; Version: @(#)fir2d3.asm	1.4	07/07/99
; 
; Compute y(n1,n2) = h(n1,n2) ** x(n1,n2) at one index n1, n2.
; The filter h(n1,n2) is an M1 x M2 filter having M = M1 M2
; coefficients.  The image x(n1,n2) is N1 x N2.
;
; Registers: A5=&a(0,0) B5=&x(n1,n2) A2=M B7=M2 B8=N2
fir2d3	ZERO .D1  A4		; initialize accumulator #1
||	SUB  .D2  B8,B7,B9	; index offset between rows
||	ZERO .L2  B2		; offset into image data
||	MVKH .S1  0xFF,A8	; mask to get lowest 8 bits
||	SHR  .S2  B7,1,B7	; divide by 2 (indexed 16-bit address)

	ZERO .D2  B4		; initialize accumulator #2
||	ZERO .L1  A6		; current coefficient value
||	ZERO .L2  B6		; current image value
||	SHR  .S1  A2,1,A2	; divide by 2 (indexed 16-bit address)
||	SHR  .S2  B9,1,B9	; divide by 2 (indexed 16-bit address) 

fir3	LDHU .D1 *A5++,A6	; load a(m1,m2) a(m1+1,m2+1)
||	LDHU .D2 *B6[B2],B6	; load two pixels of image x
||	CMPLT.L2  B2,B7,B1	; need to go to next row?
||	ADD  .S2  B2,1,B2	; incr offset into image

	AND  .L1 A6,A8,A6	; extract a(m1,m2)
||	AND  .L2 B6,A8,B6	; extract x(n1-m1,n2-m2)
||	EXTU .S1 A6,0,8,A9	; extract a(m1+1,m2+1)
||	EXTU .S2 B6,0,8,B9	; extract x(n1-m1+1,n2-m2+1)

	MPYHU .M1X A6,B6,A3	; A3=a(m1,m2) x(n1-m1,n2-m2)
||	MPYHU .M2X A9,B9,B3	; B3=a*x offset by 1 index
||	ADD  .L1  A3,A4,A4	; y(n1,n2) += A3
||	ADD  .L2  B3,B4,B4	; y(n1+1,n2+1) += B3
||[!B1]	ADD  .D2  B2,B9,B2	; move offset to next row
||[A2]	SUB  .S1  A2,1,A2	; decrement loop counter
||[A2]	B    .S2  fir3		; if A2 != 0, then branch
; A4=y(n1,n2) and B4=y(n1+1,n2+1)