[StingRay]

*******************************************
*** Chunky 2 Planar	       174 Bytes***
*******************************************

; Tiny 8bpl converter. 4k intros, anyone?
;
; c2p1x1_8_c5_gen_mini

; a0	chunkybuffer
; a1	bitplanes

; 22-Aug-2oo4:	2o bytes killed! :) -> size: 216 bytes
;		several minutes and 1 crash :) later:
;		34 bytes killed! -> 182 bytes
;		size optimizing rulez! :)
;		and the next 8 bytes killed! -> 174 bytes

c2p_merge
	movem.l	(a0)+,d0-d3
	lsr.l	d4,d0
	lsr.l	d4,d1
	lsr.l	d4,d2
	lsr.l	d4,d3
	and.l	d5,d0
	and.l	d5,d1
	and.l	d5,d2
	and.l	d5,d3
	lsl.l	#4,d0
	lsl.l	#4,d2
	or.l	d1,d0
	or.l	d3,d2
	rts
	
c2p	moveq	#0,d4

	add.w	#PLsize*2+(256-CHUNKYY)/2*40,a1	; auto centering
	bsr.b	.conv
	sub.l	#CHUNKYX*CHUNKYY+32,a0
	add.l	#PLsize*3+(256-CHUNKYY)*40,a1	; auto centering
	moveq	#4,d4

.conv	lea	32(a0),a6
	bsr.s	.pix32
	subq.l	#4,a1
	move.l	a0,a6
	add.l	#CHUNKYX*CHUNKYY,a6

.pix32	move.l	#$0f0f0f0f,d5
	bsr.b	c2p_merge		; d0,d2
	move.l	d0,d6
	move.l	d2,d7
	
	move.l	a5,-PLsize*2(a1)
	bsr.b	c2p_merge		; d1,d6
	move.l	d0,d1
	move.l	d6,d0
	
	move.l	d2,d6
	move.l	d7,d2





	swap	d1
	swap	d6
	eor.w	d0,d1
	eor.w	d2,d6
	eor.w	d1,d0
	eor.w	d6,d2
	eor.w	d0,d1
	eor.w	d2,d6
	swap	d1
	swap	d6

	move.l	a4,-PLsize(a1)

	move.l	#$33333333,d5
	move.l	d4,-(a7)
	moveq	#2,d4
	exg.l	d1,d2
	bsr.b	.swap
	exg.l	d1,d2
	

	move.l	a3,(a1)+

	move.l	#$00ff00ff,d5
	moveq	#8,d4
	bsr.b	.swap
	move.l	a2,PLsize-4(a1)

	move.l	#$55555555,d5
	moveq	#1,d4
	bsr.b	.swap
	move.l	(a7)+,d4
	
	move.l	d0,a2
	move.l	d2,a3
	move.l	d1,a4
	move.l	d6,a5
	cmp.l	a0,a6
	bne.b	.pix32

.swap	move.l	d2,d3
	move.l	d6,d7
	lsr.l	d4,d3
	lsr.l	d4,d7
	eor.l	d0,d3
	eor.l	d1,d7
	and.l	d5,d3
	and.l	d5,d7
	eor.l	d3,d0
	eor.l	d7,d1
	lsl.l	d4,d3
	lsl.l	d4,d7
	eor.l	d3,d2
	eor.l	d7,d6
	rts

That's the c2p routine I made for our 4k intros, base code by Kalms which I then optimized. It's short but the speed is still OK. MUCH shorter c2p is possible (addx) of course.