* Right-rotate 32-bit value in &loc (DP or 16-bit address) by &n positions
	macro
	ROTR4	&loc,&n
	aif	&n>16,.dorotl
	lda	&loc+2
	lcla	&i
&i	seta	&n
.rotrloop
	lsr	a		;to set carry
	ror     &loc
	ror     &loc+2
&i	seta	&i-1
	aif	&i>0,.rotrloop
	ago	.end
.dorotl
	ROTL4	&loc,32-&n
.end
	mend

* Left-rotate 32-bit value in &loc (DP or 16-bit address) by &n positions
	macro
	ROTL4	&loc,&n
	aif	&n>16,.dorotr
        lda     &loc
	lcla	&i
&i	seta	&n
.rotlloop
        asl     a		;to set carry
        rol     &loc+2
        rol     &loc
&i	seta	&i-1
	aif	&i>0,.rotlloop
	ago	.end
.dorotr
	ROTR4	&loc,32-&n
.end
	mend

* &to := &from ROTR4 &n
	macro
	ROTR4MOVE &to,&from,&n
	aif	&n>16,.dorotl
        lda     &from
        sta     &to
        lda     &from+2
        sta     &to+2
	lcla	&i
&i	seta	&n
.rotrloop
	lsr	a		;to set carry
	ror     &to
	ror     &to+2
&i	seta	&i-1
	aif	&i>0,.rotrloop
	ago	.end
dorotl
	ROTL4MOVE &to,&from,32-&n
.end
	mend

* &to := &from ROTL4 &n
	macro
	ROTL4MOVE &to,&from,&n
	aif	&n>16,.dorotr
        lda     &from+2
        sta     &to+2
        lda     &from
        sta     &to
	lcla	&i
&i	seta	&n
.rotlloop
        asl     a		;to set carry
        rol     &to+2
        rol     &to
&i	seta	&i-1
	aif	&i>0,.rotlloop
	ago	.end
.dorotr
	ROTR4MOVE &to,&from,32-&n
.end
	mend


* This makes a function wrapper that is callable from C,
* taking a pointer to the context structure as its argument.
	macro
	CFunction &fn
	phb
	plx
	ply
	tdc
	pld
	plb
	plb
	phy
	phx
	plb
	pha
	jsl	&fn
	pld
	rtl
	mend


* Macros to operate on elements of the message schedule (W)
	macro
&lab	lda_w	&i,&inc
	lcla	&j
&j	seta	&i
.modloop1
	aif	&j<20,.goodidx1
&j	seta	&j-20
	ago	.modloop1
.goodidx1
	aif	C:&inc<>0,.haveinc
	lcla	&inc
.haveinc
&lab	lda	w+(&j)*4+&inc
	mend

	macro
&lab	eor_w	&i,&inc
	lcla	&j
&j	seta	&i
.modloop2
	aif	&j<20,.goodidx2
&j	seta	&j-20
	ago	.modloop2
.goodidx2
	aif	C:&inc<>0,.haveinc
	lcla	&inc
.haveinc
&lab	eor	w+(&j)*4+&inc
	mend

	macro
&lab	sta_w	&i,&inc
	lcla	&j
&j	seta	&i
.modloop3
	aif	&j<20,.goodidx3
&j	seta	&j-20
	ago	.modloop3
.goodidx3
	aif	C:&inc<>0,.haveinc
	lcla	&inc
.haveinc
&lab	sta	w+(&j)*4+&inc
	mend

	macro
&lab	rol_w	&i,&inc
	lcla	&j
&j	seta	&i
.modloop4
	aif	&j<20,.goodidx4
&j	seta	&j-20
	ago	.modloop4
.goodidx4
	aif	C:&inc<>0,.haveinc
	lcla	&inc
.haveinc
&lab	rol	w+(&j)*4+&inc
	mend


* Compute one part of the message schedule (20 elements)
	macro
	ComputeSchedule &part
	lcla	&i

; Flip the endianness of W_0 to W_15 (the current chunk of the message)
	aif	&part<>1,.skippart1
.loop1
	lda	w+&i*4
	xba
	ldx	w+&i*4+2
	sta	w+&i*4+2
	txa
	xba
	sta	w+&i*4
&i	seta	&i+1
	aif	&i<16,.loop1
.skippart1

; compute the rest of the message schedule (W_16 to W_79)
	aif	&part=1,.loop2
&i	seta	(&part-1)*20
.loop2
	lda_w	&i-3
	eor_w	&i-8
	eor_w	&i-14
	eor_w	&i-16
	sta_w	&i
	asl	a		; to set carry

	lda_w	&i-3,2
	eor_w	&i-8,2
	eor_w	&i-14,2
	eor_w	&i-16,2
	rol	a
	sta_w	&i,2

	rol_w	&i
	
&i	seta	&i+1
	aif	&i<&part*20,.loop2
	mend


* One part of the loop for processing blocks (&part is 1, 2, 3, or 4)
	macro
	BlockLoopPart &part
	
loop&part anop
	stx	idx
	ROTL4MOVE temp,a_,5

* f_0 to f_19
	aif	&part<>1,.skip1
	lda	c
	eor	d
	and	b
	eor	d
	clc
	adc	#$7999
	sta	f_plus_k
	
	lda	c+2
	eor	d+2
	and	b+2
	eor	d+2
	adc	#$5A82
	sta	f_plus_k+2
.skip1

* f_20 to f_39
	aif	&part<>2,.skip2
	lda	b
	eor	c
	eor	d
	clc
	adc	#$EBA1
	sta	f_plus_k
	
	lda	b+2
	eor	c+2
	eor	d+2
	adc	#$6ED9
	sta	f_plus_k+2
.skip2

* f_40 to f_59
	aif	&part<>3,.skip3
	lda	c
	ora	d
	and	b
	sta	f40temp
	lda	c
	and	d
	ora	f40temp
	clc
	adc	#$BCDC
	sta	f_plus_k
	
	lda	c+2
	ora	d+2
	and	b+2
	sta	f40temp
	lda	c+2
	and	d+2
	ora	f40temp
	adc	#$8F1B
	sta	f_plus_k+2
.skip3

* f_60 to f_79
	aif	&part<>4,.skip4
	lda	b
	eor	c
	eor	d
	clc
	adc	#$C1D6
	sta	f_plus_k
	
	lda	b+2
	eor	c+2
	eor	d+2
	adc	#$CA62
	sta	f_plus_k+2
.skip4

	ldx	idx
	clc
	lda	w,x
	adc	temp
	tay
	lda	w+2,x
	adc	temp+2
	tax
	clc
	tya
	adc	e
	tay
	txa
	adc	e+2
	tax
	clc
	tya
	adc	f_plus_k
	tay
	txa
	adc	f_plus_k+2
	tax

	lda	d
	sta	e
	lda	d+2
	sta	e+2

	lda	c
	sta	d
	lda	c+2
	sta	d+2

	ROTL4MOVE c,b,30
	
	lda	a_
	sta	b
	lda	a_+2
	sta	b+2
	
	sty	a_
	stx	a_+2

	ldx	idx
	inx
	inx
	inx
	inx
	cpx	#20*4
	bge	endloop&part
	jmp	loop&part
endloop&part anop
	mend