Teach SDISel to combine fsin / fcos into a fsincos node if the following

conditions are met:
1. They share the same operand and are in the same BB.
2. Both outputs are used.
3. The target has a native instruction that maps to ISD::FSINCOS node or
   the target provides a sincos library call.

Implemented the generic optimization in sdisel and enabled it for
Mac OSX. Also added an additional optimization for x86_64 Mac OSX by
using an alternative entry point __sincos_stret which returns the two
results in xmm0 / xmm1.

rdar://13087969
PR13204


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@173755 91177308-0d34-0410-b5e6-96231b3b80d8

15 files changed, 248 insertions, 24 deletions

diff --git a/include/llvm/CodeGen/ISDOpcodes.h b/include/llvm/CodeGen/ISDOpcodes.h
index 5d0a3b4c70..092fa5a2c0 100644
--- a/include/llvm/CodeGen/ISDOpcodes.h
+++ b/include/llvm/CodeGen/ISDOpcodes.h
@@ -455,6 +455,9 @@ namespace ISD {
     FNEG, FABS, FSQRT, FSIN, FCOS, FPOWI, FPOW,
     FLOG, FLOG2, FLOG10, FEXP, FEXP2,
     FCEIL, FTRUNC, FRINT, FNEARBYINT, FFLOOR,
+    
+    /// FSINCOS - Compute both fsin and fcos as a single operation.
+    FSINCOS,
 
     /// LOAD and STORE have token chains as their first operand, then the same
     /// operands as an LLVM load/store instruction, then an offset node that
diff --git a/include/llvm/CodeGen/RuntimeLibcalls.h b/include/llvm/CodeGen/RuntimeLibcalls.h
index 1a9dc1cce3..41289a42c4 100644
--- a/include/llvm/CodeGen/RuntimeLibcalls.h
+++ b/include/llvm/CodeGen/RuntimeLibcalls.h
@@ -158,6 +158,11 @@ namespace RTLIB {
     COS_F80,
     COS_F128,
     COS_PPCF128,
+    SINCOS_F32,
+    SINCOS_F64,
+    SINCOS_F80,
+    SINCOS_F128,
+    SINCOS_PPCF128,
     POW_F32,
     POW_F64,
     POW_F80,
diff --git a/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp b/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
index d37edab66e..6a3e03b393 100644
--- a/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
+++ b/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
@@ -102,7 +102,8 @@ private:
                                                  SDNode *Node, bool isSigned);
   SDValue ExpandFPLibCall(SDNode *Node, RTLIB::Libcall Call_F32,
                           RTLIB::Libcall Call_F64, RTLIB::Libcall Call_F80,
-                          RTLIB::Libcall Call_F128, RTLIB::Libcall Call_PPCF128);
+                          RTLIB::Libcall Call_F128,
+                          RTLIB::Libcall Call_PPCF128);
   SDValue ExpandIntLibCall(SDNode *Node, bool isSigned,
                            RTLIB::Libcall Call_I8,
                            RTLIB::Libcall Call_I16,
@@ -110,6 +111,7 @@ private:
                            RTLIB::Libcall Call_I64,
                            RTLIB::Libcall Call_I128);
   void ExpandDivRemLibCall(SDNode *Node, SmallVectorImpl<SDValue> &Results);
+  void ExpandSinCosLibCall(SDNode *Node, SmallVectorImpl<SDValue> &Results);
 
   SDValue EmitStackConvert(SDValue SrcOp, EVT SlotVT, EVT DestVT, DebugLoc dl);
   SDValue ExpandBUILD_VECTOR(SDNode *Node);
@@ -2095,6 +2097,106 @@ SelectionDAGLegalize::ExpandDivRemLibCall(SDNode *Node,
   Results.push_back(Rem);
 }
 
+/// isSinCosLibcallAvailable - Return true if sincos libcall is available.
+static bool isSinCosLibcallAvailable(SDNode *Node, const TargetLowering &TLI) {
+  RTLIB::Libcall LC;
+  switch (Node->getValueType(0).getSimpleVT().SimpleTy) {
+  default: llvm_unreachable("Unexpected request for libcall!");
+  case MVT::f32:     LC = RTLIB::SINCOS_F32; break;
+  case MVT::f64:     LC = RTLIB::SINCOS_F64; break;
+  case MVT::f80:     LC = RTLIB::SINCOS_F80; break;
+  case MVT::f128:    LC = RTLIB::SINCOS_F128; break;
+  case MVT::ppcf128: LC = RTLIB::SINCOS_PPCF128; break;
+  }
+  return TLI.getLibcallName(LC) != 0;
+}
+
+/// useSinCos - Only issue sincos libcall if both sin and cos are
+/// needed.
+static bool useSinCos(SDNode *Node) {
+  unsigned OtherOpcode = Node->getOpcode() == ISD::FSIN
+    ? ISD::FCOS : ISD::FSIN;
+  
+  SDValue Op0 = Node->getOperand(0);
+  for (SDNode::use_iterator UI = Op0.getNode()->use_begin(),
+       UE = Op0.getNode()->use_end(); UI != UE; ++UI) {
+    SDNode *User = *UI;
+    if (User == Node)
+      continue;
+    // The other user might have been turned into sincos already.
+    if (User->getOpcode() == OtherOpcode || User->getOpcode() == ISD::FSINCOS)
+      return true;
+  }
+  return false;
+}
+
+/// ExpandSinCosLibCall - Issue libcalls to sincos to compute sin / cos
+/// pairs.
+void
+SelectionDAGLegalize::ExpandSinCosLibCall(SDNode *Node,
+                                          SmallVectorImpl<SDValue> &Results) {
+  RTLIB::Libcall LC;
+  switch (Node->getValueType(0).getSimpleVT().SimpleTy) {
+  default: llvm_unreachable("Unexpected request for libcall!");
+  case MVT::f32:     LC = RTLIB::SINCOS_F32; break;
+  case MVT::f64:     LC = RTLIB::SINCOS_F64; break;
+  case MVT::f80:     LC = RTLIB::SINCOS_F80; break;
+  case MVT::f128:    LC = RTLIB::SINCOS_F128; break;
+  case MVT::ppcf128: LC = RTLIB::SINCOS_PPCF128; break;
+  }
+  
+  // The input chain to this libcall is the entry node of the function.
+  // Legalizing the call will automatically add the previous call to the
+  // dependence.
+  SDValue InChain = DAG.getEntryNode();
+  
+  EVT RetVT = Node->getValueType(0);
+  Type *RetTy = RetVT.getTypeForEVT(*DAG.getContext());
+  
+  TargetLowering::ArgListTy Args;
+  TargetLowering::ArgListEntry Entry;
+  
+  // Pass the argument.
+  Entry.Node = Node->getOperand(0);
+  Entry.Ty = RetTy;
+  Entry.isSExt = false;
+  Entry.isZExt = false;
+  Args.push_back(Entry);
+  
+  // Pass the return address of sin.
+  SDValue SinPtr = DAG.CreateStackTemporary(RetVT);
+  Entry.Node = SinPtr;
+  Entry.Ty = RetTy->getPointerTo();
+  Entry.isSExt = false;
+  Entry.isZExt = false;
+  Args.push_back(Entry);
+  
+  // Also pass the return address of the cos.
+  SDValue CosPtr = DAG.CreateStackTemporary(RetVT);
+  Entry.Node = CosPtr;
+  Entry.Ty = RetTy->getPointerTo();
+  Entry.isSExt = false;
+  Entry.isZExt = false;
+  Args.push_back(Entry);
+  
+  SDValue Callee = DAG.getExternalSymbol(TLI.getLibcallName(LC),
+                                         TLI.getPointerTy());
+  
+  DebugLoc dl = Node->getDebugLoc();
+  TargetLowering::
+  CallLoweringInfo CLI(InChain, Type::getVoidTy(*DAG.getContext()),
+                       false, false, false, false,
+                       0, TLI.getLibcallCallingConv(LC), /*isTailCall=*/false,
+                       /*doesNotReturn=*/false, /*isReturnValueUsed=*/true,
+                       Callee, Args, DAG, dl);
+  std::pair<SDValue, SDValue> CallInfo = TLI.LowerCallTo(CLI);
+
+  Results.push_back(DAG.getLoad(RetVT, dl, CallInfo.second, SinPtr,
+                                MachinePointerInfo(), false, false, false, 0));
+  Results.push_back(DAG.getLoad(RetVT, dl, CallInfo.second, CosPtr,
+                                MachinePointerInfo(), false, false, false, 0));
+}
+
 /// ExpandLegalINT_TO_FP - This function is responsible for legalizing a
 /// INT_TO_FP operation of the specified operand when the target requests that
 /// we expand it.  At this point, we know that the result and operand types are
@@ -3041,14 +3143,33 @@ void SelectionDAGLegalize::ExpandNode(SDNode *Node) {
                                       RTLIB::SQRT_PPCF128));
     break;
   case ISD::FSIN:
-    Results.push_back(ExpandFPLibCall(Node, RTLIB::SIN_F32, RTLIB::SIN_F64,
-                                      RTLIB::SIN_F80, RTLIB::SIN_F128,
-                                      RTLIB::SIN_PPCF128));
+  case ISD::FCOS: {
+    EVT VT = Node->getValueType(0);
+    bool isSIN = Node->getOpcode() == ISD::FSIN;
+    // Turn fsin / fcos into ISD::FSINCOS node if there are a pair of fsin /
+    // fcos which share the same operand and both are used.
+    if ((TLI.isOperationLegalOrCustom(ISD::FSINCOS, VT) ||
+         isSinCosLibcallAvailable(Node, TLI))
+        && useSinCos(Node)) {
+      SDVTList VTs = DAG.getVTList(VT, VT);
+      Tmp1 = DAG.getNode(ISD::FSINCOS, dl, VTs, Node->getOperand(0));
+      if (!isSIN)
+        Tmp1 = Tmp1.getValue(1);
+      Results.push_back(Tmp1);
+    } else if (isSIN) {
+      Results.push_back(ExpandFPLibCall(Node, RTLIB::SIN_F32, RTLIB::SIN_F64,
+                                        RTLIB::SIN_F80, RTLIB::SIN_F128,
+                                        RTLIB::SIN_PPCF128));
+    } else {
+      Results.push_back(ExpandFPLibCall(Node, RTLIB::COS_F32, RTLIB::COS_F64,
+                                        RTLIB::COS_F80, RTLIB::COS_F128,
+                                        RTLIB::COS_PPCF128));
+    }
     break;
-  case ISD::FCOS:
-    Results.push_back(ExpandFPLibCall(Node, RTLIB::COS_F32, RTLIB::COS_F64,
-                                      RTLIB::COS_F80, RTLIB::COS_F128,
-                                      RTLIB::COS_PPCF128));
+  }
+  case ISD::FSINCOS:
+    // Expand into sincos libcall.
+    ExpandSinCosLibCall(Node, Results);
     break;
   case ISD::FLOG:
     Results.push_back(ExpandFPLibCall(Node, RTLIB::LOG_F32, RTLIB::LOG_F64,
@@ -3181,7 +3302,6 @@ void SelectionDAGLegalize::ExpandNode(SDNode *Node) {
   case ISD::UREM:
   case ISD::SREM: {
     EVT VT = Node->getValueType(0);
-    SDVTList VTs = DAG.getVTList(VT, VT);
     bool isSigned = Node->getOpcode() == ISD::SREM;
     unsigned DivOpc = isSigned ? ISD::SDIV : ISD::UDIV;
     unsigned DivRemOpc = isSigned ? ISD::SDIVREM : ISD::UDIVREM;
@@ -3192,6 +3312,7 @@ void SelectionDAGLegalize::ExpandNode(SDNode *Node) {
          // If div is legal, it's better to do the normal expansion
          !TLI.isOperationLegalOrCustom(DivOpc, Node->getValueType(0)) &&
          useDivRem(Node, isSigned, false))) {
+      SDVTList VTs = DAG.getVTList(VT, VT);
       Tmp1 = DAG.getNode(DivRemOpc, dl, VTs, Tmp2, Tmp3).getValue(1);
     } else if (TLI.isOperationLegalOrCustom(DivOpc, VT)) {
       // X % Y -> X-X/Y*Y
diff --git a/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp b/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp
index 5701b13a25..3b5823bfb2 100644
--- a/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp
+++ b/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp
@@ -140,6 +140,7 @@ std::string SDNode::getOperationName(const SelectionDAG *G) const {
   case ISD::FSQRT:                      return "fsqrt";
   case ISD::FSIN:                       return "fsin";
   case ISD::FCOS:                       return "fcos";
+  case ISD::FSINCOS:                    return "fsincos";
   case ISD::FTRUNC:                     return "ftrunc";
   case ISD::FFLOOR:                     return "ffloor";
   case ISD::FCEIL:                      return "fceil";
diff --git a/lib/CodeGen/TargetLoweringBase.cpp b/lib/CodeGen/TargetLoweringBase.cpp
index 6284d520f5..10aa9d684b 100644
--- a/lib/CodeGen/TargetLoweringBase.cpp
+++ b/lib/CodeGen/TargetLoweringBase.cpp
@@ -340,6 +340,13 @@ static void InitLibcallNames(const char **Names) {
   Names[RTLIB::SYNC_FETCH_AND_NAND_2] = "__sync_fetch_and_nand_2";
   Names[RTLIB::SYNC_FETCH_AND_NAND_4] = "__sync_fetch_and_nand_4";
   Names[RTLIB::SYNC_FETCH_AND_NAND_8] = "__sync_fetch_and_nand_8";
+  
+  // These are generally not available.
+  Names[RTLIB::SINCOS_F32] = 0;
+  Names[RTLIB::SINCOS_F64] = 0;
+  Names[RTLIB::SINCOS_F80] = 0;
+  Names[RTLIB::SINCOS_F128] = 0;
+  Names[RTLIB::SINCOS_PPCF128] = 0;
 }
 
 /// InitLibcallCallingConvs - Set default libcall CallingConvs.
diff --git a/lib/Target/ARM/ARMISelLowering.cpp b/lib/Target/ARM/ARMISelLowering.cpp
index bdbf45ca04..3d283a5ac9 100644
--- a/lib/Target/ARM/ARMISelLowering.cpp
+++ b/lib/Target/ARM/ARMISelLowering.cpp
@@ -781,6 +781,8 @@ ARMTargetLowering::ARMTargetLowering(TargetMachine &TM)
   setOperationAction(ISD::FSIN,      MVT::f32, Expand);
   setOperationAction(ISD::FCOS,      MVT::f32, Expand);
   setOperationAction(ISD::FCOS,      MVT::f64, Expand);
+  setOperationAction(ISD::FSINCOS,   MVT::f64, Expand);
+  setOperationAction(ISD::FSINCOS,   MVT::f32, Expand);
   setOperationAction(ISD::FREM,      MVT::f64, Expand);
   setOperationAction(ISD::FREM,      MVT::f32, Expand);
   if (!TM.Options.UseSoftFloat && Subtarget->hasVFP2() &&
diff --git a/lib/Target/Hexagon/HexagonISelLowering.cpp b/lib/Target/Hexagon/HexagonISelLowering.cpp
index 1a0e581051..9c7243bdce 100644
--- a/lib/Target/Hexagon/HexagonISelLowering.cpp
+++ b/lib/Target/Hexagon/HexagonISelLowering.cpp
@@ -1364,6 +1364,8 @@ HexagonTargetLowering::HexagonTargetLowering(HexagonTargetMachine
     setOperationAction(ISD::FSIN , MVT::f32, Expand);
     setOperationAction(ISD::FCOS , MVT::f32, Expand);
     setOperationAction(ISD::FREM , MVT::f32, Expand);
+    setOperationAction(ISD::FSINCOS, MVT::f64, Expand);
+    setOperationAction(ISD::FSINCOS, MVT::f32, Expand);
     setOperationAction(ISD::CTPOP, MVT::i32, Expand);
     setOperationAction(ISD::CTTZ , MVT::i32, Expand);
     setOperationAction(ISD::CTTZ_ZERO_UNDEF, MVT::i32, Expand);
diff --git a/lib/Target/MBlaze/MBlazeISelLowering.cpp b/lib/Target/MBlaze/MBlazeISelLowering.cpp
index 8a9f0922b1..5b3c6fede3 100644
--- a/lib/Target/MBlaze/MBlazeISelLowering.cpp
+++ b/lib/Target/MBlaze/MBlazeISelLowering.cpp
@@ -81,6 +81,7 @@ MBlazeTargetLowering::MBlazeTargetLowering(MBlazeTargetMachine &TM)
   setOperationAction(ISD::FCOPYSIGN,  MVT::f64, Expand);
   setOperationAction(ISD::FSIN,       MVT::f32, Expand);
   setOperationAction(ISD::FCOS,       MVT::f32, Expand);
+  setOperationAction(ISD::FSINCOS,    MVT::f32, Expand);
   setOperationAction(ISD::FPOWI,      MVT::f32, Expand);
   setOperationAction(ISD::FPOW,       MVT::f32, Expand);
   setOperationAction(ISD::FLOG,       MVT::f32, Expand);
diff --git a/lib/Target/Mips/MipsISelLowering.cpp b/lib/Target/Mips/MipsISelLowering.cpp
index 8925ddeaf3..7b8557dcd0 100644
--- a/lib/Target/Mips/MipsISelLowering.cpp
+++ b/lib/Target/Mips/MipsISelLowering.cpp
@@ -421,6 +421,8 @@ MipsTargetLowering(MipsTargetMachine &TM)
   setOperationAction(ISD::FSIN,              MVT::f64,   Expand);
   setOperationAction(ISD::FCOS,              MVT::f32,   Expand);
   setOperationAction(ISD::FCOS,              MVT::f64,   Expand);
+  setOperationAction(ISD::FSINCOS,           MVT::f32,   Expand);
+  setOperationAction(ISD::FSINCOS,           MVT::f64,   Expand);
   setOperationAction(ISD::FPOWI,             MVT::f32,   Expand);
   setOperationAction(ISD::FPOW,              MVT::f32,   Expand);
   setOperationAction(ISD::FPOW,              MVT::f64,   Expand);
diff --git a/lib/Target/PowerPC/PPCISelLowering.cpp b/lib/Target/PowerPC/PPCISelLowering.cpp
index 9966b2cc90..9a68927103 100644
--- a/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -132,11 +132,13 @@ PPCTargetLowering::PPCTargetLowering(PPCTargetMachine &TM)
   // We don't support sin/cos/sqrt/fmod/pow
   setOperationAction(ISD::FSIN , MVT::f64, Expand);
   setOperationAction(ISD::FCOS , MVT::f64, Expand);
+  setOperationAction(ISD::FSINCOS, MVT::f64, Expand);
   setOperationAction(ISD::FREM , MVT::f64, Expand);
   setOperationAction(ISD::FPOW , MVT::f64, Expand);
   setOperationAction(ISD::FMA  , MVT::f64, Legal);
   setOperationAction(ISD::FSIN , MVT::f32, Expand);
   setOperationAction(ISD::FCOS , MVT::f32, Expand);
+  setOperationAction(ISD::FSINCOS, MVT::f32, Expand);
   setOperationAction(ISD::FREM , MVT::f32, Expand);
   setOperationAction(ISD::FPOW , MVT::f32, Expand);
   setOperationAction(ISD::FMA  , MVT::f32, Legal);
diff --git a/lib/Target/Sparc/SparcISelLowering.cpp b/lib/Target/Sparc/SparcISelLowering.cpp
index 168640f457..7664abde51 100644
--- a/lib/Target/Sparc/SparcISelLowering.cpp
+++ b/lib/Target/Sparc/SparcISelLowering.cpp
@@ -759,10 +759,12 @@ SparcTargetLowering::SparcTargetLowering(TargetMachine &TM)
 
   setOperationAction(ISD::FSIN , MVT::f64, Expand);
   setOperationAction(ISD::FCOS , MVT::f64, Expand);
+  setOperationAction(ISD::FSINCOS, MVT::f64, Expand);
   setOperationAction(ISD::FREM , MVT::f64, Expand);
   setOperationAction(ISD::FMA  , MVT::f64, Expand);
   setOperationAction(ISD::FSIN , MVT::f32, Expand);
   setOperationAction(ISD::FCOS , MVT::f32, Expand);
+  setOperationAction(ISD::FSINCOS, MVT::f32, Expand);
   setOperationAction(ISD::FREM , MVT::f32, Expand);
   setOperationAction(ISD::FMA  , MVT::f32, Expand);
   setOperationAction(ISD::CTPOP, MVT::i32, Expand);
diff --git a/lib/Target/X86/X86ISelLowering.cpp b/lib/Target/X86/X86ISelLowering.cpp
index a4eae0a8f8..ca606daaba 100644
--- a/lib/Target/X86/X86ISelLowering.cpp
+++ b/lib/Target/X86/X86ISelLowering.cpp
@@ -605,10 +605,12 @@ X86TargetLowering::X86TargetLowering(X86TargetMachine &TM)
     setOperationAction(ISD::FGETSIGN, MVT::i32, Custom);
 
     // We don't support sin/cos/fmod
-    setOperationAction(ISD::FSIN , MVT::f64, Expand);
-    setOperationAction(ISD::FCOS , MVT::f64, Expand);
-    setOperationAction(ISD::FSIN , MVT::f32, Expand);
-    setOperationAction(ISD::FCOS , MVT::f32, Expand);
+    setOperationAction(ISD::FSIN   , MVT::f64, Expand);
+    setOperationAction(ISD::FCOS   , MVT::f64, Expand);
+    setOperationAction(ISD::FSINCOS, MVT::f64, Expand);
+    setOperationAction(ISD::FSIN   , MVT::f32, Expand);
+    setOperationAction(ISD::FCOS   , MVT::f32, Expand);
+    setOperationAction(ISD::FSINCOS, MVT::f32, Expand);
 
     // Expand FP immediates into loads from the stack, except for the special
     // cases we handle.
@@ -633,8 +635,9 @@ X86TargetLowering::X86TargetLowering(X86TargetMachine &TM)
     setOperationAction(ISD::FCOPYSIGN, MVT::f32, Custom);
 
     // We don't support sin/cos/fmod
-    setOperationAction(ISD::FSIN , MVT::f32, Expand);
-    setOperationAction(ISD::FCOS , MVT::f32, Expand);
+    setOperationAction(ISD::FSIN   , MVT::f32, Expand);
+    setOperationAction(ISD::FCOS   , MVT::f32, Expand);
+    setOperationAction(ISD::FSINCOS, MVT::f32, Expand);
 
     // Special cases we handle for FP constants.
     addLegalFPImmediate(APFloat(+0.0f)); // xorps
@@ -644,8 +647,9 @@ X86TargetLowering::X86TargetLowering(X86TargetMachine &TM)
     addLegalFPImmediate(APFloat(-1.0)); // FLD1/FCHS
 
     if (!TM.Options.UnsafeFPMath) {
-      setOperationAction(ISD::FSIN           , MVT::f64  , Expand);
-      setOperationAction(ISD::FCOS           , MVT::f64  , Expand);
+      setOperationAction(ISD::FSIN   , MVT::f64, Expand);
+      setOperationAction(ISD::FCOS   , MVT::f64, Expand);
+      setOperationAction(ISD::FSINCOS, MVT::f64, Expand);
     }
   } else if (!TM.Options.UseSoftFloat) {
     // f32 and f64 in x87.
@@ -659,10 +663,12 @@ X86TargetLowering::X86TargetLowering(X86TargetMachine &TM)
     setOperationAction(ISD::FCOPYSIGN, MVT::f32, Expand);
 
     if (!TM.Options.UnsafeFPMath) {
-      setOperationAction(ISD::FSIN           , MVT::f32  , Expand);
-      setOperationAction(ISD::FSIN           , MVT::f64  , Expand);
-      setOperationAction(ISD::FCOS           , MVT::f32  , Expand);
-      setOperationAction(ISD::FCOS           , MVT::f64  , Expand);
+      setOperationAction(ISD::FSIN   , MVT::f64, Expand);
+      setOperationAction(ISD::FSIN   , MVT::f32, Expand);
+      setOperationAction(ISD::FCOS   , MVT::f64, Expand);
+      setOperationAction(ISD::FCOS   , MVT::f32, Expand);
+      setOperationAction(ISD::FSINCOS, MVT::f64, Expand);
+      setOperationAction(ISD::FSINCOS, MVT::f32, Expand);
     }
     addLegalFPImmediate(APFloat(+0.0)); // FLD0
     addLegalFPImmediate(APFloat(+1.0)); // FLD1
@@ -699,8 +705,9 @@ X86TargetLowering::X86TargetLowering(X86TargetMachine &TM)
     }
 
     if (!TM.Options.UnsafeFPMath) {
-      setOperationAction(ISD::FSIN           , MVT::f80  , Expand);
-      setOperationAction(ISD::FCOS           , MVT::f80  , Expand);
+      setOperationAction(ISD::FSIN   , MVT::f80, Expand);
+      setOperationAction(ISD::FCOS   , MVT::f80, Expand);
+      setOperationAction(ISD::FSINCOS, MVT::f80, Expand);
     }
 
     setOperationAction(ISD::FFLOOR, MVT::f80, Expand);
@@ -748,7 +755,9 @@ X86TargetLowering::X86TargetLowering(X86TargetMachine &TM)
     setOperationAction(ISD::INSERT_SUBVECTOR, VT,Expand);
     setOperationAction(ISD::FABS, VT, Expand);
     setOperationAction(ISD::FSIN, VT, Expand);
+    setOperationAction(ISD::FSINCOS, VT, Expand);
     setOperationAction(ISD::FCOS, VT, Expand);
+    setOperationAction(ISD::FSINCOS, VT, Expand);
     setOperationAction(ISD::FREM, VT, Expand);
     setOperationAction(ISD::FMA,  VT, Expand);
     setOperationAction(ISD::FPOWI, VT, Expand);
@@ -1281,6 +1290,19 @@ X86TargetLowering::X86TargetLowering(X86TargetMachine &TM)
     setLibcallName(RTLIB::SRA_I128, 0);
   }
 
+  // Combine sin / cos into one node or libcall if possible.
+  if (Subtarget->hasSinCos()) {
+    setLibcallName(RTLIB::SINCOS_F32, "sincosf");
+    setLibcallName(RTLIB::SINCOS_F64, "sincos");
+    if (Subtarget->isTargetDarwin() && Subtarget->is64Bit()) {
+      // For MacOSX, we don't want to the normal expansion of a libcall to
+      // sincos. We want to issue a libcall to __sincos_stret to avoid memory
+      // traffic.
+      setOperationAction(ISD::FSINCOS, MVT::f64, Custom);
+      setOperationAction(ISD::FSINCOS, MVT::f32, Custom);
+    }
+  }
+
   // We have target-specific dag combine patterns for the following nodes:
   setTargetDAGCombine(ISD::VECTOR_SHUFFLE);
   setTargetDAGCombine(ISD::EXTRACT_VECTOR_ELT);
@@ -12014,6 +12036,50 @@ static SDValue LowerADDC_ADDE_SUBC_SUBE(SDValue Op, SelectionDAG &DAG) {
                      Op.getOperand(1), Op.getOperand(2));
 }
 
+SDValue X86TargetLowering::LowerFSINCOS(SDValue Op, SelectionDAG &DAG) const {
+  assert(Subtarget->isTargetDarwin());
+ 
+  // For MacOSX, we want to call an alternative entry point: __sincos_stret,
+  // which returns the values in two XMM registers.
+  DebugLoc dl = Op.getDebugLoc();
+  SDValue Arg = Op.getOperand(0);
+  EVT ArgVT = Arg.getValueType();
+  Type *ArgTy = ArgVT.getTypeForEVT(*DAG.getContext());
+  
+  ArgListTy Args;
+  ArgListEntry Entry;
+  
+  Entry.Node = Arg;
+  Entry.Ty = ArgTy;
+  Entry.isSExt = false;
+  Entry.isZExt = false;
+  Args.push_back(Entry);
+  
+  const char *LibcallName = (ArgVT == MVT::f64)
+    ? "__sincos_stret" : "__sincosf_stret";
+  SDValue Callee = DAG.getExternalSymbol(LibcallName, getPointerTy());
+  
+  StructType *RetTy = StructType::get(ArgTy, ArgTy, NULL);
+  TargetLowering::
+  CallLoweringInfo CLI(DAG.getEntryNode(), RetTy,
+                       false, false, false, false, 0,
+                       CallingConv::C, /*isTaillCall=*/false,
+                       /*doesNotRet=*/false, /*isReturnValueUsed*/true,
+                       Callee, Args, DAG, dl);
+  std::pair<SDValue, SDValue> CallResult = LowerCallTo(CLI);
+#if 1
+  return CallResult.first;
+#else
+  SDValue RetSin = DAG.getNode(ISD::EXTRACT_ELEMENT, dl, ArgVT,
+                               CallResult.first, DAG.getIntPtrConstant(0));
+  SDValue RetCos = DAG.getNode(ISD::EXTRACT_ELEMENT, dl, ArgVT,
+                               CallResult.first, DAG.getIntPtrConstant(1));
+  
+  SDVTList Tys = DAG.getVTList(ArgVT, ArgVT);
+  return DAG.getNode(ISD::MERGE_VALUES, dl, Tys, RetSin, RetCos);
+#endif
+}
+
 /// LowerOperation - Provide custom lowering hooks for some operations.
 ///
 SDValue X86TargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const {
@@ -12096,6 +12162,7 @@ SDValue X86TargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const {
   case ISD::ADD:                return LowerADD(Op, DAG);
   case ISD::SUB:                return LowerSUB(Op, DAG);
   case ISD::SDIV:               return LowerSDIV(Op, DAG);
+  case ISD::FSINCOS:            return LowerFSINCOS(Op, DAG);
   }
 }
 
diff --git a/lib/Target/X86/X86ISelLowering.h b/lib/Target/X86/X86ISelLowering.h
index 5e84e277c0..6758ed1404 100644
--- a/lib/Target/X86/X86ISelLowering.h
+++ b/lib/Target/X86/X86ISelLowering.h
@@ -838,8 +838,8 @@ namespace llvm {
     SDValue LowerFLT_ROUNDS_(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerShift(SDValue Op, SelectionDAG &DAG) const;
     SDValue LowerSDIV(SDValue Op, SelectionDAG &DAG) const;
-
     SDValue LowerSIGN_EXTEND_INREG(SDValue Op, SelectionDAG &DAG) const;
+    SDValue LowerFSINCOS(SDValue Op, SelectionDAG &DAG) const;
 
     // Utility functions to help LowerVECTOR_SHUFFLE & LowerBUILD_VECTOR
     SDValue LowerVectorBroadcast(SDValue Op, SelectionDAG &DAG) const;
diff --git a/lib/Target/X86/X86Subtarget.cpp b/lib/Target/X86/X86Subtarget.cpp
index 53c28f4fce..dad95c6800 100644
--- a/lib/Target/X86/X86Subtarget.cpp
+++ b/lib/Target/X86/X86Subtarget.cpp
@@ -155,6 +155,11 @@ const char *X86Subtarget::getBZeroEntry() const {
   return 0;
 }
 
+bool X86Subtarget::hasSinCos() const {
+  return getTargetTriple().isMacOSX() &&
+    !getTargetTriple().isMacOSXVersionLT(10, 9);
+}
+
 /// IsLegalToCallImmediateAddr - Return true if the subtarget allows calls
 /// to immediate address.
 bool X86Subtarget::IsLegalToCallImmediateAddr(const TargetMachine &TM) const {
diff --git a/lib/Target/X86/X86Subtarget.h b/lib/Target/X86/X86Subtarget.h
index b325f62126..eb587a5761 100644
--- a/lib/Target/X86/X86Subtarget.h
+++ b/lib/Target/X86/X86Subtarget.h
@@ -328,6 +328,10 @@ public:
   /// memset with zero passed as the second argument. Otherwise it
   /// returns null.
   const char *getBZeroEntry() const;
+  
+  /// This function returns true if the target has sincos() routine in its
+  /// compiler runtime or math libraries.
+  bool hasSinCos() const;
 
   /// enablePostRAScheduler - run for Atom optimization.
   bool enablePostRAScheduler(CodeGenOpt::Level OptLevel,