+define <4 x float> @shuffle_v4f32_0z23(<4 x float> %a) {
+; SSE2-LABEL: shuffle_v4f32_0z23:
+; SSE2: # BB#0:
+; SSE2-NEXT: xorps %xmm1, %xmm1
+; SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[1,0],xmm0[0,0]
+; SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[2,0],xmm0[2,3]
+; SSE2-NEXT: movaps %xmm1, %xmm0
+; SSE2-NEXT: retq
+;
+; SSE3-LABEL: shuffle_v4f32_0z23:
+; SSE3: # BB#0:
+; SSE3-NEXT: xorps %xmm1, %xmm1
+; SSE3-NEXT: shufps {{.*#+}} xmm1 = xmm1[1,0],xmm0[0,0]
+; SSE3-NEXT: shufps {{.*#+}} xmm1 = xmm1[2,0],xmm0[2,3]
+; SSE3-NEXT: movaps %xmm1, %xmm0
+; SSE3-NEXT: retq
+;
+; SSSE3-LABEL: shuffle_v4f32_0z23:
+; SSSE3: # BB#0:
+; SSSE3-NEXT: xorps %xmm1, %xmm1
+; SSSE3-NEXT: shufps {{.*#+}} xmm1 = xmm1[1,0],xmm0[0,0]
+; SSSE3-NEXT: shufps {{.*#+}} xmm1 = xmm1[2,0],xmm0[2,3]
+; SSSE3-NEXT: movaps %xmm1, %xmm0
+; SSSE3-NEXT: retq
+;
+; SSE41-LABEL: shuffle_v4f32_0z23:
+; SSE41: # BB#0:
+; SSE41-NEXT: xorps %xmm1, %xmm1
+; SSE41-NEXT: blendps {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
+; SSE41-NEXT: retq
+;
+; AVX-LABEL: shuffle_v4f32_0z23:
+; AVX: # BB#0:
+; AVX-NEXT: vxorps %xmm1, %xmm1, %xmm1
+; AVX-NEXT: vblendps {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
+; AVX-NEXT: retq
+ %shuffle = shufflevector <4 x float> %a, <4 x float> zeroinitializer, <4 x i32> <i32 0, i32 4, i32 2, i32 3>
+ ret <4 x float> %shuffle
+}
+
+define <4 x float> @shuffle_v4f32_01z3(<4 x float> %a) {
+; SSE2-LABEL: shuffle_v4f32_01z3:
+; SSE2: # BB#0:
+; SSE2-NEXT: xorps %xmm1, %xmm1
+; SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[2,0],xmm0[3,0]
+; SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,2]
+; SSE2-NEXT: retq
+;
+; SSE3-LABEL: shuffle_v4f32_01z3:
+; SSE3: # BB#0:
+; SSE3-NEXT: xorps %xmm1, %xmm1
+; SSE3-NEXT: shufps {{.*#+}} xmm1 = xmm1[2,0],xmm0[3,0]
+; SSE3-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,2]
+; SSE3-NEXT: retq
+;
+; SSSE3-LABEL: shuffle_v4f32_01z3:
+; SSSE3: # BB#0:
+; SSSE3-NEXT: xorps %xmm1, %xmm1
+; SSSE3-NEXT: shufps {{.*#+}} xmm1 = xmm1[2,0],xmm0[3,0]
+; SSSE3-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,2]
+; SSSE3-NEXT: retq
+;
+; SSE41-LABEL: shuffle_v4f32_01z3:
+; SSE41: # BB#0:
+; SSE41-NEXT: xorps %xmm1, %xmm1
+; SSE41-NEXT: blendps {{.*#+}} xmm0 = xmm0[0,1],xmm1[2],xmm0[3]
+; SSE41-NEXT: retq
+;
+; AVX-LABEL: shuffle_v4f32_01z3:
+; AVX: # BB#0:
+; AVX-NEXT: vxorps %xmm1, %xmm1, %xmm1
+; AVX-NEXT: vblendps {{.*#+}} xmm0 = xmm0[0,1],xmm1[2],xmm0[3]
+; AVX-NEXT: retq
+ %shuffle = shufflevector <4 x float> %a, <4 x float> zeroinitializer, <4 x i32> <i32 0, i32 1, i32 4, i32 3>
+ ret <4 x float> %shuffle
+}
+
+define <4 x float> @shuffle_v4f32_012z(<4 x float> %a) {
+; SSE2-LABEL: shuffle_v4f32_012z:
+; SSE2: # BB#0:
+; SSE2-NEXT: xorps %xmm1, %xmm1
+; SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[3,0],xmm0[2,0]
+; SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,0]
+; SSE2-NEXT: retq
+;
+; SSE3-LABEL: shuffle_v4f32_012z:
+; SSE3: # BB#0:
+; SSE3-NEXT: xorps %xmm1, %xmm1
+; SSE3-NEXT: shufps {{.*#+}} xmm1 = xmm1[3,0],xmm0[2,0]
+; SSE3-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,0]
+; SSE3-NEXT: retq
+;
+; SSSE3-LABEL: shuffle_v4f32_012z:
+; SSSE3: # BB#0:
+; SSSE3-NEXT: xorps %xmm1, %xmm1
+; SSSE3-NEXT: shufps {{.*#+}} xmm1 = xmm1[3,0],xmm0[2,0]
+; SSSE3-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,0]
+; SSSE3-NEXT: retq
+;
+; SSE41-LABEL: shuffle_v4f32_012z:
+; SSE41: # BB#0:
+; SSE41-NEXT: xorps %xmm1, %xmm1
+; SSE41-NEXT: blendps {{.*#+}} xmm0 = xmm0[0,1,2],xmm1[3]
+; SSE41-NEXT: retq
+;
+; AVX-LABEL: shuffle_v4f32_012z:
+; AVX: # BB#0:
+; AVX-NEXT: vxorps %xmm1, %xmm1, %xmm1
+; AVX-NEXT: vblendps {{.*#+}} xmm0 = xmm0[0,1,2],xmm1[3]
+; AVX-NEXT: retq
+ %shuffle = shufflevector <4 x float> %a, <4 x float> zeroinitializer, <4 x i32> <i32 0, i32 1, i32 2, i32 7>
+ ret <4 x float> %shuffle
+}
+
+define <4 x float> @shuffle_v4f32_0zz3(<4 x float> %a) {
+; SSE2-LABEL: shuffle_v4f32_0zz3:
+; SSE2: # BB#0:
+; SSE2-NEXT: xorps %xmm1, %xmm1
+; SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,3],xmm1[1,2]
+; SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2,3,1]
+; SSE2-NEXT: retq
+;
+; SSE3-LABEL: shuffle_v4f32_0zz3:
+; SSE3: # BB#0:
+; SSE3-NEXT: xorps %xmm1, %xmm1
+; SSE3-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,3],xmm1[1,2]
+; SSE3-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2,3,1]
+; SSE3-NEXT: retq
+;
+; SSSE3-LABEL: shuffle_v4f32_0zz3:
+; SSSE3: # BB#0:
+; SSSE3-NEXT: xorps %xmm1, %xmm1
+; SSSE3-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,3],xmm1[1,2]
+; SSSE3-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,2,3,1]
+; SSSE3-NEXT: retq
+;
+; SSE41-LABEL: shuffle_v4f32_0zz3:
+; SSE41: # BB#0:
+; SSE41-NEXT: xorps %xmm1, %xmm1
+; SSE41-NEXT: blendps {{.*#+}} xmm0 = xmm0[0],xmm1[1,2],xmm0[3]
+; SSE41-NEXT: retq
+;
+; AVX-LABEL: shuffle_v4f32_0zz3:
+; AVX: # BB#0:
+; AVX-NEXT: vxorps %xmm1, %xmm1, %xmm1
+; AVX-NEXT: vblendps {{.*#+}} xmm0 = xmm0[0],xmm1[1,2],xmm0[3]
+; AVX-NEXT: retq
+ %shuffle = shufflevector <4 x float> %a, <4 x float> zeroinitializer, <4 x i32> <i32 0, i32 4, i32 4, i32 3>
+ ret <4 x float> %shuffle
+}
+
+define <4 x float> @shuffle_v4f32_u051(<4 x float> %a, <4 x float> %b) {
+; SSE-LABEL: shuffle_v4f32_u051:
+; SSE: # BB#0:
+; SSE-NEXT: unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
+; SSE-NEXT: movaps %xmm1, %xmm0
+; SSE-NEXT: retq
+;
+; AVX-LABEL: shuffle_v4f32_u051:
+; AVX: # BB#0:
+; AVX-NEXT: vunpcklps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
+; AVX-NEXT: retq
+ %shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 undef, i32 0, i32 5, i32 1>
+ ret <4 x float> %shuffle
+}
+