// It saves all GP registers if necessary,
		// but clobbers R14 (LR) because it's a call,
		// and also clobbers R1 as the PLT stub does.
		// Returns a pointer to a write barrier buffer in R9.
		{name: "LoweredWB", argLength: 1, reg: regInfo{clobbers: (callerSave &^ gpg) | buildReg("R14") | r1, outputs: []regMask{r9}}, clobberFlags: true, aux: "Int64"},

	"testing"
)

type T struct {
	x [2]int64 // field that will be clobbered. Also makes type not SSAable.
	p *byte    // has a pointer
}

//go:noinline
func makeT() T {
	return T{}
}

var g T

var sink interface{}

func TestIssue15854(t *testing.T) {
	for i := 0; i < 10000; i++ {
		if g.x[0] != 0 {
			t.Fatalf("g.x[0] clobbered with %x\n", g.x[0])
		}

	sdc1	$f31, 144($29)
#endif

	// prepare SB register = pc & 0xffffffff00000000
	bal	1f
1:
	dsrl	$28, $31, 32
	dsll	$28, $28, 32

	move	$20, $4 // save R4
	move	$1, $6
	jalr	$5	// call setg_gcc (clobbers R4)
	jalr	$20	// call fn

	ld	$16, 8($29)
	ld	$17, 16($29)
	ld	$18, 24($29)
	ld	$19, 32($29)
	ld	$20, 40($29)
	ld	$21, 48($29)
	ld	$22, 56($29)
	ld	$23, 64($29)
	ld	$28, 72($29)
	ld	$30, 80($29)

	// Set up tls.
	LEAL	m_tls(CX), DI
	MOVL	CX, g_m(DX)
	MOVL	DX, g(DI)
	MOVL	DI, 4(SP)
	CALL	runtime·setldt(SB) // clobbers CX and DX

	// Someday the convention will be D is always cleared.
	CLD

	CALL	runtime·stackcheck(SB)	// clobbers AX,CX
	CALL	runtime·mstart(SB)

	RET

// uint32 tstart_stdcall(M *newm);
TEXT runtime·tstart_stdcall(SB),NOSPLIT,$0
	MOVL	newm+0(FP), BX

	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

	move	$r18, $r4 // save R4
	move	$r19, $r6
	jirl	$r1, $r5, 0	// call setg_gcc (clobbers R4)
	jirl	$r1, $r18, 0	// call fn

	ld.d	$r23, $r3, 8
	ld.d	$r24, $r3, 16
	ld.d	$r25, $r3, 24
	ld.d	$r26, $r3, 32
	ld.d	$r27, $r3, 40
	ld.d	$r28, $r3, 48
	ld.d	$r29, $r3, 56
	ld.d	$r30, $r3, 64

	fsd	f23, 160(sp)
	fsd	f24, 168(sp)
	fsd	f25, 176(sp)
	fsd	f26, 184(sp)
	fsd	f27, 192(sp)

	// a0 = *fn, a1 = *setg_gcc, a2 = *g
	mv	s1, a0
	mv	s0, a1
	mv	a0, a2
	jalr	ra, s0	// call setg_gcc (clobbers x30 aka g)
	jalr	ra, s1	// call fn

	ld	x1, 0(sp)
	ld	x8, 8(sp)
	ld	x9, 16(sp)
	ld	x18, 24(sp)
	ld	x19, 32(sp)
	ld	x20, 40(sp)
	ld	x21, 48(sp)
	ld	x22, 56(sp)
	ld	x23, 64(sp)
	ld	x24, 72(sp)

	.type	toc_func, @function
toc_func:
	addis	2,12,.TOC.-toc_func@ha
	addi	2,2,.TOC.-toc_func@l
	.localentry toc_func, .-toc_func
	mflr	0
	std	0,16(1)
	stdu	1,-32(1)

	// Call a NOTOC function which clobbers R2.
	bl	notoc_nor2_func
	nop

	// Call libc random. This should generate a TOC relative plt stub.
	bl	random
	nop

	addi	1,1,32
	ld 	0,16(1)
	mtlr	0
	blr

		// It saves all GP registers if necessary,
		// but clobbers R30 (LR) because it's a call.
		// R16 and R17 may be clobbered by linker trampoline.
		// Returns a pointer to a write barrier buffer in R25.
		{name: "LoweredWB", argLength: 1, reg: regInfo{clobbers: (callerSave &^ gpg) | buildReg("R16 R17 R30"), outputs: []regMask{buildReg("R25")}}, clobberFlags: true, aux: "Int64"},

	MOVM.DB.W [R4-R11, R14], (R13)	// push {r4-r11, lr} (SP-=40)
	SUB	$(16), R13		// reserve space for parameters/retval to go call

	MOVW	R0, R6			// Save param0
	MOVW	R1, R7			// Save param1
	BL	runtime·load_g(SB)	// Clobbers R0

	MOVW	$0, R4
	MOVW	R4, 0(R13)	// No saved link register.
	MOVW	R6, 4(R13)	// Move arg0 into position
	MOVW	R7, 8(R13)	// Move arg1 into position
	BL	runtime·sigtrampgo(SB)

(CMPconst <t> [0] (Select0 z:((ADDCCconst|ANDCCconst|NEGCC|CNTLZDCC|RLDICLCC) y))) => (Select1 <t> z)

// After trying to convert ANDconst to ANDCCconst above, if the CC result is not needed, try to avoid using
// ANDconst which clobbers CC.
(ANDconst [m] x) && isPPC64ValidShiftMask(m) => (RLDICL [encodePPC64RotateMask(0,m,64)] x)

// Likewise, trying converting RLDICLCC back to ANDCCconst as it is faster.