MULHDU  R9, R20, R25      // R25 = z1[i]
	ADD     $-1, R11          // R11 = z_len - 1
	ADDC    R4, R24
	ADDZE   R25, R4
	MOVDU   R24, 8(R10)       // z[i]
	CMP     R11, $0
	BEQ     done              // If R11 = 0, we are done

	MOVDU   8(R8), R20
	MULLD   R9, R20, R24
	MULHDU  R9, R20, R25
	ADD     $-1, R11
	ADDC    R4, R24
	ADDZE   R25, R4
	MOVDU   R24, 8(R10)
	CMP     R11, $0

	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)

 * are callee-save, so they must be saved explicitly, along with $r1 (LR).
 */
.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

	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) \

	print("r20  ", hex(c.r20()), "\t")
	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")

	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)
	MOVV R24, 184(R29)
	MOVV R25, 192(R29)
	MOVV RSB, 200(R29)
	MOVV HI, R1
	MOVV R1, 208(R29)
	MOVV LO, R1
	MOVV R1, 216(R29)
	#ifndef GOMIPS64_softfloat
	MOVV FCR31, R1
	MOVV R1, 224(R29)
	MOVD F0, 232(R29)
	MOVD F1, 240(R29)

	print("r20  ", hex(c.r20()), "\t")
	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")

	XOR	R21,R24,R21	// xor done R24
	MOVWZ	(R10)(R8),R25	// tab[4][crc>>24]
	RLDICL	$48,R7,$56,R24	// crc>>16&0xFF
	XOR	R21,R25,R21	// xor done R25
	ADD	$1024,R10,R10	// &tab[5]
	SLD	$2,R24,R24	// crc>>16&0xFF*4
	MOVWZ	(R10)(R24),R26	// tab[5][crc>>16&0xFF]
	XOR	R21,R26,R21	// xor done R26
	RLDICL	$56,R7,$56,R25	// crc>>8
	ADD	$1024,R10,R10	// &tab[6]
	SLD	$2,R25,R25	// crc>>8&FF*2
	MOVBZ   R7,R26          // crc&0xFF

	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)
	MOVV R25, 168(R3)
	MOVV R26, 176(R3)
	MOVV R27, 184(R3)
	MOVV R28, 192(R3)
	MOVV R29, 200(R3)
	MOVV R31, 208(R3)
	MOVD F0, 216(R3)
	MOVD F1, 224(R3)
	MOVD F2, 232(R3)
	MOVD F3, 240(R3)
	MOVD F4, 248(R3)

	print("r20  ", hex(c.r20()), "\t")
	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")