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")

	MSR	R6, APDBKeyHi_EL1                  // 662218d5
	MRS	APDBKeyLo_EL1, R5                  // 452238d5
	MSR	R22, APDBKeyLo_EL1                 // 562218d5
	MRS	APGAKeyHi_EL1, R22                 // 362338d5
	MSR	R5, APGAKeyHi_EL1                  // 252318d5
	MRS	APGAKeyLo_EL1, R16                 // 102338d5
	MSR	R22, APGAKeyLo_EL1                 // 162318d5
	MRS	APIAKeyHi_EL1, R23                 // 372138d5

	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	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)

	MOVW	R5, (4*2)(R29)	// a unsafe.Pointer
	MOVW	R7, (4*3)(R29)	// ctxt uintptr
	MOVW	R16, (4*4)(R29)
	MOVW	R17, (4*5)(R29)
	MOVW	R18, (4*6)(R29)
	MOVW	R19, (4*7)(R29)
	MOVW	R20, (4*8)(R29)
	MOVW	R21, (4*9)(R29)
	MOVW	R22, (4*10)(R29)
	MOVW	R23, (4*11)(R29)
	MOVW	g, (4*12)(R29)
	MOVW	R31, (4*13)(R29)
#ifndef GOMIPS_softfloat
	MOVD	F20, (4*14)(R29)
	MOVD	F22, (4*14+8*1)(R29)
	MOVD	F24, (4*14+8*2)(R29)
	MOVD	F26, (4*14+8*3)(R29)

(6) CCMN, CCMNW, CCMP, CCMPW <cond>, <Rn>, $<imm>, $<nzcv>

Examples:

	CCMP MI, R22, $12, $13     <=>    ccmp x22, #0xc, #0xd, mi
	CCMNW AL, R1, $11, $8      <=>    ccmn w1, #0xb, #0x8, al

(7) CCMN, CCMNW, CCMP, CCMPW <cond>, <Rn>, <Rm>, $<nzcv>

Examples:

	CCMN VS, R13, R22, $10     <=>    ccmn x13, x22, #0xa, vs
	CCMPW HS, R19, R14, $11    <=>    ccmp w19, w14, #0xb, cs

	// Preserve callee-save registers.
	MOVD	R14, 48(R1)
	MOVD	R15, 56(R1)
	MOVD	R16, 64(R1)
	MOVD	R17, 72(R1)
	MOVD	R18, 80(R1)
	MOVD	R19, 88(R1)
	MOVD	R20, 96(R1)
	MOVD	R21,104(R1)
	MOVD	R22, 112(R1)
	MOVD	R23, 120(R1)
	MOVD	R24, 128(R1)
	MOVD	R25, 136(R1)
	MOVD	R26, 144(R1)
	MOVD	R27, 152(R1)
	MOVD	R28, 160(R1)
	MOVD	R29, 168(R1)
	MOVD	g, 176(R1) // R30
	MOVD	R31, 184(R1)
	FMOVD	F14, 192(R1)

	*R17
	*R18
	*R19
	*R20
}

type R14 R13
type R15 R13
type R16 R13

type R17 struct {
	*R21
	*R22
	*R23
	*R24
}

type R18 R17
type R19 R17
type R20 R17

type R21 struct {
	X int
}

type R22 R21
type R23 R21
type R24 R21

	LSR	R4, R13, R23
	ORR	R8, R23		// z[i] = (x[i] << s) | (x[i-1] >> (64 - s))
	LSL	R3, R13
	LSR	R4, R12, R22
	ORR	R13, R22
	LSL	R3, R12
	LSR	R4, R11, R21
	ORR	R12, R21
	LSL	R3, R11
	LSR	R4, R10, R20
	ORR	R11, R20
	LSL	R3, R10, R8
	STP.W	(R20, R21), -32(R0)
	STP	(R22, R23), 16(R0)
	SUB	$4, R1
	B	loop
done:
	MOVD.W	R8, -8(R0)	// the first element x[0]

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