#ifdef GOARCH_mips64
	// Big endian.  ptr = ptr ^ 3
	XOR	$3, R1
#endif
	// R4 = ((ptr & 3) * 8)
	AND	$3, R1, R4
	SLLV	$3, R4
	// Shift val for aligned ptr. R2 = val << R4 | ^(0xFF << R4)
	MOVV	$0xFF, R5
	SLLV	R4, R2
	SLLV	R4, R5
	NOR	R0, R5
	OR	R5, R2

	SYNC
	LL	(R3), R4
	AND	R2, R4
	SC	R4, (R3)
	BEQ	R4, -4(PC)
	SYNC
	RET

// func Or(addr *uint32, v uint32)

	// Synchronous initialization.
	MOVD	$runtime·libpreinit(SB), R4
	BL	(R4)

	// Create a new thread to do the runtime initialization and return.
	MOVD  _cgo_sys_thread_create(SB), R4
	MOVD  $_rt0_arm64_darwin_lib_go(SB), R0
	MOVD  $0, R1
	SUB   $16, RSP		// reserve 16 bytes for sp-8 where fp may be saved.
	BL    (R4)
	ADD   $16, RSP

	// Restore callee-save registers.
	RESTORE_R19_TO_R28(8)

	// for sebsequent substring comparisons
	SUB	R3, R1, R4
	// R4 contains the start of last substring for comparison
	ADD	R0, R4, R4
	ADD	$1, R0, R8

	CMP	$8, R3
	BHI	greater_8
	TBZ	$3, R3, len_2_7
len_8:
	// R5 contains 8-byte of sep
	MOVD	(R2), R5
loop_8:
	// R6 contains substring for comparison
	CMP	R4, R0
	BHI	not_found
	MOVD.P	1(R0), R6
	CMP	R5, R6
	BNE	loop_8
	B	found

#ifndef GOPPC64_power9
	VBPERMQ	V6,V0,V6
	MFVRD	V6,R4
	CNTLZW	R4,R4
#else
#ifdef GOARCH_ppc64le
	// Put the value back into LE ordering by swapping doublewords.
	XXPERMDI	V6,V6,$2,V6
#endif
	_VCZBEBB	V6,R4
#endif
	ADD	R3,R4,R3
	RET

cmp16:	// Length 16 - 31
	CMPU	R4,$16
	ADD	R4,R3,R9
	BLT	cmp8

	ADD	$-16,R9,R9		// &s[len(s)-16]

	// Bytes 0 - 15

TEXT runtime·systemstack(SB), NOSPLIT, $0-8
	MOVD	fn+0(FP), R3	// R3 = fn
	MOVD	R3, R12		// context
	MOVD	g_m(g), R4	// R4 = m

	MOVD	m_gsignal(R4), R5	// R5 = gsignal
	CMPBEQ	g, R5, noswitch

	MOVD	m_g0(R4), R5	// R5 = g0
	CMPBEQ	g, R5, noswitch

	MOVD	m_curg(R4), R6
	CMPBEQ	g, R6, switch

	// Bad: g is not gsignal, not g0, not curg. What is it?
	// Hide call from linker nosplit analysis.

	MOVHS.W	R3, 0x20(R4)         // MOVHS.W R3, 32(R4)        // b032e4e1
	MOVHS.P	R3, 0x20(R4)         // MOVHS.P R3, 32(R4)        // b032c4e0
	MOVHU	R3, 0x20(R4)         // MOVHU R3, 32(R4)          // b032c4e1
	MOVHU.W	R3, 0x20(R4)         // MOVHU.W R3, 32(R4)        // b032e4e1
	MOVHU.P	R3, 0x20(R4)         // MOVHU.P R3, 32(R4)        // b032c4e0
	MOVH	R3, -0x20(R4)        // MOVH R3, -32(R4)          // b03244e1

	// Large backward copy for overlapping copies.
	// Copy 16 bytes and then align srcend (R4) or dstend (R5) to 16-byte alignment.
copy_long_backward:
	LDP	-16(R4), (R12, R13)
	AND	$15, R8, R14
	SUB	R14, R4, R4
	SUB	R14, R2, R2
	LDP	-16(R4), (R6, R7)
	STP	(R12, R13), -16(R5)
	LDP	-32(R4), (R8, R9)
	LDP	-48(R4), (R10, R11)
	LDP.W	-64(R4), (R12, R13)
	SUB	R14, R5, R5
	SUBS	$128, R2, R2
	BLS	copy64_from_start

	// Synchronous initialization.
	MOVD	$runtime·libpreinit(SB), R4
	BL	(R4)

	// Create a new thread to do the runtime initialization and return.
	MOVD	_cgo_sys_thread_create(SB), R4
	CBZ	R4, nocgo
	MOVD	$_rt0_arm64_linux_lib_go(SB), R0
	MOVD	$0, R1
	SUB	$16, RSP		// reserve 16 bytes for sp-8 where fp may be saved.
	BL	(R4)
	ADD	$16, RSP
	B	restore

nocgo:

// ---------------------------
// num | R4          | R11
// a1  | R5          | R4
// a2  | R6          | R5
// a3  | R7          | R6
// a4  | R8          | R7
// a5  | R9          | R8
// a6  | R10         | R9
//
// r1  | R4          | R4
// r2  | R5          | R5
// err | R6          | part of R4
TEXT ·Syscall6<ABIInternal>(SB),NOSPLIT,$0-80
	MOVV	R4, R11  // syscall entry
	MOVV	R5, R4
	MOVV	R6, R5

	MOVV	f+8(FP), REGCTXT;			\
	MOVV	(REGCTXT), R4;			\
	PCDATA  $PCDATA_StackMapIndex, $0;	\
	JAL	(R4);				\
	/* copy return values back */		\
	MOVV	stackArgsType+0(FP), R5;		\
	MOVV	stackArgs+16(FP), R1;			\
	MOVWU	stackArgsSize+24(FP), R2;			\
	MOVWU	stackRetOffset+28(FP), R4;		\
	ADDV	$8, R29, R3;				\
	ADDV	R4, R3; 			\
	ADDV	R4, R1;				\
	SUBVU	R4, R2;				\
	JAL	callRet<>(SB);			\
	RET