define <2 x double> @uitofp_2i16_to_2f64(<8 x i16> %a) {
; SSE-LABEL: uitofp_2i16_to_2f64:
; SSE: # BB#0:
-; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,1,0,3]
-; SSE-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,5,5,6,7]
-; SSE-NEXT: pand {{.*}}(%rip), %xmm0
-; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
+; SSE-NEXT: pxor %xmm1, %xmm1
+; SSE-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; SSE-NEXT: cvtdq2pd %xmm0, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: uitofp_2i16_to_2f64:
; AVX: # BB#0:
-; AVX-NEXT: vpmovzxwq {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero
-; AVX-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
-; AVX-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
+; AVX-NEXT: vpmovzxwd {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero
; AVX-NEXT: vcvtdq2pd %xmm0, %xmm0
; AVX-NEXT: retq
%shuf = shufflevector <8 x i16> %a, <8 x i16> undef, <2 x i32> <i32 0, i32 1>
define <2 x double> @uitofp_2i8_to_2f64(<16 x i8> %a) {
; SSE-LABEL: uitofp_2i8_to_2f64:
; SSE: # BB#0:
-; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
-; SSE-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
-; SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0,0,1,1]
-; SSE-NEXT: pand {{.*}}(%rip), %xmm0
-; SSE-NEXT: pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
+; SSE-NEXT: pxor %xmm1, %xmm1
+; SSE-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; SSE-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; SSE-NEXT: cvtdq2pd %xmm0, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: uitofp_2i8_to_2f64:
; AVX: # BB#0:
-; AVX-NEXT: vpmovzxbq {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,zero,zero,zero,zero,xmm0[1],zero,zero,zero,zero,zero,zero,zero
-; AVX-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
-; AVX-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
+; AVX-NEXT: vpmovzxbd {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
; AVX-NEXT: vcvtdq2pd %xmm0, %xmm0
; AVX-NEXT: retq
%shuf = shufflevector <16 x i8> %a, <16 x i8> undef, <2 x i32> <i32 0, i32 1>
define <4 x double> @uitofp_4i32_to_4f64(<4 x i32> %a) {
; SSE-LABEL: uitofp_4i32_to_4f64:
; SSE: # BB#0:
+; SSE-NEXT: movdqa %xmm0, %xmm2
; SSE-NEXT: pxor %xmm1, %xmm1
-; SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm0[2,2,3,3]
; SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE-NEXT: movdqa {{.*#+}} xmm3 = [1127219200,1160773632,0,0]
-; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
+; SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm0[2,3,0,1]
; SSE-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1]
-; SSE-NEXT: movapd {{.*#+}} xmm4 = [4.503600e+15,1.934281e+25]
-; SSE-NEXT: subpd %xmm4, %xmm0
-; SSE-NEXT: pshufd {{.*#+}} xmm5 = xmm0[2,3,0,1]
-; SSE-NEXT: addpd %xmm5, %xmm0
-; SSE-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1]
-; SSE-NEXT: subpd %xmm4, %xmm1
-; SSE-NEXT: pshufd {{.*#+}} xmm5 = xmm1[2,3,0,1]
-; SSE-NEXT: addpd %xmm1, %xmm5
-; SSE-NEXT: unpcklpd {{.*#+}} xmm0 = xmm0[0],xmm5[0]
-; SSE-NEXT: pand {{.*}}(%rip), %xmm2
-; SSE-NEXT: pshufd {{.*#+}} xmm5 = xmm2[2,3,0,1]
+; SSE-NEXT: movapd {{.*#+}} xmm5 = [4.503600e+15,1.934281e+25]
+; SSE-NEXT: subpd %xmm5, %xmm0
+; SSE-NEXT: pshufd {{.*#+}} xmm6 = xmm0[2,3,0,1]
+; SSE-NEXT: addpd %xmm6, %xmm0
+; SSE-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
+; SSE-NEXT: subpd %xmm5, %xmm4
+; SSE-NEXT: pshufd {{.*#+}} xmm6 = xmm4[2,3,0,1]
+; SSE-NEXT: addpd %xmm4, %xmm6
+; SSE-NEXT: unpcklpd {{.*#+}} xmm0 = xmm0[0],xmm6[0]
+; SSE-NEXT: punpckhdq {{.*#+}} xmm2 = xmm2[2],xmm1[2],xmm2[3],xmm1[3]
+; SSE-NEXT: pshufd {{.*#+}} xmm4 = xmm2[2,3,0,1]
; SSE-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
-; SSE-NEXT: subpd %xmm4, %xmm2
+; SSE-NEXT: subpd %xmm5, %xmm2
; SSE-NEXT: pshufd {{.*#+}} xmm1 = xmm2[2,3,0,1]
; SSE-NEXT: addpd %xmm2, %xmm1
-; SSE-NEXT: punpckldq {{.*#+}} xmm5 = xmm5[0],xmm3[0],xmm5[1],xmm3[1]
-; SSE-NEXT: subpd %xmm4, %xmm5
-; SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm5[2,3,0,1]
-; SSE-NEXT: addpd %xmm5, %xmm2
+; SSE-NEXT: punpckldq {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
+; SSE-NEXT: subpd %xmm5, %xmm4
+; SSE-NEXT: pshufd {{.*#+}} xmm2 = xmm4[2,3,0,1]
+; SSE-NEXT: addpd %xmm4, %xmm2
; SSE-NEXT: unpcklpd {{.*#+}} xmm1 = xmm1[0],xmm2[0]
; SSE-NEXT: retq
;
; SSE-NEXT: movdqa %xmm0, %xmm2
; SSE-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
; SSE-NEXT: cvtdq2ps %xmm2, %xmm2
-; SSE-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4,4,5,5,6,6,7,7]
-; SSE-NEXT: pand {{.*}}(%rip), %xmm0
+; SSE-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
; SSE-NEXT: cvtdq2ps %xmm0, %xmm1
; SSE-NEXT: movaps %xmm2, %xmm0
; SSE-NEXT: retq
; AVX1-LABEL: uitofp_8i8_to_8f32:
; AVX1: # BB#0:
; AVX1-NEXT: vpmovzxbw {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
-; AVX1-NEXT: vpmovzxbd {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
; AVX1-NEXT: vpunpckhwd {{.*#+}} xmm1 = xmm1[4,4,5,5,6,6,7,7]
+; AVX1-NEXT: vmovdqa {{.*#+}} xmm2 = [255,0,0,0,255,0,0,0,255,0,0,0,255,0,0,0]
+; AVX1-NEXT: vpand %xmm2, %xmm1, %xmm1
+; AVX1-NEXT: vpmovzxbd {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
+; AVX1-NEXT: vpand %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX1-NEXT: vandps {{.*}}(%rip), %ymm0, %ymm0
; AVX1-NEXT: vcvtdq2ps %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: uitofp_8i8_to_8f32:
; AVX2: # BB#0:
; AVX2-NEXT: vpmovzxbd {{.*#+}} ymm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero,xmm0[4],zero,zero,zero,xmm0[5],zero,zero,zero,xmm0[6],zero,zero,zero,xmm0[7],zero,zero,zero
-; AVX2-NEXT: vpbroadcastd {{.*}}(%rip), %ymm1
-; AVX2-NEXT: vpand %ymm1, %ymm0, %ymm0
+; AVX2-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
; AVX2-NEXT: vcvtdq2ps %ymm0, %ymm0
; AVX2-NEXT: retq
%shuf = shufflevector <16 x i8> %a, <16 x i8> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>