sel, _ = boothW5(uint(wvalue))

	p256Select(p, &precomp, sel)
	zero := sel

	for index > 4 {
		index -= 5
		p256PointDoubleAsm(p, p)
		p256PointDoubleAsm(p, p)
		p256PointDoubleAsm(p, p)
		p256PointDoubleAsm(p, p)
		p256PointDoubleAsm(p, p)

		if index < 192 {
			wvalue = ((scalar[index/64] >> (index % 64)) + (scalar[index/64+1] << (64 - (index % 64)))) & 0x3f
		} else {

#define s(off)	(32*0 + 8 + off)(RSP)
#define m(off)	(32*1 + 8 + off)(RSP)
#define zsqr(off) (32*2 + 8 + off)(RSP)
#define tmp(off)  (32*3 + 8 + off)(RSP)

//func p256PointDoubleAsm(res, in *P256Point)
TEXT ·p256PointDoubleAsm(SB),NOSPLIT,$136-16
	MOVD	res+0(FP), res_ptr
	MOVD	in+8(FP), a_ptr

	MOVD	p256const0<>(SB), const0
	MOVD	p256const1<>(SB), const1

	// Begin point double

#define s(off)	(32*3 + off)(SP)
#define m(off)	(32*4 + off)(SP)
#define zsqr(off) (32*5 + off)(SP)
#define tmp(off)  (32*6 + off)(SP)
#define rptr	  (32*7)(SP)

//func p256PointDoubleAsm(res, in *P256Point)
TEXT ·p256PointDoubleAsm(SB),NOSPLIT,$256-16
	// Move input to stack in order to free registers
	MOVQ res+0(FP), AX
	MOVQ in+8(FP), BX

	MOVOU (16*0)(BX), X0
	MOVOU (16*1)(BX), X1

 *       Y3 = half*Y3
 *       X3 = T2²
 *       T1 = 2*T3
 *       X3 = X3-T1
 *       T1 = T3-X3
 *       T1 = T1*T2
 *       Y3 = T1-Y3
 */
// p256PointDoubleAsm(res, in1 *p256Point)
TEXT ·p256PointDoubleAsm(SB), NOSPLIT, $0-16
	MOVD res+0(FP), P3ptr
	MOVD in+8(FP), P1ptr

	MOVD $p256mul<>+0x00(SB), CPOOL

	MOVD $16, R16
	MOVD $32, R17
	MOVD $48, R18
	MOVD $64, R19

#undef X2H
#undef Z2L
#undef Z2H
#undef X3L
#undef X3H
#undef Y3L
#undef Y3H
#undef Z3L
#undef Z3H

#undef ZER
#undef SEL1
#undef CAR1
#undef CAR2

// func p256PointDoubleAsm(res, in *P256Point)
// https://www.hyperelliptic.org/EFD/g1p/auto-shortw-jacobian.html#doubling-dbl-2007-bl
// https://www.hyperelliptic.org/EFD/g1p/auto-shortw.html