-; SSE2-NEXT: pxor %xmm2, %xmm2
-; SSE2-NEXT: movdqa %xmm0, %xmm3
-; SSE2-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1],xmm3[2],xmm2[2],xmm3[3],xmm2[3],xmm3[4],xmm2[4],xmm3[5],xmm2[5],xmm3[6],xmm2[6],xmm3[7],xmm2[7]
-; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[2,3,2,3]
-; SSE2-NEXT: pshuflw {{.*#+}} xmm4 = xmm3[0,1,1,3,4,5,6,7]
-; SSE2-NEXT: movdqa %xmm0, %xmm3
-; SSE2-NEXT: punpckhbw {{.*#+}} xmm3 = xmm3[8],xmm2[8],xmm3[9],xmm2[9],xmm3[10],xmm2[10],xmm3[11],xmm2[11],xmm3[12],xmm2[12],xmm3[13],xmm2[13],xmm3[14],xmm2[14],xmm3[15],xmm2[15]
-; SSE2-NEXT: pshufhw {{.*#+}} xmm3 = xmm3[0,1,2,3,7,5,6,7]
-; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[2,1,2,3]
-; SSE2-NEXT: pshuflw {{.*#+}} xmm3 = xmm3[0,3,1,0,4,5,6,7]
-; SSE2-NEXT: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm3[0]
-; SSE2-NEXT: movdqa %xmm1, %xmm3
-; SSE2-NEXT: punpckhbw {{.*#+}} xmm3 = xmm3[8],xmm2[8],xmm3[9],xmm2[9],xmm3[10],xmm2[10],xmm3[11],xmm2[11],xmm3[12],xmm2[12],xmm3[13],xmm2[13],xmm3[14],xmm2[14],xmm3[15],xmm2[15]
-; SSE2-NEXT: movdqa %xmm1, %xmm5
-; SSE2-NEXT: punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm2[0],xmm5[1],xmm2[1],xmm5[2],xmm2[2],xmm5[3],xmm2[3],xmm5[4],xmm2[4],xmm5[5],xmm2[5],xmm5[6],xmm2[6],xmm5[7],xmm2[7]
-; SSE2-NEXT: punpcklwd {{.*#+}} xmm5 = xmm5[0],xmm3[0],xmm5[1],xmm3[1],xmm5[2],xmm3[2],xmm5[3],xmm3[3]
-; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm5[3,1,2,1]
-; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm2[2,0,2,3,4,5,6,7]
-; SSE2-NEXT: pshufhw {{.*#+}} xmm2 = xmm2[0,1,2,3,7,5,6,7]
-; SSE2-NEXT: movdqa %xmm4, %xmm3
-; SSE2-NEXT: shufps {{.*#+}} xmm3 = xmm3[1,0],xmm2[0,0]
-; SSE2-NEXT: shufps {{.*#+}} xmm3 = xmm3[2,0],xmm2[2,3]
-; SSE2-NEXT: punpckhwd {{.*#+}} xmm4 = xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7]
-; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm4[2,1,2,3,4,5,6,7]
-; SSE2-NEXT: pshufhw {{.*#+}} xmm2 = xmm2[0,1,2,3,4,6,6,7]
-; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
-; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm2[1,0,2,3,4,5,6,7]
-; SSE2-NEXT: punpcklqdq {{.*#+}} xmm3 = xmm3[0],xmm2[0]
-; SSE2-NEXT: packuswb %xmm0, %xmm3
-; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
-; SSE2-NEXT: pand %xmm2, %xmm1
-; SSE2-NEXT: pand %xmm2, %xmm0
-; SSE2-NEXT: movdqa %xmm0, %xmm2
-; SSE2-NEXT: shufps {{.*#+}} xmm2 = xmm2[1,0],xmm1[0,0]
-; SSE2-NEXT: shufps {{.*#+}} xmm2 = xmm2[2,0],xmm1[2,3]
-; SSE2-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
-; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm1[0,3,2,3,4,5,6,7]
-; SSE2-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,6,6,7]
-; SSE2-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
-; SSE2-NEXT: punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm0[0]
-; SSE2-NEXT: packuswb %xmm0, %xmm2
-; SSE2-NEXT: punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3],xmm2[4],xmm3[4],xmm2[5],xmm3[5],xmm2[6],xmm3[6],xmm2[7],xmm3[7]
-; SSE2-NEXT: movdqa %xmm2, %xmm0