chunk_loop:
	// chunk size is 16
	SGTU	$16, R3, R8
	BNE	R0, R8, chunk_tail_8
chunk_loop_1:
	MOVV	(R1), R6
	MOVV	(R2), R7
	BNE	R6, R7, not_eq
	MOVV	8(R1), R12
	MOVV	8(R2), R13
	ADDV	$16, R1
	ADDV	$16, R2
	SUBV	$16, R3
	BEQ	R12, R13, chunk_loop
	JMP	not_eq

chunk_tail_8:
	AND	$8, R3, R14
	BEQ	R0, R14, chunk_tail_4
	MOVV	(R1), R6
	MOVV	(R2), R7
	BNE	R6, R7, not_eq
	ADDV	$8, R1
	ADDV	$8, R2

TEXT	msancall<>(SB), NOSPLIT, $0-0
	get_tls(R12)
	MOVQ	g(R12), R14
	MOVQ	SP, R12		// callee-saved, preserved across the CALL
	CMPQ	R14, $0
	JE	call	// no g; still on a system stack

	MOVQ	g_m(R14), R13
	// Switch to g0 stack.
	MOVQ	m_g0(R13), R10
	CMPQ	R10, R14
	JE	call	// already on g0

	MOVQ	(g_sched+gobuf_sp)(R10), SP
call:
	ANDQ	$~15, SP	// alignment for gcc ABI
	CALL	AX
	MOVQ	R12, SP

	BEQ	aligned			// aligned detected - skip copy

	// Copy the unaligned source data into the aligned temporary buffer
	// memmove(to=4(R13), from=8(R13), n=12(R13)) - Corrupts all registers
	MOVW	$buf, Rtable	// to
	MOVW	$64, Rc0		// n
	MOVM.IB	[Rtable,Rdata,Rc0], (R13)
	BL	runtime·memmove(SB)

	// Point to the local aligned copy of the data
	MOVW	$buf, Rdata

aligned:
	// Point to the table of constants

	print("r8   ", hex(c.r8()), "\t")
	print("r9   ", hex(c.r9()), "\n")
	print("r10  ", hex(c.r10()), "\t")
	print("r11  ", hex(c.r11()), "\n")
	print("r12  ", hex(c.r12()), "\t")
	print("r13  ", hex(c.r13()), "\n")
	print("r14  ", hex(c.r14()), "\t")
	print("r15  ", hex(c.r15()), "\n")
	print("r16  ", hex(c.r16()), "\t")
	print("r17  ", hex(c.r17()), "\n")
	print("r18  ", hex(c.r18()), "\t")

	MOVQ	a1+8(FP), DI
	MOVQ	a2+16(FP), SI
	MOVQ	a3+24(FP), DX
	MOVQ	a4+32(FP), R10
	MOVQ	a5+40(FP), R8
	MOVQ	a6+48(FP), R9
	MOVQ	a7+56(FP), R11
	MOVQ	a8+64(FP), R12
	MOVQ	a9+72(FP), R13
	SUBQ	$32, SP
	MOVQ	R11, 8(SP)
	MOVQ	R12, 16(SP)
	MOVQ	R13, 24(SP)
	ADDQ	$0x2000000, AX
	SYSCALL
	JCC	ok9
	ADDQ	$32, SP
	MOVQ	$-1, r1+80(FP)
	MOVQ	$0, r2+88(FP)
	MOVQ	AX, err+96(FP)
	CALL	runtime·exitsyscall<ABIInternal>(SB)
	RET

	MOVV R3, 24(R29)
	MOVV R4, 32(R29)
	MOVV R5, 40(R29)
	MOVV R6, 48(R29)
	MOVV R7, 56(R29)
	MOVV R8, 64(R29)
	MOVV R9, 72(R29)
	MOVV R10, 80(R29)
	MOVV R11, 88(R29)
	MOVV R12, 96(R29)
	MOVV R13, 104(R29)
	MOVV R14, 112(R29)
	MOVV R15, 120(R29)
	MOVV R16, 128(R29)
	MOVV R17, 136(R29)
	MOVV R18, 144(R29)
	MOVV R19, 152(R29)
	MOVV R20, 160(R29)
	MOVV R21, 168(R29)
	MOVV R22, 176(R29)

func (c *sigctxt) r10() uint64 { return c.regs().r10 }
func (c *sigctxt) r11() uint64 { return c.regs().r11 }
func (c *sigctxt) r12() uint64 { return c.regs().r12 }
func (c *sigctxt) r13() uint64 { return c.regs().r13 }
func (c *sigctxt) r14() uint64 { return c.regs().r14 }
func (c *sigctxt) r15() uint64 { return c.regs().r15 }

//go:nosplit
//go:nowritebarrierrec
func (c *sigctxt) rip() uint64 { return c.regs().rip }

	MOVV R1, -480(R3)
	SUBV $480, R3
	MOVV R4, 8(R3)
	MOVV R5, 16(R3)
	MOVV R6, 24(R3)
	MOVV R7, 32(R3)
	MOVV R8, 40(R3)
	MOVV R9, 48(R3)
	MOVV R10, 56(R3)
	MOVV R11, 64(R3)
	MOVV R12, 72(R3)
	MOVV R13, 80(R3)
	MOVV R14, 88(R3)
	MOVV R15, 96(R3)
	MOVV R16, 104(R3)
	MOVV R17, 112(R3)
	MOVV R18, 120(R3)
	MOVV R19, 128(R3)
	MOVV R20, 136(R3)
	MOVV R21, 144(R3)
	MOVV R23, 152(R3)
	MOVV R24, 160(R3)

	MOVW R3, 12(R29)
	MOVW R4, 16(R29)
	MOVW R5, 20(R29)
	MOVW R6, 24(R29)
	MOVW R7, 28(R29)
	MOVW R8, 32(R29)
	MOVW R9, 36(R29)
	MOVW R10, 40(R29)
	MOVW R11, 44(R29)
	MOVW R12, 48(R29)
	MOVW R13, 52(R29)
	MOVW R14, 56(R29)
	MOVW R15, 60(R29)
	MOVW R16, 64(R29)
	MOVW R17, 68(R29)
	MOVW R18, 72(R29)
	MOVW R19, 76(R29)
	MOVW R20, 80(R29)
	MOVW R21, 84(R29)
	MOVW R22, 88(R29)
	MOVW R24, 92(R29)

	print("r8      ", hex(c.r8()), "\n")
	print("r9      ", hex(c.r9()), "\n")
	print("r10     ", hex(c.r10()), "\n")
	print("r11     ", hex(c.r11()), "\n")
	print("r12     ", hex(c.r12()), "\n")
	print("r13     ", hex(c.r13()), "\n")
	print("r14     ", hex(c.r14()), "\n")
	print("r15     ", hex(c.r15()), "\n")
	print("r16     ", hex(c.r16()), "\n")
	print("r17     ", hex(c.r17()), "\n")
	print("r18     ", hex(c.r18()), "\n")