ROUND2(R22,R3,R4,R5,M01,0xf61e2562, 5);
	ROUND2(R5,R22,R3,R4,M06,0xc040b340, 9);
	ROUND2(R4,R5,R22,R3,M11,0x265e5a51,14);
	ROUND2(R3,R4,R5,R22,M00,0xe9b6c7aa,20);
	ROUND2(R22,R3,R4,R5,M05,0xd62f105d, 5);
	ROUND2(R5,R22,R3,R4,M10, 0x2441453, 9);
	ROUND2(R4,R5,R22,R3,M15,0xd8a1e681,14);
	ROUND2(R3,R4,R5,R22,M04,0xe7d3fbc8,20);
	ROUND2(R22,R3,R4,R5,M09,0x21e1cde6, 5);
	ROUND2(R5,R22,R3,R4,M14,0xc33707d6, 9);

	SUB  R21, R5, R21

	// Greater than 8 -- load the rightmost remaining bytes in msg
	// and put into R17 (h1)
	MOVD (R4)(R21), R17
	MOVD $16, R22

	// Find the offset to those bytes
	SUB R5, R22, R22
	SLD $3, R22

	// Shift to get only the bytes in msg
	SRD R22, R17, R17

	// Put 1 at high end
	MOVD $1, R23
	SLD  $3, R21
	SLD  R21, R23, R23
	OR   R23, R17, R17

	// Remainder is 8

	AND $0x7ffffffffffff, R4, R14

	ADD R0>>51, R11, R11
	ADD R1>>51, R12, R12
	ADD R2>>51, R13, R13
	ADD R3>>51, R14, R14
	// R4>>51 * 19 + R10 -> R10
	LSR $51, R4, R21
	MOVD $19, R22
	MADD R22, R10, R21, R10

	STP (R10, R11), 0(R20)
	STP (R12, R13), 16(R20)
	MOVD R14, 32(R20)

	STP (R4, R5), 40(RSP)
	STP (R6, R7), 56(RSP)
	STP (R8, R9), 72(RSP)
	STP (R10, R11), 88(RSP)
	STP (R12, R13), 104(RSP)
	STP (R14, R15), 120(RSP)
	STP (R16, R17), 136(RSP)
	STP (R19, R20), 152(RSP)
	STP (R21, R22), 168(RSP)
	STP (R23, R24), 184(RSP)
	STP (R25, R26), 200(RSP)
	MOVD NZCV, R0
	MOVD R0, 216(RSP)
	MOVD FPSR, R0
	MOVD R0, 224(RSP)
	FSTPD (F0, F1), 232(RSP)
	FSTPD (F2, F3), 248(RSP)
	FSTPD (F4, F5), 264(RSP)

#define SAVE_R19_TO_R28(offset) \
	STP	(R19, R20), ((offset)+0*8)(RSP) \
	STP	(R21, R22), ((offset)+2*8)(RSP) \
	STP	(R23, R24), ((offset)+4*8)(RSP) \
	STP	(R25, R26), ((offset)+6*8)(RSP) \
	STP	(R27, g), ((offset)+8*8)(RSP)

#define RESTORE_R19_TO_R28(offset) \
	LDP	((offset)+0*8)(RSP), (R19, R20) \
	LDP	((offset)+2*8)(RSP), (R21, R22) \
	LDP	((offset)+4*8)(RSP), (R23, R24) \
	LDP	((offset)+6*8)(RSP), (R25, R26) \

// the user should prepare stack space in advance.
// SAVE_R22_TO_R31(offset) saves R22 ~ R31 to the stack space
// of ((offset)+0*8)(R3) ~ ((offset)+9*8)(R3).
//
// SAVE_F24_TO_F31(offset) saves F24 ~ F31 to the stack space
// of ((offset)+0*8)(R3) ~ ((offset)+7*8)(R3).
//
// Note: g is R22

#define SAVE_R22_TO_R31(offset)	\
	MOVV	g,   ((offset)+(0*8))(R3)	\
	MOVV	R23, ((offset)+(1*8))(R3)	\

	print("r17  ", hex(c.r17()), "\n")
	print("r18  ", hex(c.r18()), "\t")
	print("r19  ", hex(c.r19()), "\n")
	print("r20  ", hex(c.r20()), "\t")
	print("r21  ", hex(c.r21()), "\n")
	print("r22  ", hex(c.r22()), "\t")
	print("r23  ", hex(c.r23()), "\n")
	print("r24  ", hex(c.r24()), "\t")
	print("r25  ", hex(c.r25()), "\n")
	print("r26  ", hex(c.r26()), "\t")
	print("r27  ", hex(c.r27()), "\n")

	st.d	$r1, $r3, 0
	st.d	$r23, $r3, 8
	st.d	$r24, $r3, 16
	st.d	$r25, $r3, 24
	st.d	$r26, $r3, 32
	st.d	$r27, $r3, 40
	st.d	$r28, $r3, 48
	st.d	$r29, $r3, 56
	st.d	$r30, $r3, 64
	st.d	$r2, $r3, 72
	st.d	$r22, $r3, 80
	fst.d	$f24, $r3, 88
	fst.d	$f25, $r3, 96
	fst.d	$f26, $r3, 104
	fst.d	$f27, $r3, 112
	fst.d	$f28, $r3, 120
	fst.d	$f29, $r3, 128
	fst.d	$f30, $r3, 136
	fst.d	$f31, $r3, 144

	MOVV R12, 96(R29)
	MOVV R13, 104(R29)
	MOVV R14, 112(R29)
	MOVV R15, 120(R29)
	MOVV R16, 128(R29)
	MOVV R17, 136(R29)
	MOVV R18, 144(R29)
	MOVV R19, 152(R29)
	MOVV R20, 160(R29)
	MOVV R21, 168(R29)
	MOVV R22, 176(R29)
	MOVV R24, 184(R29)
	MOVV R25, 192(R29)
	MOVV RSB, 200(R29)
	MOVV HI, R1
	MOVV R1, 208(R29)
	MOVV LO, R1
	MOVV R1, 216(R29)
	#ifndef GOMIPS64_softfloat
	MOVV FCR31, R1
	MOVV R1, 224(R29)

	MOVV	R5, (8*2)(R29) // a unsafe.Pointer
	MOVV	R7, (8*3)(R29) // ctxt uintptr
	MOVV	R16, (8*4)(R29)
	MOVV	R17, (8*5)(R29)
	MOVV	R18, (8*6)(R29)
	MOVV	R19, (8*7)(R29)
	MOVV	R20, (8*8)(R29)
	MOVV	R21, (8*9)(R29)
	MOVV	R22, (8*10)(R29)
	MOVV	R23, (8*11)(R29)
	MOVV	RSB, (8*12)(R29)
	MOVV	g, (8*13)(R29)
	MOVV	R31, (8*14)(R29)
#ifndef GOMIPS64_softfloat
	MOVD	F24, (8*15)(R29)
	MOVD	F25, (8*16)(R29)
	MOVD	F26, (8*17)(R29)