; TMS320C6x assembly language code to perform ordered dithering
; We assume that the thresholds are periodic, and hence, will be
; circularly addressed.  The two instructions that set the AMR 
; register set up the modulo addressing.  Remove them if the
; thresholds are in a linear array.
	MVK    .S1 0x00ff,A8		; white pixel #1
||	MVK    .S2 0x0001,AMR	; modulo block size 2^2
	SHL    .S1 A8,8,A9		; white pixel #2
||	MVKH   .S2 0x4000,AMR	; modulo addr reg. B6
	SHL    .S1 A8,16,A10		; white pixel #3
||	SHL    .S2 A8,24,B9		; white pixel #4

; initialize
;   A2 number of pixels divided by 4
;   A6 pointer to pixels (will be overwritten)
;   B6 pointer to thresholds
dith2:	LDW    .D1 *A6,A4		; read 4 pixels (bytes)
	LDW    .D2 *B6++,B4		; read 4 thresholds
	EXTU   .S1 A4,24,24,A12	; extract pixel #2
	EXTU   .S2 B4,24,24,B12	; extract threshold #2
	ZERO   .L1 A5			; store output in A5
	CMPLTU .L2 A12,B12,B0	; B0 = (A12 < B12)
	EXTU   .S1 A4,16,24,A13	; extract pixel #2
	EXTU   .S2 B4,16,24,B13	; extract threshold #2
[!B0]	OR     .L1 A5,A8,A5		; output of pixel 1
	CMPLTU .L2 A13,B13,B1	; B1 = (A13 < B13)

	EXTU   .S1 A4,8,24,A14	; extract pixel #3
	EXTU   .S2 B4,8,24,B14	; extract threshold #3
[!B1]	OR     .L1 A5,A9,A5		; output of pixels 1-2
	CMPLTU .L2 A14,B14,B2	; B2 = (A14 < B14)

	EXTU   .S1 A4,0,24,A15	; extract pixel #4
	EXTU   .S2 B4,0,24,B15	; extract threshold #4
[!B2]	OR     .L2 A5,B9,B5		; output of pixels 1-3
	CMPLTU .L1 A15,B15,A1	; B2 = (A15 < B15)

[!A1]	OR     .S1 B5,A11,A5		; output of pixels 1-4
	STW    .D1 A5,*A6++	  	; store results
[A2]	SUB    .L1 A2,1,A2		; decrement loop count
[A2]	B      .L2 dith2		; if A2 != 0, branch