MOVOU X3, y1in(16*1)
	MOVOU X4, z1in(16*0)
	MOVOU X5, z1in(16*1)

	MOVOU (16*0)(CX), X0
	MOVOU (16*1)(CX), X1
	MOVOU (16*2)(CX), X2
	MOVOU (16*3)(CX), X3
	MOVOU (16*4)(CX), X4
	MOVOU (16*5)(CX), X5

	MOVOU X0, x2in(16*0)
	MOVOU X1, x2in(16*1)
	MOVOU X2, y2in(16*0)
	MOVOU X3, y2in(16*1)
	MOVOU X4, z2in(16*0)
	MOVOU X5, z2in(16*1)
	// Store pointer to result

	CSEL	EQ, y2, acc2, y2
	CSEL	EQ, y3, acc3, y3
	// Store result
	STy(y2in)
	// Begin point add
	LDx(z1in)
	CALL	p256SqrInternal<>(SB)    // z1ˆ2
	STy(z1sqr)

	LDx(x2in)
	CALL	p256MulInternal<>(SB)    // x2 * z1ˆ2

	LDx(x1in)
	CALL	p256SubInternal<>(SB)    // h = u2 - u1
	STx(h)

	LDy(z1in)
	CALL	p256MulInternal<>(SB)    // z3 = h * z1