#define SHUFFLE(Re) \
	MOVW	(-16*4)(Rw), Rt0 ; \
	MOVW	(-14*4)(Rw), Rt1 ; \
	MOVW	(-8*4)(Rw), Rt2  ; \
	EOR	Rt0, Rt1, Rt0  ; \
	MOVW	(-3*4)(Rw), Rt1  ; \
	EOR	Rt2, Rt0, Rt0  ; \
	EOR	Rt0, Rt1, Rt0  ; \
	MOVW	Rt0@>(32-1), Rt0  ; \
	MOVW.P	Rt0, 4(Rw)	  ; \
	ADD	Rt0, Re, Re

	// t1 = (b & c) | ((~b) & d)
#define FUNC1(Ra, Rb, Rc, Rd, Re) \
	MVN	Rb, Rt1	   ; \
	AND	Rb, Rc, Rt0  ; \
	AND	Rd, Rt1, Rt1 ; \
	ORR	Rt0, Rt1, Rt1

// a += (((c^d)&b)^d) + X[index] + const
// a = a<<shift | a>>(32-shift) + b
#define ROUND1(Ra, Rb, Rc, Rd, index, shift, Rconst) \
	EOR	Rc, Rd, Rt0		; \
	AND	Rb, Rt0			; \
	EOR	Rd, Rt0			; \
	MOVW	(index<<2)(Rdata), Rt1	; \
	ADD	Rt1, Rt0			; \
	ADD	Rconst, Rt0			; \
	ADD	Rt0, Ra			; \
	ADD	Ra@>(32-shift), Rb, Ra	;

	MOVM.IA.W (Rtable), [Rc0,Rc1,Rc2,Rc3]
	ROUND1(Ra, Rb, Rc, Rd,  0,	7, Rc0)