*/
.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
	fst.d	$f27, $r3, 112

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

#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)

#define SAVE_F24_TO_F31(offset)	\

	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)
	FMOVD	F18, 224(R1)

package codegen

type T [2]*int // contain pointer, not SSA-able (so locals are not registerized)

var p1, p2, p3 T

func F() {
	// 3735936685 is 0xdeaddead. On ARM64 R27 is REGTMP.
	// clobber x, y at entry. not clobber z (stack object).
	// amd64:`MOVL\t\$3735936685, command-line-arguments\.x`, `MOVL\t\$3735936685, command-line-arguments\.y`, -`MOVL\t\$3735936685, command-line-arguments\.z`

	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)
	MOVD F5, 256(R3)
	MOVD F6, 264(R3)

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

	print("r22     ", hex(c.r22()), "\n")
	print("r23     ", hex(c.r23()), "\n")
	print("r24     ", hex(c.r24()), "\n")
	print("r25     ", hex(c.r25()), "\n")
	print("r26     ", hex(c.r26()), "\n")
	print("r27     ", hex(c.r27()), "\n")
	print("r28     ", hex(c.r28()), "\n")
	print("r29     ", hex(c.r29()), "\n")
	print("lr      ", hex(c.lr()), "\n")
	print("sp      ", hex(c.sp()), "\n")
	print("pc      ", hex(c.pc()), "\n")

	// R20: ptr to source memory
	// R21: ptr to destination memory
	// R26, R27 (aka REGTMP): scratch space
	// R20 and R21 are updated as a side effect
	fmt.Fprintln(w, "TEXT runtime·duffcopy<ABIInternal>(SB), NOSPLIT|NOFRAME, $0-0")

	for i := 0; i < 64; i++ {
		fmt.Fprintln(w, "\tLDP.P\t16(R20), (R26, R27)")
		fmt.Fprintln(w, "\tSTP.P\t(R26, R27), 16(R21)")
		fmt.Fprintln(w)
	}
	fmt.Fprintln(w, "\tRET")
}

	MOVD	R21, (offset+8*7)(R1)  \
	MOVD	R22, (offset+8*8)(R1)  \
	MOVD	R23, (offset+8*9)(R1)  \
	MOVD	R24, (offset+8*10)(R1) \
	MOVD	R25, (offset+8*11)(R1) \
	MOVD	R26, (offset+8*12)(R1) \
	MOVD	R27, (offset+8*13)(R1) \
	MOVD	R28, (offset+8*14)(R1) \
	MOVD	R29, (offset+8*15)(R1) \
	MOVD	g,   (offset+8*16)(R1) \
	MOVD	R31, (offset+8*17)(R1)

#define RESTORE_GPR(offset)            \
	MOVD	(offset+8*0)(R1), R14  \