movdqu xmm1, [rdi] 	; xmm1 = | a0 b0 g0 r0 | a1 b1 g1 r1 | a2 b2 g2 r2 | a3 b3 g3 r3
	movdqu xmm2, [rdi] 	; xmm2 = | a0 b0 g0 r0 | a1 b1 g1 r1 | a2 b2 g2 r2 | a3 b3 g3 r3
	movdqu xmm3, [rdi] 	; xmm3 = | a0 b0 g0 r0 | a1 b1 g1 r1 | a2 b2 g2 r2 | a3 b3 g3 r3
	movdqu xmm13, [rdi] ;xmm13 = | a0 b0 g0 r0 | a1 b1 g1 r1 | a2 b2 g2 r2 | a3 b3 g3 r3 ;esto me lo guardo para despues

	pxor xmm10, xmm10

	movdqu xmm0, [mascaraA]
	pblendvb xmm13, xmm10, xmm0 ; xmm13 = | a0 | a1 | a2 | a3

	movdqu xmm0, [mascaraB]
	pblendvb xmm3, xmm10, xmm0 ; xmm3 = | b0 | b1 | b2 | b3

	movdqu xmm0, [mascaraG]
	pblendvb xmm2, xmm10, xmm0; xmm2 = | g0 | g1 | g2 | g3

	movdqu xmm0, [mascaraR]
	pblendvb xmm1, xmm10, xmm0 ; xmm1 = | r0 | r1 | r2 | r3

	cvtdq2ps xmm1, xmm1
	cvtdq2ps xmm2, xmm2 ; los paso a floats
	cvtdq2ps xmm3, xmm3

	movdqu xmm4, [mascara66]
	mulps xmm4, xmm1 ; xmm4 = | r0*66 | r1*66 | r2*66 | r3*66

	movdqu xmm5, [mascara38]
	mulps xmm5, xmm1 ; xmm5 = | r0*-38 | r1*-38 | r2*-38 | r3*-38

	movdqu xmm6, [mascara112]
	mulps xmm6, xmm1 ; xmm6 = | r0*112 | r1*112 | r2*112 | r3*112

	movdqu xmm7, [mascara129]
	mulps xmm7, xmm2 ; xmm7 = | g0*129 | g1*129 | g2*129 | g3*129

	movdqu xmm8, [mascara74]
	mulps xmm8, xmm2 ; xmm8 = | g0*-74 | g1*-74 | g2*-74 | g3*-74