[X86][SSE] Improve support for 128-bit vector sign extension

This patch improves support for sign extension of the lower lanes of vectors of integers by making use of the SSE41 pmovsx* sign extension instructions where possible, and optimizing the sign extension by shifts on pre-SSE41 targets (avoiding the use of i64 arithmetic shifts which require scalarization).

It converts SIGN_EXTEND nodes to SIGN_EXTEND_VECTOR_INREG where necessary, that more closely matches the pmovsx* instruction than the default approach of using SIGN_EXTEND_INREG which splits the operation (into an ANY_EXTEND lowered to a shuffle followed by shifts) making instruction matching difficult during lowering. Necessary support for SIGN_EXTEND_VECTOR_INREG has been added to the DAGCombiner.

Differential Revision: http://reviews.llvm.org/D9848

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@237885 91177308-0d34-0410-b5e6-96231b3b80d8

7 files changed, 298 insertions, 300 deletions

diff --git a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 3ff4c4062f1..77e648c152c 100644
--- a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -268,6 +268,7 @@ namespace {
     SDValue visitZERO_EXTEND(SDNode *N);
     SDValue visitANY_EXTEND(SDNode *N);
     SDValue visitSIGN_EXTEND_INREG(SDNode *N);
+    SDValue visitSIGN_EXTEND_VECTOR_INREG(SDNode *N);
     SDValue visitTRUNCATE(SDNode *N);
     SDValue visitBITCAST(SDNode *N);
     SDValue visitBUILD_PAIR(SDNode *N);
@@ -1347,6 +1348,7 @@ SDValue DAGCombiner::visit(SDNode *N) {
   case ISD::ZERO_EXTEND:        return visitZERO_EXTEND(N);
   case ISD::ANY_EXTEND:         return visitANY_EXTEND(N);
   case ISD::SIGN_EXTEND_INREG:  return visitSIGN_EXTEND_INREG(N);
+  case ISD::SIGN_EXTEND_VECTOR_INREG: return visitSIGN_EXTEND_VECTOR_INREG(N);
   case ISD::TRUNCATE:           return visitTRUNCATE(N);
   case ISD::BITCAST:            return visitBITCAST(N);
   case ISD::BUILD_PAIR:         return visitBUILD_PAIR(N);
@@ -5541,7 +5543,8 @@ static SDNode *tryToFoldExtendOfConstant(SDNode *N, const TargetLowering &TLI,
   EVT VT = N->getValueType(0);
 
   assert((Opcode == ISD::SIGN_EXTEND || Opcode == ISD::ZERO_EXTEND ||
-         Opcode == ISD::ANY_EXTEND) && "Expected EXTEND dag node in input!");
+         Opcode == ISD::ANY_EXTEND || Opcode == ISD::SIGN_EXTEND_VECTOR_INREG)
+         && "Expected EXTEND dag node in input!");
 
   // fold (sext c1) -> c1
   // fold (zext c1) -> c1
@@ -5563,7 +5566,7 @@ static SDNode *tryToFoldExtendOfConstant(SDNode *N, const TargetLowering &TLI,
   unsigned EVTBits = N0->getValueType(0).getScalarType().getSizeInBits();
   unsigned ShAmt = VTBits - EVTBits;
   SmallVector<SDValue, 8> Elts;
-  unsigned NumElts = N0->getNumOperands();
+  unsigned NumElts = VT.getVectorNumElements();
   SDLoc DL(N);
 
   for (unsigned i=0; i != NumElts; ++i) {
@@ -5576,7 +5579,7 @@ static SDNode *tryToFoldExtendOfConstant(SDNode *N, const TargetLowering &TLI,
     SDLoc DL(Op);
     ConstantSDNode *CurrentND = cast<ConstantSDNode>(Op);
     const APInt &C = APInt(VTBits, CurrentND->getAPIntValue().getZExtValue());
-    if (Opcode == ISD::SIGN_EXTEND)
+    if (Opcode == ISD::SIGN_EXTEND || Opcode == ISD::SIGN_EXTEND_VECTOR_INREG)
       Elts.push_back(DAG.getConstant(C.shl(ShAmt).ashr(ShAmt).getZExtValue(),
                                      DL, SVT));
     else
@@ -6805,6 +6808,20 @@ SDValue DAGCombiner::visitSIGN_EXTEND_INREG(SDNode *N) {
   return SDValue();
 }
 
+SDValue DAGCombiner::visitSIGN_EXTEND_VECTOR_INREG(SDNode *N) {
+  SDValue N0 = N->getOperand(0);
+  EVT VT = N->getValueType(0);
+
+  if (N0.getOpcode() == ISD::UNDEF)
+    return DAG.getUNDEF(VT);
+
+  if (SDNode *Res = tryToFoldExtendOfConstant(N, TLI, DAG, LegalTypes,
+                                              LegalOperations))
+    return SDValue(Res, 0);
+
+  return SDValue();
+}
+
 SDValue DAGCombiner::visitTRUNCATE(SDNode *N) {
   SDValue N0 = N->getOperand(0);
   EVT VT = N->getValueType(0);
diff --git a/lib/CodeGen/SelectionDAG/SelectionDAG.cpp b/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
index 6d75a7c9533..eaba9ca14eb 100644
--- a/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
+++ b/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
@@ -3429,12 +3429,35 @@ SDValue SelectionDAG::getNode(unsigned Opcode, SDLoc DL, EVT VT, SDValue N1,
     assert(EVT.bitsLE(VT) && "Not extending!");
     if (EVT == VT) return N1;  // Not actually extending
 
+    auto SignExtendInReg = [&](APInt Val) {
+      unsigned FromBits = EVT.getScalarType().getSizeInBits();
+      Val <<= Val.getBitWidth() - FromBits;
+      Val = Val.ashr(Val.getBitWidth() - FromBits);
+      return getConstant(Val, DL, VT.getScalarType());
+    };
+
     if (N1C) {
       APInt Val = N1C->getAPIntValue();
-      unsigned FromBits = EVT.getScalarType().getSizeInBits();
-      Val <<= Val.getBitWidth()-FromBits;
-      Val = Val.ashr(Val.getBitWidth()-FromBits);
-      return getConstant(Val, DL, VT);
+      return SignExtendInReg(Val);
+    }
+    if (ISD::isBuildVectorOfConstantSDNodes(N1.getNode())) {
+      SmallVector<SDValue, 8> Ops;
+      for (int i = 0, e = VT.getVectorNumElements(); i != e; ++i) {
+        SDValue Op = N1.getOperand(i);
+        if (Op.getValueType() != VT.getScalarType()) break;
+        if (Op.getOpcode() == ISD::UNDEF) {
+          Ops.push_back(Op);
+          continue;
+        }
+        if (ConstantSDNode *C = dyn_cast<ConstantSDNode>(Op.getNode())) {
+          APInt Val = C->getAPIntValue();
+          Ops.push_back(SignExtendInReg(Val));
+          continue;
+        }
+        break;
+      }
+      if (Ops.size() == VT.getVectorNumElements())
+        return getNode(ISD::BUILD_VECTOR, DL, VT, Ops);
     }
     break;
   }
diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index de28fdbb229..35d7c80c0db 100644
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -1004,6 +1004,10 @@ X86TargetLowering::X86TargetLowering(const X86TargetMachine &TM,
   }
 
   if (Subtarget->hasSSE2()) {
+    setOperationAction(ISD::SIGN_EXTEND_VECTOR_INREG, MVT::v2i64, Custom);
+    setOperationAction(ISD::SIGN_EXTEND_VECTOR_INREG, MVT::v4i32, Custom);
+    setOperationAction(ISD::SIGN_EXTEND_VECTOR_INREG, MVT::v8i16, Custom);
+
     setOperationAction(ISD::SRL,               MVT::v8i16, Custom);
     setOperationAction(ISD::SRL,               MVT::v16i8, Custom);
 
@@ -13914,6 +13918,63 @@ static SDValue LowerSIGN_EXTEND_AVX512(SDValue Op, const X86Subtarget *Subtarget
   return DAG.getNode(X86ISD::VTRUNC, dl, VT, V);
 }
 
+static SDValue LowerSIGN_EXTEND_VECTOR_INREG(SDValue Op,
+                                             const X86Subtarget *Subtarget,
+                                             SelectionDAG &DAG) {
+  SDValue In = Op->getOperand(0);
+  MVT VT = Op->getSimpleValueType(0);
+  MVT InVT = In.getSimpleValueType();
+  assert(VT.getSizeInBits() == InVT.getSizeInBits());
+
+  MVT SVT = VT.getScalarType();
+  MVT InSVT = InVT.getScalarType();
+  assert(SVT.getScalarSizeInBits() > InSVT.getScalarSizeInBits());
+
+  if (VT != MVT::v2i64 && VT != MVT::v4i32 && VT != MVT::v8i16)
+    return SDValue();
+  if (InSVT != MVT::i32 && InSVT != MVT::i16 && InSVT != MVT::i8)
+    return SDValue();
+
+  SDLoc dl(Op);
+
+  // SSE41 targets can use the pmovsx* instructions directly.
+  if (Subtarget->hasSSE41())
+    return DAG.getNode(X86ISD::VSEXT, dl, VT, In);
+
+  // pre-SSE41 targets unpack lower lanes and then sign-extend using SRAI.
+  SDValue Curr = In;
+  MVT CurrVT = InVT;
+
+  // As SRAI is only available on i16/i32 types, we expand only up to i32
+  // and handle i64 separately.
+  while (CurrVT != VT && CurrVT.getScalarType() != MVT::i32) {
+    Curr = DAG.getNode(X86ISD::UNPCKL, dl, CurrVT, DAG.getUNDEF(CurrVT), Curr);
+    MVT CurrSVT = MVT::getIntegerVT(CurrVT.getScalarSizeInBits() * 2);
+    CurrVT = MVT::getVectorVT(CurrSVT, CurrVT.getVectorNumElements() / 2);
+    Curr = DAG.getNode(ISD::BITCAST, dl, CurrVT, Curr);
+  }
+
+  SDValue SignExt = Curr;
+  if (CurrVT != InVT) {
+    unsigned SignExtShift =
+        CurrVT.getScalarSizeInBits() - InSVT.getScalarSizeInBits();
+    SignExt = DAG.getNode(X86ISD::VSRAI, dl, CurrVT, Curr,
+                          DAG.getConstant(SignExtShift, dl, MVT::i8));
+  }
+
+  if (CurrVT == VT)
+    return SignExt;
+
+  if (VT == MVT::v2i64 && CurrVT == MVT::v4i32) {
+    SDValue Sign = DAG.getNode(X86ISD::VSRAI, dl, CurrVT, Curr,
+                               DAG.getConstant(31, dl, MVT::i8));
+    SDValue Ext = DAG.getVectorShuffle(CurrVT, dl, SignExt, Sign, {0, 4, 1, 5});
+    return DAG.getNode(ISD::BITCAST, dl, VT, Ext);
+  }
+
+  return SDValue();
+}
+
 static SDValue LowerSIGN_EXTEND(SDValue Op, const X86Subtarget *Subtarget,
                                 SelectionDAG &DAG) {
   MVT VT = Op->getSimpleValueType(0);
@@ -17580,6 +17641,8 @@ SDValue X86TargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const {
   case ISD::ZERO_EXTEND:        return LowerZERO_EXTEND(Op, Subtarget, DAG);
   case ISD::SIGN_EXTEND:        return LowerSIGN_EXTEND(Op, Subtarget, DAG);
   case ISD::ANY_EXTEND:         return LowerANY_EXTEND(Op, Subtarget, DAG);
+  case ISD::SIGN_EXTEND_VECTOR_INREG:
+    return LowerSIGN_EXTEND_VECTOR_INREG(Op, Subtarget, DAG);
   case ISD::FP_TO_SINT:         return LowerFP_TO_SINT(Op, DAG);
   case ISD::FP_TO_UINT:         return LowerFP_TO_UINT(Op, DAG);
   case ISD::FP_EXTEND:          return LowerFP_EXTEND(Op, DAG);
@@ -23683,16 +23746,19 @@ static SDValue PerformSExtCombine(SDNode *N, SelectionDAG &DAG,
                                   const X86Subtarget *Subtarget) {
   SDValue N0 = N->getOperand(0);
   EVT VT = N->getValueType(0);
-  SDLoc dl(N);
+  EVT SVT = VT.getScalarType();
+  EVT InVT = N0->getValueType(0);
+  EVT InSVT = InVT.getScalarType();
+  SDLoc DL(N);
 
   // (i8,i32 sext (sdivrem (i8 x, i8 y)) ->
   // (i8,i32 (sdivrem_sext_hreg (i8 x, i8 y)
   // This exposes the sext to the sdivrem lowering, so that it directly extends
   // from AH (which we otherwise need to do contortions to access).
   if (N0.getOpcode() == ISD::SDIVREM && N0.getResNo() == 1 &&
-      N0.getValueType() == MVT::i8 && VT == MVT::i32) {
+      InVT == MVT::i8 && VT == MVT::i32) {
     SDVTList NodeTys = DAG.getVTList(MVT::i8, VT);
-    SDValue R = DAG.getNode(X86ISD::SDIVREM8_SEXT_HREG, dl, NodeTys,
+    SDValue R = DAG.getNode(X86ISD::SDIVREM8_SEXT_HREG, DL, NodeTys,
                             N0.getOperand(0), N0.getOperand(1));
     DAG.ReplaceAllUsesOfValueWith(N0.getValue(0), R.getValue(0));
     return R.getValue(1);
@@ -23700,14 +23766,57 @@ static SDValue PerformSExtCombine(SDNode *N, SelectionDAG &DAG,
 
   if (!DCI.isBeforeLegalizeOps()) {
     if (N0.getValueType() == MVT::i1) {
-      SDValue Zero = DAG.getConstant(0, dl, VT);
+      SDValue Zero = DAG.getConstant(0, DL, VT);
       SDValue AllOnes =
-        DAG.getConstant(APInt::getAllOnesValue(VT.getSizeInBits()), dl, VT);
-      return DAG.getNode(ISD::SELECT, dl, VT, N0, AllOnes, Zero);
+        DAG.getConstant(APInt::getAllOnesValue(VT.getSizeInBits()), DL, VT);
+      return DAG.getNode(ISD::SELECT, DL, VT, N0, AllOnes, Zero);
     }
     return SDValue();
   }
 
+  if (VT.isVector()) {
+    auto ExtendToVec128 = [&DAG](SDLoc DL, SDValue N) {
+      EVT InVT = N->getValueType(0);
+      EVT OutVT = EVT::getVectorVT(*DAG.getContext(), InVT.getScalarType(),
+                                   128 / InVT.getScalarSizeInBits());
+      SmallVector<SDValue, 8> Opnds(128 / InVT.getSizeInBits(),
+                                    DAG.getUNDEF(InVT));
+      Opnds[0] = N;
+      return DAG.getNode(ISD::CONCAT_VECTORS, DL, OutVT, Opnds);
+    };
+
+    // If target-size is 128-bits, then convert to ISD::SIGN_EXTEND_VECTOR_INREG
+    // which ensures lowering to X86ISD::VSEXT (pmovsx*).
+    if (VT.getSizeInBits() == 128 &&
+        (SVT == MVT::i64 || SVT == MVT::i32 || SVT == MVT::i16) &&
+        (InSVT == MVT::i32 || InSVT == MVT::i16 || InSVT == MVT::i8)) {
+      SDValue ExOp = ExtendToVec128(DL, N0);
+      return DAG.getSignExtendVectorInReg(ExOp, DL, VT);
+    }
+
+    // On pre-AVX2 targets, split into 128-bit nodes of
+    // ISD::SIGN_EXTEND_VECTOR_INREG.
+    if (!Subtarget->hasInt256() && !(VT.getSizeInBits() % 128) &&
+        (SVT == MVT::i64 || SVT == MVT::i32 || SVT == MVT::i16) &&
+        (InSVT == MVT::i32 || InSVT == MVT::i16 || InSVT == MVT::i8)) {
+      unsigned NumVecs = VT.getSizeInBits() / 128;
+      unsigned NumSubElts = 128 / SVT.getSizeInBits();
+      EVT SubVT = EVT::getVectorVT(*DAG.getContext(), SVT, NumSubElts);
+      EVT InSubVT = EVT::getVectorVT(*DAG.getContext(), InSVT, NumSubElts);
+
+      SmallVector<SDValue, 8> Opnds;
+      for (unsigned i = 0, Offset = 0; i != NumVecs;
+           ++i, Offset += NumSubElts) {
+        SDValue SrcVec = DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, InSubVT, N0,
+                                     DAG.getIntPtrConstant(Offset, DL));
+        SrcVec = ExtendToVec128(DL, SrcVec);
+        SrcVec = DAG.getSignExtendVectorInReg(SrcVec, DL, SubVT);
+        Opnds.push_back(SrcVec);
+      }
+      return DAG.getNode(ISD::CONCAT_VECTORS, DL, VT, Opnds);
+    }
+  }
+
   if (!Subtarget->hasFp256())
     return SDValue();
 
diff --git a/test/CodeGen/X86/pr15267.ll b/test/CodeGen/X86/pr15267.ll
index e9f41d9ded4..95d7deb3417 100644
--- a/test/CodeGen/X86/pr15267.ll
+++ b/test/CodeGen/X86/pr15267.ll
@@ -50,20 +50,22 @@ define <4 x i64> @test3(<4 x i1>* %in) nounwind {
 ; CHECK: movq
 ; CHECK: shlq
 ; CHECK: sarq
-; CHECK: vmovq
 ; CHECK: movq
 ; CHECK: shlq
 ; CHECK: sarq
-; CHECK: vmovq
-; CHECK: vpunpcklqdq
+; CHECK: vmovd
+; CHECK: vpinsrd
 ; CHECK: movq
 ; CHECK: shlq
 ; CHECK: sarq
-; CHECK: vmovq
+; CHECK: vpinsrd
 ; CHECK: shlq
 ; CHECK: sarq
-; CHECK: vmovq
-; CHECK: vpunpcklqdq
+; CHECK: vpinsrd
+; CHECK: vpmovsxdq
+; CHECK: vmovd
+; CHECK: vpinsrd
+; CHECK: vpmovsxdq
 ; CHECK: vinsertf128
 ; CHECK: ret
 
diff --git a/test/CodeGen/X86/vec_cast2.ll b/test/CodeGen/X86/vec_cast2.ll
index e50789570ed..1ba11f51baa 100644
--- a/test/CodeGen/X86/vec_cast2.ll
+++ b/test/CodeGen/X86/vec_cast2.ll
@@ -16,13 +16,9 @@ define <8 x float> @foo1_8(<8 x i8> %src) {
 ;
 ; CHECK-WIDE-LABEL: foo1_8:
 ; CHECK-WIDE:       ## BB#0:
-; CHECK-WIDE-NEXT:    vpmovzxbd {{.*#+}} xmm1 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
-; CHECK-WIDE-NEXT:    vpslld $24, %xmm1, %xmm1
-; CHECK-WIDE-NEXT:    vpsrad $24, %xmm1, %xmm1
-; CHECK-WIDE-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
-; CHECK-WIDE-NEXT:    vpunpckhwd {{.*#+}} xmm0 = xmm0[4,4,5,5,6,6,7,7]
-; CHECK-WIDE-NEXT:    vpslld $24, %xmm0, %xmm0
-; CHECK-WIDE-NEXT:    vpsrad $24, %xmm0, %xmm0
+; CHECK-WIDE-NEXT:    vpmovsxbd %xmm0, %xmm1
+; CHECK-WIDE-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
+; CHECK-WIDE-NEXT:    vpmovsxbd %xmm0, %xmm0
 ; CHECK-WIDE-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; CHECK-WIDE-NEXT:    vcvtdq2ps %ymm0, %ymm0
 ; CHECK-WIDE-NEXT:    retl
@@ -40,9 +36,7 @@ define <4 x float> @foo1_4(<4 x i8> %src) {
 ;
 ; CHECK-WIDE-LABEL: foo1_4:
 ; CHECK-WIDE:       ## BB#0:
-; CHECK-WIDE-NEXT:    vpmovzxbd {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[2],zero,zero,zero,xmm0[3],zero,zero,zero
-; CHECK-WIDE-NEXT:    vpslld $24, %xmm0, %xmm0
-; CHECK-WIDE-NEXT:    vpsrad $24, %xmm0, %xmm0
+; CHECK-WIDE-NEXT:    vpmovsxbd %xmm0, %xmm0
 ; CHECK-WIDE-NEXT:    vcvtdq2ps %xmm0, %xmm0
 ; CHECK-WIDE-NEXT:    retl
   %res = sitofp <4 x i8> %src to <4 x float>
diff --git a/test/CodeGen/X86/vector-sext.ll b/test/CodeGen/X86/vector-sext.ll
index c4273710a91..e6acc7efaf3 100644
--- a/test/CodeGen/X86/vector-sext.ll
+++ b/test/CodeGen/X86/vector-sext.ll
@@ -10,37 +10,30 @@
 define <8 x i32> @sext_8i16_to_8i32(<8 x i16> %A) nounwind uwtable readnone ssp {
 ; SSE2-LABEL: sext_8i16_to_8i32:
 ; SSE2:       # BB#0: # %entry
-; SSE2-NEXT:    movdqa %xmm0, %xmm1
-; SSE2-NEXT:   # kill: XMM0<def> XMM1<kill>
-; SSE2-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
-; SSE2-NEXT:    pslld $16, %xmm0
-; SSE2-NEXT:    psrad $16, %xmm0
-; SSE2-NEXT:    punpckhwd {{.*#+}} xmm1 = xmm1[4,4,5,5,6,6,7,7]
-; SSE2-NEXT:    pslld $16, %xmm1
+; SSE2-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3]
+; SSE2-NEXT:    psrad $16, %xmm2
+; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; SSE2-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
 ; SSE2-NEXT:    psrad $16, %xmm1
+; SSE2-NEXT:    movdqa %xmm2, %xmm0
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: sext_8i16_to_8i32:
 ; SSSE3:       # BB#0: # %entry
-; SSSE3-NEXT:    movdqa %xmm0, %xmm1
-; SSSE3-NEXT:   # kill: XMM0<def> XMM1<kill>
-; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
-; SSSE3-NEXT:    pslld $16, %xmm0
-; SSSE3-NEXT:    psrad $16, %xmm0
-; SSSE3-NEXT:    punpckhwd {{.*#+}} xmm1 = xmm1[4,4,5,5,6,6,7,7]
-; SSSE3-NEXT:    pslld $16, %xmm1
+; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3]
+; SSSE3-NEXT:    psrad $16, %xmm2
+; SSSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
 ; SSSE3-NEXT:    psrad $16, %xmm1
+; SSSE3-NEXT:    movdqa %xmm2, %xmm0
 ; SSSE3-NEXT:    retq
 ;
 ; SSE41-LABEL: sext_8i16_to_8i32:
 ; SSE41:       # BB#0: # %entry
-; SSE41-NEXT:    movdqa %xmm0, %xmm1
-; SSE41-NEXT:    pmovzxwd %xmm1, %xmm0
-; SSE41-NEXT:    pslld $16, %xmm0
-; SSE41-NEXT:    psrad $16, %xmm0
-; SSE41-NEXT:    punpckhwd {{.*#+}} xmm1 = xmm1[4,4,5,5,6,6,7,7]
-; SSE41-NEXT:    pslld $16, %xmm1
-; SSE41-NEXT:    psrad $16, %xmm1
+; SSE41-NEXT:    pmovsxwd %xmm0, %xmm2
+; SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; SSE41-NEXT:    pmovsxwd %xmm0, %xmm1
+; SSE41-NEXT:    movdqa %xmm2, %xmm0
 ; SSE41-NEXT:    retq
 ;
 ; AVX1-LABEL: sext_8i16_to_8i32:
@@ -58,13 +51,10 @@ define <8 x i32> @sext_8i16_to_8i32(<8 x i16> %A) nounwind uwtable readnone ssp
 ;
 ; X32-SSE41-LABEL: sext_8i16_to_8i32:
 ; X32-SSE41:       # BB#0: # %entry
-; X32-SSE41-NEXT:    movdqa %xmm0, %xmm1
-; X32-SSE41-NEXT:    pmovzxwd %xmm1, %xmm0
-; X32-SSE41-NEXT:    pslld $16, %xmm0
-; X32-SSE41-NEXT:    psrad $16, %xmm0
-; X32-SSE41-NEXT:    punpckhwd {{.*#+}} xmm1 = xmm1[4,4,5,5,6,6,7,7]
-; X32-SSE41-NEXT:    pslld $16, %xmm1
-; X32-SSE41-NEXT:    psrad $16, %xmm1
+; X32-SSE41-NEXT:    pmovsxwd %xmm0, %xmm2
+; X32-SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; X32-SSE41-NEXT:    pmovsxwd %xmm0, %xmm1
+; X32-SSE41-NEXT:    movdqa %xmm2, %xmm0
 ; X32-SSE41-NEXT:    retl
 entry:
   %B = sext <8 x i16> %A to <8 x i32>
@@ -74,68 +64,31 @@ entry:
 define <4 x i64> @sext_4i32_to_4i64(<4 x i32> %A) nounwind uwtable readnone ssp {
 ; SSE2-LABEL: sext_4i32_to_4i64:
 ; SSE2:       # BB#0: # %entry
-; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[0,1,1,3]
-; SSE2-NEXT:    movd %xmm1, %rax
-; SSE2-NEXT:    cltq
-; SSE2-NEXT:    movd %rax, %xmm2
-; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
-; SSE2-NEXT:    movd %xmm1, %rax
-; SSE2-NEXT:    cltq
-; SSE2-NEXT:    movd %rax, %xmm1
-; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm1[0]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,2,3,3]
-; SSE2-NEXT:    movd %xmm0, %rax
-; SSE2-NEXT:    cltq
-; SSE2-NEXT:    movd %rax, %xmm1
-; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
-; SSE2-NEXT:    movd %xmm0, %rax
-; SSE2-NEXT:    cltq
-; SSE2-NEXT:    movd %rax, %xmm0
-; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm0[0]
-; SSE2-NEXT:    movdqa %xmm2, %xmm0
+; SSE2-NEXT:    movdqa %xmm0, %xmm2
+; SSE2-NEXT:    psrad $31, %xmm2
+; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
+; SSE2-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
+; SSE2-NEXT:    movdqa %xmm1, %xmm2
+; SSE2-NEXT:    psrad $31, %xmm2
+; SSE2-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: sext_4i32_to_4i64:
 ; SSSE3:       # BB#0: # %entry
-; SSSE3-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[0,1,1,3]
-; SSSE3-NEXT:    movd %xmm1, %rax
-; SSSE3-NEXT:    cltq
-; SSSE3-NEXT:    movd %rax, %xmm2
-; SSSE3-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
-; SSSE3-NEXT:    movd %xmm1, %rax
-; SSSE3-NEXT:    cltq
-; SSSE3-NEXT:    movd %rax, %xmm1
-; SSSE3-NEXT:    punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm1[0]
-; SSSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,2,3,3]
-; SSSE3-NEXT:    movd %xmm0, %rax
-; SSSE3-NEXT:    cltq
-; SSSE3-NEXT:    movd %rax, %xmm1
-; SSSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
-; SSSE3-NEXT:    movd %xmm0, %rax
-; SSSE3-NEXT:    cltq
-; SSSE3-NEXT:    movd %rax, %xmm0
-; SSSE3-NEXT:    punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm0[0]
-; SSSE3-NEXT:    movdqa %xmm2, %xmm0
+; SSSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSSE3-NEXT:    psrad $31, %xmm2
+; SSSE3-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
+; SSSE3-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
+; SSSE3-NEXT:    movdqa %xmm1, %xmm2
+; SSSE3-NEXT:    psrad $31, %xmm2
+; SSSE3-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
 ; SSSE3-NEXT:    retq
 ;
 ; SSE41-LABEL: sext_4i32_to_4i64:
 ; SSE41:       # BB#0: # %entry
-; SSE41-NEXT:    pmovzxdq %xmm0, %xmm1
-; SSE41-NEXT:    pextrq $1, %xmm1, %rax
-; SSE41-NEXT:    cltq
-; SSE41-NEXT:    movd %rax, %xmm3
-; SSE41-NEXT:    movd %xmm1, %rax
-; SSE41-NEXT:    cltq
-; SSE41-NEXT:    movd %rax, %xmm2
-; SSE41-NEXT:    punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm3[0]
-; SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,2,3,3]
-; SSE41-NEXT:    pextrq $1, %xmm0, %rax
-; SSE41-NEXT:    cltq
-; SSE41-NEXT:    movd %rax, %xmm3
-; SSE41-NEXT:    movd %xmm0, %rax
-; SSE41-NEXT:    cltq
-; SSE41-NEXT:    movd %rax, %xmm1
-; SSE41-NEXT:    punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm3[0]
+; SSE41-NEXT:    pmovsxdq %xmm0, %xmm2
+; SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; SSE41-NEXT:    pmovsxdq %xmm0, %xmm1
 ; SSE41-NEXT:    movdqa %xmm2, %xmm0
 ; SSE41-NEXT:    retq
 ;
@@ -154,20 +107,9 @@ define <4 x i64> @sext_4i32_to_4i64(<4 x i32> %A) nounwind uwtable readnone ssp
 ;
 ; X32-SSE41-LABEL: sext_4i32_to_4i64:
 ; X32-SSE41:       # BB#0: # %entry
-; X32-SSE41-NEXT:    pmovzxdq %xmm0, %xmm2
-; X32-SSE41-NEXT:    movd %xmm2, %eax
-; X32-SSE41-NEXT:    sarl $31, %eax
-; X32-SSE41-NEXT:    pextrd $2, %xmm2, %ecx
-; X32-SSE41-NEXT:    pinsrd $1, %eax, %xmm2
-; X32-SSE41-NEXT:    sarl $31, %ecx
-; X32-SSE41-NEXT:    pinsrd $3, %ecx, %xmm2
-; X32-SSE41-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[2,2,3,3]
-; X32-SSE41-NEXT:    movd %xmm1, %eax
-; X32-SSE41-NEXT:    sarl $31, %eax
-; X32-SSE41-NEXT:    pextrd $2, %xmm1, %ecx
-; X32-SSE41-NEXT:    pinsrd $1, %eax, %xmm1
-; X32-SSE41-NEXT:    sarl $31, %ecx
-; X32-SSE41-NEXT:    pinsrd $3, %ecx, %xmm1
+; X32-SSE41-NEXT:    pmovsxdq %xmm0, %xmm2
+; X32-SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; X32-SSE41-NEXT:    pmovsxdq %xmm0, %xmm1
 ; X32-SSE41-NEXT:    movdqa %xmm2, %xmm0
 ; X32-SSE41-NEXT:    retl
 entry:
@@ -252,20 +194,26 @@ entry:
 define <2 x i64> @load_sext_test3(<2 x i8> *%ptr) {
 ; SSE2-LABEL: load_sext_test3:
 ; SSE2:       # BB#0: # %entry
-; SSE2-NEXT:    movsbq 1(%rdi), %rax
-; SSE2-NEXT:    movd %rax, %xmm1
-; SSE2-NEXT:    movsbq (%rdi), %rax
-; SSE2-NEXT:    movd %rax, %xmm0
-; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; SSE2-NEXT:    movzwl (%rdi), %eax
+; SSE2-NEXT:    movd %eax, %xmm0
+; SSE2-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
+; SSE2-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrad $31, %xmm1
+; SSE2-NEXT:    psrad $24, %xmm0
+; SSE2-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: load_sext_test3:
 ; SSSE3:       # BB#0: # %entry
-; SSSE3-NEXT:    movsbq 1(%rdi), %rax
-; SSSE3-NEXT:    movd %rax, %xmm1
-; SSSE3-NEXT:    movsbq (%rdi), %rax
-; SSSE3-NEXT:    movd %rax, %xmm0
-; SSSE3-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; SSSE3-NEXT:    movzwl (%rdi), %eax
+; SSSE3-NEXT:    movd %eax, %xmm0
+; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
+; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
+; SSSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSSE3-NEXT:    psrad $31, %xmm1
+; SSSE3-NEXT:    psrad $24, %xmm0
+; SSSE3-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
 ; SSSE3-NEXT:    retq
 ;
 ; SSE41-LABEL: load_sext_test3:
@@ -292,20 +240,22 @@ entry:
 define <2 x i64> @load_sext_test4(<2 x i16> *%ptr) {
 ; SSE2-LABEL: load_sext_test4:
 ; SSE2:       # BB#0: # %entry
-; SSE2-NEXT:    movswq 2(%rdi), %rax
-; SSE2-NEXT:    movd %rax, %xmm1
-; SSE2-NEXT:    movswq (%rdi), %rax
-; SSE2-NEXT:    movd %rax, %xmm0
-; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; SSE2-NEXT:    movd (%rdi), %xmm0
+; SSE2-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrad $31, %xmm1
+; SSE2-NEXT:    psrad $16, %xmm0
+; SSE2-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: load_sext_test4:
 ; SSSE3:       # BB#0: # %entry
-; SSSE3-NEXT:    movswq 2(%rdi), %rax
-; SSSE3-NEXT:    movd %rax, %xmm1
-; SSSE3-NEXT:    movswq (%rdi), %rax
-; SSSE3-NEXT:    movd %rax, %xmm0
-; SSSE3-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; SSSE3-NEXT:    movd (%rdi), %xmm0
+; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
+; SSSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSSE3-NEXT:    psrad $31, %xmm1
+; SSSE3-NEXT:    psrad $16, %xmm0
+; SSSE3-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
 ; SSSE3-NEXT:    retq
 ;
 ; SSE41-LABEL: load_sext_test4:
@@ -332,20 +282,18 @@ entry:
 define <2 x i64> @load_sext_test5(<2 x i32> *%ptr) {
 ; SSE2-LABEL: load_sext_test5:
 ; SSE2:       # BB#0: # %entry
-; SSE2-NEXT:    movslq 4(%rdi), %rax
-; SSE2-NEXT:    movd %rax, %xmm1
-; SSE2-NEXT:    movslq (%rdi), %rax
-; SSE2-NEXT:    movd %rax, %xmm0
-; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; SSE2-NEXT:    movq (%rdi), %xmm0
+; SSE2-NEXT:    movdqa %xmm0, %xmm1
+; SSE2-NEXT:    psrad $31, %xmm1
+; SSE2-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: load_sext_test5:
 ; SSSE3:       # BB#0: # %entry
-; SSSE3-NEXT:    movslq 4(%rdi), %rax
-; SSSE3-NEXT:    movd %rax, %xmm1
-; SSSE3-NEXT:    movslq (%rdi), %rax
-; SSSE3-NEXT:    movd %rax, %xmm0
-; SSSE3-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; SSSE3-NEXT:    movq (%rdi), %xmm0
+; SSSE3-NEXT:    movdqa %xmm0, %xmm1
+; SSSE3-NEXT:    psrad $31, %xmm1
+; SSSE3-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
 ; SSSE3-NEXT:    retq
 ;
 ; SSE41-LABEL: load_sext_test5:
@@ -410,72 +358,35 @@ define <4 x i64> @sext_4i1_to_4i64(<4 x i1> %mask) {
 ; SSE2:       # BB#0:
 ; SSE2-NEXT:    pslld $31, %xmm0
 ; SSE2-NEXT:    psrad $31, %xmm0
-; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[0,1,1,3]
-; SSE2-NEXT:    movd %xmm1, %rax
-; SSE2-NEXT:    cltq
-; SSE2-NEXT:    movd %rax, %xmm2
-; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
-; SSE2-NEXT:    movd %xmm1, %rax
-; SSE2-NEXT:    cltq
-; SSE2-NEXT:    movd %rax, %xmm1
-; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm1[0]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,2,3,3]
-; SSE2-NEXT:    movd %xmm0, %rax
-; SSE2-NEXT:    cltq
-; SSE2-NEXT:    movd %rax, %xmm1
-; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
-; SSE2-NEXT:    movd %xmm0, %rax
-; SSE2-NEXT:    cltq
-; SSE2-NEXT:    movd %rax, %xmm0
-; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm0[0]
-; SSE2-NEXT:    movdqa %xmm2, %xmm0
+; SSE2-NEXT:    movdqa %xmm0, %xmm2
+; SSE2-NEXT:    psrad $31, %xmm2
+; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
+; SSE2-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
+; SSE2-NEXT:    movdqa %xmm1, %xmm2
+; SSE2-NEXT:    psrad $31, %xmm2
+; SSE2-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: sext_4i1_to_4i64:
 ; SSSE3:       # BB#0:
 ; SSSE3-NEXT:    pslld $31, %xmm0
 ; SSSE3-NEXT:    psrad $31, %xmm0
-; SSSE3-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[0,1,1,3]
-; SSSE3-NEXT:    movd %xmm1, %rax
-; SSSE3-NEXT:    cltq
-; SSSE3-NEXT:    movd %rax, %xmm2
-; SSSE3-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
-; SSSE3-NEXT:    movd %xmm1, %rax
-; SSSE3-NEXT:    cltq
-; SSSE3-NEXT:    movd %rax, %xmm1
-; SSSE3-NEXT:    punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm1[0]
-; SSSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,2,3,3]
-; SSSE3-NEXT:    movd %xmm0, %rax
-; SSSE3-NEXT:    cltq
-; SSSE3-NEXT:    movd %rax, %xmm1
-; SSSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
-; SSSE3-NEXT:    movd %xmm0, %rax
-; SSSE3-NEXT:    cltq
-; SSSE3-NEXT:    movd %rax, %xmm0
-; SSSE3-NEXT:    punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm0[0]
-; SSSE3-NEXT:    movdqa %xmm2, %xmm0
+; SSSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSSE3-NEXT:    psrad $31, %xmm2
+; SSSE3-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
+; SSSE3-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
+; SSSE3-NEXT:    movdqa %xmm1, %xmm2
+; SSSE3-NEXT:    psrad $31, %xmm2
+; SSSE3-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
 ; SSSE3-NEXT:    retq
 ;
 ; SSE41-LABEL: sext_4i1_to_4i64:
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pslld $31, %xmm0
 ; SSE41-NEXT:    psrad $31, %xmm0
-; SSE41-NEXT:    pmovzxdq %xmm0, %xmm1
-; SSE41-NEXT:    pextrq $1, %xmm1, %rax
-; SSE41-NEXT:    cltq
-; SSE41-NEXT:    movd %rax, %xmm3
-; SSE41-NEXT:    movd %xmm1, %rax
-; SSE41-NEXT:    cltq
-; SSE41-NEXT:    movd %rax, %xmm2
-; SSE41-NEXT:    punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm3[0]
-; SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,2,3,3]
-; SSE41-NEXT:    pextrq $1, %xmm0, %rax
-; SSE41-NEXT:    cltq
-; SSE41-NEXT:    movd %rax, %xmm3
-; SSE41-NEXT:    movd %xmm0, %rax
-; SSE41-NEXT:    cltq
-; SSE41-NEXT:    movd %rax, %xmm1
-; SSE41-NEXT:    punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm3[0]
+; SSE41-NEXT:    pmovsxdq %xmm0, %xmm2
+; SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; SSE41-NEXT:    pmovsxdq %xmm0, %xmm1
 ; SSE41-NEXT:    movdqa %xmm2, %xmm0
 ; SSE41-NEXT:    retq
 ;
@@ -500,20 +411,9 @@ define <4 x i64> @sext_4i1_to_4i64(<4 x i1> %mask) {
 ; X32-SSE41:       # BB#0:
 ; X32-SSE41-NEXT:    pslld $31, %xmm0
 ; X32-SSE41-NEXT:    psrad $31, %xmm0
-; X32-SSE41-NEXT:    pmovzxdq %xmm0, %xmm2
-; X32-SSE41-NEXT:    movd %xmm2, %eax
-; X32-SSE41-NEXT:    sarl $31, %eax
-; X32-SSE41-NEXT:    pextrd $2, %xmm2, %ecx
-; X32-SSE41-NEXT:    pinsrd $1, %eax, %xmm2
-; X32-SSE41-NEXT:    sarl $31, %ecx
-; X32-SSE41-NEXT:    pinsrd $3, %ecx, %xmm2
-; X32-SSE41-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[2,2,3,3]
-; X32-SSE41-NEXT:    movd %xmm1, %eax
-; X32-SSE41-NEXT:    sarl $31, %eax
-; X32-SSE41-NEXT:    pextrd $2, %xmm1, %ecx
-; X32-SSE41-NEXT:    pinsrd $1, %eax, %xmm1
-; X32-SSE41-NEXT:    sarl $31, %ecx
-; X32-SSE41-NEXT:    pinsrd $3, %ecx, %xmm1
+; X32-SSE41-NEXT:    pmovsxdq %xmm0, %xmm2
+; X32-SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; X32-SSE41-NEXT:    pmovsxdq %xmm0, %xmm1
 ; X32-SSE41-NEXT:    movdqa %xmm2, %xmm0
 ; X32-SSE41-NEXT:    retl
   %extmask = sext <4 x i1> %mask to <4 x i64>
@@ -576,72 +476,35 @@ define <4 x i64> @sext_4i8_to_4i64(<4 x i8> %mask) {
 ; SSE2:       # BB#0:
 ; SSE2-NEXT:    pslld $24, %xmm0
 ; SSE2-NEXT:    psrad $24, %xmm0
-; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[0,1,1,3]
-; SSE2-NEXT:    movd %xmm1, %rax
-; SSE2-NEXT:    cltq
-; SSE2-NEXT:    movd %rax, %xmm2
-; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
-; SSE2-NEXT:    movd %xmm1, %rax
-; SSE2-NEXT:    cltq
-; SSE2-NEXT:    movd %rax, %xmm1
-; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm1[0]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,2,3,3]
-; SSE2-NEXT:    movd %xmm0, %rax
-; SSE2-NEXT:    cltq
-; SSE2-NEXT:    movd %rax, %xmm1
-; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
-; SSE2-NEXT:    movd %xmm0, %rax
-; SSE2-NEXT:    cltq
-; SSE2-NEXT:    movd %rax, %xmm0
-; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm0[0]
-; SSE2-NEXT:    movdqa %xmm2, %xmm0
+; SSE2-NEXT:    movdqa %xmm0, %xmm2
+; SSE2-NEXT:    psrad $31, %xmm2
+; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
+; SSE2-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
+; SSE2-NEXT:    movdqa %xmm1, %xmm2
+; SSE2-NEXT:    psrad $31, %xmm2
+; SSE2-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: sext_4i8_to_4i64:
 ; SSSE3:       # BB#0:
 ; SSSE3-NEXT:    pslld $24, %xmm0
 ; SSSE3-NEXT:    psrad $24, %xmm0
-; SSSE3-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[0,1,1,3]
-; SSSE3-NEXT:    movd %xmm1, %rax
-; SSSE3-NEXT:    cltq
-; SSSE3-NEXT:    movd %rax, %xmm2
-; SSSE3-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
-; SSSE3-NEXT:    movd %xmm1, %rax
-; SSSE3-NEXT:    cltq
-; SSSE3-NEXT:    movd %rax, %xmm1
-; SSSE3-NEXT:    punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm1[0]
-; SSSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,2,3,3]
-; SSSE3-NEXT:    movd %xmm0, %rax
-; SSSE3-NEXT:    cltq
-; SSSE3-NEXT:    movd %rax, %xmm1
-; SSSE3-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
-; SSSE3-NEXT:    movd %xmm0, %rax
-; SSSE3-NEXT:    cltq
-; SSSE3-NEXT:    movd %rax, %xmm0
-; SSSE3-NEXT:    punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm0[0]
-; SSSE3-NEXT:    movdqa %xmm2, %xmm0
+; SSSE3-NEXT:    movdqa %xmm0, %xmm2
+; SSSE3-NEXT:    psrad $31, %xmm2
+; SSSE3-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[2,3,0,1]
+; SSSE3-NEXT:    punpckldq {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
+; SSSE3-NEXT:    movdqa %xmm1, %xmm2
+; SSSE3-NEXT:    psrad $31, %xmm2
+; SSSE3-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
 ; SSSE3-NEXT:    retq
 ;
 ; SSE41-LABEL: sext_4i8_to_4i64:
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pslld $24, %xmm0
 ; SSE41-NEXT:    psrad $24, %xmm0
-; SSE41-NEXT:    pmovzxdq %xmm0, %xmm1
-; SSE41-NEXT:    pextrq $1, %xmm1, %rax
-; SSE41-NEXT:    cltq
-; SSE41-NEXT:    movd %rax, %xmm3
-; SSE41-NEXT:    movd %xmm1, %rax
-; SSE41-NEXT:    cltq
-; SSE41-NEXT:    movd %rax, %xmm2
-; SSE41-NEXT:    punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm3[0]
-; SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,2,3,3]
-; SSE41-NEXT:    pextrq $1, %xmm0, %rax
-; SSE41-NEXT:    cltq
-; SSE41-NEXT:    movd %rax, %xmm3
-; SSE41-NEXT:    movd %xmm0, %rax
-; SSE41-NEXT:    cltq
-; SSE41-NEXT:    movd %rax, %xmm1
-; SSE41-NEXT:    punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm3[0]
+; SSE41-NEXT:    pmovsxdq %xmm0, %xmm2
+; SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; SSE41-NEXT:    pmovsxdq %xmm0, %xmm1
 ; SSE41-NEXT:    movdqa %xmm2, %xmm0
 ; SSE41-NEXT:    retq
 ;
@@ -666,20 +529,9 @@ define <4 x i64> @sext_4i8_to_4i64(<4 x i8> %mask) {
 ; X32-SSE41:       # BB#0:
 ; X32-SSE41-NEXT:    pslld $24, %xmm0
 ; X32-SSE41-NEXT:    psrad $24, %xmm0
-; X32-SSE41-NEXT:    pmovzxdq %xmm0, %xmm2
-; X32-SSE41-NEXT:    movd %xmm2, %eax
-; X32-SSE41-NEXT:    sarl $31, %eax
-; X32-SSE41-NEXT:    pextrd $2, %xmm2, %ecx
-; X32-SSE41-NEXT:    pinsrd $1, %eax, %xmm2
-; X32-SSE41-NEXT:    sarl $31, %ecx
-; X32-SSE41-NEXT:    pinsrd $3, %ecx, %xmm2
-; X32-SSE41-NEXT:    pshufd {{.*#+}} xmm1 = xmm0[2,2,3,3]
-; X32-SSE41-NEXT:    movd %xmm1, %eax
-; X32-SSE41-NEXT:    sarl $31, %eax
-; X32-SSE41-NEXT:    pextrd $2, %xmm1, %ecx
-; X32-SSE41-NEXT:    pinsrd $1, %eax, %xmm1
-; X32-SSE41-NEXT:    sarl $31, %ecx
-; X32-SSE41-NEXT:    pinsrd $3, %ecx, %xmm1
+; X32-SSE41-NEXT:    pmovsxdq %xmm0, %xmm2
+; X32-SSE41-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; X32-SSE41-NEXT:    pmovsxdq %xmm0, %xmm1
 ; X32-SSE41-NEXT:    movdqa %xmm2, %xmm0
 ; X32-SSE41-NEXT:    retl
   %extmask = sext <4 x i8> %mask to <4 x i64>
diff --git a/test/CodeGen/X86/vselect-avx.ll b/test/CodeGen/X86/vselect-avx.ll
index ff26aebaac6..de04a097de0 100644
--- a/test/CodeGen/X86/vselect-avx.ll
+++ b/test/CodeGen/X86/vselect-avx.ll
@@ -14,8 +14,8 @@ target triple = "x86_64-apple-macosx"
 ; <rdar://problem/18675020>
 
 ; CHECK-LABEL: test:
-; CHECK: vmovdqa {{.*#+}} xmm0 = [65535,0,0,65535]
-; CHECK: vmovdqa {{.*#+}} xmm2 = [65533,124,125,14807]
+; CHECK: vmovdqa {{.*#+}} xmm1 = [65533,124,125,14807]
+; CHECK: vmovdqa {{.*#+}} xmm1 = [65535,0,0,65535]
 ; CHECK: ret
 define void @test(<4 x i16>* %a, <4 x i16>* %b) {
 body:
@@ -33,13 +33,14 @@ body:
 ; of the condition.
 ;
 ; CHECK-LABEL: test2:
-; CHECK:	vpslld	$31, %xmm0, %xmm0
-; CHECK-NEXT:	vpmovsxdq	%xmm0, %xmm1
-; CHECK-NEXT:	vpshufd	$78, %xmm0, %xmm0       ## xmm0 = xmm0[2,3,0,1]
-; CHECK-NEXT:	vpmovsxdq	%xmm0, %xmm0
-; CHECK-NEXT:	vinsertf128	$1, %xmm0, %ymm1, [[MASK:%ymm[0-9]+]]
-; CHECK: vblendvpd	[[MASK]]
-; CHECK: retq
+; CHECK:       vpslld $31, %xmm0, %xmm0
+; CHECK-NEXT:  vpsrad $31, %xmm0, %xmm0
+; CHECK-NEXT:  vpmovsxdq %xmm0, %xmm1
+; CHECK-NEXT:  vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; CHECK-NEXT:  vpmovsxdq %xmm0, %xmm0
+; CHECK-NEXT:  vinsertf128 $1, %xmm0, %ymm1, [[MASK:%ymm[0-9]+]]
+; CHECK:       vblendvpd [[MASK]]
+; CHECK:       retq
 define void @test2(double** %call1559, i64 %indvars.iv4198, <4 x i1> %tmp1895) {
 bb:
   %arrayidx1928 = getelementptr inbounds double*, double** %call1559, i64 %indvars.iv4198