Index: llvm/trunk/include/llvm/CodeGen/TargetLowering.h
===================================================================
--- llvm/trunk/include/llvm/CodeGen/TargetLowering.h
+++ llvm/trunk/include/llvm/CodeGen/TargetLowering.h
@@ -1814,6 +1814,11 @@
     return IsSigned;
   }
 
+  /// Returns true if arguments should be extended in lib calls.
+  virtual bool shouldExtendTypeInLibCall(EVT Type) const {
+    return true;
+  }
+
   /// Returns how the given (atomic) load should be expanded by the
   /// IR-level AtomicExpand pass.
   virtual AtomicExpansionKind shouldExpandAtomicLoadInIR(LoadInst *LI) const {
@@ -2987,7 +2992,8 @@
 
   void softenSetCCOperands(SelectionDAG &DAG, EVT VT, SDValue &NewLHS,
                            SDValue &NewRHS, ISD::CondCode &CCCode,
-                           const SDLoc &DL) const;
+                           const SDLoc &DL, const SDValue OldLHS,
+                           const SDValue OldRHS) const;
 
   /// Returns a pair of (return value, chain).
   /// It is an error to pass RTLIB::UNKNOWN_LIBCALL as \p LC.
@@ -3533,6 +3539,11 @@
 
   /// This structure is used to pass arguments to makeLibCall function.
   struct MakeLibCallOptions {
+    // By passing the node before soften to makeLibCall, the target hook
+    // shouldExtendTypeInLibCall can get the original type before soften.
+    // It could be generalized by passing orignal type lists if necessary
+    // in the future.
+    SDNode *NodeBeforeSoften = nullptr;
     bool IsSExt : 1;
     bool DoesNotReturn : 1;
     bool IsReturnValueUsed : 1;
@@ -3561,6 +3572,11 @@
       IsPostTypeLegalization = Value;
       return *this;
     }
+
+    MakeLibCallOptions &setNodeBeforeSoften(SDNode *N) {
+      NodeBeforeSoften = N;
+      return *this;
+    }
   };
 
   /// This function lowers an abstract call to a function into an actual call.
Index: llvm/trunk/lib/CodeGen/SelectionDAG/LegalizeFloatTypes.cpp
===================================================================
--- llvm/trunk/lib/CodeGen/SelectionDAG/LegalizeFloatTypes.cpp
+++ llvm/trunk/lib/CodeGen/SelectionDAG/LegalizeFloatTypes.cpp
@@ -201,6 +201,7 @@
   SDValue Ops[2] = { GetSoftenedFloat(N->getOperand(0)),
                      GetSoftenedFloat(N->getOperand(1)) };
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::FMIN_F32,
                                            RTLIB::FMIN_F64,
@@ -215,6 +216,7 @@
   SDValue Ops[2] = { GetSoftenedFloat(N->getOperand(0)),
                      GetSoftenedFloat(N->getOperand(1)) };
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::FMAX_F32,
                                            RTLIB::FMAX_F64,
@@ -229,6 +231,7 @@
   SDValue Ops[2] = { GetSoftenedFloat(N->getOperand(0)),
                      GetSoftenedFloat(N->getOperand(1)) };
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::ADD_F32,
                                            RTLIB::ADD_F64,
@@ -242,6 +245,7 @@
   EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0));
   SDValue Op = GetSoftenedFloat(N->getOperand(0));
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::CEIL_F32,
                                            RTLIB::CEIL_F64,
@@ -306,6 +310,7 @@
   EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0));
   SDValue Op = GetSoftenedFloat(N->getOperand(0));
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::COS_F32,
                                            RTLIB::COS_F64,
@@ -320,6 +325,7 @@
   SDValue Ops[2] = { GetSoftenedFloat(N->getOperand(0)),
                      GetSoftenedFloat(N->getOperand(1)) };
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::DIV_F32,
                                            RTLIB::DIV_F64,
@@ -333,6 +339,7 @@
   EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0));
   SDValue Op = GetSoftenedFloat(N->getOperand(0));
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::EXP_F32,
                                            RTLIB::EXP_F64,
@@ -346,6 +353,7 @@
   EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0));
   SDValue Op = GetSoftenedFloat(N->getOperand(0));
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::EXP2_F32,
                                            RTLIB::EXP2_F64,
@@ -359,6 +367,7 @@
   EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0));
   SDValue Op = GetSoftenedFloat(N->getOperand(0));
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::FLOOR_F32,
                                            RTLIB::FLOOR_F64,
@@ -372,6 +381,7 @@
   EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0));
   SDValue Op = GetSoftenedFloat(N->getOperand(0));
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::LOG_F32,
                                            RTLIB::LOG_F64,
@@ -385,6 +395,7 @@
   EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0));
   SDValue Op = GetSoftenedFloat(N->getOperand(0));
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::LOG2_F32,
                                            RTLIB::LOG2_F64,
@@ -398,6 +409,7 @@
   EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0));
   SDValue Op = GetSoftenedFloat(N->getOperand(0));
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::LOG10_F32,
                                            RTLIB::LOG10_F64,
@@ -413,6 +425,7 @@
                      GetSoftenedFloat(N->getOperand(1)),
                      GetSoftenedFloat(N->getOperand(2)) };
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::FMA_F32,
                                            RTLIB::FMA_F64,
@@ -427,6 +440,7 @@
   SDValue Ops[2] = { GetSoftenedFloat(N->getOperand(0)),
                      GetSoftenedFloat(N->getOperand(1)) };
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::MUL_F32,
                                            RTLIB::MUL_F64,
@@ -440,6 +454,7 @@
   EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0));
   SDValue Op = GetSoftenedFloat(N->getOperand(0));
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::NEARBYINT_F32,
                                            RTLIB::NEARBYINT_F64,
@@ -502,6 +517,7 @@
   RTLIB::Libcall LC = RTLIB::getFPEXT(Op.getValueType(), N->getValueType(0));
   assert(LC != RTLIB::UNKNOWN_LIBCALL && "Unsupported FP_EXTEND!");
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, LC, NVT, Op, CallOptions, SDLoc(N)).first;
 }
 
@@ -511,6 +527,7 @@
   EVT MidVT = TLI.getTypeToTransformTo(*DAG.getContext(), MVT::f32);
   SDValue Op = N->getOperand(0);
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   SDValue Res32 = TLI.makeLibCall(DAG, RTLIB::FPEXT_F16_F32, MidVT, Op,
                                   CallOptions, SDLoc(N)).first;
   if (N->getValueType(0) == MVT::f32)
@@ -534,6 +551,7 @@
   RTLIB::Libcall LC = RTLIB::getFPROUND(Op.getValueType(), N->getValueType(0));
   assert(LC != RTLIB::UNKNOWN_LIBCALL && "Unsupported FP_ROUND!");
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, LC, NVT, Op, CallOptions, SDLoc(N)).first;
 }
 
@@ -542,6 +560,7 @@
   SDValue Ops[2] = { GetSoftenedFloat(N->getOperand(0)),
                      GetSoftenedFloat(N->getOperand(1)) };
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::POW_F32,
                                            RTLIB::POW_F64,
@@ -557,6 +576,7 @@
   EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0));
   SDValue Ops[2] = { GetSoftenedFloat(N->getOperand(0)), N->getOperand(1) };
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::POWI_F32,
                                            RTLIB::POWI_F64,
@@ -571,6 +591,7 @@
   SDValue Ops[2] = { GetSoftenedFloat(N->getOperand(0)),
                      GetSoftenedFloat(N->getOperand(1)) };
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::REM_F32,
                                            RTLIB::REM_F64,
@@ -584,6 +605,7 @@
   EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0));
   SDValue Op = GetSoftenedFloat(N->getOperand(0));
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::RINT_F32,
                                            RTLIB::RINT_F64,
@@ -597,6 +619,7 @@
   EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0));
   SDValue Op = GetSoftenedFloat(N->getOperand(0));
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::ROUND_F32,
                                            RTLIB::ROUND_F64,
@@ -610,6 +633,7 @@
   EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0));
   SDValue Op = GetSoftenedFloat(N->getOperand(0));
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::SIN_F32,
                                            RTLIB::SIN_F64,
@@ -623,6 +647,7 @@
   EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0));
   SDValue Op = GetSoftenedFloat(N->getOperand(0));
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::SQRT_F32,
                                            RTLIB::SQRT_F64,
@@ -637,6 +662,7 @@
   SDValue Ops[2] = { GetSoftenedFloat(N->getOperand(0)),
                      GetSoftenedFloat(N->getOperand(1)) };
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::SUB_F32,
                                            RTLIB::SUB_F64,
@@ -653,6 +679,7 @@
 
   SDValue Op = GetSoftenedFloat(N->getOperand(0));
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::TRUNC_F32,
                                            RTLIB::TRUNC_F64,
@@ -766,6 +793,7 @@
                            NVT, N->getOperand(0));
   TargetLowering::MakeLibCallOptions CallOptions;
   CallOptions.setSExt(Signed);
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, LC,
                          TLI.getTypeToTransformTo(*DAG.getContext(), RVT),
                          Op, CallOptions, dl).first;
@@ -899,6 +927,7 @@
   assert(LC != RTLIB::UNKNOWN_LIBCALL && "Unsupported FP_EXTEND libcall");
 
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, LC, RVT, Op, CallOptions, SDLoc(N)).first;
 }
 
@@ -917,6 +946,7 @@
 
   SDValue Op = GetSoftenedFloat(N->getOperand(0));
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, LC, RVT, Op, CallOptions, SDLoc(N)).first;
 }
 
@@ -927,7 +957,8 @@
   EVT VT = NewLHS.getValueType();
   NewLHS = GetSoftenedFloat(NewLHS);
   NewRHS = GetSoftenedFloat(NewRHS);
-  TLI.softenSetCCOperands(DAG, VT, NewLHS, NewRHS, CCCode, SDLoc(N));
+  TLI.softenSetCCOperands(DAG, VT, NewLHS, NewRHS, CCCode, SDLoc(N),
+                          N->getOperand(2), N->getOperand(3));
 
   // If softenSetCCOperands returned a scalar, we need to compare the result
   // against zero to select between true and false values.
@@ -995,6 +1026,7 @@
 
   SDValue Op = GetSoftenedFloat(N->getOperand(0));
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   SDValue Res = TLI.makeLibCall(DAG, LC, NVT, Op, CallOptions, dl).first;
 
   // Truncate the result if the libcall returns a larger type.
@@ -1019,7 +1051,8 @@
   EVT VT = NewLHS.getValueType();
   NewLHS = GetSoftenedFloat(NewLHS);
   NewRHS = GetSoftenedFloat(NewRHS);
-  TLI.softenSetCCOperands(DAG, VT, NewLHS, NewRHS, CCCode, SDLoc(N));
+  TLI.softenSetCCOperands(DAG, VT, NewLHS, NewRHS, CCCode, SDLoc(N),
+                          N->getOperand(0), N->getOperand(1));
 
   // If softenSetCCOperands returned a scalar, we need to compare the result
   // against zero to select between true and false values.
@@ -1042,7 +1075,8 @@
   EVT VT = NewLHS.getValueType();
   NewLHS = GetSoftenedFloat(NewLHS);
   NewRHS = GetSoftenedFloat(NewRHS);
-  TLI.softenSetCCOperands(DAG, VT, NewLHS, NewRHS, CCCode, SDLoc(N));
+  TLI.softenSetCCOperands(DAG, VT, NewLHS, NewRHS, CCCode, SDLoc(N),
+                          N->getOperand(0), N->getOperand(1));
 
   // If softenSetCCOperands returned a scalar, use it.
   if (!NewRHS.getNode()) {
@@ -1081,6 +1115,7 @@
   SDValue Op = GetSoftenedFloat(N->getOperand(0));
   EVT RetVT = N->getOperand(0).getValueType().getSimpleVT().SimpleTy;
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(RetVT,
                                            RTLIB::LROUND_F32,
                                            RTLIB::LROUND_F64,
@@ -1096,6 +1131,7 @@
   SDValue Op = GetSoftenedFloat(N->getOperand(0));
   EVT RetVT = N->getOperand(0).getValueType().getSimpleVT().SimpleTy;
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(RetVT,
                                            RTLIB::LLROUND_F32,
                                            RTLIB::LLROUND_F64,
@@ -1111,6 +1147,7 @@
   SDValue Op = GetSoftenedFloat(N->getOperand(0));
   EVT RetVT = N->getOperand(0).getValueType().getSimpleVT().SimpleTy;
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(RetVT,
                                            RTLIB::LRINT_F32,
                                            RTLIB::LRINT_F64,
@@ -1126,6 +1163,7 @@
   SDValue Op = GetSoftenedFloat(N->getOperand(0));
   EVT RetVT = N->getOperand(0).getValueType().getSimpleVT().SimpleTy;
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(N);
   return TLI.makeLibCall(DAG, GetFPLibCall(RetVT,
                                            RTLIB::LLRINT_F32,
                                            RTLIB::LLRINT_F64,
Index: llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp
===================================================================
--- llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp
+++ llvm/trunk/lib/CodeGen/SelectionDAG/TargetLowering.cpp
@@ -127,12 +127,19 @@
   Args.reserve(Ops.size());
 
   TargetLowering::ArgListEntry Entry;
-  for (SDValue Op : Ops) {
-    Entry.Node = Op;
+  SDNode *N = CallOptions.NodeBeforeSoften;
+  for (unsigned i = 0; i < Ops.size(); ++i) {
+    SDValue NewOp = Ops[i];
+    Entry.Node = NewOp;
     Entry.Ty = Entry.Node.getValueType().getTypeForEVT(*DAG.getContext());
-    Entry.IsSExt = shouldSignExtendTypeInLibCall(Op.getValueType(),
+    Entry.IsSExt = shouldSignExtendTypeInLibCall(NewOp.getValueType(),
                                                  CallOptions.IsSExt);
     Entry.IsZExt = !Entry.IsSExt;
+
+    SDValue OldOp = N ? N->getOperand(i) : NewOp;
+    if (!shouldExtendTypeInLibCall(OldOp.getValueType())) {
+      Entry.IsSExt = Entry.IsZExt = false;
+    }
     Args.push_back(Entry);
   }
 
@@ -144,6 +151,13 @@
   Type *RetTy = RetVT.getTypeForEVT(*DAG.getContext());
   TargetLowering::CallLoweringInfo CLI(DAG);
   bool signExtend = shouldSignExtendTypeInLibCall(RetVT, CallOptions.IsSExt);
+  bool zeroExtend = !signExtend;
+
+  RetVT = N ? N->getValueType(0) : RetVT;
+  if (!shouldExtendTypeInLibCall(RetVT)) {
+    signExtend = zeroExtend = false;
+  }
+
   CLI.setDebugLoc(dl)
       .setChain(DAG.getEntryNode())
       .setLibCallee(getLibcallCallingConv(LC), RetTy, Callee, std::move(Args))
@@ -151,7 +165,7 @@
       .setDiscardResult(!CallOptions.IsReturnValueUsed)
       .setIsPostTypeLegalization(CallOptions.IsPostTypeLegalization)
       .setSExtResult(signExtend)
-      .setZExtResult(!signExtend);
+      .setZExtResult(zeroExtend);
   return LowerCallTo(CLI);
 }
 
@@ -262,7 +276,8 @@
 void TargetLowering::softenSetCCOperands(SelectionDAG &DAG, EVT VT,
                                          SDValue &NewLHS, SDValue &NewRHS,
                                          ISD::CondCode &CCCode,
-                                         const SDLoc &dl) const {
+                                         const SDLoc &dl, const SDValue OldLHS,
+                                         const SDValue OldRHS) const {
   assert((VT == MVT::f32 || VT == MVT::f64 || VT == MVT::f128 || VT == MVT::ppcf128)
          && "Unsupported setcc type!");
 
@@ -364,7 +379,12 @@
   // Use the target specific return value for comparions lib calls.
   EVT RetVT = getCmpLibcallReturnType();
   SDValue Ops[2] = {NewLHS, NewRHS};
+  SDValue OldSETCC = DAG.getNode(
+      ISD::SETCC, dl,
+      getSetCCResultType(DAG.getDataLayout(), *DAG.getContext(), RetVT),
+      OldLHS, OldRHS, DAG.getCondCode(CCCode));
   TargetLowering::MakeLibCallOptions CallOptions;
+  CallOptions.setNodeBeforeSoften(OldSETCC.getNode());
   NewLHS = makeLibCall(DAG, LC1, RetVT, Ops, CallOptions, dl).first;
   NewRHS = DAG.getConstant(0, dl, RetVT);
 
Index: llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.cpp
===================================================================
--- llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ llvm/trunk/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -4555,7 +4555,7 @@
   // value of a libcall against zero, which is just what the rest of LowerBR_CC
   // is expecting to deal with.
   if (LHS.getValueType() == MVT::f128) {
-    softenSetCCOperands(DAG, MVT::f128, LHS, RHS, CC, dl);
+    softenSetCCOperands(DAG, MVT::f128, LHS, RHS, CC, dl, LHS, RHS);
 
     // If softenSetCCOperands returned a scalar, we need to compare the result
     // against zero to select between true and false values.
@@ -4821,7 +4821,7 @@
   // Handle f128 first, since one possible outcome is a normal integer
   // comparison which gets picked up by the next if statement.
   if (LHS.getValueType() == MVT::f128) {
-    softenSetCCOperands(DAG, MVT::f128, LHS, RHS, CC, dl);
+    softenSetCCOperands(DAG, MVT::f128, LHS, RHS, CC, dl, LHS, RHS);
 
     // If softenSetCCOperands returned a scalar, use it.
     if (!RHS.getNode()) {
@@ -4883,7 +4883,7 @@
   // Handle f128 first, because it will result in a comparison of some RTLIB
   // call result against zero.
   if (LHS.getValueType() == MVT::f128) {
-    softenSetCCOperands(DAG, MVT::f128, LHS, RHS, CC, dl);
+    softenSetCCOperands(DAG, MVT::f128, LHS, RHS, CC, dl, LHS, RHS);
 
     // If softenSetCCOperands returned a scalar, we need to compare the result
     // against zero to select between true and false values.
Index: llvm/trunk/lib/Target/ARM/ARMISelLowering.cpp
===================================================================
--- llvm/trunk/lib/Target/ARM/ARMISelLowering.cpp
+++ llvm/trunk/lib/Target/ARM/ARMISelLowering.cpp
@@ -4818,7 +4818,7 @@
 
   if (isUnsupportedFloatingType(LHS.getValueType())) {
     DAG.getTargetLoweringInfo().softenSetCCOperands(
-        DAG, LHS.getValueType(), LHS, RHS, CC, dl);
+        DAG, LHS.getValueType(), LHS, RHS, CC, dl, LHS, RHS);
 
     // If softenSetCCOperands only returned one value, we should compare it to
     // zero.
@@ -5062,7 +5062,7 @@
 
   if (isUnsupportedFloatingType(LHS.getValueType())) {
     DAG.getTargetLoweringInfo().softenSetCCOperands(
-        DAG, LHS.getValueType(), LHS, RHS, CC, dl);
+        DAG, LHS.getValueType(), LHS, RHS, CC, dl, LHS, RHS);
 
     // If softenSetCCOperands only returned one value, we should compare it to
     // zero.
Index: llvm/trunk/lib/Target/RISCV/RISCVISelLowering.h
===================================================================
--- llvm/trunk/lib/Target/RISCV/RISCVISelLowering.h
+++ llvm/trunk/lib/Target/RISCV/RISCVISelLowering.h
@@ -145,6 +145,8 @@
   unsigned
   getExceptionSelectorRegister(const Constant *PersonalityFn) const override;
 
+  bool shouldExtendTypeInLibCall(EVT Type) const override;
+
 private:
   void analyzeInputArgs(MachineFunction &MF, CCState &CCInfo,
                         const SmallVectorImpl<ISD::InputArg> &Ins,
Index: llvm/trunk/lib/Target/RISCV/RISCVISelLowering.cpp
===================================================================
--- llvm/trunk/lib/Target/RISCV/RISCVISelLowering.cpp
+++ llvm/trunk/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -2777,3 +2777,13 @@
     const Constant *PersonalityFn) const {
   return RISCV::X11;
 }
+
+bool RISCVTargetLowering::shouldExtendTypeInLibCall(EVT Type) const {
+  // Return false to suppress the unnecessary extensions if the LibCall
+  // arguments or return value is f32 type for LP64 ABI.
+  RISCVABI::ABI ABI = Subtarget.getTargetABI();
+  if (ABI == RISCVABI::ABI_LP64 && (Type == MVT::f32))
+    return false;
+
+  return true;
+}
Index: llvm/trunk/test/CodeGen/RISCV/calling-conv-lp64.ll
===================================================================
--- llvm/trunk/test/CodeGen/RISCV/calling-conv-lp64.ll
+++ llvm/trunk/test/CodeGen/RISCV/calling-conv-lp64.ll
@@ -21,8 +21,7 @@
 ; RV64I-FPELIM-NEXT:    sd ra, 8(sp)
 ; RV64I-FPELIM-NEXT:    sd s0, 0(sp)
 ; RV64I-FPELIM-NEXT:    mv s0, a0
-; RV64I-FPELIM-NEXT:    slli a0, a1, 32
-; RV64I-FPELIM-NEXT:    srli a0, a0, 32
+; RV64I-FPELIM-NEXT:    mv a0, a1
 ; RV64I-FPELIM-NEXT:    call __fixsfdi
 ; RV64I-FPELIM-NEXT:    add a0, s0, a0
 ; RV64I-FPELIM-NEXT:    ld s0, 0(sp)
@@ -38,8 +37,7 @@
 ; RV64I-WITHFP-NEXT:    sd s1, 8(sp)
 ; RV64I-WITHFP-NEXT:    addi s0, sp, 32
 ; RV64I-WITHFP-NEXT:    mv s1, a0
-; RV64I-WITHFP-NEXT:    slli a0, a1, 32
-; RV64I-WITHFP-NEXT:    srli a0, a0, 32
+; RV64I-WITHFP-NEXT:    mv a0, a1
 ; RV64I-WITHFP-NEXT:    call __fixsfdi
 ; RV64I-WITHFP-NEXT:    add a0, s1, a0
 ; RV64I-WITHFP-NEXT:    ld s1, 8(sp)
Index: llvm/trunk/test/CodeGen/RISCV/rv32i-rv64i-float-double.ll
===================================================================
--- llvm/trunk/test/CodeGen/RISCV/rv32i-rv64i-float-double.ll
+++ llvm/trunk/test/CodeGen/RISCV/rv32i-rv64i-float-double.ll
@@ -31,11 +31,7 @@
 ; RV64IF-NEXT:    addi sp, sp, -16
 ; RV64IF-NEXT:    sd ra, 8(sp)
 ; RV64IF-NEXT:    sd s0, 0(sp)
-; RV64IF-NEXT:    slli a0, a0, 32
-; RV64IF-NEXT:    srli a0, a0, 32
-; RV64IF-NEXT:    slli a1, a1, 32
-; RV64IF-NEXT:    srli s0, a1, 32
-; RV64IF-NEXT:    mv a1, s0
+; RV64IF-NEXT:    mv s0, a1
 ; RV64IF-NEXT:    call __addsf3
 ; RV64IF-NEXT:    mv a1, s0
 ; RV64IF-NEXT:    call __divsf3
Index: llvm/trunk/test/CodeGen/RISCV/rv64i-complex-float.ll
===================================================================
--- llvm/trunk/test/CodeGen/RISCV/rv64i-complex-float.ll
+++ llvm/trunk/test/CodeGen/RISCV/rv64i-complex-float.ll
@@ -0,0 +1,53 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv64 -verify-machineinstrs < %s | FileCheck %s
+
+; The complex floating value will be returned by a single register for LP64 ABI.
+; The test case check that the real part returned by __addsf3 will be
+; cleared upper bits by shifts to avoid corrupting the imaginary part.
+
+define i64 @complex_float_add(i64 %a.coerce, i64 %b.coerce) nounwind {
+; CHECK-LABEL: complex_float_add:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    addi sp, sp, -32
+; CHECK-NEXT:    sd ra, 24(sp)
+; CHECK-NEXT:    sd s0, 16(sp)
+; CHECK-NEXT:    sd s1, 8(sp)
+; CHECK-NEXT:    sd s2, 0(sp)
+; CHECK-NEXT:    mv s0, a1
+; CHECK-NEXT:    mv s1, a0
+; CHECK-NEXT:    call __addsf3
+; CHECK-NEXT:    mv s2, a0
+; CHECK-NEXT:    srli a0, s1, 32
+; CHECK-NEXT:    srli a1, s0, 32
+; CHECK-NEXT:    call __addsf3
+; CHECK-NEXT:    slli a1, s2, 32
+; CHECK-NEXT:    srli a1, a1, 32
+; CHECK-NEXT:    slli a0, a0, 32
+; CHECK-NEXT:    or a0, a0, a1
+; CHECK-NEXT:    ld s2, 0(sp)
+; CHECK-NEXT:    ld s1, 8(sp)
+; CHECK-NEXT:    ld s0, 16(sp)
+; CHECK-NEXT:    ld ra, 24(sp)
+; CHECK-NEXT:    addi sp, sp, 32
+; CHECK-NEXT:    ret
+entry:
+  %a.sroa.0.0.extract.trunc = trunc i64 %a.coerce to i32
+  %0 = bitcast i32 %a.sroa.0.0.extract.trunc to float
+  %a.sroa.2.0.extract.shift = lshr i64 %a.coerce, 32
+  %a.sroa.2.0.extract.trunc = trunc i64 %a.sroa.2.0.extract.shift to i32
+  %1 = bitcast i32 %a.sroa.2.0.extract.trunc to float
+  %b.sroa.0.0.extract.trunc = trunc i64 %b.coerce to i32
+  %2 = bitcast i32 %b.sroa.0.0.extract.trunc to float
+  %b.sroa.2.0.extract.shift = lshr i64 %b.coerce, 32
+  %b.sroa.2.0.extract.trunc = trunc i64 %b.sroa.2.0.extract.shift to i32
+  %3 = bitcast i32 %b.sroa.2.0.extract.trunc to float
+  %add.r = fadd float %0, %2
+  %add.i = fadd float %1, %3
+  %4 = bitcast float %add.r to i32
+  %5 = bitcast float %add.i to i32
+  %retval.sroa.2.0.insert.ext = zext i32 %5 to i64
+  %retval.sroa.2.0.insert.shift = shl nuw i64 %retval.sroa.2.0.insert.ext, 32
+  %retval.sroa.0.0.insert.ext = zext i32 %4 to i64
+  %retval.sroa.0.0.insert.insert = or i64 %retval.sroa.2.0.insert.shift, %retval.sroa.0.0.insert.ext
+  ret i64 %retval.sroa.0.0.insert.insert
+}
Index: llvm/trunk/test/CodeGen/RISCV/rv64i-single-softfloat.ll
===================================================================
--- llvm/trunk/test/CodeGen/RISCV/rv64i-single-softfloat.ll
+++ llvm/trunk/test/CodeGen/RISCV/rv64i-single-softfloat.ll
@@ -0,0 +1,712 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv64 -verify-machineinstrs < %s \
+; RUN:   | FileCheck -check-prefix=RV64I %s
+
+; The test cases check that the single float arguments won't be extended
+; when passing to softfloat functions.
+; RISCV backend using shouldExtendTypeInLibCall target hook to suppress
+; the extension generation.
+
+define float @fadd_s(float %a, float %b) nounwind {
+; RV64I-LABEL: fadd_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call __addsf3
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = fadd float %a, %b
+  ret float %1
+}
+
+define float @fsub_s(float %a, float %b) nounwind {
+; RV64I-LABEL: fsub_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call __subsf3
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = fsub float %a, %b
+  ret float %1
+}
+
+define float @fmul_s(float %a, float %b) nounwind {
+; RV64I-LABEL: fmul_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call __mulsf3
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = fmul float %a, %b
+  ret float %1
+}
+
+define float @fdiv_s(float %a, float %b) nounwind {
+; RV64I-LABEL: fdiv_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call __divsf3
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = fdiv float %a, %b
+  ret float %1
+}
+
+define i32 @feq_s(float %a, float %b) nounwind {
+; RV64I-LABEL: feq_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call __eqsf2
+; RV64I-NEXT:    seqz a0, a0
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = fcmp oeq float %a, %b
+  %2 = zext i1 %1 to i32
+  ret i32 %2
+}
+
+define i32 @flt_s(float %a, float %b) nounwind {
+; RV64I-LABEL: flt_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call __ltsf2
+; RV64I-NEXT:    sext.w a0, a0
+; RV64I-NEXT:    slti a0, a0, 0
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = fcmp olt float %a, %b
+  %2 = zext i1 %1 to i32
+  ret i32 %2
+}
+
+define i32 @fle_s(float %a, float %b) nounwind {
+; RV64I-LABEL: fle_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call __lesf2
+; RV64I-NEXT:    sext.w a0, a0
+; RV64I-NEXT:    slti a0, a0, 1
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = fcmp ole float %a, %b
+  %2 = zext i1 %1 to i32
+  ret i32 %2
+}
+
+define i32 @fcmp_ogt(float %a, float %b) nounwind {
+; RV64I-LABEL: fcmp_ogt:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call __gtsf2
+; RV64I-NEXT:    sext.w a0, a0
+; RV64I-NEXT:    sgtz a0, a0
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = fcmp ogt float %a, %b
+  %2 = zext i1 %1 to i32
+  ret i32 %2
+}
+
+define i32 @fcmp_oge(float %a, float %b) nounwind {
+; RV64I-LABEL: fcmp_oge:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call __gesf2
+; RV64I-NEXT:    sext.w a0, a0
+; RV64I-NEXT:    addi a1, zero, -1
+; RV64I-NEXT:    slt a0, a1, a0
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = fcmp oge float %a, %b
+  %2 = zext i1 %1 to i32
+  ret i32 %2
+}
+
+define i32 @fcmp_ord(float %a, float %b) nounwind {
+; RV64I-LABEL: fcmp_ord:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call __unordsf2
+; RV64I-NEXT:    seqz a0, a0
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = fcmp ord float %a, %b
+  %2 = zext i1 %1 to i32
+  ret i32 %2
+}
+
+define i32 @fcmp_une(float %a, float %b) nounwind {
+; RV64I-LABEL: fcmp_une:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call __nesf2
+; RV64I-NEXT:    snez a0, a0
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = fcmp une float %a, %b
+  %2 = zext i1 %1 to i32
+  ret i32 %2
+}
+
+define i32 @fcvt_w_s(float %a) nounwind {
+; RV64I-LABEL: fcvt_w_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call __fixsfdi
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = fptosi float %a to i32
+  ret i32 %1
+}
+
+define i32 @fcvt_wu_s(float %a) nounwind {
+; RV64I-LABEL: fcvt_wu_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call __fixunssfdi
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = fptoui float %a to i32
+  ret i32 %1
+}
+
+define float @fcvt_s_w(i32 %a) nounwind {
+; RV64I-LABEL: fcvt_s_w:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    sext.w a0, a0
+; RV64I-NEXT:    call __floatsisf
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = sitofp i32 %a to float
+  ret float %1
+}
+
+define float @fcvt_s_wu(i32 %a) nounwind {
+; RV64I-LABEL: fcvt_s_wu:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    slli a0, a0, 32
+; RV64I-NEXT:    srli a0, a0, 32
+; RV64I-NEXT:    call __floatunsisf
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = uitofp i32 %a to float
+  ret float %1
+}
+
+define i64 @fcvt_l_s(float %a) nounwind {
+; RV64I-LABEL: fcvt_l_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call __fixsfdi
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = fptosi float %a to i64
+  ret i64 %1
+}
+
+define i64 @fcvt_lu_s(float %a) nounwind {
+; RV64I-LABEL: fcvt_lu_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call __fixunssfdi
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = fptoui float %a to i64
+  ret i64 %1
+}
+
+define float @fcvt_s_l(i64 %a) nounwind {
+; RV64I-LABEL: fcvt_s_l:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call __floatdisf
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = sitofp i64 %a to float
+  ret float %1
+}
+
+define float @fcvt_s_lu(i64 %a) nounwind {
+; RV64I-LABEL: fcvt_s_lu:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call __floatundisf
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = uitofp i64 %a to float
+  ret float %1
+}
+
+declare float @llvm.sqrt.f32(float)
+
+define float @fsqrt_s(float %a) nounwind {
+; RV64I-LABEL: fsqrt_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call sqrtf
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = call float @llvm.sqrt.f32(float %a)
+  ret float %1
+}
+
+declare float @llvm.copysign.f32(float, float)
+
+define float @fsgnj_s(float %a, float %b) nounwind {
+; RV64I-LABEL: fsgnj_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    lui a2, 524288
+; RV64I-NEXT:    and a1, a1, a2
+; RV64I-NEXT:    addiw a2, a2, -1
+; RV64I-NEXT:    and a0, a0, a2
+; RV64I-NEXT:    or a0, a0, a1
+; RV64I-NEXT:    ret
+  %1 = call float @llvm.copysign.f32(float %a, float %b)
+  ret float %1
+}
+
+declare float @llvm.minnum.f32(float, float)
+
+define float @fmin_s(float %a, float %b) nounwind {
+; RV64I-LABEL: fmin_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call fminf
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = call float @llvm.minnum.f32(float %a, float %b)
+  ret float %1
+}
+
+declare float @llvm.maxnum.f32(float, float)
+
+define float @fmax_s(float %a, float %b) nounwind {
+; RV64I-LABEL: fmax_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call fmaxf
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = call float @llvm.maxnum.f32(float %a, float %b)
+  ret float %1
+}
+
+
+declare float @llvm.fma.f32(float, float, float)
+
+define float @fmadd_s(float %a, float %b, float %c) nounwind {
+; RV64I-LABEL: fmadd_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call fmaf
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = call float @llvm.fma.f32(float %a, float %b, float %c)
+  ret float %1
+}
+
+define float @fmsub_s(float %a, float %b, float %c) nounwind {
+; RV64I-LABEL: fmsub_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -32
+; RV64I-NEXT:    sd ra, 24(sp)
+; RV64I-NEXT:    sd s0, 16(sp)
+; RV64I-NEXT:    sd s1, 8(sp)
+; RV64I-NEXT:    mv s0, a1
+; RV64I-NEXT:    mv s1, a0
+; RV64I-NEXT:    mv a0, a2
+; RV64I-NEXT:    mv a1, zero
+; RV64I-NEXT:    call __addsf3
+; RV64I-NEXT:    lui a1, 524288
+; RV64I-NEXT:    xor a2, a0, a1
+; RV64I-NEXT:    mv a0, s1
+; RV64I-NEXT:    mv a1, s0
+; RV64I-NEXT:    call fmaf
+; RV64I-NEXT:    ld s1, 8(sp)
+; RV64I-NEXT:    ld s0, 16(sp)
+; RV64I-NEXT:    ld ra, 24(sp)
+; RV64I-NEXT:    addi sp, sp, 32
+; RV64I-NEXT:    ret
+  %c_ = fadd float 0.0, %c ; avoid negation using xor
+  %negc = fsub float -0.0, %c_
+  %1 = call float @llvm.fma.f32(float %a, float %b, float %negc)
+  ret float %1
+}
+
+define float @fnmadd_s(float %a, float %b, float %c) nounwind {
+; RV64I-LABEL: fnmadd_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -32
+; RV64I-NEXT:    sd ra, 24(sp)
+; RV64I-NEXT:    sd s0, 16(sp)
+; RV64I-NEXT:    sd s1, 8(sp)
+; RV64I-NEXT:    sd s2, 0(sp)
+; RV64I-NEXT:    mv s0, a2
+; RV64I-NEXT:    mv s2, a1
+; RV64I-NEXT:    mv a1, zero
+; RV64I-NEXT:    call __addsf3
+; RV64I-NEXT:    mv s1, a0
+; RV64I-NEXT:    mv a0, s0
+; RV64I-NEXT:    mv a1, zero
+; RV64I-NEXT:    call __addsf3
+; RV64I-NEXT:    lui a2, 524288
+; RV64I-NEXT:    xor a1, s1, a2
+; RV64I-NEXT:    xor a2, a0, a2
+; RV64I-NEXT:    mv a0, a1
+; RV64I-NEXT:    mv a1, s2
+; RV64I-NEXT:    call fmaf
+; RV64I-NEXT:    ld s2, 0(sp)
+; RV64I-NEXT:    ld s1, 8(sp)
+; RV64I-NEXT:    ld s0, 16(sp)
+; RV64I-NEXT:    ld ra, 24(sp)
+; RV64I-NEXT:    addi sp, sp, 32
+; RV64I-NEXT:    ret
+  %a_ = fadd float 0.0, %a
+  %c_ = fadd float 0.0, %c
+  %nega = fsub float -0.0, %a_
+  %negc = fsub float -0.0, %c_
+  %1 = call float @llvm.fma.f32(float %nega, float %b, float %negc)
+  ret float %1
+}
+
+define float @fnmsub_s(float %a, float %b, float %c) nounwind {
+; RV64I-LABEL: fnmsub_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -32
+; RV64I-NEXT:    sd ra, 24(sp)
+; RV64I-NEXT:    sd s0, 16(sp)
+; RV64I-NEXT:    sd s1, 8(sp)
+; RV64I-NEXT:    mv s0, a2
+; RV64I-NEXT:    mv s1, a1
+; RV64I-NEXT:    mv a1, zero
+; RV64I-NEXT:    call __addsf3
+; RV64I-NEXT:    lui a1, 524288
+; RV64I-NEXT:    xor a0, a0, a1
+; RV64I-NEXT:    mv a1, s1
+; RV64I-NEXT:    mv a2, s0
+; RV64I-NEXT:    call fmaf
+; RV64I-NEXT:    ld s1, 8(sp)
+; RV64I-NEXT:    ld s0, 16(sp)
+; RV64I-NEXT:    ld ra, 24(sp)
+; RV64I-NEXT:    addi sp, sp, 32
+; RV64I-NEXT:    ret
+  %a_ = fadd float 0.0, %a
+  %nega = fsub float -0.0, %a_
+  %1 = call float @llvm.fma.f32(float %nega, float %b, float %c)
+  ret float %1
+}
+
+declare float @llvm.ceil.f32(float)
+
+define float @fceil_s(float %a) nounwind {
+; RV64I-LABEL: fceil_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call ceilf
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = call float @llvm.ceil.f32(float %a)
+  ret float %1
+}
+
+declare float @llvm.cos.f32(float)
+
+define float @fcos_s(float %a) nounwind {
+; RV64I-LABEL: fcos_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call cosf
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = call float @llvm.cos.f32(float %a)
+  ret float %1
+}
+
+declare float @llvm.sin.f32(float)
+
+define float @fsin_s(float %a) nounwind {
+; RV64I-LABEL: fsin_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call sinf
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = call float @llvm.sin.f32(float %a)
+  ret float %1
+}
+
+declare float @llvm.exp.f32(float)
+
+define float @fexp_s(float %a) nounwind {
+; RV64I-LABEL: fexp_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call expf
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = call float @llvm.exp.f32(float %a)
+  ret float %1
+}
+
+declare float @llvm.exp2.f32(float)
+
+define float @fexp2_s(float %a) nounwind {
+; RV64I-LABEL: fexp2_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call exp2f
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = call float @llvm.exp2.f32(float %a)
+  ret float %1
+}
+
+declare float @llvm.floor.f32(float)
+
+define float @ffloor_s(float %a) nounwind {
+; RV64I-LABEL: ffloor_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call floorf
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = call float @llvm.floor.f32(float %a)
+  ret float %1
+}
+
+declare float @llvm.flog.f32(float)
+
+define float @fflog_s(float %a) nounwind {
+; RV64I-LABEL: fflog_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call llvm.flog.f32
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = call float @llvm.flog.f32(float %a)
+  ret float %1
+}
+
+declare float @llvm.flog2.f32(float)
+
+define float @fflog2_s(float %a) nounwind {
+; RV64I-LABEL: fflog2_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call llvm.flog2.f32
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = call float @llvm.flog2.f32(float %a)
+  ret float %1
+}
+
+declare float @llvm.flog10.f32(float)
+
+define float @fflog10_s(float %a) nounwind {
+; RV64I-LABEL: fflog10_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call llvm.flog10.f32
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = call float @llvm.flog10.f32(float %a)
+  ret float %1
+}
+
+declare float @llvm.fnearbyint.f32(float)
+
+define float @fnearbyint_s(float %a) nounwind {
+; RV64I-LABEL: fnearbyint_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call llvm.fnearbyint.f32
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = call float @llvm.fnearbyint.f32(float %a)
+  ret float %1
+}
+
+declare float @llvm.round.f32(float)
+
+define float @fround_s(float %a) nounwind {
+; RV64I-LABEL: fround_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call roundf
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = call float @llvm.round.f32(float %a)
+  ret float %1
+}
+
+declare float @llvm.fpround.f32(float)
+
+define float @fpround_s(float %a) nounwind {
+; RV64I-LABEL: fpround_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call llvm.fpround.f32
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = call float @llvm.fpround.f32(float %a)
+  ret float %1
+}
+
+declare float @llvm.rint.f32(float)
+
+define float @frint_s(float %a) nounwind {
+; RV64I-LABEL: frint_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call rintf
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = call float @llvm.rint.f32(float %a)
+  ret float %1
+}
+
+declare float @llvm.rem.f32(float)
+
+define float @frem_s(float %a) nounwind {
+; RV64I-LABEL: frem_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call llvm.rem.f32
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = call float @llvm.rem.f32(float %a)
+  ret float %1
+}
+
+declare float @llvm.pow.f32(float %Val, float %power)
+
+define float @fpow_s(float %a, float %b) nounwind {
+; RV64I-LABEL: fpow_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call powf
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = call float @llvm.pow.f32(float %a, float %b)
+  ret float %1
+}
+
+declare float @llvm.powi.f32(float %Val, i32 %power)
+
+define float @fpowi_s(float %a, i32 %b) nounwind {
+; RV64I-LABEL: fpowi_s:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    slli a1, a1, 32
+; RV64I-NEXT:    srli a1, a1, 32
+; RV64I-NEXT:    call __powisf2
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %1 = call float @llvm.powi.f32(float %a, i32 %b)
+  ret float %1
+}
+
+define double @fp_ext(float %a) nounwind {
+; RV64I-LABEL: fp_ext:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call __extendsfdf2
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %conv = fpext float %a to double
+  ret double %conv
+}
+
+define float @fp_trunc(double %a) nounwind {
+; RV64I-LABEL: fp_trunc:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi sp, sp, -16
+; RV64I-NEXT:    sd ra, 8(sp)
+; RV64I-NEXT:    call __truncdfsf2
+; RV64I-NEXT:    ld ra, 8(sp)
+; RV64I-NEXT:    addi sp, sp, 16
+; RV64I-NEXT:    ret
+  %conv = fptrunc double %a to float
+  ret float %conv
+}