; Version: @(#)fir2d2.asm	1.2	07/06/99
; 
; 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
fir2d2	SUB  .D2  B8,B7,B9	; byte offset between rows
||	ZERO .L1  A4		; initialize accumulator
||	SUB  .L2  B7,1,B7	; B7 = numFilCols - 1
||	ZERO .S2  B2		; offset into image data

fir2	LDBU .D1 *A5++,A6	; load a(m1,m2), zero fill
||	LDBU .D2 *B6[B2],B6	; load x(n1-m1,n2-m2)
||	MPYU .M1X A6,B6,A3	; A3=a(m1,m2) x(n1-m1,n2-m2)
||	ADD  .L1  A3,A4,A4	; y(n1,n2) += A3
||	CMPLT.L2  B2,B7,B1	; need to go to next row?
||	ADD  .S2  B2,1,B2	; incr offset into image

[!B1]	ADD  .L2  B2,B9,B2	; move offset to next row
|| [A2]	SUB  .S1  A2,1,A2	; decrement loop counter
|| [A2]	B    .S2  fir2		; if A2 != 0, then branch
; return y(n1,n2)