define <8 x float> @shuffle_v8f32_08192a3b(<8 x float> %a, <8 x float> %b) {
; AVX1-LABEL: shuffle_v8f32_08192a3b:
; AVX1: # BB#0:
-; AVX1-NEXT: vpermilps {{.*#+}} xmm2 = xmm1[0,0,2,1]
-; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[0,2,2,3]
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm2, %ymm1
-; AVX1-NEXT: vpermilps {{.*#+}} xmm2 = xmm0[0,1,1,3]
-; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[2,1,3,3]
-; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm2, %ymm0
-; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
+; AVX1-NEXT: vunpckhps {{.*#+}} xmm2 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX1-NEXT: vunpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8f32_08192a3b:
define <8 x float> @shuffle_v8f32_08991abb(<8 x float> %a, <8 x float> %b) {
; AVX1-LABEL: shuffle_v8f32_08991abb:
; AVX1: # BB#0:
-; AVX1-NEXT: vpermilps {{.*#+}} xmm2 = xmm0[1,1,2,3]
+; AVX1-NEXT: vshufps {{.*#+}} xmm2 = xmm0[1,0],xmm1[2,0]
+; AVX1-NEXT: vshufps {{.*#+}} xmm2 = xmm2[0,2],xmm1[3,3]
+; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,0],xmm1[0,0]
+; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[1,1]
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
-; AVX1-NEXT: vunpcklps {{.*#+}} xmm2 = xmm1[0,0,1,1]
-; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[0,2,3,3]
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm2, %ymm1
-; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8f32_08991abb:
ret <8 x float> %shuffle
}
+define <8 x float> @shuffle_v8f32_32103210(<8 x float> %a, <8 x float> %b) {
+; AVX1-LABEL: shuffle_v8f32_32103210:
+; AVX1: # BB#0:
+; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v8f32_32103210:
+; AVX2: # BB#0:
+; AVX2-NEXT: vmovaps {{.*#+}} ymm1 = [3,2,1,0,3,2,1,0]
+; AVX2-NEXT: vpermps %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: retq
+ %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 3, i32 2, i32 1, i32 0>
+ ret <8 x float> %shuffle
+}
+
+define <8 x float> @shuffle_v8f32_76547654(<8 x float> %a, <8 x float> %b) {
+; AVX1-LABEL: shuffle_v8f32_76547654:
+; AVX1: # BB#0:
+; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v8f32_76547654:
+; AVX2: # BB#0:
+; AVX2-NEXT: vmovaps {{.*#+}} ymm1 = [7,6,5,4,7,6,5,4]
+; AVX2-NEXT: vpermps %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: retq
+ %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 7, i32 6, i32 5, i32 4>
+ ret <8 x float> %shuffle
+}
+
+define <8 x float> @shuffle_v8f32_76543210(<8 x float> %a, <8 x float> %b) {
+; AVX1-LABEL: shuffle_v8f32_76543210:
+; AVX1: # BB#0:
+; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
+; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v8f32_76543210:
+; AVX2: # BB#0:
+; AVX2-NEXT: vmovaps {{.*#+}} ymm1 = [7,6,5,4,3,2,1,0]
+; AVX2-NEXT: vpermps %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: retq
+ %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+ ret <8 x float> %shuffle
+}
+
+define <8 x float> @shuffle_v8f32_3210ba98(<8 x float> %a, <8 x float> %b) {
+; ALL-LABEL: shuffle_v8f32_3210ba98:
+; ALL: # BB#0:
+; ALL-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
+; ALL-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; ALL-NEXT: retq
+ %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 11, i32 10, i32 9, i32 8>
+ ret <8 x float> %shuffle
+}
+
+define <8 x float> @shuffle_v8f32_3210fedc(<8 x float> %a, <8 x float> %b) {
+; ALL-LABEL: shuffle_v8f32_3210fedc:
+; ALL: # BB#0:
+; ALL-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3]
+; ALL-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; ALL-NEXT: retq
+ %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 15, i32 14, i32 13, i32 12>
+ ret <8 x float> %shuffle
+}
+
+define <8 x float> @shuffle_v8f32_7654fedc(<8 x float> %a, <8 x float> %b) {
+; ALL-LABEL: shuffle_v8f32_7654fedc:
+; ALL: # BB#0:
+; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],ymm1[2,3]
+; ALL-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; ALL-NEXT: retq
+ %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 15, i32 14, i32 13, i32 12>
+ ret <8 x float> %shuffle
+}
+
+define <8 x float> @shuffle_v8f32_fedc7654(<8 x float> %a, <8 x float> %b) {
+; ALL-LABEL: shuffle_v8f32_fedc7654:
+; ALL: # BB#0:
+; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm1[2,3],ymm0[2,3]
+; ALL-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; ALL-NEXT: retq
+ %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 15, i32 14, i32 13, i32 12, i32 7, i32 6, i32 5, i32 4>
+ ret <8 x float> %shuffle
+}
+
+define <8 x float> @shuffle_v8f32_ba987654(<8 x float> %a, <8 x float> %b) {
+; ALL-LABEL: shuffle_v8f32_ba987654:
+; ALL: # BB#0:
+; ALL-NEXT: vblendpd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3]
+; ALL-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; ALL-NEXT: retq
+ %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4>
+ ret <8 x float> %shuffle
+}
+
+define <8 x float> @shuffle_v8f32_ba983210(<8 x float> %a, <8 x float> %b) {
+; ALL-LABEL: shuffle_v8f32_ba983210:
+; ALL: # BB#0:
+; ALL-NEXT: vblendpd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3]
+; ALL-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; ALL-NEXT: retq
+ %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4>
+ ret <8 x float> %shuffle
+}
+
define <8 x i32> @shuffle_v8i32_00000000(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_00000000:
; AVX1: # BB#0:
define <8 x i32> @shuffle_v8i32_08192a3b(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_08192a3b:
; AVX1: # BB#0:
-; AVX1-NEXT: vpermilps {{.*#+}} xmm2 = xmm1[0,0,2,1]
-; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[0,2,2,3]
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm2, %ymm1
-; AVX1-NEXT: vpermilps {{.*#+}} xmm2 = xmm0[0,1,1,3]
-; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[2,1,3,3]
-; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm2, %ymm0
-; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
+; AVX1-NEXT: vunpckhps {{.*#+}} xmm2 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX1-NEXT: vunpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
+; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_08192a3b:
define <8 x i32> @shuffle_v8i32_08991abb(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_08991abb:
; AVX1: # BB#0:
-; AVX1-NEXT: vpermilps {{.*#+}} xmm2 = xmm0[1,1,2,3]
+; AVX1-NEXT: vshufps {{.*#+}} xmm2 = xmm0[1,0],xmm1[2,0]
+; AVX1-NEXT: vshufps {{.*#+}} xmm2 = xmm2[0,2],xmm1[3,3]
+; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,0],xmm1[0,0]
+; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[1,1]
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
-; AVX1-NEXT: vunpcklps {{.*#+}} xmm2 = xmm1[0,0,1,1]
-; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[0,2,3,3]
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm2, %ymm1
-; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_08991abb:
ret <8 x i32> %shuffle
}
+define <8 x i32> @shuffle_v8i32_32103210(<8 x i32> %a, <8 x i32> %b) {
+; AVX1-LABEL: shuffle_v8i32_32103210:
+; AVX1: # BB#0:
+; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v8i32_32103210:
+; AVX2: # BB#0:
+; AVX2-NEXT: vmovdqa {{.*#+}} ymm1 = [3,2,1,0,3,2,1,0]
+; AVX2-NEXT: vpermd %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: retq
+ %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 3, i32 2, i32 1, i32 0>
+ ret <8 x i32> %shuffle
+}
+
+define <8 x i32> @shuffle_v8i32_76547654(<8 x i32> %a, <8 x i32> %b) {
+; AVX1-LABEL: shuffle_v8i32_76547654:
+; AVX1: # BB#0:
+; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
+; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v8i32_76547654:
+; AVX2: # BB#0:
+; AVX2-NEXT: vmovdqa {{.*#+}} ymm1 = [7,6,5,4,7,6,5,4]
+; AVX2-NEXT: vpermd %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: retq
+ %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 7, i32 6, i32 5, i32 4>
+ ret <8 x i32> %shuffle
+}
+
+define <8 x i32> @shuffle_v8i32_76543210(<8 x i32> %a, <8 x i32> %b) {
+; AVX1-LABEL: shuffle_v8i32_76543210:
+; AVX1: # BB#0:
+; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
+; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v8i32_76543210:
+; AVX2: # BB#0:
+; AVX2-NEXT: vmovdqa {{.*#+}} ymm1 = [7,6,5,4,3,2,1,0]
+; AVX2-NEXT: vpermd %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: retq
+ %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
+ ret <8 x i32> %shuffle
+}
+
+define <8 x i32> @shuffle_v8i32_3210ba98(<8 x i32> %a, <8 x i32> %b) {
+; AVX1-LABEL: shuffle_v8i32_3210ba98:
+; AVX1: # BB#0:
+; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
+; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v8i32_3210ba98:
+; AVX2: # BB#0:
+; AVX2-NEXT: vinserti128 $1, %xmm1, %ymm0, %ymm0
+; AVX2-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; AVX2-NEXT: retq
+ %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 11, i32 10, i32 9, i32 8>
+ ret <8 x i32> %shuffle
+}
+
+define <8 x i32> @shuffle_v8i32_3210fedc(<8 x i32> %a, <8 x i32> %b) {
+; AVX1-LABEL: shuffle_v8i32_3210fedc:
+; AVX1: # BB#0:
+; AVX1-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3]
+; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v8i32_3210fedc:
+; AVX2: # BB#0:
+; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm1[4,5,6,7]
+; AVX2-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; AVX2-NEXT: retq
+ %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 15, i32 14, i32 13, i32 12>
+ ret <8 x i32> %shuffle
+}
+
+define <8 x i32> @shuffle_v8i32_7654fedc(<8 x i32> %a, <8 x i32> %b) {
+; AVX1-LABEL: shuffle_v8i32_7654fedc:
+; AVX1: # BB#0:
+; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],ymm1[2,3]
+; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v8i32_7654fedc:
+; AVX2: # BB#0:
+; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[2,3],ymm1[2,3]
+; AVX2-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; AVX2-NEXT: retq
+ %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 15, i32 14, i32 13, i32 12>
+ ret <8 x i32> %shuffle
+}
+
+define <8 x i32> @shuffle_v8i32_fedc7654(<8 x i32> %a, <8 x i32> %b) {
+; AVX1-LABEL: shuffle_v8i32_fedc7654:
+; AVX1: # BB#0:
+; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm1[2,3],ymm0[2,3]
+; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v8i32_fedc7654:
+; AVX2: # BB#0:
+; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm1[2,3],ymm0[2,3]
+; AVX2-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; AVX2-NEXT: retq
+ %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 15, i32 14, i32 13, i32 12, i32 7, i32 6, i32 5, i32 4>
+ ret <8 x i32> %shuffle
+}
+
+define <8 x i32> @shuffle_v8i32_ba987654(<8 x i32> %a, <8 x i32> %b) {
+; AVX1-LABEL: shuffle_v8i32_ba987654:
+; AVX1: # BB#0:
+; AVX1-NEXT: vblendpd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3]
+; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v8i32_ba987654:
+; AVX2: # BB#0:
+; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm1[0,1,2,3],ymm0[4,5,6,7]
+; AVX2-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; AVX2-NEXT: retq
+ %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4>
+ ret <8 x i32> %shuffle
+}
+
+define <8 x i32> @shuffle_v8i32_ba983210(<8 x i32> %a, <8 x i32> %b) {
+; AVX1-LABEL: shuffle_v8i32_ba983210:
+; AVX1: # BB#0:
+; AVX1-NEXT: vblendpd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3]
+; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; AVX1-NEXT: retq
+;
+; AVX2-LABEL: shuffle_v8i32_ba983210:
+; AVX2: # BB#0:
+; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm1[0,1,2,3],ymm0[4,5,6,7]
+; AVX2-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; AVX2-NEXT: retq
+ %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4>
+ ret <8 x i32> %shuffle
+}
+
define <8 x float> @splat_mem_v8f32_2(float* %p) {
; ALL-LABEL: splat_mem_v8f32_2:
; ALL: # BB#0: