VSPLTW	$3, IN0, KEY        // vspltw 3,1,3
	VSLDOI	$12, ZERO, IN1, TMP // vsldoi 6,0,2,12
	VSBOX	KEY, KEY            // vsbox 3,3

	VXOR	IN1, TMP, IN1       // vxor 2,2,6
	VSLDOI	$12, ZERO, TMP, TMP // vsldoi 6,0,6,12
	VXOR	IN1, TMP, IN1       // vxor 2,2,6
	VSLDOI	$12, ZERO, TMP, TMP // vsldoi 6,0,6,12
	VXOR	IN1, TMP, IN1       // vxor 2,2,6

	VXOR	IN1, KEY, IN1 // vxor 2,2,3
	JMP	loop256       // b .Loop256

done:

// If zero is 0, sets res = in2. If sel is 0, sets res = in1.
// If sign is not 0, sets res = in1 + -in2. Otherwise, sets res = in1 + in2
//
//go:noescape
func p256PointAddAffineAsm(res, in1 *P256Point, in2 *p256AffinePoint, sign, sel, zero int)

// Point addition. Sets res = in1 + in2. Returns one if the two input points
// were equal and zero otherwise. If in1 or in2 are the point at infinity, res