jcs@crash.cts.com (John Schultz) (06/09/90)
To borrow a phrase from Young MC, You want it? You got it. Here are my
complete processor polygon fill routines. Now you can find out how much
faster the processor is first hand. I made this code as generic as
possible, so Macs and other 68000 based system should be able to use this
code (although register convention may force some changes).
This code also points out a bug in Lattice 5.04, read on for more info.
This *source* code may be used for whatever purpose you wish, but cannot
be published or sold without permission of author. You can use the source
without restriction in your own programs.
If you can make this code go faster, by all means, let me know...
Have fun, enjoy, etc,
John Schultz
jcs@crash.cts.com
#! /bin/sh
# This is a shell archive, meaning:
# 1. Remove everything above the #! /bin/sh line.
# 2. Save the resulting text in a file.
# 3. Execute the file with /bin/sh (not csh) to create the files:
# fill.c
# scanconvert.a
# This archive created: Fri Jun 8 21:06:48 1990
export PATH; PATH=/bin:$PATH
if test -f 'fill.c'
then
echo shar: will not over-write existing file "'fill.c'"
else
cat << \SHAR_EOF > 'fill.c'
/* fill.c, a processor polygon filler */
/* Copyright (c) 1990 John Schultz, All Rights Reserved */
/* This is the C interface to the assembly code that does most of the */
/* work. I haven't seen an algorithm of this type for filling polygons */
/* elsewhere, so I'd like to think my implementation of this table fill */
/* algorithm is unique :-).The algorithm works by first finding out the */
/* orientation of the polygon, then filling the tables from miny to */
/* maxy. This allows the table to be updated unconditionally, without */
/* having to read the current values from the tables, compare, then */
/* write back to memory. */
/* The polygons are an array of drawpoints, and you don't need to */
/* close the polygons: a triangle will only have three points. */
/* This code has been optimized for 320x200x4 bitmaps, which have */
/* been allocated linearly (One 32,000 byte allocation as opposed */
/* to four 8,000 byte allocations). */
/* To compile this code use:
/* lc -O -cuf -v fill.c */
/* asm scanconvert.a */
/* Link to your own code as appropriate. */
/* I am using Lattice 5.04, and get a CXERR: 26, Line: 0, if the */
/* optimizer is not used! */
/* Look ma, no includes. */
typedef struct drawpoint {short dx,dy;} drawpoint;
#define MAXY 201 /* Bitmap max y + 1 */
short xmin[MAXY], xmax[MAXY]; /* Scanconverter tables */
short * xtable[] = {xmin,xmax}; /* For toggling between fill tables */
/* Prototypes */
extern void __asm drawline68k(register __a1 char * p, /* 1st Plane Ptr */
register __d0 short x,
register __d1 short y,
register __d2 short x2,
register __d3 short y2,
register __d4 short color);
extern void __asm fillline68k(register __d0 short x,
register __d1 short y,
register __d2 short x2,
register __d3 short y2,
register __a0 short * table);
extern void __asm scanconvpix(register __a0 char * p, /* 1st Plane Ptr */
register __a1 short * minx,
register __a2 short * maxx,
register __d0 short miny,
register __d1 short maxy,
register __d2 short color);
void drawpoly(drawpoint * dl, /* An array of drawpoints */
char * p, /* 1st Plane Ptr */
short cl, /* Number of points */
short color);
/* Code */
void drawpoly(drawpoint * dl, /* An array of drawpoints */
char * p, /* 1st Plane Ptr */
short cl, /* Number of points */
short color){
short miny,maxy;
short i,inext,index;
short tminy,tmaxy;
short j;
long orient=0;
/* Find out if polygon is clockwise or counterclockwise */
for (i=0; i < cl; i++) { /* Use the Newell method */
if (i == (cl-1)) {
j = 0;
} else {
j = i+1;
}
orient += (dl[i].dx - dl[j].dx)*(dl[i].dy + dl[j].dy);
} /* for i */
if (orient != 0) { /* Check to see if we have a line or polygon */
index = (orient < 0) ? 0 : 1;
/* Find miny,maxy */
tminy = 199;
tmaxy = 0;
for (i=0; i < cl; i++) {
if (dl[i].dy < tminy) {miny = i; tminy = dl[i].dy;}
if (dl[i].dy > tmaxy) {maxy = i; tmaxy = dl[i].dy;}
} /* for i */
/* Fill tables */
i = miny; /* Start at top, fill to bottom, filling lines from top */
do { /* to bottom for efficient assembly implementation. */
inext = i + 1;
if (inext >= cl) inext = 0; /* Wrap around */
fillline68k(dl[i].dx,dl[i].dy,dl[inext].dx,dl[inext].dy,xtable[index]);
if (inext == maxy) index ^= 1; /* Toggle min/max to keep lines */
i++; /* being filled from top to bottom */
if (i >= cl) i = 0; /* Wrap around */
} while (inext != miny); /* Come full circle, done */
/* Draw polygon */
scanconvpix(p,xmin,xmax,tminy,tmaxy,color);
} else { /* Draw a line */
/* This test really only works for triangles */
if ((dl[0].dx == dl[1].dx) && (dl[0].dy == dl[1].dy))
drawline68k(p,dl[0].dx,dl[0].dy,dl[1].dx,dl[1].dy,color);
else
drawline68k(p,dl[0].dx,dl[0].dy,dl[2].dx,dl[2].dy,color);
} /* if orient */
} /* end drawpoly */
/* end fill.c */
SHAR_EOF
fi # end of overwriting check
if test -f 'scanconvert.a'
then
echo shar: will not over-write existing file "'scanconvert.a'"
else
cat << \SHAR_EOF > 'scanconvert.a'
; scanconvert.a
; Copyright (c) 1990 John Schultz, All Rights Reserved
; Created 14-March-90
; Modified 17-May-90
; Re-written with long word aligned writes: now up to twice as fast
; as using bfset/bfclr (bitfield instructions can hit up to 5 bytes,
; not long word aligned).
; Code is now 68000 compatible.
; Modified 8-June-90
; Included filline68k, drawline68k in this file for Fill example.
; Assembles to 3840 bytes using the Devpac 2.0 assembler.
section scanconvert,code
xdef _scanconvpix
xdef _fillline68k
xdef _drawline68k
; This code has been optimized for 320x200x4 bitmaps, which have
; been allocated linearly (One 32,000 byte allocation as opposed
; to four 8,000 byte allocations).
PLANESIZE equ 8000 ; 320x200 bitplanes
BYTESROW equ 40 ; " "
;extern void __asm scanconvpix(register __a0 PLANEPTR p,
; register __a1 short * minx,
; register __a2 short * maxx,
; register __d0 short miny,
; register __d1 short maxy,
; register __d2 short color);
_scanconvpix:
movem.l d2-d7/a2-a5,-(sp)
move.w d1,d7 ; get maxy. d0 = miny.
sub.w d0,d7 ; compute yheight. +1 not necessary: using dbra.
movea.l a1,a4 ; copy xminptr
movea.l a2,a5 ; copy xmaxptr
move.w d0,d6 ; copy miny
add.w d6,d6 ; y index is 2 bytes, so *2 offset
adda.w d6,a4 ; get to start postion minx
adda.w d6,a5 ; get to start postion maxx
move.w d0,d6 ; copy miny
lsl.w #3,d6 ; *8
lsl.w #5,d0 ; *32
add.w d6,d0 ; *40
adda.w d0,a0 ; go to first scanline in bitmap
move.l a0,d6 ; setup for first pass (d6 += 40 each pass)
moveq.l #BYTESROW,d5 ; bytes per row, to be added each scanline
lea colorplanes(pc),a2 ; get colorplane table
add.w d2,d2
add.w d2,d2 ; entries are 4 bytes long
movea.l 0(a2,d2.w),a2 ; get color jsr address
jmp (a2) ; do specific plane writes/clears
; end of scanconvpix
; Specific fill cases for 0-15 colors. Speed is of the essence, not
; code size :-). Each case is specifically optimized. Could be made
; shorter, but slower.
COLOR0 macro
color0:
scanloop4\@
move.w (a4)+,d0 ; get minx
move.w (a5)+,d1 ; get maxx
cmp.w d0,d1 ; error check
bmi.b finished4\@
move.w d0,d4 ; copy minx
lsr.w #5,d4 ; get first long word
lsl.w #2,d4 ; *4 = number of bytes
adda.w d4,a0 ; add x offset to scanline
lea PLANESIZE(a0),a1
lea PLANESIZE(a1),a2
lea PLANESIZE(a2),a3
move.w d0,d4 ; copy minx
moveq.l #-1,d2 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
lsr.l d4,d2 ; shift mask by d4 pixels
move.w d1,d4 ; copy maxx
moveq.l #-1,d3 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
neg.w d4 ; - d4
add.w #31,d4 ; d4 = 31 - d4
lsl.l d4,d3 ; shift mask by d4 pixels
lsr.w #5,d0 ; get start long word
lsr.w #5,d1 ; get end long word
sub.w d0,d1 ; get width in long words
bne.b doublewrite4\@ ; check for single write
; single write
and.l d2,d3 ; combine left and right masks
not.l d3 ; invert
and.l d3,(a0) ; clear
and.l d3,(a1) ; clear
and.l d3,(a2) ; clear
and.l d3,(a3) ; clear
bra.b finished4\@
doublewrite4\@
not.l d2 ; invert
and.l d2,(a0)+ ; write left mask
and.l d2,(a1)+ ; write left mask
and.l d2,(a2)+ ; write left mask
and.l d2,(a3)+ ; write left mask
subq.w #2,d1 ; subtract left and right writes
bmi.b writeright4\@ ; don't do a multiwrite
; multiwrite
moveq.l #0,d2 ; zereos
multiloop4\@
move.l d2,(a0)+ ; write middle 0's
move.l d2,(a1)+ ; write middle 0's
move.l d2,(a2)+ ; write middle 0's
move.l d2,(a3)+ ; write middle 0's
dbra d1,multiloop4\@
writeright4\@
not.l d3
and.l d3,(a0) ; write right mask
and.l d3,(a1) ; write right mask
and.l d3,(a2) ; write right mask
and.l d3,(a3) ; write right mask
finished4\@
add.l d5,d6 ; go to next scanline
movea.l d6,a0 ; copy ptr to modify
dbra d7,scanloop4\@ ; d7 = yheight-1.
movem.l (sp)+,d2-d7/a2-a5
rts
endm
COLOR1 macro
color1:
scanloop4\@
move.w (a4)+,d0 ; get minx
move.w (a5)+,d1 ; get maxx
cmp.w d0,d1 ; error check
bmi.b finished4\@
move.w d0,d4 ; copy minx
lsr.w #5,d4 ; get first long word
lsl.w #2,d4 ; *4 = number of bytes
adda.w d4,a0 ; add x offset to scanline
lea PLANESIZE(a0),a1
lea PLANESIZE(a1),a2
lea PLANESIZE(a2),a3
move.w d0,d4 ; copy minx
moveq.l #-1,d2 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
lsr.l d4,d2 ; shift mask by d4 pixels
move.w d1,d4 ; copy maxx
moveq.l #-1,d3 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
neg.w d4 ; - d4
add.w #31,d4 ; d4 = 31 - d4
lsl.l d4,d3 ; shift mask by d4 pixels
lsr.w #5,d0 ; get start long word
lsr.w #5,d1 ; get end long word
sub.w d0,d1 ; get width in long words
bne.b doublewrite4\@ ; check for single write
; single write
and.l d2,d3 ; combine left and right masks
or.l d3,(a0) ; set
not.l d3 ; invert
and.l d3,(a1) ; clear
and.l d3,(a2) ; clear
and.l d3,(a3) ; clear
not.l d3
bra.b finished4\@
doublewrite4\@
or.l d2,(a0)+ ; set
not.l d2
and.l d2,(a1)+ ; clear
and.l d2,(a2)+ ; clear
and.l d2,(a3)+ ; clear
subq.w #2,d1 ; subtract left and right writes
bmi.b writeright4\@ ; don't do a multiwrite
; multiwrite\@
moveq.l #-1,d2 ; $ffffffff
moveq.l #0,d4 ; zeroes
multiloop4\@
move.l d2,(a0)+ ; set
move.l d4,(a1)+ ; clear
move.l d4,(a2)+ ; clear
move.l d4,(a3)+ ; clear
dbra d1,multiloop4\@
writeright4\@
or.l d3,(a0) ; set
not.l d3
and.l d3,(a1) ; clear
and.l d3,(a2) ; clear
and.l d3,(a3) ; clear
finished4\@
add.l d5,d6 ; go to next scanline
movea.l d6,a0 ; copy ptr to modify
dbra d7,scanloop4\@ ; d7 = yheight-1.
movem.l (sp)+,d2-d7/a2-a5
rts
endm
COLOR2 macro
color2:
scanloop4\@
move.w (a4)+,d0 ; get minx
move.w (a5)+,d1 ; get maxx
cmp.w d0,d1 ; error check
bmi.b finished4\@
move.w d0,d4 ; copy minx
lsr.w #5,d4 ; get first long word
lsl.w #2,d4 ; *4 = number of bytes
adda.w d4,a0 ; add x offset to scanline
lea PLANESIZE(a0),a1
lea PLANESIZE(a1),a2
lea PLANESIZE(a2),a3
move.w d0,d4 ; copy minx
moveq.l #-1,d2 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
lsr.l d4,d2 ; shift mask by d4 pixels
move.w d1,d4 ; copy maxx
moveq.l #-1,d3 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
neg.w d4 ; - d4
add.w #31,d4 ; d4 = 31 - d4
lsl.l d4,d3 ; shift mask by d4 pixels
lsr.w #5,d0 ; get start long word
lsr.w #5,d1 ; get end long word
sub.w d0,d1 ; get width in long words
bne.b doublewrite4\@ ; check for single write
; single write
and.l d2,d3 ; combine left and right masks
or.l d3,(a1) ; set
not.l d3 ; invert
and.l d3,(a0) ; clear
and.l d3,(a2) ; clear
and.l d3,(a3) ; clear
bra.b finished4\@
doublewrite4\@
or.l d2,(a1)+ ; set
not.l d2
and.l d2,(a0)+ ; clear
and.l d2,(a2)+ ; clear
and.l d2,(a3)+ ; clear
subq.w #2,d1 ; subtract left and right writes
bmi.b writeright4\@ ; don't do a multiwrite
; multiwrite\@
moveq.l #-1,d2 ; $ffffffff
moveq.l #0,d4 ; zeroes
multiloop4\@
move.l d2,(a1)+ ; set
move.l d4,(a0)+ ; clear
move.l d4,(a2)+ ; clear
move.l d4,(a3)+ ; clear
dbra d1,multiloop4\@
writeright4\@
or.l d3,(a1) ; set
not.l d3 ; invert
and.l d3,(a0) ; clear
and.l d3,(a2) ; clear
and.l d3,(a3) ; clear
finished4\@
add.l d5,d6 ; go to next scanline
movea.l d6,a0 ; copy ptr to modify
dbra d7,scanloop4\@ ; d7 = yheight-1.
movem.l (sp)+,d2-d7/a2-a5
rts
endm
COLOR3 macro
color3:
scanloop4\@
move.w (a4)+,d0 ; get minx
move.w (a5)+,d1 ; get maxx
cmp.w d0,d1 ; error check
bmi.b finished4\@
move.w d0,d4 ; copy minx
lsr.w #5,d4 ; get first long word
lsl.w #2,d4 ; *4 = number of bytes
adda.w d4,a0 ; add x offset to scanline
lea PLANESIZE(a0),a1
lea PLANESIZE(a1),a2
lea PLANESIZE(a2),a3
move.w d0,d4 ; copy minx
moveq.l #-1,d2 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
lsr.l d4,d2 ; shift mask by d4 pixels
move.w d1,d4 ; copy maxx
moveq.l #-1,d3 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
neg.w d4 ; - d4
add.w #31,d4 ; d4 = 31 - d4
lsl.l d4,d3 ; shift mask by d4 pixels
lsr.w #5,d0 ; get start long word
lsr.w #5,d1 ; get end long word
sub.w d0,d1 ; get width in long words
bne.b doublewrite4\@ ; check for single write
; single write
and.l d2,d3 ; combine left and right masks
or.l d3,(a0) ; set
or.l d3,(a1) ; set
not.l d3 ; invert
and.l d3,(a2) ; clear
and.l d3,(a3) ; clear
bra.b finished4\@
doublewrite4\@
or.l d2,(a0)+ ; set
or.l d2,(a1)+ ; set
not.l d2
and.l d2,(a2)+ ; clear
and.l d2,(a3)+ ; clear
subq.w #2,d1 ; subtract left and right writes
bmi.b writeright4\@ ; don't do a multiwrite
; multiwrite\@
moveq.l #-1,d2 ; $ffffffff
moveq.l #0,d4 ; zeroes
multiloop4\@
move.l d2,(a0)+ ; set
move.l d2,(a1)+ ; set
move.l d4,(a2)+ ; clear
move.l d4,(a3)+ ; clear
dbra d1,multiloop4\@
writeright4\@
or.l d3,(a0) ; set
or.l d3,(a1) ; set
not.l d3
and.l d3,(a2) ; clear
and.l d3,(a3) ; clear
finished4\@
add.l d5,d6 ; go to next scanline
movea.l d6,a0 ; copy ptr to modify
dbra d7,scanloop4\@ ; d7 = yheight-1.
movem.l (sp)+,d2-d7/a2-a5
rts
endm
COLOR4 macro
color4:
scanloop4\@
move.w (a4)+,d0 ; get minx
move.w (a5)+,d1 ; get maxx
cmp.w d0,d1 ; error check
bmi.b finished4\@
move.w d0,d4 ; copy minx
lsr.w #5,d4 ; get first long word
lsl.w #2,d4 ; *4 = number of bytes
adda.w d4,a0 ; add x offset to scanline
lea PLANESIZE(a0),a1
lea PLANESIZE(a1),a2
lea PLANESIZE(a2),a3
move.w d0,d4 ; copy minx
moveq.l #-1,d2 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
lsr.l d4,d2 ; shift mask by d4 pixels
move.w d1,d4 ; copy maxx
moveq.l #-1,d3 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
neg.w d4 ; - d4
add.w #31,d4 ; d4 = 31 - d4
lsl.l d4,d3 ; shift mask by d4 pixels
lsr.w #5,d0 ; get start long word
lsr.w #5,d1 ; get end long word
sub.w d0,d1 ; get width in long words
bne.b doublewrite4\@ ; check for single write
; single write
and.l d2,d3 ; combine left and right masks
or.l d3,(a2) ; set
not.l d3 ; invert
and.l d3,(a0) ; clear
and.l d3,(a1) ; clear
and.l d3,(a3) ; clear
bra.b finished4\@
doublewrite4\@
or.l d2,(a2)+ ; set
not.l d2
and.l d2,(a0)+ ; clear
and.l d2,(a1)+ ; clear
and.l d2,(a3)+ ; clear
subq.w #2,d1 ; subtract left and right writes
bmi.b writeright4\@ ; don't do a multiwrite
; multiwrite\@
moveq.l #-1,d2 ; $ffffffff
moveq.l #0,d4 ; zeroes
multiloop4\@
move.l d2,(a2)+ ; set
move.l d4,(a0)+ ; clear
move.l d4,(a1)+ ; clear
move.l d4,(a3)+ ; clear
dbra d1,multiloop4\@
writeright4\@
or.l d3,(a2) ; set
not.l d3 ; invert
and.l d3,(a0) ; clear
and.l d3,(a1) ; clear
and.l d3,(a3) ; clear
finished4\@
add.l d5,d6 ; go to next scanline
movea.l d6,a0 ; copy ptr to modify
dbra d7,scanloop4\@ ; d7 = yheight-1.
movem.l (sp)+,d2-d7/a2-a5
rts
endm
COLOR5 macro
color5:
scanloop4\@
move.w (a4)+,d0 ; get minx
move.w (a5)+,d1 ; get maxx
cmp.w d0,d1 ; error check
bmi.b finished4\@
move.w d0,d4 ; copy minx
lsr.w #5,d4 ; get first long word
lsl.w #2,d4 ; *4 = number of bytes
adda.w d4,a0 ; add x offset to scanline
lea PLANESIZE(a0),a1
lea PLANESIZE(a1),a2
lea PLANESIZE(a2),a3
move.w d0,d4 ; copy minx
moveq.l #-1,d2 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
lsr.l d4,d2 ; shift mask by d4 pixels
move.w d1,d4 ; copy maxx
moveq.l #-1,d3 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
neg.w d4 ; - d4
add.w #31,d4 ; d4 = 31 - d4
lsl.l d4,d3 ; shift mask by d4 pixels
lsr.w #5,d0 ; get start long word
lsr.w #5,d1 ; get end long word
sub.w d0,d1 ; get width in long words
bne.b doublewrite4\@ ; check for single write
; single write
and.l d2,d3 ; combine left and right masks
or.l d3,(a0) ; set
or.l d3,(a2) ; set
not.l d3 ; invert
and.l d3,(a1) ; clear
and.l d3,(a3) ; clear
bra.b finished4\@
doublewrite4\@
or.l d2,(a0)+ ; set
or.l d2,(a2)+ ; set
not.l d2
and.l d2,(a1)+ ; clear
and.l d2,(a3)+ ; clear
subq.w #2,d1 ; subtract left and right writes
bmi.b writeright4\@ ; don't do a multiwrite
; multiwrite\@
moveq.l #-1,d2 ; $ffffffff
moveq.l #0,d4 ; zeroes
multiloop4\@
move.l d2,(a0)+ ; set
move.l d2,(a2)+ ; set
move.l d4,(a1)+ ; clear
move.l d4,(a3)+ ; clear
dbra d1,multiloop4\@
writeright4\@
or.l d3,(a0) ; set
or.l d3,(a2) ; set
not.l d3 ; invert
and.l d3,(a1) ; clear
and.l d3,(a3) ; clear
finished4\@
add.l d5,d6 ; go to next scanline
movea.l d6,a0 ; copy ptr to modify
dbra d7,scanloop4\@ ; d7 = yheight-1.
movem.l (sp)+,d2-d7/a2-a5
rts
endm
COLOR6 macro
color6:
scanloop4\@
move.w (a4)+,d0 ; get minx
move.w (a5)+,d1 ; get maxx
cmp.w d0,d1 ; error check
bmi.b finished4\@
move.w d0,d4 ; copy minx
lsr.w #5,d4 ; get first long word
lsl.w #2,d4 ; *4 = number of bytes
adda.w d4,a0 ; add x offset to scanline
lea PLANESIZE(a0),a1
lea PLANESIZE(a1),a2
lea PLANESIZE(a2),a3
move.w d0,d4 ; copy minx
moveq.l #-1,d2 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
lsr.l d4,d2 ; shift mask by d4 pixels
move.w d1,d4 ; copy maxx
moveq.l #-1,d3 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
neg.w d4 ; - d4
add.w #31,d4 ; d4 = 31 - d4
lsl.l d4,d3 ; shift mask by d4 pixels
lsr.w #5,d0 ; get start long word
lsr.w #5,d1 ; get end long word
sub.w d0,d1 ; get width in long words
bne.b doublewrite4\@ ; check for single write
; single write
and.l d2,d3 ; combine left and right masks
or.l d3,(a1) ; set
or.l d3,(a2) ; set
not.l d3 ; invert
and.l d3,(a0) ; clear
and.l d3,(a3) ; clear
bra.b finished4\@
doublewrite4\@
or.l d2,(a1)+ ; set
or.l d2,(a2)+ ; set
not.l d2
and.l d2,(a0)+ ; clear
and.l d2,(a3)+ ; clear
subq.w #2,d1 ; subtract left and right writes
bmi.b writeright4\@ ; don't do a multiwrite
; multiwrite\@
moveq.l #-1,d2 ; $ffffffff
moveq.l #0,d4 ; zeroes
multiloop4\@
move.l d2,(a1)+ ; set
move.l d2,(a2)+ ; set
move.l d4,(a0)+ ; clear
move.l d4,(a3)+ ; clear
dbra d1,multiloop4\@
writeright4\@
or.l d3,(a1) ; set
or.l d3,(a2) ; set
not.l d3 ; invert
and.l d3,(a0) ; clear
and.l d3,(a3) ; clear
finished4\@
add.l d5,d6 ; go to next scanline
movea.l d6,a0 ; copy ptr to modify
dbra d7,scanloop4\@ ; d7 = yheight-1.
movem.l (sp)+,d2-d7/a2-a5
rts
endm
COLOR7 macro
color7:
scanloop4\@
move.w (a4)+,d0 ; get minx
move.w (a5)+,d1 ; get maxx
cmp.w d0,d1 ; error check
bmi.b finished4\@
move.w d0,d4 ; copy minx
lsr.w #5,d4 ; get first long word
lsl.w #2,d4 ; *4 = number of bytes
adda.w d4,a0 ; add x offset to scanline
lea PLANESIZE(a0),a1
lea PLANESIZE(a1),a2
lea PLANESIZE(a2),a3
move.w d0,d4 ; copy minx
moveq.l #-1,d2 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
lsr.l d4,d2 ; shift mask by d4 pixels
move.w d1,d4 ; copy maxx
moveq.l #-1,d3 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
neg.w d4 ; - d4
add.w #31,d4 ; d4 = 31 - d4
lsl.l d4,d3 ; shift mask by d4 pixels
lsr.w #5,d0 ; get start long word
lsr.w #5,d1 ; get end long word
sub.w d0,d1 ; get width in long words
bne.b doublewrite4\@ ; check for single write
; single write
and.l d2,d3 ; combine left and right masks
or.l d3,(a0) ; set
or.l d3,(a1) ; set
or.l d3,(a2) ; set
not.l d3 ; invert
and.l d3,(a3) ; clear
bra.b finished4\@
doublewrite4\@
or.l d2,(a0)+ ; set
or.l d2,(a1)+ ; set
or.l d2,(a2)+ ; set
not.l d2
and.l d2,(a3)+ ; clear
subq.w #2,d1 ; subtract left and right writes
bmi.b writeright4\@ ; don't do a multiwrite
; multiwrite\@
moveq.l #-1,d2 ; $ffffffff
moveq.l #0,d4 ; zeroes
multiloop4\@
move.l d2,(a0)+ ; set
move.l d2,(a1)+ ; set
move.l d2,(a2)+ ; set
move.l d4,(a3)+ ; clear
dbra d1,multiloop4\@
writeright4\@
or.l d3,(a0) ; set
or.l d3,(a1) ; set
or.l d3,(a2) ; set
not.l d3 ; invert
and.l d3,(a3) ; clear
finished4\@
add.l d5,d6 ; go to next scanline
movea.l d6,a0 ; copy ptr to modify
dbra d7,scanloop4\@ ; d7 = yheight-1.
movem.l (sp)+,d2-d7/a2-a5
rts
endm
COLOR8 macro
color8:
scanloop4\@
move.w (a4)+,d0 ; get minx
move.w (a5)+,d1 ; get maxx
cmp.w d0,d1 ; error check
bmi.b finished4\@
move.w d0,d4 ; copy minx
lsr.w #5,d4 ; get first long word
lsl.w #2,d4 ; *4 = number of bytes
adda.w d4,a0 ; add x offset to scanline
lea PLANESIZE(a0),a1
lea PLANESIZE(a1),a2
lea PLANESIZE(a2),a3
move.w d0,d4 ; copy minx
moveq.l #-1,d2 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
lsr.l d4,d2 ; shift mask by d4 pixels
move.w d1,d4 ; copy maxx
moveq.l #-1,d3 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
neg.w d4 ; - d4
add.w #31,d4 ; d4 = 31 - d4
lsl.l d4,d3 ; shift mask by d4 pixels
lsr.w #5,d0 ; get start long word
lsr.w #5,d1 ; get end long word
sub.w d0,d1 ; get width in long words
bne.b doublewrite4\@ ; check for single write
; single write
and.l d2,d3 ; combine left and right masks
or.l d3,(a3) ; set
not.l d3 ; invert
and.l d3,(a0) ; clear
and.l d3,(a1) ; clear
and.l d3,(a2) ; clear
bra.b finished4\@
doublewrite4\@
or.l d2,(a3)+ ; set
not.l d2
and.l d2,(a0)+ ; clear
and.l d2,(a1)+ ; clear
and.l d2,(a2)+ ; clear
subq.w #2,d1 ; subtract left and right writes
bmi.b writeright4\@ ; don't do a multiwrite
; multiwrite\@
moveq.l #-1,d2 ; $ffffffff
moveq.l #0,d4 ; zeroes
multiloop4\@
move.l d2,(a3)+ ; set
move.l d4,(a0)+ ; clear
move.l d4,(a1)+ ; clear
move.l d4,(a2)+ ; clear
dbra d1,multiloop4\@
writeright4\@
or.l d3,(a3) ; set
not.l d3 ; invert
and.l d3,(a0) ; clear
and.l d3,(a1) ; clear
and.l d3,(a2) ; clear
finished4\@
add.l d5,d6 ; go to next scanline
movea.l d6,a0 ; copy ptr to modify
dbra d7,scanloop4\@ ; d7 = yheight-1.
movem.l (sp)+,d2-d7/a2-a5
rts
endm
COLOR9 macro
color9:
scanloop4\@
move.w (a4)+,d0 ; get minx
move.w (a5)+,d1 ; get maxx
cmp.w d0,d1 ; error check
bmi.b finished4\@
move.w d0,d4 ; copy minx
lsr.w #5,d4 ; get first long word
lsl.w #2,d4 ; *4 = number of bytes
adda.w d4,a0 ; add x offset to scanline
lea PLANESIZE(a0),a1
lea PLANESIZE(a1),a2
lea PLANESIZE(a2),a3
move.w d0,d4 ; copy minx
moveq.l #-1,d2 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
lsr.l d4,d2 ; shift mask by d4 pixels
move.w d1,d4 ; copy maxx
moveq.l #-1,d3 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
neg.w d4 ; - d4
add.w #31,d4 ; d4 = 31 - d4
lsl.l d4,d3 ; shift mask by d4 pixels
lsr.w #5,d0 ; get start long word
lsr.w #5,d1 ; get end long word
sub.w d0,d1 ; get width in long words
bne.b doublewrite4\@ ; check for single write
; single write
and.l d2,d3 ; combine left and right masks
or.l d3,(a0) ; set
or.l d3,(a3) ; set
not.l d3 ; invert
and.l d3,(a1) ; clear
and.l d3,(a2) ; clear
bra.b finished4\@
doublewrite4\@
or.l d2,(a0)+ ; set
or.l d2,(a3)+ ; set
not.l d2
and.l d2,(a1)+ ; clear
and.l d2,(a2)+ ; clear
subq.w #2,d1 ; subtract left and right writes
bmi.b writeright4\@ ; don't do a multiwrite
; multiwrite\@
moveq.l #-1,d2 ; $ffffffff
moveq.l #0,d4 ; zeroes
multiloop4\@
move.l d2,(a0)+ ; set
move.l d2,(a3)+ ; set
move.l d4,(a1)+ ; clear
move.l d4,(a2)+ ; clear
dbra d1,multiloop4\@
writeright4\@
or.l d3,(a0) ; set
or.l d3,(a3) ; set
not.l d3 ; invert
and.l d3,(a1) ; clear
and.l d3,(a2) ; clear
finished4\@
add.l d5,d6 ; go to next scanline
movea.l d6,a0 ; copy ptr to modify
dbra d7,scanloop4\@ ; d7 = yheight-1.
movem.l (sp)+,d2-d7/a2-a5
rts
endm
COLOR10 macro
color10:
scanloop4\@
move.w (a4)+,d0 ; get minx
move.w (a5)+,d1 ; get maxx
cmp.w d0,d1 ; error check
bmi.b finished4\@
move.w d0,d4 ; copy minx
lsr.w #5,d4 ; get first long word
lsl.w #2,d4 ; *4 = number of bytes
adda.w d4,a0 ; add x offset to scanline
lea PLANESIZE(a0),a1
lea PLANESIZE(a1),a2
lea PLANESIZE(a2),a3
move.w d0,d4 ; copy minx
moveq.l #-1,d2 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
lsr.l d4,d2 ; shift mask by d4 pixels
move.w d1,d4 ; copy maxx
moveq.l #-1,d3 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
neg.w d4 ; - d4
add.w #31,d4 ; d4 = 31 - d4
lsl.l d4,d3 ; shift mask by d4 pixels
lsr.w #5,d0 ; get start long word
lsr.w #5,d1 ; get end long word
sub.w d0,d1 ; get width in long words
bne.b doublewrite4\@ ; check for single write
; single write
and.l d2,d3 ; combine left and right masks
or.l d3,(a1) ; set
or.l d3,(a3) ; set
not.l d3 ; invert
and.l d3,(a0) ; clear
and.l d3,(a2) ; clear
bra.b finished4\@
doublewrite4\@
or.l d2,(a1)+ ; set
or.l d2,(a3)+ ; set
not.l d2
and.l d2,(a0)+ ; clear
and.l d2,(a2)+ ; clear
subq.w #2,d1 ; subtract left and right writes
bmi.b writeright4\@ ; don't do a multiwrite
; multiwrite\@
moveq.l #-1,d2 ; $ffffffff
moveq.l #0,d4 ; zeroes
multiloop4\@
move.l d2,(a1)+ ; set
move.l d2,(a3)+ ; set
move.l d4,(a0)+ ; clear
move.l d4,(a2)+ ; clear
dbra d1,multiloop4\@
writeright4\@
or.l d3,(a1) ; set
or.l d3,(a3) ; set
not.l d3 ; invert
and.l d3,(a0) ; clear
and.l d3,(a2) ; clear
finished4\@
add.l d5,d6 ; go to next scanline
movea.l d6,a0 ; copy ptr to modify
dbra d7,scanloop4\@ ; d7 = yheight-1.
movem.l (sp)+,d2-d7/a2-a5
rts
endm
COLOR11 macro
color11:
scanloop4\@
move.w (a4)+,d0 ; get minx
move.w (a5)+,d1 ; get maxx
cmp.w d0,d1 ; error check
bmi.b finished4\@
move.w d0,d4 ; copy minx
lsr.w #5,d4 ; get first long word
lsl.w #2,d4 ; *4 = number of bytes
adda.w d4,a0 ; add x offset to scanline
lea PLANESIZE(a0),a1
lea PLANESIZE(a1),a2
lea PLANESIZE(a2),a3
move.w d0,d4 ; copy minx
moveq.l #-1,d2 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
lsr.l d4,d2 ; shift mask by d4 pixels
move.w d1,d4 ; copy maxx
moveq.l #-1,d3 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
neg.w d4 ; - d4
add.w #31,d4 ; d4 = 31 - d4
lsl.l d4,d3 ; shift mask by d4 pixels
lsr.w #5,d0 ; get start long word
lsr.w #5,d1 ; get end long word
sub.w d0,d1 ; get width in long words
bne.b doublewrite4\@ ; check for single write
; single write
and.l d2,d3 ; combine left and right masks
or.l d3,(a0) ; set
or.l d3,(a1) ; set
or.l d3,(a3) ; set
not.l d3 ; invert
and.l d3,(a2) ; clear
bra.b finished4\@
doublewrite4\@
or.l d2,(a0)+ ; set
or.l d2,(a1)+ ; set
or.l d2,(a3)+ ; set
not.l d2
and.l d2,(a2)+ ; clear
subq.w #2,d1 ; subtract left and right writes
bmi.b writeright4\@ ; don't do a multiwrite
; multiwrite\@
moveq.l #-1,d2 ; $ffffffff
moveq.l #0,d4 ; zeroes
multiloop4\@
move.l d2,(a0)+ ; set
move.l d2,(a1)+ ; set
move.l d2,(a3)+ ; set
move.l d4,(a2)+ ; clear
dbra d1,multiloop4\@
writeright4\@
or.l d3,(a0) ; set
or.l d3,(a1) ; set
or.l d3,(a3) ; set
not.l d3 ; invert
and.l d3,(a2) ; clear
finished4\@
add.l d5,d6 ; go to next scanline
movea.l d6,a0 ; copy ptr to modify
dbra d7,scanloop4\@ ; d7 = yheight-1.
movem.l (sp)+,d2-d7/a2-a5
rts
endm
COLOR12 macro
color12:
scanloop4\@
move.w (a4)+,d0 ; get minx
move.w (a5)+,d1 ; get maxx
cmp.w d0,d1 ; error check
bmi.b finished4\@
move.w d0,d4 ; copy minx
lsr.w #5,d4 ; get first long word
lsl.w #2,d4 ; *4 = number of bytes
adda.w d4,a0 ; add x offset to scanline
lea PLANESIZE(a0),a1
lea PLANESIZE(a1),a2
lea PLANESIZE(a2),a3
move.w d0,d4 ; copy minx
moveq.l #-1,d2 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
lsr.l d4,d2 ; shift mask by d4 pixels
move.w d1,d4 ; copy maxx
moveq.l #-1,d3 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
neg.w d4 ; - d4
add.w #31,d4 ; d4 = 31 - d4
lsl.l d4,d3 ; shift mask by d4 pixels
lsr.w #5,d0 ; get start long word
lsr.w #5,d1 ; get end long word
sub.w d0,d1 ; get width in long words
bne.b doublewrite4\@ ; check for single write
; single write
and.l d2,d3 ; combine left and right masks
or.l d3,(a2) ; set
or.l d3,(a3) ; set
not.l d3 ; invert
and.l d3,(a0) ; clear
and.l d3,(a1) ; clear
bra.b finished4\@
doublewrite4\@
or.l d2,(a2)+ ; set
or.l d2,(a3)+ ; set
not.l d2
and.l d2,(a0)+ ; clear
and.l d2,(a1)+ ; clear
subq.w #2,d1 ; subtract left and right writes
bmi.b writeright4\@ ; don't do a multiwrite
; multiwrite\@
moveq.l #-1,d2 ; $ffffffff
moveq.l #0,d4 ; zeroes
multiloop4\@
move.l d2,(a2)+ ; set
move.l d2,(a3)+ ; set
move.l d4,(a0)+ ; clear
move.l d4,(a1)+ ; clear
dbra d1,multiloop4\@
writeright4\@
or.l d3,(a2) ; set
or.l d3,(a3) ; set
not.l d3 ; invert
and.l d3,(a0) ; clear
and.l d3,(a1) ; clear
finished4\@
add.l d5,d6 ; go to next scanline
movea.l d6,a0 ; copy ptr to modify
dbra d7,scanloop4\@ ; d7 = yheight-1.
movem.l (sp)+,d2-d7/a2-a5
rts
endm
COLOR13 macro
color13:
scanloop4\@
move.w (a4)+,d0 ; get minx
move.w (a5)+,d1 ; get maxx
cmp.w d0,d1 ; error check
bmi.b finished4\@
move.w d0,d4 ; copy minx
lsr.w #5,d4 ; get first long word
lsl.w #2,d4 ; *4 = number of bytes
adda.w d4,a0 ; add x offset to scanline
lea PLANESIZE(a0),a1
lea PLANESIZE(a1),a2
lea PLANESIZE(a2),a3
move.w d0,d4 ; copy minx
moveq.l #-1,d2 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
lsr.l d4,d2 ; shift mask by d4 pixels
move.w d1,d4 ; copy maxx
moveq.l #-1,d3 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
neg.w d4 ; - d4
add.w #31,d4 ; d4 = 31 - d4
lsl.l d4,d3 ; shift mask by d4 pixels
lsr.w #5,d0 ; get start long word
lsr.w #5,d1 ; get end long word
sub.w d0,d1 ; get width in long words
bne.b doublewrite4\@ ; check for single write
; single write
and.l d2,d3 ; combine left and right masks
or.l d3,(a0) ; set
or.l d3,(a2) ; set
or.l d3,(a3) ; set
not.l d3 ; invert
and.l d3,(a1) ; clear
bra.b finished4\@
doublewrite4\@
or.l d2,(a0)+ ; set
or.l d2,(a2)+ ; set
or.l d2,(a3)+ ; set
not.l d2
and.l d2,(a1)+ ; clear
subq.w #2,d1 ; subtract left and right writes
bmi.b writeright4\@ ; don't do a multiwrite
; multiwrite\@
moveq.l #-1,d2 ; $ffffffff
moveq.l #0,d4 ; zeroes
multiloop4\@
move.l d2,(a0)+ ; set
move.l d2,(a2)+ ; set
move.l d2,(a3)+ ; set
move.l d4,(a1)+ ; clear
dbra d1,multiloop4\@
writeright4\@
or.l d3,(a0) ; set
or.l d3,(a2) ; set
or.l d3,(a3) ; set
not.l d3 ; invert
and.l d3,(a1) ; clear
finished4\@
add.l d5,d6 ; go to next scanline
movea.l d6,a0 ; copy ptr to modify
dbra d7,scanloop4\@ ; d7 = yheight-1.
movem.l (sp)+,d2-d7/a2-a5
rts
endm
COLOR14 macro
color14:
scanloop4\@
move.w (a4)+,d0 ; get minx
move.w (a5)+,d1 ; get maxx
cmp.w d0,d1 ; error check
bmi.b finished4\@
move.w d0,d4 ; copy minx
lsr.w #5,d4 ; get first long word
lsl.w #2,d4 ; *4 = number of bytes
adda.w d4,a0 ; add x offset to scanline
lea PLANESIZE(a0),a1
lea PLANESIZE(a1),a2
lea PLANESIZE(a2),a3
move.w d0,d4 ; copy minx
moveq.l #-1,d2 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
lsr.l d4,d2 ; shift mask by d4 pixels
move.w d1,d4 ; copy maxx
moveq.l #-1,d3 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
neg.w d4 ; - d4
add.w #31,d4 ; d4 = 31 - d4
lsl.l d4,d3 ; shift mask by d4 pixels
lsr.w #5,d0 ; get start long word
lsr.w #5,d1 ; get end long word
sub.w d0,d1 ; get width in long words
bne.b doublewrite4\@ ; check for single write
; single write
and.l d2,d3 ; combine left and right masks
or.l d3,(a1) ; set
or.l d3,(a2) ; set
or.l d3,(a3) ; set
not.l d3 ; invert
and.l d3,(a0) ; clear
bra.b finished4\@
doublewrite4\@
or.l d2,(a1)+ ; set
or.l d2,(a2)+ ; set
or.l d2,(a3)+ ; set
not.l d2
and.l d2,(a0)+ ; clear
subq.w #2,d1 ; subtract left and right writes
bmi.b writeright4\@ ; don't do a multiwrite
; multiwrite\@
moveq.l #-1,d2 ; $ffffffff
moveq.l #0,d4 ; zeroes
multiloop4\@
move.l d2,(a1)+ ; set
move.l d2,(a2)+ ; set
move.l d2,(a3)+ ; set
move.l d4,(a0)+ ; clear
dbra d1,multiloop4\@
writeright4\@
or.l d3,(a1) ; set
or.l d3,(a2) ; set
or.l d3,(a3) ; set
not.l d3 ; invert
and.l d3,(a0) ; clear
finished4\@
add.l d5,d6 ; go to next scanline
movea.l d6,a0 ; copy ptr to modify
dbra d7,scanloop4\@ ; d7 = yheight-1.
movem.l (sp)+,d2-d7/a2-a5
rts
endm
COLOR15 macro
color15:
scanloop4\@
move.w (a4)+,d0 ; get minx
move.w (a5)+,d1 ; get maxx
cmp.w d0,d1 ; error check
bmi.b finished4\@
move.w d0,d4 ; copy minx
lsr.w #5,d4 ; get first long word
lsl.w #2,d4 ; *4 = number of bytes
adda.w d4,a0 ; add x offset to scanline
lea PLANESIZE(a0),a1
lea PLANESIZE(a1),a2
lea PLANESIZE(a2),a3
move.w d0,d4 ; copy minx
moveq.l #-1,d2 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
lsr.l d4,d2 ; shift mask by d4 pixels
move.w d1,d4 ; copy maxx
moveq.l #-1,d3 ; start mask, $ffffffff
andi.w #$1f,d4 ; minx mod 31 = shift count
neg.w d4 ; - d4
add.w #31,d4 ; d4 = 31 - d4
lsl.l d4,d3 ; shift mask by d4 pixels
lsr.w #5,d0 ; get start long word
lsr.w #5,d1 ; get end long word
sub.w d0,d1 ; get width in long words
bne.b doublewrite4\@ ; check for single write
; single write
and.l d2,d3 ; combine left and right masks
or.l d3,(a0) ; set
or.l d3,(a1) ; set
or.l d3,(a2) ; set
or.l d3,(a3) ; set
bra.b finished4\@
doublewrite4\@
or.l d2,(a0)+ ; set
or.l d2,(a1)+ ; set
or.l d2,(a2)+ ; set
or.l d2,(a3)+ ; set
subq.w #2,d1 ; subtract left and right writes
bmi.b writeright4\@ ; don't do a multiwrite
; multiwrite\@
moveq.l #-1,d2 ; $ffffffff
multiloop4\@
move.l d2,(a0)+ ; set
move.l d2,(a1)+ ; set
move.l d2,(a2)+ ; set
move.l d2,(a3)+ ; set
dbra d1,multiloop4\@
writeright4\@
or.l d3,(a0) ; set
or.l d3,(a1) ; set
or.l d3,(a2) ; set
or.l d3,(a3) ; set
finished4\@
add.l d5,d6 ; go to next scanline
movea.l d6,a0 ; copy ptr to modify
dbra d7,scanloop4\@ ; d7 = yheight-1.
movem.l (sp)+,d2-d7/a2-a5
rts
endm
; Expand the macros...
COLOR0
COLOR1
COLOR2
COLOR3
COLOR4
COLOR5
COLOR6
COLOR7
COLOR8
COLOR9
COLOR10
COLOR11
COLOR12
COLOR13
COLOR14
COLOR15
CNOP 0,4 ; longword align for 020/030 speed
colorplanes:
dc.l color0
dc.l color1
dc.l color2
dc.l color3
dc.l color4
dc.l color5
dc.l color6
dc.l color7
dc.l color8
dc.l color9
dc.l color10
dc.l color11
dc.l color12
dc.l color13
dc.l color14
dc.l color15
; A 68000 line drawer, originally from 68000 Assembly Language, by
; Krantz and Stanley. Modified for the Amiga and the 320x200,
; four bitplane case.
;extern void __asm drawline68k(register __a1 PLANEPTR p,
; register __d0 short x,
; register __d1 short y,
; register __d2 short x2,
; register __d3 short y2,
; register __d4 short color);
_drawline68k
movem.l d2-d7/a2-a6,-(sp)
movea.l a1,a2
lea PLANESIZE(a2),a3
lea PLANESIZE(a3),a4
lea PLANESIZE(a4),a5
andi.w #15,d4 ; 0..15 color
add.w d4,d4 ;
add.w d4,d4 ; (4 byte entries) get table index
lea linejmptable(pc),a6 ; table base
movea.l 0(a6,d4.w),a6 ; get jmp address
move.w d0,d4
swap d4
clr.w d4
move.w d1,d5
swap d5
clr.w d5
sub.w d0,d2
move.w d2,d0
bpl.b sk1_vecd
neg.w d0
sk1_vecd
sub.w d1,d3
move.w d3,d1
bpl.b sk2_vecd
neg.w d1
sk2_vecd
cmp.w d0,d1
bgt.b y_biggerd
tst.w d2
bmi.b sk3_vecd
move.l #$10000,d6
bra.b sk4_vecd
sk3_vecd
move.l #$ffff0000,d6
sk4_vecd
swap d3
clr.w d3
asr.l #2,d3
tst.w d0
beq divtrapd
divs d0,d3
ext.l d3
asl.l #2,d3
move.l d3,d7
move.w d0,d2
bra.b sk7_vecd
y_biggerd
tst.w d3
bmi.b sk5_vecd
move.l #$10000,d7
bra.b sk6_vecd
sk5_vecd
move.l #$ffff0000,d7
sk6_vecd
swap d2
clr.w d2
asr.l #2,d2
tst.w d1
beq divtrapd
divs d1,d2
ext.l d2
asl.l #2,d2
move.l d2,d6
move.w d1,d2
sk7_vecd
sk8_vecd
subq.w #1,d2 ; setup dbra
move.l #$8000,a0 ; .5 to add to round up
move.l #$8000,a1 ; " "
jsr (a6) ; draw line
divtrapd
movem.l (sp)+,d2-d7/a2-a6
rts
LINEPLOT macro
lp0_vecd\@
move.l d4,d0 ; fixed point arithmetic
move.l d5,d1
add.l a0,d0
add.l a1,d1
swap d0
swap d1
move.w d1,d3 ; save y
add.w d1,d1 ; *2
add.w d1,d1 ; *4
add.w d1,d3 ; *5
lsl.w #3,d3 ; *40
move.w d0,d1 ; save x
lsr.w #3,d0 ; get x byte offset
add.w d0,d3 ; x offset + y offset
andi.w #7,d1 ; get x bit set
not.b d1 ; invert bits (left to right)
\1.b d1,0(a2,d3.w)
\2.b d1,0(a3,d3.w)
\3.b d1,0(a4,d3.w)
\4.b d1,0(a5,d3.w)
add.l d6,d4
add.l d7,d5
dbra d2,lp0_vecd\@
rts
endm
linecolor0:
LINEPLOT bclr,bclr,bclr,bclr
linecolor1:
LINEPLOT bset,bclr,bclr,bclr
linecolor2:
LINEPLOT bclr,bset,bclr,bclr
linecolor3:
LINEPLOT bset,bset,bclr,bclr
linecolor4:
LINEPLOT bclr,bclr,bset,bclr
linecolor5:
LINEPLOT bset,bclr,bset,bclr
linecolor6:
LINEPLOT bclr,bset,bset,bclr
linecolor7:
LINEPLOT bset,bset,bset,bclr
linecolor8:
LINEPLOT bclr,bclr,bclr,bset
linecolor9:
LINEPLOT bset,bclr,bclr,bset
linecolor10:
LINEPLOT bclr,bset,bclr,bset
linecolor11:
LINEPLOT bset,bset,bclr,bset
linecolor12:
LINEPLOT bclr,bclr,bset,bset
linecolor13:
LINEPLOT bset,bclr,bset,bset
linecolor14:
LINEPLOT bclr,bset,bset,bset
linecolor15:
LINEPLOT bset,bset,bset,bset
linejmptable:
dc.l linecolor0
dc.l linecolor1
dc.l linecolor2
dc.l linecolor3
dc.l linecolor4
dc.l linecolor5
dc.l linecolor6
dc.l linecolor7
dc.l linecolor8
dc.l linecolor9
dc.l linecolor10
dc.l linecolor11
dc.l linecolor12
dc.l linecolor13
dc.l linecolor14
dc.l linecolor15
;extern void __asm fillline68k(register __d0 short x,
; register __d1 short y,
; register __d2 short x2,
; register __d3 short y2,
; register __a0 short * table);
; The line drawer modified...
_fillline68k:
movem.l d2-d7,-(sp)
cmp.w d1,d3 ; always draw top->bottom
bgt.b oky
exg d1,d3 ; swap y's
exg d0,d2 ; sway x's
oky
move.w d3,d6
add.w d6,d6 ; 2 byte entries
move.w d2,0(a0,d6.w) ; save x in scan table
move.w d1,d6
add.w d6,d6 ; 2 byte entries
move.w d0,0(a0,d6.w) ; save x in scan table
adda.w d6,a0 ; set up address to start of table
move.w d0,d4
swap d4
clr.w d4
move.w d1,d5
swap d5
clr.w d5
sub.w d0,d2
move.w d2,d0
bpl.b sk1_vec
neg.w d0
sk1_vec
sub.w d1,d3
move.w d3,d1
bpl.b sk2_vec
neg.w d1
sk2_vec
cmp.w d0,d1
bgt.b y_bigger
tst.w d2
bmi.b sk3_vec
move.l #$10000,d6
bra.b sk4_vec
sk3_vec
move.l #$ffff0000,d6
sk4_vec
swap d3
clr.w d3
asr.l #2,d3
tst.w d0
beq divtrap
divs d0,d3
ext.l d3
asl.l #2,d3
move.l d3,d7
move.w d0,d2
bra.b sk7_vec
y_bigger
tst.w d3
bmi.b sk5_vec
move.l #$10000,d7
bra.b sk6_vec
sk5_vec
move.l #$ffff0000,d7
sk6_vec
swap d2
clr.w d2
asr.l #2,d2
tst.w d1
beq divtrap
divs d1,d2
ext.l d2
asl.l #2,d2
move.l d2,d6
move.w d1,d2
sk7_vec
; subq.w #1,d2 ; set up dbra
move.l #$8000,d3 ; .5 to add to round up
move.w d1,a1 ; old y = current y
move.l d4,d0 ; compute 2nd x point
add.l d3,d0
swap d0
move.l d5,d1 ; compute 2nd y point
add.l d3,d1
swap d1
lp0_vec
cmp.w a1,d1 ; newy # oldy?
beq.b ynochange ; no
move.w d0,(a0)+ ; fastest possible write to memory.
ynochange
move.w d1,a1
add.l d6,d4
add.l d7,d5
move.l d4,d0 ; fixed point arithmetic
add.l d3,d0
swap d0
move.l d5,d1
add.l d3,d1
swap d1
sk8_vec
dbra d2,lp0_vec
divtrap
movem.l (sp)+,d2-d7
rts
END
SHAR_EOF
fi # end of overwriting check
# End of shell archive
exit 0jcs@crash.cts.com (John Schultz) (06/10/90)
Here are a few subtle changes to improve performance of the processor polygon fill code I posted earlier. Both changes are for the file scanconvert.a. Also, my polygon fill code only works on convex polygons. If the screen width is changed from 320 pixels, the line drawer's pixel offset calculations will have to be rewritten to handle a non-40 bytes per row case (The 80 bytes per row (640 pixels) case is trivial, just change the lsl.w #3,d3 to lsl.w #4,d3). The polygon routines simply require a changed define, and could be generalized so it could handle screen width changes dynamically. In _drawline68k, change the code between sk8_vecd and the second add.l to the below: ; start _drawline changes sk8_vecd subq.w #1,d2 ; setup dbra move.l #$8000,a0 ; .5 to add to round up move.w #7,a1 jsr (a6) ; draw line divtrapd movem.l (sp)+,d2-d7/a2-a6 rts LINEPLOT macro lp0_vecd\@ move.l d4,d0 ; fixed point arithmetic move.l d5,d1 add.l a0,d0 add.l a0,d1 ; end of _drawline68k changes In _fillline68k, change everything from sk7_vec to sk8_vec to: ; start _fillline68k changes sk7_vec move.l #$8000,d3 ; .5 to add to round up move.w d1,a1 ; old y = current y lp0_vec move.l d4,d0 ; fixed point arithmetic add.l d3,d0 swap d0 move.l d5,d1 add.l d3,d1 swap d1 cmp.w a1,d1 ; newy # oldy? beq.b ynochange ; no move.w d0,(a0)+ ; fastest possible write to memory. ynochange move.w d1,a1 add.l d6,d4 add.l d7,d5 sk8_vec ; end of _filline68k changes