

Link to post

Share on other sites

geek504 44

Share this post

Link to post

Share on other sites

desertfish 331

Share this post

Link to post

Share on other sites

SlithyMatt 608

Share this post

Link to post

Share on other sites

geek504 44

Share this post

Link to post

Share on other sites

Ender 64

Share this post

Link to post

Share on other sites

Stefan 95

Share this post

Link to post

Share on other sites

geek504 44

Share this post

Link to post

Share on other sites

Stefan 95

Share this post

Link to post

Share on other sites

SlithyMatt 608

Share this post

Link to post

Share on other sites

geek504 44

Share this post

Link to post

Share on other sites

SlithyMatt 608

Share this post

Link to post

Share on other sites

geek504 44

Share this post

Link to post

Share on other sites

desertfish 331

Share this post

Link to post

Share on other sites

geek504 44

Share this post

Link to post

Share on other sites