diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index f9661b0ea18b0..6e68b8ad0b7ab 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -58006,13 +58006,18 @@ static SDValue combineConcatVectorOps(const SDLoc &DL, MVT VT,
     }
     case X86ISD::SHUFP: {
       // Add SHUFPD support if/when necessary.
-      if (!IsSplat && VT.getScalarType() == MVT::f32 &&
+      if (!IsSplat &&
+          (VT == MVT::v8f32 || (MVT::v16f32 && Subtarget.useAVX512Regs())) &&
           llvm::all_of(Ops, [Op0](SDValue Op) {
             return Op.getOperand(2) == Op0.getOperand(2);
           })) {
-        return DAG.getNode(Op0.getOpcode(), DL, VT,
-                           ConcatSubOperand(VT, Ops, 0),
-                           ConcatSubOperand(VT, Ops, 1), Op0.getOperand(2));
+        SDValue Concat0 = CombineSubOperand(VT, Ops, 0);
+        SDValue Concat1 = CombineSubOperand(VT, Ops, 1);
+        if (Concat0 || Concat1)
+          return DAG.getNode(Op0.getOpcode(), DL, VT,
+                             Concat0 ? Concat0 : ConcatSubOperand(VT, Ops, 0),
+                             Concat1 ? Concat1 : ConcatSubOperand(VT, Ops, 1),
+                             Op0.getOperand(2));
       }
       break;
     }
diff --git a/llvm/test/CodeGen/X86/masked_store_trunc_ssat.ll b/llvm/test/CodeGen/X86/masked_store_trunc_ssat.ll
index da4432bd88e7d..31ef44bd6b42b 100644
--- a/llvm/test/CodeGen/X86/masked_store_trunc_ssat.ll
+++ b/llvm/test/CodeGen/X86/masked_store_trunc_ssat.ll
@@ -289,31 +289,31 @@ define void @truncstore_v8i64_v8i32(<8 x i64> %x, ptr %p, <8 x i32> %mask) {
 ; AVX1-NEXT:    vpcmpeqd %xmm4, %xmm2, %xmm2
 ; AVX1-NEXT:    vpxor %xmm5, %xmm2, %xmm2
 ; AVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm2, %ymm2
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
-; AVX1-NEXT:    vmovddup {{.*#+}} xmm4 = [2147483647,2147483647]
-; AVX1-NEXT:    # xmm4 = mem[0,0]
+; AVX1-NEXT:    vmovddup {{.*#+}} xmm3 = [2147483647,2147483647]
+; AVX1-NEXT:    # xmm3 = mem[0,0]
+; AVX1-NEXT:    vpcmpgtq %xmm1, %xmm3, %xmm4
+; AVX1-NEXT:    vblendvpd %xmm4, %xmm1, %xmm3, %xmm4
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm1
+; AVX1-NEXT:    vpcmpgtq %xmm1, %xmm3, %xmm5
+; AVX1-NEXT:    vblendvpd %xmm5, %xmm1, %xmm3, %xmm1
+; AVX1-NEXT:    vpcmpgtq %xmm0, %xmm3, %xmm5
+; AVX1-NEXT:    vblendvpd %xmm5, %xmm0, %xmm3, %xmm5
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT:    vpcmpgtq %xmm0, %xmm3, %xmm6
+; AVX1-NEXT:    vblendvpd %xmm6, %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vmovddup {{.*#+}} xmm3 = [18446744071562067968,18446744071562067968]
+; AVX1-NEXT:    # xmm3 = mem[0,0]
+; AVX1-NEXT:    vpcmpgtq %xmm3, %xmm0, %xmm6
+; AVX1-NEXT:    vblendvpd %xmm6, %xmm0, %xmm3, %xmm0
+; AVX1-NEXT:    vpcmpgtq %xmm3, %xmm5, %xmm6
+; AVX1-NEXT:    vblendvpd %xmm6, %xmm5, %xmm3, %xmm5
+; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm5[0,2],xmm0[0,2]
+; AVX1-NEXT:    vpcmpgtq %xmm3, %xmm1, %xmm5
+; AVX1-NEXT:    vblendvpd %xmm5, %xmm1, %xmm3, %xmm1
 ; AVX1-NEXT:    vpcmpgtq %xmm3, %xmm4, %xmm5
-; AVX1-NEXT:    vblendvpd %xmm5, %xmm3, %xmm4, %xmm3
-; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm5
-; AVX1-NEXT:    vpcmpgtq %xmm5, %xmm4, %xmm6
-; AVX1-NEXT:    vblendvpd %xmm6, %xmm5, %xmm4, %xmm5
-; AVX1-NEXT:    vpcmpgtq %xmm0, %xmm4, %xmm6
-; AVX1-NEXT:    vblendvpd %xmm6, %xmm0, %xmm4, %xmm0
-; AVX1-NEXT:    vpcmpgtq %xmm1, %xmm4, %xmm6
-; AVX1-NEXT:    vblendvpd %xmm6, %xmm1, %xmm4, %xmm1
-; AVX1-NEXT:    vmovddup {{.*#+}} xmm4 = [18446744071562067968,18446744071562067968]
-; AVX1-NEXT:    # xmm4 = mem[0,0]
-; AVX1-NEXT:    vpcmpgtq %xmm4, %xmm1, %xmm6
-; AVX1-NEXT:    vblendvpd %xmm6, %xmm1, %xmm4, %xmm1
-; AVX1-NEXT:    vpcmpgtq %xmm4, %xmm0, %xmm6
-; AVX1-NEXT:    vblendvpd %xmm6, %xmm0, %xmm4, %xmm0
-; AVX1-NEXT:    vpcmpgtq %xmm4, %xmm5, %xmm6
-; AVX1-NEXT:    vblendvpd %xmm6, %xmm5, %xmm4, %xmm5
-; AVX1-NEXT:    vpcmpgtq %xmm4, %xmm3, %xmm6
-; AVX1-NEXT:    vblendvpd %xmm6, %xmm3, %xmm4, %xmm3
-; AVX1-NEXT:    vinsertf128 $1, %xmm5, %ymm3, %ymm3
+; AVX1-NEXT:    vblendvpd %xmm5, %xmm4, %xmm3, %xmm3
+; AVX1-NEXT:    vshufps {{.*#+}} xmm1 = xmm3[0,2],xmm1[0,2]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm3[0,2],ymm0[4,6],ymm3[4,6]
 ; AVX1-NEXT:    vmaskmovps %ymm0, %ymm2, (%rdi)
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
diff --git a/llvm/test/CodeGen/X86/masked_store_trunc_usat.ll b/llvm/test/CodeGen/X86/masked_store_trunc_usat.ll
index 1597e13f02719..590f090c59596 100644
--- a/llvm/test/CodeGen/X86/masked_store_trunc_usat.ll
+++ b/llvm/test/CodeGen/X86/masked_store_trunc_usat.ll
@@ -224,29 +224,29 @@ define void @truncstore_v8i64_v8i32(<8 x i64> %x, ptr %p, <8 x i32> %mask) {
 ; AVX1-NEXT:    vpcmpeqd %xmm4, %xmm2, %xmm2
 ; AVX1-NEXT:    vpxor %xmm5, %xmm2, %xmm2
 ; AVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm2, %ymm2
-; AVX1-NEXT:    vmovddup {{.*#+}} xmm3 = [9223372036854775808,9223372036854775808]
-; AVX1-NEXT:    # xmm3 = mem[0,0]
-; AVX1-NEXT:    vpxor %xmm3, %xmm1, %xmm4
-; AVX1-NEXT:    vmovddup {{.*#+}} xmm5 = [9223372041149743103,9223372041149743103]
-; AVX1-NEXT:    # xmm5 = mem[0,0]
-; AVX1-NEXT:    vpcmpgtq %xmm4, %xmm5, %xmm4
-; AVX1-NEXT:    vmovddup {{.*#+}} xmm6 = [4294967295,4294967295]
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
+; AVX1-NEXT:    vmovddup {{.*#+}} xmm4 = [9223372036854775808,9223372036854775808]
+; AVX1-NEXT:    # xmm4 = mem[0,0]
+; AVX1-NEXT:    vpxor %xmm4, %xmm3, %xmm5
+; AVX1-NEXT:    vmovddup {{.*#+}} xmm6 = [9223372041149743103,9223372041149743103]
 ; AVX1-NEXT:    # xmm6 = mem[0,0]
-; AVX1-NEXT:    vblendvpd %xmm4, %xmm1, %xmm6, %xmm4
-; AVX1-NEXT:    vpxor %xmm3, %xmm0, %xmm7
-; AVX1-NEXT:    vpcmpgtq %xmm7, %xmm5, %xmm7
-; AVX1-NEXT:    vblendvpd %xmm7, %xmm0, %xmm6, %xmm7
-; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm1
-; AVX1-NEXT:    vpxor %xmm3, %xmm1, %xmm8
-; AVX1-NEXT:    vpcmpgtq %xmm8, %xmm5, %xmm8
-; AVX1-NEXT:    vblendvpd %xmm8, %xmm1, %xmm6, %xmm1
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpxor %xmm3, %xmm0, %xmm3
-; AVX1-NEXT:    vpcmpgtq %xmm3, %xmm5, %xmm3
-; AVX1-NEXT:    vblendvpd %xmm3, %xmm0, %xmm6, %xmm0
+; AVX1-NEXT:    vpcmpgtq %xmm5, %xmm6, %xmm5
+; AVX1-NEXT:    vmovddup {{.*#+}} xmm7 = [4294967295,4294967295]
+; AVX1-NEXT:    # xmm7 = mem[0,0]
+; AVX1-NEXT:    vblendvpd %xmm5, %xmm3, %xmm7, %xmm3
+; AVX1-NEXT:    vpxor %xmm4, %xmm0, %xmm5
+; AVX1-NEXT:    vpcmpgtq %xmm5, %xmm6, %xmm5
+; AVX1-NEXT:    vblendvpd %xmm5, %xmm0, %xmm7, %xmm0
+; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm3[0,2]
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm3
+; AVX1-NEXT:    vpxor %xmm4, %xmm3, %xmm5
+; AVX1-NEXT:    vpcmpgtq %xmm5, %xmm6, %xmm5
+; AVX1-NEXT:    vblendvpd %xmm5, %xmm3, %xmm7, %xmm3
+; AVX1-NEXT:    vpxor %xmm4, %xmm1, %xmm4
+; AVX1-NEXT:    vpcmpgtq %xmm4, %xmm6, %xmm4
+; AVX1-NEXT:    vblendvpd %xmm4, %xmm1, %xmm7, %xmm1
+; AVX1-NEXT:    vshufps {{.*#+}} xmm1 = xmm1[0,2],xmm3[0,2]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; AVX1-NEXT:    vinsertf128 $1, %xmm4, %ymm7, %ymm1
-; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm1[0,2],ymm0[0,2],ymm1[4,6],ymm0[4,6]
 ; AVX1-NEXT:    vmaskmovps %ymm0, %ymm2, (%rdi)
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
diff --git a/llvm/test/CodeGen/X86/vector-fshl-256.ll b/llvm/test/CodeGen/X86/vector-fshl-256.ll
index 32ad72b2aa56a..6fb74643e4bb7 100644
--- a/llvm/test/CodeGen/X86/vector-fshl-256.ll
+++ b/llvm/test/CodeGen/X86/vector-fshl-256.ll
@@ -887,15 +887,15 @@ define <8 x i32> @splatvar_funnnel_v8i32(<8 x i32> %x, <8 x i32> %y, <8 x i32> %
 ; AVX1-NEXT:    vpunpckhdq {{.*#+}} xmm5 = xmm4[2],xmm3[2],xmm4[3],xmm3[3]
 ; AVX1-NEXT:    vpand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm2, %xmm2
 ; AVX1-NEXT:    vpsllq %xmm2, %xmm5, %xmm5
-; AVX1-NEXT:    vpunpckhdq {{.*#+}} xmm6 = xmm1[2],xmm0[2],xmm1[3],xmm0[3]
-; AVX1-NEXT:    vpsllq %xmm2, %xmm6, %xmm6
-; AVX1-NEXT:    vinsertf128 $1, %xmm5, %ymm6, %ymm5
 ; AVX1-NEXT:    vpunpckldq {{.*#+}} xmm3 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
 ; AVX1-NEXT:    vpsllq %xmm2, %xmm3, %xmm3
+; AVX1-NEXT:    vshufps {{.*#+}} xmm3 = xmm3[1,3],xmm5[1,3]
+; AVX1-NEXT:    vpunpckhdq {{.*#+}} xmm4 = xmm1[2],xmm0[2],xmm1[3],xmm0[3]
+; AVX1-NEXT:    vpsllq %xmm2, %xmm4, %xmm4
 ; AVX1-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
 ; AVX1-NEXT:    vpsllq %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[1,3],xmm4[1,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm0, %ymm0
-; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm5[1,3],ymm0[5,7],ymm5[5,7]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: splatvar_funnnel_v8i32:
@@ -970,15 +970,15 @@ define <8 x i32> @splatvar_funnnel_v8i32(<8 x i32> %x, <8 x i32> %y, <8 x i32> %
 ; XOPAVX1-NEXT:    vpunpckhdq {{.*#+}} xmm5 = xmm4[2],xmm3[2],xmm4[3],xmm3[3]
 ; XOPAVX1-NEXT:    vpand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm2, %xmm2
 ; XOPAVX1-NEXT:    vpsllq %xmm2, %xmm5, %xmm5
-; XOPAVX1-NEXT:    vpunpckhdq {{.*#+}} xmm6 = xmm1[2],xmm0[2],xmm1[3],xmm0[3]
-; XOPAVX1-NEXT:    vpsllq %xmm2, %xmm6, %xmm6
-; XOPAVX1-NEXT:    vinsertf128 $1, %xmm5, %ymm6, %ymm5
 ; XOPAVX1-NEXT:    vpunpckldq {{.*#+}} xmm3 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
 ; XOPAVX1-NEXT:    vpsllq %xmm2, %xmm3, %xmm3
+; XOPAVX1-NEXT:    vshufps {{.*#+}} xmm3 = xmm3[1,3],xmm5[1,3]
+; XOPAVX1-NEXT:    vpunpckhdq {{.*#+}} xmm4 = xmm1[2],xmm0[2],xmm1[3],xmm0[3]
+; XOPAVX1-NEXT:    vpsllq %xmm2, %xmm4, %xmm4
 ; XOPAVX1-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
 ; XOPAVX1-NEXT:    vpsllq %xmm2, %xmm0, %xmm0
+; XOPAVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[1,3],xmm4[1,3]
 ; XOPAVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm0, %ymm0
-; XOPAVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm5[1,3],ymm0[5,7],ymm5[5,7]
 ; XOPAVX1-NEXT:    retq
 ;
 ; XOPAVX2-LABEL: splatvar_funnnel_v8i32:
diff --git a/llvm/test/CodeGen/X86/vector-fshl-rot-256.ll b/llvm/test/CodeGen/X86/vector-fshl-rot-256.ll
index c7e430de1af97..9806d63257180 100644
--- a/llvm/test/CodeGen/X86/vector-fshl-rot-256.ll
+++ b/llvm/test/CodeGen/X86/vector-fshl-rot-256.ll
@@ -668,15 +668,15 @@ define <8 x i32> @splatvar_funnnel_v8i32(<8 x i32> %x, <8 x i32> %amt) nounwind
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
 ; AVX1-NEXT:    vpshufd {{.*#+}} xmm3 = xmm2[2,2,3,3]
 ; AVX1-NEXT:    vpsllq %xmm1, %xmm3, %xmm3
-; AVX1-NEXT:    vpshufd {{.*#+}} xmm4 = xmm0[2,2,3,3]
-; AVX1-NEXT:    vpsllq %xmm1, %xmm4, %xmm4
-; AVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm4, %ymm3
 ; AVX1-NEXT:    vpshufd {{.*#+}} xmm2 = xmm2[0,0,1,1]
 ; AVX1-NEXT:    vpsllq %xmm1, %xmm2, %xmm2
+; AVX1-NEXT:    vshufps {{.*#+}} xmm2 = xmm2[1,3],xmm3[1,3]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm3 = xmm0[2,2,3,3]
+; AVX1-NEXT:    vpsllq %xmm1, %xmm3, %xmm3
 ; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,0,1,1]
 ; AVX1-NEXT:    vpsllq %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[1,3],xmm3[1,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
-; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm3[1,3],ymm0[5,7],ymm3[5,7]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: splatvar_funnnel_v8i32:
diff --git a/llvm/test/CodeGen/X86/vector-fshr-256.ll b/llvm/test/CodeGen/X86/vector-fshr-256.ll
index 9c259ed38321d..1741ae213d126 100644
--- a/llvm/test/CodeGen/X86/vector-fshr-256.ll
+++ b/llvm/test/CodeGen/X86/vector-fshr-256.ll
@@ -918,15 +918,15 @@ define <8 x i32> @splatvar_funnnel_v8i32(<8 x i32> %x, <8 x i32> %y, <8 x i32> %
 ; AVX1-NEXT:    vpunpckhdq {{.*#+}} xmm5 = xmm4[2],xmm3[2],xmm4[3],xmm3[3]
 ; AVX1-NEXT:    vpand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm2, %xmm2
 ; AVX1-NEXT:    vpsrlq %xmm2, %xmm5, %xmm5
-; AVX1-NEXT:    vpunpckhdq {{.*#+}} xmm6 = xmm1[2],xmm0[2],xmm1[3],xmm0[3]
-; AVX1-NEXT:    vpsrlq %xmm2, %xmm6, %xmm6
-; AVX1-NEXT:    vinsertf128 $1, %xmm5, %ymm6, %ymm5
 ; AVX1-NEXT:    vpunpckldq {{.*#+}} xmm3 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
 ; AVX1-NEXT:    vpsrlq %xmm2, %xmm3, %xmm3
+; AVX1-NEXT:    vshufps {{.*#+}} xmm3 = xmm3[0,2],xmm5[0,2]
+; AVX1-NEXT:    vpunpckhdq {{.*#+}} xmm4 = xmm1[2],xmm0[2],xmm1[3],xmm0[3]
+; AVX1-NEXT:    vpsrlq %xmm2, %xmm4, %xmm4
 ; AVX1-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
 ; AVX1-NEXT:    vpsrlq %xmm2, %xmm0, %xmm0
+; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm4[0,2]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm0, %ymm0
-; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm5[0,2],ymm0[4,6],ymm5[4,6]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: splatvar_funnnel_v8i32:
@@ -1002,15 +1002,15 @@ define <8 x i32> @splatvar_funnnel_v8i32(<8 x i32> %x, <8 x i32> %y, <8 x i32> %
 ; XOPAVX1-NEXT:    vpunpckhdq {{.*#+}} xmm5 = xmm4[2],xmm3[2],xmm4[3],xmm3[3]
 ; XOPAVX1-NEXT:    vpand {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm2, %xmm2
 ; XOPAVX1-NEXT:    vpsrlq %xmm2, %xmm5, %xmm5
-; XOPAVX1-NEXT:    vpunpckhdq {{.*#+}} xmm6 = xmm1[2],xmm0[2],xmm1[3],xmm0[3]
-; XOPAVX1-NEXT:    vpsrlq %xmm2, %xmm6, %xmm6
-; XOPAVX1-NEXT:    vinsertf128 $1, %xmm5, %ymm6, %ymm5
 ; XOPAVX1-NEXT:    vpunpckldq {{.*#+}} xmm3 = xmm4[0],xmm3[0],xmm4[1],xmm3[1]
 ; XOPAVX1-NEXT:    vpsrlq %xmm2, %xmm3, %xmm3
+; XOPAVX1-NEXT:    vshufps {{.*#+}} xmm3 = xmm3[0,2],xmm5[0,2]
+; XOPAVX1-NEXT:    vpunpckhdq {{.*#+}} xmm4 = xmm1[2],xmm0[2],xmm1[3],xmm0[3]
+; XOPAVX1-NEXT:    vpsrlq %xmm2, %xmm4, %xmm4
 ; XOPAVX1-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
 ; XOPAVX1-NEXT:    vpsrlq %xmm2, %xmm0, %xmm0
+; XOPAVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm4[0,2]
 ; XOPAVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm0, %ymm0
-; XOPAVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm5[0,2],ymm0[4,6],ymm5[4,6]
 ; XOPAVX1-NEXT:    retq
 ;
 ; XOPAVX2-LABEL: splatvar_funnnel_v8i32:
diff --git a/llvm/test/CodeGen/X86/vector-fshr-rot-256.ll b/llvm/test/CodeGen/X86/vector-fshr-rot-256.ll
index d81d6ef7c9f28..3055663786740 100644
--- a/llvm/test/CodeGen/X86/vector-fshr-rot-256.ll
+++ b/llvm/test/CodeGen/X86/vector-fshr-rot-256.ll
@@ -703,15 +703,15 @@ define <8 x i32> @splatvar_funnnel_v8i32(<8 x i32> %x, <8 x i32> %amt) nounwind
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
 ; AVX1-NEXT:    vpshufd {{.*#+}} xmm3 = xmm2[2,2,3,3]
 ; AVX1-NEXT:    vpsrlq %xmm1, %xmm3, %xmm3
-; AVX1-NEXT:    vpshufd {{.*#+}} xmm4 = xmm0[2,2,3,3]
-; AVX1-NEXT:    vpsrlq %xmm1, %xmm4, %xmm4
-; AVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm4, %ymm3
 ; AVX1-NEXT:    vpshufd {{.*#+}} xmm2 = xmm2[0,0,1,1]
 ; AVX1-NEXT:    vpsrlq %xmm1, %xmm2, %xmm2
+; AVX1-NEXT:    vshufps {{.*#+}} xmm2 = xmm2[0,2],xmm3[0,2]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm3 = xmm0[2,2,3,3]
+; AVX1-NEXT:    vpsrlq %xmm1, %xmm3, %xmm3
 ; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,0,1,1]
 ; AVX1-NEXT:    vpsrlq %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm3[0,2]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
-; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm3[0,2],ymm0[4,6],ymm3[4,6]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: splatvar_funnnel_v8i32:
diff --git a/llvm/test/CodeGen/X86/vector-rotate-256.ll b/llvm/test/CodeGen/X86/vector-rotate-256.ll
index ec45f64bdb0e6..c19e69ad66654 100644
--- a/llvm/test/CodeGen/X86/vector-rotate-256.ll
+++ b/llvm/test/CodeGen/X86/vector-rotate-256.ll
@@ -584,15 +584,15 @@ define <8 x i32> @splatvar_rotate_v8i32(<8 x i32> %a, <8 x i32> %b) nounwind {
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
 ; AVX1-NEXT:    vpshufd {{.*#+}} xmm3 = xmm2[2,2,3,3]
 ; AVX1-NEXT:    vpsllq %xmm1, %xmm3, %xmm3
-; AVX1-NEXT:    vpshufd {{.*#+}} xmm4 = xmm0[2,2,3,3]
-; AVX1-NEXT:    vpsllq %xmm1, %xmm4, %xmm4
-; AVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm4, %ymm3
 ; AVX1-NEXT:    vpshufd {{.*#+}} xmm2 = xmm2[0,0,1,1]
 ; AVX1-NEXT:    vpsllq %xmm1, %xmm2, %xmm2
+; AVX1-NEXT:    vshufps {{.*#+}} xmm2 = xmm2[1,3],xmm3[1,3]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm3 = xmm0[2,2,3,3]
+; AVX1-NEXT:    vpsllq %xmm1, %xmm3, %xmm3
 ; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,0,1,1]
 ; AVX1-NEXT:    vpsllq %xmm1, %xmm0, %xmm0
+; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[1,3],xmm3[1,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
-; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm3[1,3],ymm0[5,7],ymm3[5,7]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: splatvar_rotate_v8i32:
diff --git a/llvm/test/CodeGen/X86/vector-trunc-packus.ll b/llvm/test/CodeGen/X86/vector-trunc-packus.ll
index 0af5e9aeccd92..cdb1026452691 100644
--- a/llvm/test/CodeGen/X86/vector-trunc-packus.ll
+++ b/llvm/test/CodeGen/X86/vector-trunc-packus.ll
@@ -676,26 +676,26 @@ define <8 x i32> @trunc_packus_v8i64_v8i32(ptr %p0) "min-legal-vector-width"="25
 ; AVX1-NEXT:    vmovdqa 32(%rdi), %xmm2
 ; AVX1-NEXT:    vmovdqa 48(%rdi), %xmm3
 ; AVX1-NEXT:    vpmovsxbd {{.*#+}} xmm4 = [4294967295,0,4294967295,0]
-; AVX1-NEXT:    vpcmpgtq %xmm1, %xmm4, %xmm5
-; AVX1-NEXT:    vblendvpd %xmm5, %xmm1, %xmm4, %xmm1
+; AVX1-NEXT:    vpcmpgtq %xmm2, %xmm4, %xmm5
+; AVX1-NEXT:    vblendvpd %xmm5, %xmm2, %xmm4, %xmm2
 ; AVX1-NEXT:    vpcmpgtq %xmm3, %xmm4, %xmm5
 ; AVX1-NEXT:    vblendvpd %xmm5, %xmm3, %xmm4, %xmm3
 ; AVX1-NEXT:    vpcmpgtq %xmm0, %xmm4, %xmm5
 ; AVX1-NEXT:    vblendvpd %xmm5, %xmm0, %xmm4, %xmm0
-; AVX1-NEXT:    vpcmpgtq %xmm2, %xmm4, %xmm5
-; AVX1-NEXT:    vblendvpd %xmm5, %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vpcmpgtq %xmm1, %xmm4, %xmm5
+; AVX1-NEXT:    vblendvpd %xmm5, %xmm1, %xmm4, %xmm1
 ; AVX1-NEXT:    vpxor %xmm4, %xmm4, %xmm4
-; AVX1-NEXT:    vpcmpgtq %xmm4, %xmm2, %xmm5
-; AVX1-NEXT:    vpand %xmm2, %xmm5, %xmm2
+; AVX1-NEXT:    vpcmpgtq %xmm4, %xmm1, %xmm5
+; AVX1-NEXT:    vpand %xmm1, %xmm5, %xmm1
 ; AVX1-NEXT:    vpcmpgtq %xmm4, %xmm0, %xmm5
 ; AVX1-NEXT:    vpand %xmm0, %xmm5, %xmm0
-; AVX1-NEXT:    vpcmpgtq %xmm4, %xmm3, %xmm5
-; AVX1-NEXT:    vpand %xmm3, %xmm5, %xmm3
-; AVX1-NEXT:    vpcmpgtq %xmm4, %xmm1, %xmm4
-; AVX1-NEXT:    vpand %xmm1, %xmm4, %xmm1
-; AVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm1, %ymm1
-; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
-; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
+; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; AVX1-NEXT:    vpcmpgtq %xmm4, %xmm3, %xmm1
+; AVX1-NEXT:    vpand %xmm3, %xmm1, %xmm1
+; AVX1-NEXT:    vpcmpgtq %xmm4, %xmm2, %xmm3
+; AVX1-NEXT:    vpand %xmm2, %xmm3, %xmm2
+; AVX1-NEXT:    vshufps {{.*#+}} xmm1 = xmm2[0,2],xmm1[0,2]
+; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-SLOW-LABEL: trunc_packus_v8i64_v8i32:
diff --git a/llvm/test/CodeGen/X86/vector-trunc-ssat.ll b/llvm/test/CodeGen/X86/vector-trunc-ssat.ll
index 3c03c521c2722..b6557e929a5fd 100644
--- a/llvm/test/CodeGen/X86/vector-trunc-ssat.ll
+++ b/llvm/test/CodeGen/X86/vector-trunc-ssat.ll
@@ -697,27 +697,27 @@ define <8 x i32> @trunc_ssat_v8i64_v8i32(ptr %p0) "min-legal-vector-width"="256"
 ; AVX1-NEXT:    vmovdqa 48(%rdi), %xmm3
 ; AVX1-NEXT:    vmovddup {{.*#+}} xmm4 = [2147483647,2147483647]
 ; AVX1-NEXT:    # xmm4 = mem[0,0]
-; AVX1-NEXT:    vpcmpgtq %xmm1, %xmm4, %xmm5
-; AVX1-NEXT:    vblendvpd %xmm5, %xmm1, %xmm4, %xmm1
+; AVX1-NEXT:    vpcmpgtq %xmm2, %xmm4, %xmm5
+; AVX1-NEXT:    vblendvpd %xmm5, %xmm2, %xmm4, %xmm2
 ; AVX1-NEXT:    vpcmpgtq %xmm3, %xmm4, %xmm5
 ; AVX1-NEXT:    vblendvpd %xmm5, %xmm3, %xmm4, %xmm3
 ; AVX1-NEXT:    vpcmpgtq %xmm0, %xmm4, %xmm5
 ; AVX1-NEXT:    vblendvpd %xmm5, %xmm0, %xmm4, %xmm0
-; AVX1-NEXT:    vpcmpgtq %xmm2, %xmm4, %xmm5
-; AVX1-NEXT:    vblendvpd %xmm5, %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vpcmpgtq %xmm1, %xmm4, %xmm5
+; AVX1-NEXT:    vblendvpd %xmm5, %xmm1, %xmm4, %xmm1
 ; AVX1-NEXT:    vmovddup {{.*#+}} xmm4 = [18446744071562067968,18446744071562067968]
 ; AVX1-NEXT:    # xmm4 = mem[0,0]
-; AVX1-NEXT:    vpcmpgtq %xmm4, %xmm2, %xmm5
-; AVX1-NEXT:    vblendvpd %xmm5, %xmm2, %xmm4, %xmm2
-; AVX1-NEXT:    vpcmpgtq %xmm4, %xmm0, %xmm5
-; AVX1-NEXT:    vblendvpd %xmm5, %xmm0, %xmm4, %xmm0
-; AVX1-NEXT:    vpcmpgtq %xmm4, %xmm3, %xmm5
-; AVX1-NEXT:    vblendvpd %xmm5, %xmm3, %xmm4, %xmm3
 ; AVX1-NEXT:    vpcmpgtq %xmm4, %xmm1, %xmm5
 ; AVX1-NEXT:    vblendvpd %xmm5, %xmm1, %xmm4, %xmm1
-; AVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm1, %ymm1
-; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
-; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
+; AVX1-NEXT:    vpcmpgtq %xmm4, %xmm0, %xmm5
+; AVX1-NEXT:    vblendvpd %xmm5, %xmm0, %xmm4, %xmm0
+; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; AVX1-NEXT:    vpcmpgtq %xmm4, %xmm3, %xmm1
+; AVX1-NEXT:    vblendvpd %xmm1, %xmm3, %xmm4, %xmm1
+; AVX1-NEXT:    vpcmpgtq %xmm4, %xmm2, %xmm3
+; AVX1-NEXT:    vblendvpd %xmm3, %xmm2, %xmm4, %xmm2
+; AVX1-NEXT:    vshufps {{.*#+}} xmm1 = xmm2[0,2],xmm1[0,2]
+; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-SLOW-LABEL: trunc_ssat_v8i64_v8i32:
diff --git a/llvm/test/CodeGen/X86/vector-trunc-usat.ll b/llvm/test/CodeGen/X86/vector-trunc-usat.ll
index c1d22dc7daf21..23af4283dc79a 100644
--- a/llvm/test/CodeGen/X86/vector-trunc-usat.ll
+++ b/llvm/test/CodeGen/X86/vector-trunc-usat.ll
@@ -456,25 +456,25 @@ define <8 x i32> @trunc_usat_v8i64_v8i32(ptr %p0) {
 ; AVX1-NEXT:    vmovdqa 48(%rdi), %xmm3
 ; AVX1-NEXT:    vmovddup {{.*#+}} xmm4 = [9223372036854775808,9223372036854775808]
 ; AVX1-NEXT:    # xmm4 = mem[0,0]
-; AVX1-NEXT:    vpxor %xmm4, %xmm2, %xmm5
+; AVX1-NEXT:    vpxor %xmm4, %xmm1, %xmm5
 ; AVX1-NEXT:    vmovddup {{.*#+}} xmm6 = [9223372041149743103,9223372041149743103]
 ; AVX1-NEXT:    # xmm6 = mem[0,0]
 ; AVX1-NEXT:    vpcmpgtq %xmm5, %xmm6, %xmm5
 ; AVX1-NEXT:    vmovddup {{.*#+}} xmm7 = [4294967295,4294967295]
 ; AVX1-NEXT:    # xmm7 = mem[0,0]
-; AVX1-NEXT:    vblendvpd %xmm5, %xmm2, %xmm7, %xmm2
+; AVX1-NEXT:    vblendvpd %xmm5, %xmm1, %xmm7, %xmm1
 ; AVX1-NEXT:    vpxor %xmm4, %xmm0, %xmm5
 ; AVX1-NEXT:    vpcmpgtq %xmm5, %xmm6, %xmm5
 ; AVX1-NEXT:    vblendvpd %xmm5, %xmm0, %xmm7, %xmm0
-; AVX1-NEXT:    vpxor %xmm4, %xmm3, %xmm5
-; AVX1-NEXT:    vpcmpgtq %xmm5, %xmm6, %xmm5
-; AVX1-NEXT:    vblendvpd %xmm5, %xmm3, %xmm7, %xmm3
-; AVX1-NEXT:    vpxor %xmm4, %xmm1, %xmm4
-; AVX1-NEXT:    vpcmpgtq %xmm4, %xmm6, %xmm4
-; AVX1-NEXT:    vblendvpd %xmm4, %xmm1, %xmm7, %xmm1
-; AVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm1, %ymm1
-; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
-; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
+; AVX1-NEXT:    vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[0,2]
+; AVX1-NEXT:    vpxor %xmm4, %xmm3, %xmm1
+; AVX1-NEXT:    vpcmpgtq %xmm1, %xmm6, %xmm1
+; AVX1-NEXT:    vblendvpd %xmm1, %xmm3, %xmm7, %xmm1
+; AVX1-NEXT:    vpxor %xmm4, %xmm2, %xmm3
+; AVX1-NEXT:    vpcmpgtq %xmm3, %xmm6, %xmm3
+; AVX1-NEXT:    vblendvpd %xmm3, %xmm2, %xmm7, %xmm2
+; AVX1-NEXT:    vshufps {{.*#+}} xmm1 = xmm2[0,2],xmm1[0,2]
+; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-SLOW-LABEL: trunc_usat_v8i64_v8i32: