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