ADD	X9, X22, X9	// z_hi[0] = x[0] * y + z[0]
	ADD	X21, X29, X10	// z_lo[0] = x[0] * y + z[0] + c
	SLTU	X21, X10, X22
	ADD	X9, X22, X29	// next c

	MULHU	X11, X6, X12	// z_hi[1] = x[1] * y
	MUL	X11, X6, X11	// z_lo[1] = x[1] * y
	ADD	X11, X13, X21	// z_lo[1] = x[1] * y + z[1]
	SLTU	X11, X21, X22
	ADD	X12, X22, X12	// z_hi[1] = x[1] * y + z[1]
	ADD	X21, X29, X13	// z_lo[1] = x[1] * y + z[1] + c
	SLTU	X21, X13, X22

package main

func main() {
	var x00, x01, x02, x03, x04, x05, x06, x07, x08, x09 int
	var x10, x11, x12, x13, x14, x15, x16, x17, x18, x19 int
	var x20, x21, x22, x23, x24, x25, x26, x27, x28, x29 int
	var x30, x31, x32 int

	_ = x00
	_ = x01
	_ = x02
	_ = x03
	_ = x04
	_ = x05
	_ = x06
	_ = x07
	_ = x08
	_ = x09

	_ = x10
	_ = x11
	_ = x12
	_ = x13
	_ = x14

#define MSGSCHEDULE0(index) \
	MOVBU	((index*8)+0)(X29), X5; \
	MOVBU	((index*8)+1)(X29), X6; \
	MOVBU	((index*8)+2)(X29), X7; \
	MOVBU	((index*8)+3)(X29), X8; \
	SLL	$56, X5; \
	SLL	$48, X6; \
	OR	X5, X6, X5; \
	SLL	$40, X7; \
	OR	X5, X7, X5; \
	SLL	$32, X8; \
	OR	X5, X8, X5; \
	MOVBU	((index*8)+4)(X29), X9; \
	MOVBU	((index*8)+5)(X29), X6; \
	MOVBU	((index*8)+6)(X29), X7; \
	MOVBU	((index*8)+7)(X29), X8; \

 * Called from standard ARM EABI, where x19-x29 are callee-save, so they
 * must be saved explicitly, along with x30 (LR).
 */
.globl EXT(crosscall1)
EXT(crosscall1):
	.cfi_startproc
	stp x29, x30, [sp, #-96]!
	.cfi_def_cfa_offset 96
	.cfi_offset 29, -96
	.cfi_offset 30, -88
	mov x29, sp
	.cfi_def_cfa_register 29
	stp x19, x20, [sp, #80]
	.cfi_offset 19, -16

	VADDPD X30, X11, X28        // 6201a50858e6
	VADDPD X12, X29, X28        // 6241950058e4
	VADDPD X30, X29, X28        // 6201950058e6
	VADDPD (AX), X29, X0        // 62f195005800
	VADDPD (AX), X1, X28        // 6261f5085820
	VADDPD (AX), X29, X28       // 626195005820
	VADDPD (AX), X29, X10       // 627195005810
	VADDPD (AX), X10, X28       // 6261ad085820
	VADDPD (CX)(AX*1), X29, X0  // 62f19500580401

	MOVBU	6(X10), X25
	MOVBU	7(X10), X29
	MOVBU	0(X12), X9
	MOVBU	1(X12), X16
	MOVBU	2(X12), X18
	MOVBU	3(X12), X20
	MOVBU	4(X12), X22
	MOVBU	5(X12), X24
	MOVBU	6(X12), X28
	MOVBU	7(X12), X30
	BNE	X8, X9, cmp1a
	BNE	X15, X16, cmp1b
	BNE	X17, X18, cmp1c
	BNE	X19, X20, cmp1d
	BNE	X21, X22, cmp1e
	BNE	X23, X24, cmp1f
	BNE	X25, X28, cmp1g
	BNE	X29, X30, cmp1h
	ADD	$8, X10
	ADD	$8, X12

	CPOP	X22, X23				// 931b2b60
	CPOPW	X23, X24				// 1b9c2b60
	CTZ	X24, X25				// 931c1c60
	CTZW	X25, X26				// 1b9d1c60
	MAX	X26, X28, X29				// b36eae0b
	MAX	X26, X28				// 336eae0b
	MAXU	X28, X29, X30				// 33ffce0b
	MAXU	X28, X29				// b3fece0b
	MIN	X29, X30, X5				// b342df0b
	MIN	X29, X30				// 334fdf0b
	MINU	X30, X5, X6				// 33d3e20b
	MINU	X30, X5					// b3d2e20b
	ORN	X6, X7, X8				// 33e46340

	MOV X17, 104(X2)
	MOV X18, 112(X2)
	MOV X19, 120(X2)
	MOV X20, 128(X2)
	MOV X21, 136(X2)
	MOV X22, 144(X2)
	MOV X23, 152(X2)
	MOV X24, 160(X2)
	MOV X25, 168(X2)
	MOV X26, 176(X2)
	MOV X28, 184(X2)
	MOV X29, 192(X2)
	MOV X30, 200(X2)
	MOVD F0, 208(X2)
	MOVD F1, 216(X2)
	MOVD F2, 224(X2)
	MOVD F3, 232(X2)
	MOVD F4, 240(X2)
	MOVD F5, 248(X2)
	MOVD F6, 256(X2)
	MOVD F7, 264(X2)
	MOVD F8, 272(X2)

	var x26 uint64
	var x27 uint64
	x27, x26 = bits.Mul64(x20, 0xffffffff00000000)
	var x28 uint64
	var x29 uint64
	x28, x29 = bits.Add64(x27, x24, uint64(0x0))
	var x30 uint64
	var x31 uint64
	x30, x31 = bits.Add64(x25, x22, uint64(p224Uint1(x29)))
	x32 := (uint64(p224Uint1(x31)) + x23)
	var x34 uint64
	_, x34 = bits.Add64(x11, x20, uint64(0x0))
	var x35 uint64
	var x36 uint64

	var x25 uint64
	x25, x24 = bits.Mul64(x20, 0x14def9dea2f79cd6)
	var x26 uint64
	var x27 uint64
	x27, x26 = bits.Mul64(x20, 0x5812631a5cf5d3ed)
	var x28 uint64
	var x29 uint64
	x28, x29 = bits.Add64(x27, x24, uint64(0x0))
	x30 := (uint64(fiatScalarUint1(x29)) + x25)
	var x32 uint64
	_, x32 = bits.Add64(x11, x26, uint64(0x0))
	var x33 uint64
	var x34 uint64
	x33, x34 = bits.Add64(x13, x28, uint64(fiatScalarUint1(x32)))