func copyARM64(w io.Writer) {
	// R20: ptr to source memory
	// R21: ptr to destination memory
	// R26, R27 (aka REGTMP): scratch space
	// R20 and R21 are updated as a side effect
	fmt.Fprintln(w, "TEXT runtime·duffcopy<ABIInternal>(SB), NOSPLIT|NOFRAME, $0-0")

	for i := 0; i < 64; i++ {
		fmt.Fprintln(w, "\tLDP.P\t16(R20), (R26, R27)")
		fmt.Fprintln(w, "\tSTP.P\t(R26, R27), 16(R21)")
		fmt.Fprintln(w)
	}
	fmt.Fprintln(w, "\tRET")

		if h2r0.hi != 0 {
			panic("poly1305: unexpected overflow")
		}
		if h2r1.hi != 0 {
			panic("poly1305: unexpected overflow")
		}

		m0 := h0r0
		m1 := add128(h1r0, h0r1) // These two additions don't overflow thanks again
		m2 := add128(h2r0, h1r1) // to the 4 masked bits at the top of r0 and r1.
		m3 := h2r1

		t0 := m0.lo
		t1, c := bits.Add64(m1.lo, m0.hi, 0)

	print("r16  ", hex(c.r16()), "\t")
	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")

	ADCS	R15, R11
	MUL	R8, R3, R16
	ADCS	R16, R12
	UMULH	R8, R3, R20
	ADC	$0, R20

	MUL	R5, R3, R13
	ADDS	R13, R9
	UMULH	R5, R3, R17
	ADCS	R17, R10
	UMULH	R6, R3, R21
	STP.P	(R9, R10), 16(R1)
	ADCS	R21, R11
	UMULH	R7, R3, R19
	ADCS	R19, R12
	STP.P	(R11, R12), 16(R1)
	ADC	$0, R20, R4

	SUB	$4, R0
	B	loop

done:
	MOVD	R4, c+24(FP)

		// large or unaligned move
		// arg0 = address of dst memory (in R21, changed as side effect)
		// arg1 = address of src memory (in R20, changed as side effect)
		// arg2 = address of the last element of src
		// arg3 = mem
		// auxint = alignment
		// returns mem
		//	MOVx	(R20), Rtmp
		//	MOVx	Rtmp, (R21)
		//	ADDV	$sz, R20
		//	ADDV	$sz, R21
		//	BGEU	Rarg2, R20, -4(PC)
		{
			name:      "LoweredMove",

	MOVV R11, 88(R29)
	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

TEXT runtime·panicIndex<ABIInternal>(SB),NOSPLIT,$0-16
	MOVV	R20, R4
	MOVV	R21, R5
	JMP	runtime·goPanicIndex<ABIInternal>(SB)
TEXT runtime·panicIndexU<ABIInternal>(SB),NOSPLIT,$0-16
	MOVV	R20, R4
	MOVV	R21, R5
	JMP	runtime·goPanicIndexU<ABIInternal>(SB)
TEXT runtime·panicSliceAlen<ABIInternal>(SB),NOSPLIT,$0-16
	MOVV	R21, R4
	MOVV	R23, R5
	JMP	runtime·goPanicSliceAlen<ABIInternal>(SB)

loop:
	MOVD	0(R4), R14	// x[i]
	MOVD	8(R4), R16	// x[i+1]
	MOVD	16(R4), R18	// x[i+2]
	MOVD	24(R4), R20	// x[i+3]
	MOVD	0(R3), R15	// z[i]
	MOVD	8(R3), R17	// z[i+1]
	MOVD	16(R3), R19	// z[i+2]
	MOVD	24(R3), R21	// z[i+3]
	MULLD	R5, R14, R10	// low x[i]*y
	MULHDU	R5, R14, R11	// high x[i]*y
	ADDC	R15, R10
	ADDZE	R11
	ADDC	R9, R10
	ADDZE	R11, R9
	MULLD	R5, R16, R14	// low x[i+1]*y
	MULHDU	R5, R16, R15	// high x[i+1]*y

	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)

	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)