Golang cmd-compile-avail-gc.Regalloc类(方法)实例源码

/*
 * generate byte multiply:
 *	res = nl * nr
 * there is no 2-operand byte multiply instruction so
 * we do a full-width multiplication and truncate afterwards.
 */
func cgen_bmul(op gc.Op, nl *gc.Node, nr *gc.Node, res *gc.Node) bool {
	if optoas(op, nl.Type) != x86.AIMULB {
		return false
	}

	// copy from byte to full registers
	t := gc.Types[gc.TUINT32]

	if nl.Type.IsSigned() {
		t = gc.Types[gc.TINT32]
	}

	// largest ullman on left.
	if nl.Ullman < nr.Ullman {
		nl, nr = nr, nl
	}

	var nt gc.Node
	gc.Tempname(&nt, nl.Type)
	gc.Cgen(nl, &nt)
	var n1 gc.Node
	gc.Regalloc(&n1, t, res)
	gc.Cgen(nr, &n1)
	var n2 gc.Node
	gc.Regalloc(&n2, t, nil)
	gmove(&nt, &n2)
	a := optoas(op, t)
	gins(a, &n2, &n1)
	gc.Regfree(&n2)
	gmove(&n1, res)
	gc.Regfree(&n1)

	return true
}

/*
 * generate array index into res.
 * n might be any size; res is 32-bit.
 * returns Prog* to patch to panic call.
 */
func cgenindex(n *gc.Node, res *gc.Node, bounded bool) *obj.Prog {
	if !gc.Is64(n.Type) {
		gc.Cgen(n, res)
		return nil
	}

	var tmp gc.Node
	gc.Tempname(&tmp, gc.Types[gc.TINT64])
	gc.Cgen(n, &tmp)
	var lo gc.Node
	var hi gc.Node
	split64(&tmp, &lo, &hi)
	gmove(&lo, res)
	if bounded {
		splitclean()
		return nil
	}

	var n1 gc.Node
	gc.Regalloc(&n1, gc.Types[gc.TINT32], nil)
	var n2 gc.Node
	gc.Regalloc(&n2, gc.Types[gc.TINT32], nil)
	var zero gc.Node
	gc.Nodconst(&zero, gc.Types[gc.TINT32], 0)
	gmove(&hi, &n1)
	gmove(&zero, &n2)
	gins(arm.ACMP, &n1, &n2)
	gc.Regfree(&n2)
	gc.Regfree(&n1)
	splitclean()
	return gc.Gbranch(arm.ABNE, nil, -1)
}

/*
 * generate division.
 * generates one of:
 *	res = nl / nr
 *	res = nl % nr
 * according to op.
 */
func dodiv(op gc.Op, nl *gc.Node, nr *gc.Node, res *gc.Node) {
	t := nl.Type

	t0 := t

	if t.Width < 8 {
		if t.IsSigned() {
			t = gc.Types[gc.TINT64]
		} else {
			t = gc.Types[gc.TUINT64]
		}
	}

	a := optoas(gc.ODIV, t)

	var tl gc.Node
	gc.Regalloc(&tl, t0, nil)
	var tr gc.Node
	gc.Regalloc(&tr, t0, nil)
	if nl.Ullman >= nr.Ullman {
		gc.Cgen(nl, &tl)
		gc.Cgen(nr, &tr)
	} else {
		gc.Cgen(nr, &tr)
		gc.Cgen(nl, &tl)
	}

	if t != t0 {
		// Convert
		tl2 := tl

		tr2 := tr
		tl.Type = t
		tr.Type = t
		gmove(&tl2, &tl)
		gmove(&tr2, &tr)
	}

	// Handle divide-by-zero panic.
	p1 := ginsbranch(mips.ABNE, nil, &tr, nil, 0)
	if panicdiv == nil {
		panicdiv = gc.Sysfunc("panicdivide")
	}
	gc.Ginscall(panicdiv, -1)
	gc.Patch(p1, gc.Pc)

	gins3(a, &tr, &tl, nil)
	gc.Regfree(&tr)
	if op == gc.ODIV {
		var lo gc.Node
		gc.Nodreg(&lo, gc.Types[gc.TUINT64], mips.REG_LO)
		gins(mips.AMOVV, &lo, &tl)
	} else { // remainder in REG_HI
		var hi gc.Node
		gc.Nodreg(&hi, gc.Types[gc.TUINT64], mips.REG_HI)
		gins(mips.AMOVV, &hi, &tl)
	}
	gmove(&tl, res)
	gc.Regfree(&tl)
}

func ginscmp(op gc.Op, t *gc.Type, n1, n2 *gc.Node, likely int) *obj.Prog {
	if t.IsInteger() && n1.Op == gc.OLITERAL && n2.Op != gc.OLITERAL {
		// Reverse comparison to place constant last.
		op = gc.Brrev(op)
		n1, n2 = n2, n1
	}

	var r1, r2, g1, g2 gc.Node
	gc.Regalloc(&r1, t, n1)
	gc.Regalloc(&g1, n1.Type, &r1)
	gc.Cgen(n1, &g1)
	gmove(&g1, &r1)
	if t.IsInteger() && gc.Isconst(n2, gc.CTINT) {
		ginscon2(optoas(gc.OCMP, t), &r1, n2.Int64())
	} else {
		gc.Regalloc(&r2, t, n2)
		gc.Regalloc(&g2, n1.Type, &r2)
		gc.Cgen(n2, &g2)
		gmove(&g2, &r2)
		gcmp(optoas(gc.OCMP, t), &r1, &r2)
		gc.Regfree(&g2)
		gc.Regfree(&r2)
	}
	gc.Regfree(&g1)
	gc.Regfree(&r1)
	return gc.Gbranch(optoas(op, t), nil, likely)
}

func ginscmp(op gc.Op, t *gc.Type, n1, n2 *gc.Node, likely int) *obj.Prog {
	if t.IsInteger() && n1.Op == gc.OLITERAL && n1.Int64() == 0 && n2.Op != gc.OLITERAL {
		op = gc.Brrev(op)
		n1, n2 = n2, n1
	}
	var r1, r2, g1, g2 gc.Node
	gc.Regalloc(&r1, t, n1)
	gc.Regalloc(&g1, n1.Type, &r1)
	gc.Cgen(n1, &g1)
	gmove(&g1, &r1)
	if t.IsInteger() && n2.Op == gc.OLITERAL && n2.Int64() == 0 {
		gins(arm.ACMP, &r1, n2)
	} else {
		gc.Regalloc(&r2, t, n2)
		gc.Regalloc(&g2, n1.Type, &r2)
		gc.Cgen(n2, &g2)
		gmove(&g2, &r2)
		gins(optoas(gc.OCMP, t), &r1, &r2)
		gc.Regfree(&g2)
		gc.Regfree(&r2)
	}
	gc.Regfree(&g1)
	gc.Regfree(&r1)
	return gc.Gbranch(optoas(op, t), nil, likely)
}

/*
 * generate high multiply
 *  res = (nl * nr) >> wordsize
 */
func cgen_hmul(nl *gc.Node, nr *gc.Node, res *gc.Node) {
	if nl.Ullman < nr.Ullman {
		nl, nr = nr, nl
	}

	t := nl.Type
	w := t.Width * 8
	var n1 gc.Node
	gc.Regalloc(&n1, t, res)
	gc.Cgen(nl, &n1)
	var n2 gc.Node
	gc.Regalloc(&n2, t, nil)
	gc.Cgen(nr, &n2)
	switch gc.Simtype[t.Etype] {
	case gc.TINT8,
		gc.TINT16:
		gins(optoas(gc.OMUL, t), &n2, &n1)
		gshift(arm.AMOVW, &n1, arm.SHIFT_AR, int32(w), &n1)

	case gc.TUINT8,
		gc.TUINT16:
		gins(optoas(gc.OMUL, t), &n2, &n1)
		gshift(arm.AMOVW, &n1, arm.SHIFT_LR, int32(w), &n1)

		// perform a long multiplication.
	case gc.TINT32,
		gc.TUINT32:
		var p *obj.Prog
		if t.IsSigned() {
			p = gins(arm.AMULL, &n2, nil)
		} else {
			p = gins(arm.AMULLU, &n2, nil)
		}

		// n2 * n1 -> (n1 n2)
		p.Reg = n1.Reg

		p.To.Type = obj.TYPE_REGREG
		p.To.Reg = n1.Reg
		p.To.Offset = int64(n2.Reg)

	default:
		gc.Fatalf("cgen_hmul %v", t)
	}

	gc.Cgen(&n1, res)
	gc.Regfree(&n1)
	gc.Regfree(&n2)
}

/*
 * generate
 *	as $c, n
 */
func ginscon(as obj.As, c int64, n2 *gc.Node) {
	var n1 gc.Node

	switch as {
	case x86.AADDL,
		x86.AMOVL,
		x86.ALEAL:
		gc.Nodconst(&n1, gc.Types[gc.TINT32], c)

	default:
		gc.Nodconst(&n1, gc.Types[gc.TINT64], c)
	}

	if as != x86.AMOVQ && (c < -(1<<31) || c >= 1<<31) {
		// cannot have 64-bit immediate in ADD, etc.
		// instead, MOV into register first.
		var ntmp gc.Node
		gc.Regalloc(&ntmp, gc.Types[gc.TINT64], nil)

		gins(x86.AMOVQ, &n1, &ntmp)
		gins(as, &ntmp, n2)
		gc.Regfree(&ntmp)
		return
	}

	gins(as, &n1, n2)
}

/*
 * generate
 *	as n, $c (CMP/CMPU)
 */
func ginscon2(as obj.As, n2 *gc.Node, c int64) {
	var n1 gc.Node

	gc.Nodconst(&n1, gc.Types[gc.TINT64], c)

	switch as {
	default:
		gc.Fatalf("ginscon2")

	case ppc64.ACMP:
		if -ppc64.BIG <= c && c <= ppc64.BIG {
			rawgins(as, n2, &n1)
			return
		}

	case ppc64.ACMPU:
		if 0 <= c && c <= 2*ppc64.BIG {
			rawgins(as, n2, &n1)
			return
		}
	}

	// MOV n1 into register first
	var ntmp gc.Node
	gc.Regalloc(&ntmp, gc.Types[gc.TINT64], nil)

	rawgins(ppc64.AMOVD, &n1, &ntmp)
	rawgins(as, n2, &ntmp)
	gc.Regfree(&ntmp)
}

// RightShiftWithCarry generates a constant unsigned
// right shift with carry.
//
// res = n >> shift // with carry
func RightShiftWithCarry(n *gc.Node, shift uint, res *gc.Node) {
	// Extra 1 is for carry bit.
	maxshift := uint(n.Type.Width*8 + 1)
	if shift == 0 {
		gmove(n, res)
	} else if shift < maxshift {
		// 1. clear rightmost bit of target
		var n1 gc.Node
		gc.Nodconst(&n1, n.Type, 1)
		gins(optoas(gc.ORSH, n.Type), &n1, n)
		gins(optoas(gc.OLSH, n.Type), &n1, n)
		// 2. add carry flag to target
		var n2 gc.Node
		gc.Nodconst(&n1, n.Type, 0)
		gc.Regalloc(&n2, n.Type, nil)
		gins(optoas(gc.OAS, n.Type), &n1, &n2)
		gins(arm64.AADC, &n2, n)
		// 3. right rotate 1 bit
		gc.Nodconst(&n1, n.Type, 1)
		gins(arm64.AROR, &n1, n)

		// ARM64 backend doesn't eliminate shifts by 0. It is manually checked here.
		if shift > 1 {
			var n3 gc.Node
			gc.Nodconst(&n3, n.Type, int64(shift-1))
			cgen_shift(gc.ORSH, true, n, &n3, res)
		} else {
			gmove(n, res)
		}
		gc.Regfree(&n2)
	} else {
		gc.Fatalf("RightShiftWithCarry: shift(%v) is bigger than max size(%v)", shift, maxshift)
	}
}

/*
 * generate
 *	as $c, n
 */
func ginscon(as obj.As, c int64, n *gc.Node) {
	var n1 gc.Node
	gc.Nodconst(&n1, gc.Types[gc.TINT32], c)
	var n2 gc.Node
	gc.Regalloc(&n2, gc.Types[gc.TINT32], nil)
	gmove(&n1, &n2)
	gins(as, &n2, n)
	gc.Regfree(&n2)
}

// res = runtime.getg()
func getg(res *gc.Node) {
	var n1 gc.Node
	gc.Regalloc(&n1, res.Type, res)
	mov := optoas(gc.OAS, gc.Types[gc.Tptr])
	p := gins(mov, nil, &n1)
	p.From.Type = obj.TYPE_REG
	p.From.Reg = x86.REG_TLS
	p = gins(mov, nil, &n1)
	p.From = p.To
	p.From.Type = obj.TYPE_MEM
	p.From.Index = x86.REG_TLS
	p.From.Scale = 1
	gmove(&n1, res)
	gc.Regfree(&n1)
}

func savex(dr int, x *gc.Node, oldx *gc.Node, res *gc.Node, t *gc.Type) {
	r := gc.GetReg(dr)
	gc.Nodreg(x, gc.Types[gc.TINT32], dr)

	// save current ax and dx if they are live
	// and not the destination
	*oldx = gc.Node{}

	if r > 0 && !gc.Samereg(x, res) {
		gc.Tempname(oldx, gc.Types[gc.TINT32])
		gmove(x, oldx)
	}

	gc.Regalloc(x, t, x)
}

func gmove(f *gc.Node, t *gc.Node) {
	if gc.Debug['M'] != 0 {
		fmt.Printf("gmove %v -> %v\n", f, t)
	}

	ft := gc.Simsimtype(f.Type)
	tt := gc.Simsimtype(t.Type)
	cvt := t.Type

	if gc.Iscomplex[ft] || gc.Iscomplex[tt] {
		gc.Complexmove(f, t)
		return
	}

	// cannot have two memory operands;
	// except 64-bit, which always copies via registers anyway.
	var a obj.As
	var r1 gc.Node
	if !gc.Is64(f.Type) && !gc.Is64(t.Type) && gc.Ismem(f) && gc.Ismem(t) {
		goto hard
	}

	// convert constant to desired type
	if f.Op == gc.OLITERAL {
		var con gc.Node
		switch tt {
		default:
			f.Convconst(&con, t.Type)

		case gc.TINT16,
			gc.TINT8:
			var con gc.Node
			f.Convconst(&con, gc.Types[gc.TINT32])
			var r1 gc.Node
			gc.Regalloc(&r1, con.Type, t)
			gins(arm.AMOVW, &con, &r1)
			gmove(&r1, t)
			gc.Regfree(&r1)
			return

		case gc.TUINT16,
			gc.TUINT8:
			var con gc.Node
			f.Convconst(&con, gc.Types[gc.TUINT32])
			var r1 gc.Node
			gc.Regalloc(&r1, con.Type, t)
			gins(arm.AMOVW, &con, &r1)
			gmove(&r1, t)
			gc.Regfree(&r1)
			return
		}

		f = &con
		ft = gc.Simsimtype(con.Type)

		// constants can't move directly to memory
		if gc.Ismem(t) && !gc.Is64(t.Type) {
			goto hard
		}
	}

	// value -> value copy, only one memory operand.
	// figure out the instruction to use.
	// break out of switch for one-instruction gins.
	// goto rdst for "destination must be register".
	// goto hard for "convert to cvt type first".
	// otherwise handle and return.

	switch uint32(ft)<<16 | uint32(tt) {
	default:
		// should not happen
		gc.Fatalf("gmove %v -> %v", f, t)
		return

		/*
		 * integer copy and truncate
		 */
	case gc.TINT8<<16 | gc.TINT8: // same size
		if !gc.Ismem(f) {
			a = arm.AMOVB
			break
		}
		fallthrough

	case gc.TUINT8<<16 | gc.TINT8,
		gc.TINT16<<16 | gc.TINT8, // truncate
		gc.TUINT16<<16 | gc.TINT8,
		gc.TINT32<<16 | gc.TINT8,
		gc.TUINT32<<16 | gc.TINT8:
		a = arm.AMOVBS

	case gc.TUINT8<<16 | gc.TUINT8:
		if !gc.Ismem(f) {
			a = arm.AMOVB
			break
		}
		fallthrough

	case gc.TINT8<<16 | gc.TUINT8,
		gc.TINT16<<16 | gc.TUINT8,
//.........这里部分代码省略.........

/*
 * generate code to compute address of n,
 * a reference to a (perhaps nested) field inside
 * an array or struct.
 * return 0 on failure, 1 on success.
 * on success, leaves usable address in a.
 *
 * caller is responsible for calling sudoclean
 * after successful sudoaddable,
 * to release the register used for a.
 */
func sudoaddable(as obj.As, n *gc.Node, a *obj.Addr) bool {
	if n.Type == nil {
		return false
	}

	*a = obj.Addr{}

	switch n.Op {
	case gc.OLITERAL:
		if !gc.Isconst(n, gc.CTINT) {
			break
		}
		v := n.Int64()
		if v >= 32000 || v <= -32000 {
			break
		}
		switch as {
		default:
			return false

		case arm.AADD,
			arm.ASUB,
			arm.AAND,
			arm.AORR,
			arm.AEOR,
			arm.AMOVB,
			arm.AMOVBS,
			arm.AMOVBU,
			arm.AMOVH,
			arm.AMOVHS,
			arm.AMOVHU,
			arm.AMOVW:
			break
		}

		cleani += 2
		reg := &clean[cleani-1]
		reg1 := &clean[cleani-2]
		reg.Op = gc.OEMPTY
		reg1.Op = gc.OEMPTY
		gc.Naddr(a, n)
		return true

	case gc.ODOT,
		gc.ODOTPTR:
		cleani += 2
		reg := &clean[cleani-1]
		reg1 := &clean[cleani-2]
		reg.Op = gc.OEMPTY
		reg1.Op = gc.OEMPTY
		var nn *gc.Node
		var oary [10]int64
		o := gc.Dotoffset(n, oary[:], &nn)
		if nn == nil {
			sudoclean()
			return false
		}

		if nn.Addable && o == 1 && oary[0] >= 0 {
			// directly addressable set of DOTs
			n1 := *nn

			n1.Type = n.Type
			n1.Xoffset += oary[0]
			gc.Naddr(a, &n1)
			return true
		}

		gc.Regalloc(reg, gc.Types[gc.Tptr], nil)
		n1 := *reg
		n1.Op = gc.OINDREG
		if oary[0] >= 0 {
			gc.Agen(nn, reg)
			n1.Xoffset = oary[0]
		} else {
			gc.Cgen(nn, reg)
			gc.Cgen_checknil(reg)
			n1.Xoffset = -(oary[0] + 1)
		}

		for i := 1; i < o; i++ {
			if oary[i] >= 0 {
				gc.Fatalf("can't happen")
			}
			gins(arm.AMOVW, &n1, reg)
			gc.Cgen_checknil(reg)
			n1.Xoffset = -(oary[i] + 1)
		}

//.........这里部分代码省略.........

/*
 * generate comparison of nl, nr, both 64-bit.
 * nl is memory; nr is constant or memory.
 */
func cmp64(nl *gc.Node, nr *gc.Node, op gc.Op, likely int, to *obj.Prog) {
	var lo1 gc.Node
	var hi1 gc.Node
	var lo2 gc.Node
	var hi2 gc.Node
	var rr gc.Node

	split64(nl, &lo1, &hi1)
	split64(nr, &lo2, &hi2)

	// compare most significant word;
	// if they differ, we're done.
	t := hi1.Type

	if nl.Op == gc.OLITERAL || nr.Op == gc.OLITERAL {
		gins(x86.ACMPL, &hi1, &hi2)
	} else {
		gc.Regalloc(&rr, gc.Types[gc.TINT32], nil)
		gins(x86.AMOVL, &hi1, &rr)
		gins(x86.ACMPL, &rr, &hi2)
		gc.Regfree(&rr)
	}

	var br *obj.Prog
	switch op {
	default:
		gc.Fatalf("cmp64 %v %v", op, t)

		// cmp hi
	// jne L
	// cmp lo
	// jeq to
	// L:
	case gc.OEQ:
		br = gc.Gbranch(x86.AJNE, nil, -likely)

		// cmp hi
	// jne to
	// cmp lo
	// jne to
	case gc.ONE:
		gc.Patch(gc.Gbranch(x86.AJNE, nil, likely), to)

		// cmp hi
	// jgt to
	// jlt L
	// cmp lo
	// jge to (or jgt to)
	// L:
	case gc.OGE,
		gc.OGT:
		gc.Patch(gc.Gbranch(optoas(gc.OGT, t), nil, likely), to)

		br = gc.Gbranch(optoas(gc.OLT, t), nil, -likely)

		// cmp hi
	// jlt to
	// jgt L
	// cmp lo
	// jle to (or jlt to)
	// L:
	case gc.OLE,
		gc.OLT:
		gc.Patch(gc.Gbranch(optoas(gc.OLT, t), nil, likely), to)

		br = gc.Gbranch(optoas(gc.OGT, t), nil, -likely)
	}

	// compare least significant word
	t = lo1.Type

	if nl.Op == gc.OLITERAL || nr.Op == gc.OLITERAL {
		gins(x86.ACMPL, &lo1, &lo2)
	} else {
		gc.Regalloc(&rr, gc.Types[gc.TINT32], nil)
		gins(x86.AMOVL, &lo1, &rr)
		gins(x86.ACMPL, &rr, &lo2)
		gc.Regfree(&rr)
	}

	// jump again
	gc.Patch(gc.Gbranch(optoas(op, t), nil, likely), to)

	// point first branch down here if appropriate
	if br != nil {
		gc.Patch(br, gc.Pc)
	}

	splitclean()
	splitclean()
}

//.........这里部分代码省略.........

	// Setup for binary operation.
	var hi1 gc.Node
	var lo1 gc.Node
	split64(l, &lo1, &hi1)

	var lo2 gc.Node
	var hi2 gc.Node
	if gc.Is64(r.Type) {
		split64(r, &lo2, &hi2)
	}

	// Do op. Leave result in DX:AX.
	switch n.Op {
	// TODO: Constants
	case gc.OADD:
		gins(x86.AMOVL, &lo1, &ax)

		gins(x86.AMOVL, &hi1, &dx)
		gins(x86.AADDL, &lo2, &ax)
		gins(x86.AADCL, &hi2, &dx)

		// TODO: Constants.
	case gc.OSUB:
		gins(x86.AMOVL, &lo1, &ax)

		gins(x86.AMOVL, &hi1, &dx)
		gins(x86.ASUBL, &lo2, &ax)
		gins(x86.ASBBL, &hi2, &dx)

	case gc.OMUL:
		// let's call the next three EX, FX and GX
		var ex, fx, gx gc.Node
		gc.Regalloc(&ex, gc.Types[gc.TPTR32], nil)
		gc.Regalloc(&fx, gc.Types[gc.TPTR32], nil)
		gc.Regalloc(&gx, gc.Types[gc.TPTR32], nil)

		// load args into DX:AX and EX:GX.
		gins(x86.AMOVL, &lo1, &ax)

		gins(x86.AMOVL, &hi1, &dx)
		gins(x86.AMOVL, &lo2, &gx)
		gins(x86.AMOVL, &hi2, &ex)

		// if DX and EX are zero, use 32 x 32 -> 64 unsigned multiply.
		gins(x86.AMOVL, &dx, &fx)

		gins(x86.AORL, &ex, &fx)
		p1 := gc.Gbranch(x86.AJNE, nil, 0)
		gins(x86.AMULL, &gx, nil) // implicit &ax
		p2 := gc.Gbranch(obj.AJMP, nil, 0)
		gc.Patch(p1, gc.Pc)

		// full 64x64 -> 64, from 32x32 -> 64.
		gins(x86.AIMULL, &gx, &dx)

		gins(x86.AMOVL, &ax, &fx)
		gins(x86.AIMULL, &ex, &fx)
		gins(x86.AADDL, &dx, &fx)
		gins(x86.AMOVL, &gx, &dx)
		gins(x86.AMULL, &dx, nil) // implicit &ax
		gins(x86.AADDL, &fx, &dx)
		gc.Patch(p2, gc.Pc)

		gc.Regfree(&ex)
		gc.Regfree(&fx)

func clearfat(nl *gc.Node) {
	/* clear a fat object */
	if gc.Debug['g'] != 0 {
		fmt.Printf("clearfat %v (%v, size: %d)\n", nl, nl.Type, nl.Type.Width)
	}

	w := uint64(nl.Type.Width)

	// Avoid taking the address for simple enough types.
	if gc.Componentgen(nil, nl) {
		return
	}

	c := w % 8 // bytes
	q := w / 8 // dwords

	var r0 gc.Node
	gc.Nodreg(&r0, gc.Types[gc.TUINT64], arm64.REGZERO)
	var dst gc.Node

	// REGRT1 is reserved on arm64, see arm64/gsubr.go.
	gc.Nodreg(&dst, gc.Types[gc.Tptr], arm64.REGRT1)
	gc.Agen(nl, &dst)

	var boff uint64
	if q > 128 {
		p := gins(arm64.ASUB, nil, &dst)
		p.From.Type = obj.TYPE_CONST
		p.From.Offset = 8

		var end gc.Node
		gc.Regalloc(&end, gc.Types[gc.Tptr], nil)
		p = gins(arm64.AMOVD, &dst, &end)
		p.From.Type = obj.TYPE_ADDR
		p.From.Offset = int64(q * 8)

		p = gins(arm64.AMOVD, &r0, &dst)
		p.To.Type = obj.TYPE_MEM
		p.To.Offset = 8
		p.Scond = arm64.C_XPRE
		pl := p

		p = gcmp(arm64.ACMP, &dst, &end)
		gc.Patch(gc.Gbranch(arm64.ABNE, nil, 0), pl)

		gc.Regfree(&end)

		// The loop leaves R16 on the last zeroed dword
		boff = 8
	} else if q >= 4 && !darwin { // darwin ld64 cannot handle BR26 reloc with non-zero addend
		p := gins(arm64.ASUB, nil, &dst)
		p.From.Type = obj.TYPE_CONST
		p.From.Offset = 8
		f := gc.Sysfunc("duffzero")
		p = gins(obj.ADUFFZERO, nil, f)
		gc.Afunclit(&p.To, f)

		// 4 and 128 = magic constants: see ../../runtime/asm_arm64x.s
		p.To.Offset = int64(4 * (128 - q))

		// duffzero leaves R16 on the last zeroed dword
		boff = 8
	} else {
		var p *obj.Prog
		for t := uint64(0); t < q; t++ {
			p = gins(arm64.AMOVD, &r0, &dst)
			p.To.Type = obj.TYPE_MEM
			p.To.Offset = int64(8 * t)
		}

		boff = 8 * q
	}

	var p *obj.Prog
	for t := uint64(0); t < c; t++ {
		p = gins(arm64.AMOVB, &r0, &dst)
		p.To.Type = obj.TYPE_MEM
		p.To.Offset = int64(t + boff)
	}
}

/*
 * generate shift according to op, one of:
 *	res = nl << nr
 *	res = nl >> nr
 */
func cgen_shift(op gc.Op, bounded bool, nl *gc.Node, nr *gc.Node, res *gc.Node) {
	a := optoas(op, nl.Type)

	if nr.Op == gc.OLITERAL {
		var n1 gc.Node
		gc.Regalloc(&n1, nl.Type, res)
		gc.Cgen(nl, &n1)
		sc := uint64(nr.Int64())
		if sc >= uint64(nl.Type.Width*8) {
			// large shift gets 2 shifts by width-1
			var n3 gc.Node
			gc.Nodconst(&n3, gc.Types[gc.TUINT32], nl.Type.Width*8-1)

			gins(a, &n3, &n1)
			gins(a, &n3, &n1)
		} else {
			gins(a, nr, &n1)
		}
		gmove(&n1, res)
		gc.Regfree(&n1)
		return
	}

	if nl.Ullman >= gc.UINF {
		var n4 gc.Node
		gc.Tempname(&n4, nl.Type)
		gc.Cgen(nl, &n4)
		nl = &n4
	}

	if nr.Ullman >= gc.UINF {
		var n5 gc.Node
		gc.Tempname(&n5, nr.Type)
		gc.Cgen(nr, &n5)
		nr = &n5
	}

	// Allow either uint32 or uint64 as shift type,
	// to avoid unnecessary conversion from uint32 to uint64
	// just to do the comparison.
	tcount := gc.Types[gc.Simtype[nr.Type.Etype]]

	if tcount.Etype < gc.TUINT32 {
		tcount = gc.Types[gc.TUINT32]
	}

	var n1 gc.Node
	gc.Regalloc(&n1, nr.Type, nil) // to hold the shift type in CX
	var n3 gc.Node
	gc.Regalloc(&n3, tcount, &n1) // to clear high bits of CX

	var n2 gc.Node
	gc.Regalloc(&n2, nl.Type, res)

	if nl.Ullman >= nr.Ullman {
		gc.Cgen(nl, &n2)
		gc.Cgen(nr, &n1)
		gmove(&n1, &n3)
	} else {
		gc.Cgen(nr, &n1)
		gmove(&n1, &n3)
		gc.Cgen(nl, &n2)
	}

	gc.Regfree(&n3)

	// test and fix up large shifts
	if !bounded {
		gc.Nodconst(&n3, tcount, nl.Type.Width*8)
		gins(optoas(gc.OCMP, tcount), &n1, &n3)
		p1 := gc.Gbranch(optoas(gc.OLT, tcount), nil, 1)
		if op == gc.ORSH && nl.Type.IsSigned() {
			gc.Nodconst(&n3, gc.Types[gc.TUINT32], nl.Type.Width*8-1)
			gins(a, &n3, &n2)
		} else {
			gc.Nodconst(&n3, nl.Type, 0)
			gmove(&n3, &n2)
		}

		gc.Patch(p1, gc.Pc)
	}

	gins(a, &n1, &n2)

	gmove(&n2, res)

	gc.Regfree(&n1)
	gc.Regfree(&n2)
}

// blockcopy copies w bytes from &n to &res
func blockcopy(n, res *gc.Node, osrc, odst, w int64) {
	var dst gc.Node
	var src gc.Node
	if n.Ullman >= res.Ullman {
		gc.Agenr(n, &dst, res) // temporarily use dst
		gc.Regalloc(&src, gc.Types[gc.Tptr], nil)
		gins(s390x.AMOVD, &dst, &src)
		if res.Op == gc.ONAME {
			gc.Gvardef(res)
		}
		gc.Agen(res, &dst)
	} else {
		if res.Op == gc.ONAME {
			gc.Gvardef(res)
		}
		gc.Agenr(res, &dst, res)
		gc.Agenr(n, &src, nil)
	}
	defer gc.Regfree(&src)
	defer gc.Regfree(&dst)

	var tmp gc.Node
	gc.Regalloc(&tmp, gc.Types[gc.Tptr], nil)
	defer gc.Regfree(&tmp)

	offset := int64(0)
	dir := _FORWARDS
	if osrc < odst && odst < osrc+w {
		// Reverse. Can't use MVC, fall back onto basic moves.
		dir = _BACKWARDS
		const copiesPerIter = 2
		if w >= 8*copiesPerIter {
			cnt := w - (w % (8 * copiesPerIter))
			ginscon(s390x.AADD, w, &src)
			ginscon(s390x.AADD, w, &dst)

			var end gc.Node
			gc.Regalloc(&end, gc.Types[gc.Tptr], nil)
			p := gins(s390x.ASUB, nil, &end)
			p.From.Type = obj.TYPE_CONST
			p.From.Offset = cnt
			p.Reg = src.Reg

			var label *obj.Prog
			for i := 0; i < copiesPerIter; i++ {
				offset := int64(-8 * (i + 1))
				p := gins(s390x.AMOVD, &src, &tmp)
				p.From.Type = obj.TYPE_MEM
				p.From.Offset = offset
				if i == 0 {
					label = p
				}
				p = gins(s390x.AMOVD, &tmp, &dst)
				p.To.Type = obj.TYPE_MEM
				p.To.Offset = offset
			}

			ginscon(s390x.ASUB, 8*copiesPerIter, &src)
			ginscon(s390x.ASUB, 8*copiesPerIter, &dst)
			gins(s390x.ACMP, &src, &end)
			gc.Patch(gc.Gbranch(s390x.ABNE, nil, 0), label)
			gc.Regfree(&end)

			w -= cnt
		} else {
			offset = w
		}
	}

	if dir == _FORWARDS && w > 1024 {
		// Loop over MVCs
		cnt := w - (w % 256)

		var end gc.Node
		gc.Regalloc(&end, gc.Types[gc.Tptr], nil)
		add := gins(s390x.AADD, nil, &end)
		add.From.Type = obj.TYPE_CONST
		add.From.Offset = cnt
		add.Reg = src.Reg

		mvc := gins(s390x.AMVC, &src, &dst)
		mvc.From.Type = obj.TYPE_MEM
		mvc.From.Offset = 0
		mvc.To.Type = obj.TYPE_MEM
		mvc.To.Offset = 0
		mvc.From3 = new(obj.Addr)
		mvc.From3.Type = obj.TYPE_CONST
		mvc.From3.Offset = 256

		ginscon(s390x.AADD, 256, &src)
		ginscon(s390x.AADD, 256, &dst)
		gins(s390x.ACMP, &src, &end)
		gc.Patch(gc.Gbranch(s390x.ABNE, nil, 0), mvc)
		gc.Regfree(&end)

		w -= cnt
	}

	for w > 0 {
//.........这里部分代码省略.........