MUL	R6, R3, R14
	ADCS	R14, R10
	MUL	R7, R3, R15
	LDP	16(R1), (R11, R12)
	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:

	// Code stolen from compiler output for:
	//
	//	var x uint64
	//	func f() (sec uint64, nsec uint32) { return x / 1000000000, uint32(x % 1000000000) }
	//
	LSR	$1, R0, R1
	MOVD	$-8543223759426509416, R2
	UMULH	R1, R2, R1
	LSR	$28, R1, R1
	MOVD	R1, sec+0(FP)
	MOVD	$1000000000, R2
	MSUB	R1, R0, R2, R0
	MOVW	R0, nsec+8(FP)

	"UBFIZ",
	"UBFIZW",
	"UBFM",
	"UBFMW",
	"UBFX",
	"UBFXW",
	"UCVTFD",
	"UCVTFS",
	"UCVTFWD",
	"UCVTFWS",
	"UDIV",
	"UDIVW",
	"UMADDL",
	"UMNEGL",
	"UMSUBL",
	"UMULH",
	"UMULL",
	"UREM",
	"UREMW",
	"UXTB",
	"UXTBW",
	"UXTH",
	"UXTHW",
	"UXTW",
	"VADD",
	"VADDP",
	"VADDV",
	"VAND",
	"VBCAX",
	"VBIF",
	"VBIT",
	"VBSL",