STP.P	(R26, R27), 16(R21)

	LDP.P	16(R20), (R26, R27)
	STP.P	(R26, R27), 16(R21)

	LDP.P	16(R20), (R26, R27)
	STP.P	(R26, R27), 16(R21)

	LDP.P	16(R20), (R26, R27)
	STP.P	(R26, R27), 16(R21)

	LDP.P	16(R20), (R26, R27)
	STP.P	(R26, R27), 16(R21)

	LDP.P	16(R20), (R26, R27)
	STP.P	(R26, R27), 16(R21)

	LDP.P	16(R20), (R26, R27)
	STP.P	(R26, R27), 16(R21)

	// frame is specially handled in the runtime. See the comment above LOCAL_RETVALID.
	ADD	$LOCAL_REGARGS, RSP, R20
	CALL	runtime·spillArgs(SB)
	MOVD	R26, 32(RSP) // outside of moveMakeFuncArgPtrs's arg area
	MOVD	R26, R0
	MOVD	R20, R1
	CALL	·moveMakeFuncArgPtrs<ABIInternal>(SB)
	MOVD	32(RSP), R26
	MOVD	R26, 8(RSP)
	MOVD	$argframe+0(FP), R3
	MOVD	R3, 16(RSP)
	MOVB	$0, LOCAL_RETVALID(RSP)
	ADD	$LOCAL_RETVALID, RSP, R3
	MOVD	R3, 24(RSP)

	STP (R8, R9), 72(RSP)
	STP (R10, R11), 88(RSP)
	STP (R12, R13), 104(RSP)
	STP (R14, R15), 120(RSP)
	STP (R16, R17), 136(RSP)
	STP (R19, R20), 152(RSP)
	STP (R21, R22), 168(RSP)
	STP (R23, R24), 184(RSP)
	STP (R25, R26), 200(RSP)
	MOVD NZCV, R0
	MOVD R0, 216(RSP)
	MOVD FPSR, R0
	MOVD R0, 224(RSP)
	FSTPD (F0, F1), 232(RSP)
	FSTPD (F2, F3), 248(RSP)
	FSTPD (F4, F5), 264(RSP)
	FSTPD (F6, F7), 280(RSP)
	FSTPD (F8, F9), 296(RSP)

	print("r21  ", hex(c.r21()), "\n")
	print("r22  ", hex(c.r22()), "\t")
	print("r23  ", hex(c.r23()), "\n")
	print("r24  ", hex(c.r24()), "\t")
	print("r25  ", hex(c.r25()), "\n")
	print("r26  ", hex(c.r26()), "\t")
	print("r27  ", hex(c.r27()), "\n")
	print("r28  ", hex(c.r28()), "\t")
	print("r29  ", hex(c.r29()), "\n")
	print("r30  ", hex(c.r30()), "\t")
	print("r31  ", hex(c.r31()), "\n")

	STP	(R21, R22), ((offset)+2*8)(RSP) \
	STP	(R23, R24), ((offset)+4*8)(RSP) \
	STP	(R25, R26), ((offset)+6*8)(RSP) \
	STP	(R27, g), ((offset)+8*8)(RSP)

#define RESTORE_R19_TO_R28(offset) \
	LDP	((offset)+0*8)(RSP), (R19, R20) \
	LDP	((offset)+2*8)(RSP), (R21, R22) \
	LDP	((offset)+4*8)(RSP), (R23, R24) \
	LDP	((offset)+6*8)(RSP), (R25, R26) \
	LDP	((offset)+8*8)(RSP), (R27, g) /* R28 */

#define SAVE_F8_TO_F15(offset) \

 */
.globl crosscall1
crosscall1:
	addi.d	$r3, $r3, -160
	st.d	$r1, $r3, 0
	st.d	$r23, $r3, 8
	st.d	$r24, $r3, 16
	st.d	$r25, $r3, 24
	st.d	$r26, $r3, 32
	st.d	$r27, $r3, 40
	st.d	$r28, $r3, 48
	st.d	$r29, $r3, 56
	st.d	$r30, $r3, 64
	st.d	$r2, $r3, 72
	st.d	$r22, $r3, 80
	fst.d	$f24, $r3, 88
	fst.d	$f25, $r3, 96
	fst.d	$f26, $r3, 104

//
// Note: g is R22

#define SAVE_R22_TO_R31(offset)	\
	MOVV	g,   ((offset)+(0*8))(R3)	\
	MOVV	R23, ((offset)+(1*8))(R3)	\
	MOVV	R24, ((offset)+(2*8))(R3)	\
	MOVV	R25, ((offset)+(3*8))(R3)	\
	MOVV	R26, ((offset)+(4*8))(R3)	\
	MOVV	R27, ((offset)+(5*8))(R3)	\
	MOVV	R28, ((offset)+(6*8))(R3)	\
	MOVV	R29, ((offset)+(7*8))(R3)	\
	MOVV	R30, ((offset)+(8*8))(R3)	\
	MOVV	R31, ((offset)+(9*8))(R3)

	MOVD	R16, 64(R1)
	MOVD	R17, 72(R1)
	MOVD	R18, 80(R1)
	MOVD	R19, 88(R1)
	MOVD	R20, 96(R1)
	MOVD	R21,104(R1)
	MOVD	R22, 112(R1)
	MOVD	R23, 120(R1)
	MOVD	R24, 128(R1)
	MOVD	R25, 136(R1)
	MOVD	R26, 144(R1)
	MOVD	R27, 152(R1)
	MOVD	R28, 160(R1)
	MOVD	R29, 168(R1)
	MOVD	g, 176(R1) // R30
	MOVD	R31, 184(R1)
	FMOVD	F14, 192(R1)
	FMOVD	F15, 200(R1)
	FMOVD	F16, 208(R1)
	FMOVD	F17, 216(R1)

	print("r21  ", hex(c.r21()), "\n")
	print("r22  ", hex(c.r22()), "\t")
	print("r23  ", hex(c.r23()), "\n")
	print("r24  ", hex(c.r24()), "\t")
	print("r25  ", hex(c.r25()), "\n")
	print("r26  ", hex(c.r26()), "\t")
	print("r27  ", hex(c.r27()), "\n")
	print("r28  ", hex(c.r28()), "\t")
	print("r29  ", hex(c.r29()), "\n")
	print("r30  ", hex(c.r30()), "\t")
	print("r31  ", hex(c.r31()), "\n")

Examples:

	ADD R19>>30, R10, R24     <=>    add x24, x10, x19, lsr #30
	ADDW R26->24, R21, R15    <=>    add w15, w21, w26, asr #24

Extended registers are written as <Rm>{.<extend>{<<<amount>}}.
<extend> can be UXTB, UXTH, UXTW, UXTX, SXTB, SXTH, SXTW or SXTX.

Examples:

	ADDS R19.UXTB<<4, R9, R26     <=>    adds x26, x9, w19, uxtb #4
	ADDSW R14.SXTX, R14, R6       <=>    adds w6, w14, w14, sxtx