CMP     R8, R4
	BGE     loopexit        // Already at end?

	// vectorize if len(z) is >=3, else jump to scalar loop
	CMP     R4, $3
	BLT     scalar
	MTVSRD  R9, VS38        // s
	VSPLTB  $7, V6, V4
	MTVSRD  R5, VS39        // ŝ
	VSPLTB  $7, V7, V2
	ADD     $-2, R4, R16
	PCALIGN $16
loopback:
	ADD     $-1, R8, R10
	SLD     $3, R10
	LXVD2X  (R6)(R10), VS32 // load x[i-1], x[i]

		{name: "MFVSRD", argLength: 1, reg: fpgp, asm: "MFVSRD", typ: "Int64"},   // move 64 bits of F register into G register
		{name: "MTVSRD", argLength: 1, reg: gpfp, asm: "MTVSRD", typ: "Float64"}, // move 64 bits of G register into F register

		{name: "AND", argLength: 2, reg: gp21, asm: "AND", commutative: true},                           // arg0&arg1

			},
			outputs: []outputInfo{
				{0, 1073733624}, // R3 R4 R5 R6 R7 R8 R9 R10 R11 R12 R14 R15 R16 R17 R18 R19 R20 R21 R22 R23 R24 R25 R26 R27 R28 R29
			},
		},
	},
	{
		name:   "MTVSRD",
		argLen: 1,
		asm:    ppc64.AMTVSRD,
		reg: regInfo{
			inputs: []inputInfo{
				{0, 1073733624}, // R3 R4 R5 R6 R7 R8 R9 R10 R11 R12 R14 R15 R16 R17 R18 R19 R20 R21 R22 R23 R24 R25 R26 R27 R28 R29