ret <64 x i16> %result
}
-define <64 x i8> @interleave2x32(<32 x i8> %a, <32 x i8> %b) {
-; SSE-LABEL: interleave2x32:
+define <8 x double> @interleave2x4f64(<4 x double> %a, <4 x double> %b) {
+; SSE-LABEL: interleave2x4f64:
+; SSE: # %bb.0:
+; SSE-NEXT: movaps %xmm0, %xmm4
+; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm2[0]
+; SSE-NEXT: unpckhpd {{.*#+}} xmm4 = xmm4[1],xmm2[1]
+; SSE-NEXT: movaps %xmm1, %xmm2
+; SSE-NEXT: movlhps {{.*#+}} xmm2 = xmm2[0],xmm3[0]
+; SSE-NEXT: movhlps {{.*#+}} xmm3 = xmm1[1],xmm3[1]
+; SSE-NEXT: movaps %xmm4, %xmm1
+; SSE-NEXT: retq
+;
+; AVX1-LABEL: interleave2x4f64:
+; AVX1: # %bb.0:
+; AVX1-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm1[2,3,2,3]
+; AVX1-NEXT: vperm2f128 {{.*#+}} ymm3 = ymm0[2,3,2,3]
+; AVX1-NEXT: vshufpd {{.*#+}} ymm2 = ymm3[0],ymm2[0],ymm3[3],ymm2[3]
+; AVX1-NEXT: vunpckhpd {{.*#+}} xmm3 = xmm0[1],xmm1[1]
+; AVX1-NEXT: vunpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm0, %ymm0
+; AVX1-NEXT: vmovapd %ymm2, %ymm1
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: interleave2x4f64:
+; AVX2: # %bb.0:
+; AVX2-NEXT: vpermpd {{.*#+}} ymm2 = ymm1[0,0,2,1]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm3 = ymm0[0,1,1,3]
+; AVX2-NEXT: vblendpd {{.*#+}} ymm2 = ymm3[0],ymm2[1],ymm3[2],ymm2[3]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[2,1,2,3]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[2,1,2,3]
+; AVX2-NEXT: vshufpd {{.*#+}} ymm1 = ymm0[0],ymm1[0],ymm0[3],ymm1[3]
+; AVX2-NEXT: vmovapd %ymm2, %ymm0
+; AVX2-NEXT: retq
+ %result = shufflevector <4 x double> %a, <4 x double> %b, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
+ ret <8 x double> %result
+}
+
+define <8 x i64> @interleave2x4i64(<4 x i64> %a, <4 x i64> %b) {
+; SSE-LABEL: interleave2x4i64:
+; SSE: # %bb.0:
+; SSE-NEXT: movaps %xmm1, %xmm4
+; SSE-NEXT: movaps %xmm0, %xmm1
+; SSE-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm2[0]
+; SSE-NEXT: unpckhpd {{.*#+}} xmm1 = xmm1[1],xmm2[1]
+; SSE-NEXT: movaps %xmm4, %xmm2
+; SSE-NEXT: movlhps {{.*#+}} xmm2 = xmm2[0],xmm3[0]
+; SSE-NEXT: unpckhpd {{.*#+}} xmm4 = xmm4[1],xmm3[1]
+; SSE-NEXT: movaps %xmm4, %xmm3
+; SSE-NEXT: retq
+;
+; AVX1-LABEL: interleave2x4i64:
+; AVX1: # %bb.0:
+; AVX1-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm1[2,3,2,3]
+; AVX1-NEXT: vperm2f128 {{.*#+}} ymm3 = ymm0[2,3,2,3]
+; AVX1-NEXT: vshufpd {{.*#+}} ymm2 = ymm3[0],ymm2[0],ymm3[3],ymm2[3]
+; AVX1-NEXT: vunpckhpd {{.*#+}} xmm3 = xmm0[1],xmm1[1]
+; AVX1-NEXT: vunpcklpd {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm0, %ymm0
+; AVX1-NEXT: vmovapd %ymm2, %ymm1
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: interleave2x4i64:
+; AVX2: # %bb.0:
+; AVX2-NEXT: vpermpd {{.*#+}} ymm2 = ymm1[0,0,2,1]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm3 = ymm0[0,1,1,3]
+; AVX2-NEXT: vblendps {{.*#+}} ymm2 = ymm3[0,1],ymm2[2,3],ymm3[4,5],ymm2[6,7]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[0,2,2,3]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[2,1,3,3]
+; AVX2-NEXT: vblendps {{.*#+}} ymm1 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
+; AVX2-NEXT: vmovaps %ymm2, %ymm0
+; AVX2-NEXT: retq
+ %result = shufflevector <4 x i64> %a, <4 x i64> %b, <8 x i32> <i32 0, i32 4, i32 1, i32 5, i32 2, i32 6, i32 3, i32 7>
+ ret <8 x i64> %result
+}
+
+define <16 x float> @interleave2x8f32(<8 x float> %a, <8 x float> %b) {
+; SSE-LABEL: interleave2x8f32:
+; SSE: # %bb.0:
+; SSE-NEXT: movaps %xmm1, %xmm4
+; SSE-NEXT: movaps %xmm0, %xmm1
+; SSE-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
+; SSE-NEXT: unpckhps {{.*#+}} xmm1 = xmm1[2],xmm2[2],xmm1[3],xmm2[3]
+; SSE-NEXT: movaps %xmm4, %xmm2
+; SSE-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
+; SSE-NEXT: unpckhps {{.*#+}} xmm4 = xmm4[2],xmm3[2],xmm4[3],xmm3[3]
+; SSE-NEXT: movaps %xmm4, %xmm3
+; SSE-NEXT: retq
+;
+; AVX1-LABEL: interleave2x8f32:
+; AVX1: # %bb.0:
+; AVX1-NEXT: vunpckhps {{.*#+}} xmm2 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX1-NEXT: vunpcklps {{.*#+}} xmm3 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm3, %ymm2
+; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
+; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT: vunpckhps {{.*#+}} xmm3 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX1-NEXT: vunpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm0, %ymm1
+; AVX1-NEXT: vmovaps %ymm2, %ymm0
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: interleave2x8f32:
+; AVX2: # %bb.0:
+; AVX2-NEXT: vunpckhps {{.*#+}} xmm2 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX2-NEXT: vunpcklps {{.*#+}} xmm3 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX2-NEXT: vinsertf128 $1, %xmm2, %ymm3, %ymm2
+; AVX2-NEXT: vextractf128 $1, %ymm1, %xmm1
+; AVX2-NEXT: vextractf128 $1, %ymm0, %xmm0
+; AVX2-NEXT: vunpckhps {{.*#+}} xmm3 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX2-NEXT: vunpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX2-NEXT: vinsertf128 $1, %xmm3, %ymm0, %ymm1
+; AVX2-NEXT: vmovaps %ymm2, %ymm0
+; AVX2-NEXT: retq
+ %result = shufflevector <8 x float> %a, <8 x float> %b, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
+ ret <16 x float> %result
+}
+
+define <16 x i32> @interleave2x8i32(<8 x i32> %a, <8 x i32> %b) {
+; SSE-LABEL: interleave2x8i32:
+; SSE: # %bb.0:
+; SSE-NEXT: movaps %xmm1, %xmm4
+; SSE-NEXT: movaps %xmm0, %xmm1
+; SSE-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
+; SSE-NEXT: unpckhps {{.*#+}} xmm1 = xmm1[2],xmm2[2],xmm1[3],xmm2[3]
+; SSE-NEXT: movaps %xmm4, %xmm2
+; SSE-NEXT: unpcklps {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1]
+; SSE-NEXT: unpckhps {{.*#+}} xmm4 = xmm4[2],xmm3[2],xmm4[3],xmm3[3]
+; SSE-NEXT: movaps %xmm4, %xmm3
+; SSE-NEXT: retq
+;
+; AVX1-LABEL: interleave2x8i32:
+; AVX1: # %bb.0:
+; AVX1-NEXT: vunpckhps {{.*#+}} xmm2 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX1-NEXT: vunpcklps {{.*#+}} xmm3 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm3, %ymm2
+; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
+; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT: vunpckhps {{.*#+}} xmm3 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX1-NEXT: vunpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm0, %ymm1
+; AVX1-NEXT: vmovaps %ymm2, %ymm0
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: interleave2x8i32:
+; AVX2: # %bb.0:
+; AVX2-NEXT: vunpckhps {{.*#+}} xmm2 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX2-NEXT: vunpcklps {{.*#+}} xmm3 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX2-NEXT: vinsertf128 $1, %xmm2, %ymm3, %ymm2
+; AVX2-NEXT: vextractf128 $1, %ymm1, %xmm1
+; AVX2-NEXT: vextractf128 $1, %ymm0, %xmm0
+; AVX2-NEXT: vunpckhps {{.*#+}} xmm3 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX2-NEXT: vunpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX2-NEXT: vinsertf128 $1, %xmm3, %ymm0, %ymm1
+; AVX2-NEXT: vmovaps %ymm2, %ymm0
+; AVX2-NEXT: retq
+ %result = shufflevector <8 x i32> %a, <8 x i32> %b, <16 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
+ ret <16 x i32> %result
+}
+
+define <32 x i16> @interleave2x16i16(<16 x i16> %a, <16 x i16> %b) {
+; SSE-LABEL: interleave2x16i16:
+; SSE: # %bb.0:
+; SSE-NEXT: movdqa %xmm1, %xmm4
+; SSE-NEXT: movdqa %xmm0, %xmm1
+; SSE-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
+; SSE-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
+; SSE-NEXT: movdqa %xmm4, %xmm2
+; SSE-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3]
+; SSE-NEXT: punpckhwd {{.*#+}} xmm4 = xmm4[4],xmm3[4],xmm4[5],xmm3[5],xmm4[6],xmm3[6],xmm4[7],xmm3[7]
+; SSE-NEXT: movdqa %xmm4, %xmm3
+; SSE-NEXT: retq
+;
+; AVX1-LABEL: interleave2x16i16:
+; AVX1: # %bb.0:
+; AVX1-NEXT: vpunpckhwd {{.*#+}} xmm2 = xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm3 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm3, %ymm2
+; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
+; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT: vpunpckhwd {{.*#+}} xmm3 = xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm0, %ymm1
+; AVX1-NEXT: vmovaps %ymm2, %ymm0
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: interleave2x16i16:
+; AVX2: # %bb.0:
+; AVX2-NEXT: vpunpckhwd {{.*#+}} xmm2 = xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm3 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX2-NEXT: vinserti128 $1, %xmm2, %ymm3, %ymm2
+; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm1
+; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm0
+; AVX2-NEXT: vpunpckhwd {{.*#+}} xmm3 = xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX2-NEXT: vinserti128 $1, %xmm3, %ymm0, %ymm1
+; AVX2-NEXT: vmovdqa %ymm2, %ymm0
+; AVX2-NEXT: retq
+ %result = shufflevector <16 x i16> %a, <16 x i16> %b, <32 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23, i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>
+ ret <32 x i16> %result
+}
+
+define <64 x i16> @interleave2x32i16(<32 x i16> %a, <32 x i16> %b) {
+; SSE-LABEL: interleave2x32i16:
+; SSE: # %bb.0:
+; SSE-NEXT: movq %rdi, %rax
+; SSE-NEXT: movdqa %xmm0, %xmm8
+; SSE-NEXT: punpcklwd {{.*#+}} xmm8 = xmm8[0],xmm4[0],xmm8[1],xmm4[1],xmm8[2],xmm4[2],xmm8[3],xmm4[3]
+; SSE-NEXT: punpckhwd {{.*#+}} xmm0 = xmm0[4],xmm4[4],xmm0[5],xmm4[5],xmm0[6],xmm4[6],xmm0[7],xmm4[7]
+; SSE-NEXT: movdqa %xmm1, %xmm4
+; SSE-NEXT: punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1],xmm4[2],xmm5[2],xmm4[3],xmm5[3]
+; SSE-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm5[4],xmm1[5],xmm5[5],xmm1[6],xmm5[6],xmm1[7],xmm5[7]
+; SSE-NEXT: movdqa %xmm2, %xmm5
+; SSE-NEXT: punpcklwd {{.*#+}} xmm5 = xmm5[0],xmm6[0],xmm5[1],xmm6[1],xmm5[2],xmm6[2],xmm5[3],xmm6[3]
+; SSE-NEXT: punpckhwd {{.*#+}} xmm2 = xmm2[4],xmm6[4],xmm2[5],xmm6[5],xmm2[6],xmm6[6],xmm2[7],xmm6[7]
+; SSE-NEXT: movdqa %xmm3, %xmm6
+; SSE-NEXT: punpcklwd {{.*#+}} xmm6 = xmm6[0],xmm7[0],xmm6[1],xmm7[1],xmm6[2],xmm7[2],xmm6[3],xmm7[3]
+; SSE-NEXT: punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm7[4],xmm3[5],xmm7[5],xmm3[6],xmm7[6],xmm3[7],xmm7[7]
+; SSE-NEXT: movdqa %xmm3, 112(%rdi)
+; SSE-NEXT: movdqa %xmm6, 96(%rdi)
+; SSE-NEXT: movdqa %xmm2, 80(%rdi)
+; SSE-NEXT: movdqa %xmm5, 64(%rdi)
+; SSE-NEXT: movdqa %xmm1, 48(%rdi)
+; SSE-NEXT: movdqa %xmm4, 32(%rdi)
+; SSE-NEXT: movdqa %xmm0, 16(%rdi)
+; SSE-NEXT: movdqa %xmm8, (%rdi)
+; SSE-NEXT: retq
+;
+; AVX1-LABEL: interleave2x32i16:
+; AVX1: # %bb.0:
+; AVX1-NEXT: vpunpckhwd {{.*#+}} xmm4 = xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
+; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm5 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
+; AVX1-NEXT: vinsertf128 $1, %xmm4, %ymm5, %ymm4
+; AVX1-NEXT: vextractf128 $1, %ymm2, %xmm2
+; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT: vpunpckhwd {{.*#+}} xmm5 = xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
+; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
+; AVX1-NEXT: vinsertf128 $1, %xmm5, %ymm0, %ymm5
+; AVX1-NEXT: vpunpckhwd {{.*#+}} xmm0 = xmm1[4],xmm3[4],xmm1[5],xmm3[5],xmm1[6],xmm3[6],xmm1[7],xmm3[7]
+; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm2 = xmm1[0],xmm3[0],xmm1[1],xmm3[1],xmm1[2],xmm3[2],xmm1[3],xmm3[3]
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm2, %ymm2
+; AVX1-NEXT: vextractf128 $1, %ymm3, %xmm0
+; AVX1-NEXT: vextractf128 $1, %ymm1, %xmm1
+; AVX1-NEXT: vpunpckhwd {{.*#+}} xmm3 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
+; AVX1-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
+; AVX1-NEXT: vinsertf128 $1, %xmm3, %ymm0, %ymm3
+; AVX1-NEXT: vmovaps %ymm4, %ymm0
+; AVX1-NEXT: vmovaps %ymm5, %ymm1
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: interleave2x32i16:
+; AVX2: # %bb.0:
+; AVX2-NEXT: vpunpckhwd {{.*#+}} xmm4 = xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
+; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm5 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
+; AVX2-NEXT: vinserti128 $1, %xmm4, %ymm5, %ymm4
+; AVX2-NEXT: vextracti128 $1, %ymm2, %xmm2
+; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm0
+; AVX2-NEXT: vpunpckhwd {{.*#+}} xmm5 = xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
+; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
+; AVX2-NEXT: vinserti128 $1, %xmm5, %ymm0, %ymm5
+; AVX2-NEXT: vpunpckhwd {{.*#+}} xmm0 = xmm1[4],xmm3[4],xmm1[5],xmm3[5],xmm1[6],xmm3[6],xmm1[7],xmm3[7]
+; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm2 = xmm1[0],xmm3[0],xmm1[1],xmm3[1],xmm1[2],xmm3[2],xmm1[3],xmm3[3]
+; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm2, %ymm2
+; AVX2-NEXT: vextracti128 $1, %ymm3, %xmm0
+; AVX2-NEXT: vextracti128 $1, %ymm1, %xmm1
+; AVX2-NEXT: vpunpckhwd {{.*#+}} xmm3 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
+; AVX2-NEXT: vpunpcklwd {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
+; AVX2-NEXT: vinserti128 $1, %xmm3, %ymm0, %ymm3
+; AVX2-NEXT: vmovdqa %ymm4, %ymm0
+; AVX2-NEXT: vmovdqa %ymm5, %ymm1
+; AVX2-NEXT: retq
+ %result = shufflevector <32 x i16> %a, <32 x i16> %b, <64 x i32> <i32 0, i32 32, i32 1, i32 33, i32 2, i32 34, i32 3, i32 35, i32 4, i32 36, i32 5, i32 37, i32 6, i32 38, i32 7, i32 39, i32 8, i32 40, i32 9, i32 41, i32 10, i32 42, i32 11, i32 43, i32 12, i32 44, i32 13, i32 45, i32 14, i32 46, i32 15, i32 47, i32 16, i32 48, i32 17, i32 49, i32 18, i32 50, i32 19, i32 51, i32 20, i32 52, i32 21, i32 53, i32 22, i32 54, i32 23, i32 55, i32 24, i32 56, i32 25, i32 57, i32 26, i32 58, i32 27, i32 59, i32 28, i32 60, i32 29, i32 61, i32 30, i32 62, i32 31, i32 63>
+ ret <64 x i16> %result
+}
+
+define <64 x i8> @interleave2x32i8(<32 x i8> %a, <32 x i8> %b) {
+; SSE-LABEL: interleave2x32i8:
; SSE: # %bb.0:
; SSE-NEXT: movdqa %xmm1, %xmm4
; SSE-NEXT: movdqa %xmm0, %xmm1
; SSE-NEXT: movdqa %xmm4, %xmm3
; SSE-NEXT: retq
;
-; AVX1-LABEL: interleave2x32:
+; AVX1-LABEL: interleave2x32i8:
; AVX1: # %bb.0:
; AVX1-NEXT: vpunpckhbw {{.*#+}} xmm2 = xmm0[8],xmm1[8],xmm0[9],xmm1[9],xmm0[10],xmm1[10],xmm0[11],xmm1[11],xmm0[12],xmm1[12],xmm0[13],xmm1[13],xmm0[14],xmm1[14],xmm0[15],xmm1[15]
; AVX1-NEXT: vpunpcklbw {{.*#+}} xmm3 = 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]
; AVX1-NEXT: vmovaps %ymm2, %ymm0
; AVX1-NEXT: retq
;
-; AVX2-LABEL: interleave2x32:
+; AVX2-LABEL: interleave2x32i8:
; AVX2: # %bb.0:
; AVX2-NEXT: vpunpckhbw {{.*#+}} xmm2 = xmm0[8],xmm1[8],xmm0[9],xmm1[9],xmm0[10],xmm1[10],xmm0[11],xmm1[11],xmm0[12],xmm1[12],xmm0[13],xmm1[13],xmm0[14],xmm1[14],xmm0[15],xmm1[15]
; AVX2-NEXT: vpunpcklbw {{.*#+}} xmm3 = 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]