[LegalizeTypes][FPEnv][X86] Add initial support for softening strict fp nodes

[craig.topper]

Summary

This is based on what's required for softening fp128 operations on 32-bit X86 assuming f32/f64/f80 are legal. So there could be some things missing.

[efriedma]

Could you split the refactoring to introduce SoftenFloatRes_Unary and SoftenFloatRes_Binary into a separate patch?

llvm/lib/CodeGen/SelectionDAG/LegalizeFloatTypes.cpp

878

This is different from the other operations?

[craig.topper]

llvm/lib/CodeGen/SelectionDAG/LegalizeFloatTypes.cpp

878

There's an assert in the caller than checks that the node only has a single result if you return a node. This assert only exists in the softening operand case. The softening result does not do this check. Returning SDValue() bypasses the assert. The same problem came up in vector splitting for operands and the assert was modified into 2 asserts that are selected based on whether the node is strict or not. I could do the same here, but it seemed like spreading strict fp details to a place that didn't really need to know about it.

[craig.topper]

Rebase after pre-commiting some of the refactoring

[craig.topper]

Add support for LRINT/LLRINT/LROUND/LLROUND as well

[efriedma]

LGTM, but I'd appreciate if someone following the STRICT_FP stuff a bit more closely could look to make sure the libcalls we're generating make sense.

llvm/lib/CodeGen/SelectionDAG/LegalizeFloatTypes.cpp

#endif
 
     case ISD::MERGE_VALUES:R = SoftenFloatRes_MERGE_VALUES(N, ResNo); break;
     case ISD::BITCAST:     R = SoftenFloatRes_BITCAST(N); break;
     case ISD::BUILD_PAIR:  R = SoftenFloatRes_BUILD_PAIR(N); break;
     case ISD::ConstantFP:  R = SoftenFloatRes_ConstantFP(N); break;
     case ISD::EXTRACT_VECTOR_ELT:
       R = SoftenFloatRes_EXTRACT_VECTOR_ELT(N, ResNo); break;
     case ISD::FABS:        R = SoftenFloatRes_FABS(N); break;
+    case ISD::STRICT_FMINNUM:
     case ISD::FMINNUM:     R = SoftenFloatRes_FMINNUM(N); break;
+    case ISD::STRICT_FMAXNUM:
     case ISD::FMAXNUM:     R = SoftenFloatRes_FMAXNUM(N); break;
+    case ISD::STRICT_FADD:
     case ISD::FADD:        R = SoftenFloatRes_FADD(N); break;
     case ISD::FCBRT:       R = SoftenFloatRes_FCBRT(N); break;
+    case ISD::STRICT_FCEIL:
     case ISD::FCEIL:       R = SoftenFloatRes_FCEIL(N); break;
     case ISD::FCOPYSIGN:   R = SoftenFloatRes_FCOPYSIGN(N); break;
+    case ISD::STRICT_FCOS:
     case ISD::FCOS:        R = SoftenFloatRes_FCOS(N); break;
+    case ISD::STRICT_FDIV:
     case ISD::FDIV:        R = SoftenFloatRes_FDIV(N); break;
+    case ISD::STRICT_FEXP:
     case ISD::FEXP:        R = SoftenFloatRes_FEXP(N); break;
+    case ISD::STRICT_FEXP2:
     case ISD::FEXP2:       R = SoftenFloatRes_FEXP2(N); break;
+    case ISD::STRICT_FFLOOR:
     case ISD::FFLOOR:      R = SoftenFloatRes_FFLOOR(N); break;
+    case ISD::STRICT_FLOG:
     case ISD::FLOG:        R = SoftenFloatRes_FLOG(N); break;
+    case ISD::STRICT_FLOG2:
     case ISD::FLOG2:       R = SoftenFloatRes_FLOG2(N); break;
+    case ISD::STRICT_FLOG10:
     case ISD::FLOG10:      R = SoftenFloatRes_FLOG10(N); break;
+    case ISD::STRICT_FMA:
     case ISD::FMA:         R = SoftenFloatRes_FMA(N); break;
+    case ISD::STRICT_FMUL:
     case ISD::FMUL:        R = SoftenFloatRes_FMUL(N); break;
+    case ISD::STRICT_FNEARBYINT:
     case ISD::FNEARBYINT:  R = SoftenFloatRes_FNEARBYINT(N); break;
     case ISD::FNEG:        R = SoftenFloatRes_FNEG(N); break;
+    case ISD::STRICT_FP_EXTEND:
     case ISD::FP_EXTEND:   R = SoftenFloatRes_FP_EXTEND(N); break;
     case ISD::FP_ROUND:    R = SoftenFloatRes_FP_ROUND(N); break;
     case ISD::FP16_TO_FP:  R = SoftenFloatRes_FP16_TO_FP(N); break;
+    case ISD::STRICT_FPOW:
     case ISD::FPOW:        R = SoftenFloatRes_FPOW(N); break;
+    case ISD::STRICT_FPOWI:
     case ISD::FPOWI:       R = SoftenFloatRes_FPOWI(N); break;
+    case ISD::STRICT_FREM:
     case ISD::FREM:        R = SoftenFloatRes_FREM(N); break;
+    case ISD::STRICT_FRINT:
     case ISD::FRINT:       R = SoftenFloatRes_FRINT(N); break;
+    case ISD::STRICT_FROUND:
     case ISD::FROUND:      R = SoftenFloatRes_FROUND(N); break;
+    case ISD::STRICT_FSIN:
     case ISD::FSIN:        R = SoftenFloatRes_FSIN(N); break;
+    case ISD::STRICT_FSQRT:
     case ISD::FSQRT:       R = SoftenFloatRes_FSQRT(N); break;
+    case ISD::STRICT_FSUB:
     case ISD::FSUB:        R = SoftenFloatRes_FSUB(N); break;
+    case ISD::STRICT_FTRUNC:
     case ISD::FTRUNC:      R = SoftenFloatRes_FTRUNC(N); break;
     case ISD::LOAD:        R = SoftenFloatRes_LOAD(N); break;
     case ISD::ATOMIC_SWAP: R = BitcastToInt_ATOMIC_SWAP(N); break;
     case ISD::SELECT:      R = SoftenFloatRes_SELECT(N); break;
     case ISD::SELECT_CC:   R = SoftenFloatRes_SELECT_CC(N); break;
     case ISD::SINT_TO_FP:
     case ISD::UINT_TO_FP:  R = SoftenFloatRes_XINT_TO_FP(N); break;
     case ISD::UNDEF:       R = SoftenFloatRes_UNDEF(N); break;
     case ISD::VAARG:       R = SoftenFloatRes_VAARG(N); break;
   }
 
   // If R is null, the sub-method took care of registering the result.
   if (R.getNode()) {
     assert(R.getNode() != N);
     SetSoftenedFloat(SDValue(N, ResNo), R);
   }
 }
 
 SDValue DAGTypeLegalizer::SoftenFloatRes_Unary(SDNode *N, RTLIB::Libcall LC) {
+  bool IsStrict = N->isStrictFPOpcode();
   EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0));
-  assert(N->getNumOperands() == 1 && "Unexpected number of operands!");
-  SDValue Op = GetSoftenedFloat(N->getOperand(0));
+  unsigned Offset = IsStrict ? 1 : 0;
+  assert(N->getNumOperands() == (1 + Offset) &&
+         "Unexpected number of operands!");
+  SDValue Op = GetSoftenedFloat(N->getOperand(0 + Offset));
+  SDValue Chain = IsStrict ? N->getOperand(0) : SDValue();
   TargetLowering::MakeLibCallOptions CallOptions;
-  EVT OpVT = N->getOperand(0).getValueType();
+  EVT OpVT = N->getOperand(0 + Offset).getValueType();
   CallOptions.setTypeListBeforeSoften(OpVT, N->getValueType(0), true);
-  return TLI.makeLibCall(DAG, LC, NVT, Op, CallOptions, SDLoc(N)).first;
+  std::pair<SDValue, SDValue> Tmp = TLI.makeLibCall(DAG, LC, NVT, Op,
+                                                    CallOptions, SDLoc(N),
+                                                    Chain);
+  if (IsStrict)
+    ReplaceValueWith(SDValue(N, 1), Tmp.second);
+  return Tmp.first;
 }
 
 SDValue DAGTypeLegalizer::SoftenFloatRes_Binary(SDNode *N, RTLIB::Libcall LC) {
+  bool IsStrict = N->isStrictFPOpcode();
   EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0));
-  assert(N->getNumOperands() == 2 && "Unexpected number of operands!");
-  SDValue Ops[2] = { GetSoftenedFloat(N->getOperand(0)),
-                     GetSoftenedFloat(N->getOperand(1)) };
+  unsigned Offset = IsStrict ? 1 : 0;
+  assert(N->getNumOperands() == (2 + Offset) &&
+         "Unexpected number of operands!");
+  SDValue Ops[2] = { GetSoftenedFloat(N->getOperand(0 + Offset)),
+                     GetSoftenedFloat(N->getOperand(1 + Offset)) };
+  SDValue Chain = IsStrict ? N->getOperand(0) : SDValue();
   TargetLowering::MakeLibCallOptions CallOptions;
-  EVT OpsVT[2] = { N->getOperand(0).getValueType(),
-                   N->getOperand(1).getValueType() };
+  EVT OpsVT[2] = { N->getOperand(0 + Offset).getValueType(),
+                   N->getOperand(1 + Offset).getValueType() };
   CallOptions.setTypeListBeforeSoften(OpsVT, N->getValueType(0), true);
-  return TLI.makeLibCall(DAG, LC, NVT, Ops, CallOptions, SDLoc(N)).first;
+  std::pair<SDValue, SDValue> Tmp = TLI.makeLibCall(DAG, LC, NVT, Ops,
+                                                    CallOptions, SDLoc(N),
+                                                    Chain);
+  if (IsStrict)
+    ReplaceValueWith(SDValue(N, 1), Tmp.second);
+  return Tmp.first;
 }
 
 SDValue DAGTypeLegalizer::SoftenFloatRes_BITCAST(SDNode *N) {
   return BitConvertToInteger(N->getOperand(0));
 }
 
 SDValue DAGTypeLegalizer::SoftenFloatRes_MERGE_VALUES(SDNode *N,
                                                       unsigned ResNo) {
return SoftenFloatRes_Unary(N, GetFPLibCall(N->getValueType(0),
                                               RTLIB::LOG10_F32,
                                               RTLIB::LOG10_F64,
                                               RTLIB::LOG10_F80,
                                               RTLIB::LOG10_F128,
                                               RTLIB::LOG10_PPCF128));
 }
 
 SDValue DAGTypeLegalizer::SoftenFloatRes_FMA(SDNode *N) {
+  bool IsStrict = N->isStrictFPOpcode();
   EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0));
-  SDValue Ops[3] = { GetSoftenedFloat(N->getOperand(0)),
-                     GetSoftenedFloat(N->getOperand(1)),
-                     GetSoftenedFloat(N->getOperand(2)) };
-  TargetLowering::MakeLibCallOptions CallOptions;
-  EVT OpsVT[3] = { N->getOperand(0).getValueType(),
-                   N->getOperand(1).getValueType(),
-                   N->getOperand(2).getValueType() };
+  unsigned Offset = IsStrict ? 1 : 0;
+  SDValue Ops[3] = { GetSoftenedFloat(N->getOperand(0 + Offset)),
+                     GetSoftenedFloat(N->getOperand(1 + Offset)),
+                     GetSoftenedFloat(N->getOperand(2 + Offset)) };
+  SDValue Chain = IsStrict ? N->getOperand(0) : SDValue();
+  TargetLowering::MakeLibCallOptions CallOptions;
+  EVT OpsVT[3] = { N->getOperand(0 + Offset).getValueType(),
+                   N->getOperand(1 + Offset).getValueType(),
+                   N->getOperand(2 + Offset).getValueType() };
   CallOptions.setTypeListBeforeSoften(OpsVT, N->getValueType(0), true);
-  return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
+  std::pair<SDValue, SDValue> Tmp = TLI.makeLibCall(DAG,
+                                                    GetFPLibCall(N->getValueType(0),
                                                                  RTLIB::FMA_F32,
                                                                  RTLIB::FMA_F64,
                                                                  RTLIB::FMA_F80,
                                                                  RTLIB::FMA_F128,
                                                                  RTLIB::FMA_PPCF128),
-                         NVT, Ops, CallOptions, SDLoc(N)).first;
+                         NVT, Ops, CallOptions, SDLoc(N), Chain);
+  if (IsStrict)
+    ReplaceValueWith(SDValue(N, 1), Tmp.second);
+  return Tmp.first;
 }
 
 SDValue DAGTypeLegalizer::SoftenFloatRes_FMUL(SDNode *N) {
   return SoftenFloatRes_Binary(N, GetFPLibCall(N->getValueType(0),
                                                RTLIB::MUL_F32,
                                                RTLIB::MUL_F64,
                                                RTLIB::MUL_F80,
                                                RTLIB::MUL_F128,
return TLI.makeLibCall(DAG, GetFPLibCall(N->getValueType(0),
                                            RTLIB::SUB_F64,
                                            RTLIB::SUB_F80,
                                            RTLIB::SUB_F128,
                                            RTLIB::SUB_PPCF128),
                          NVT, Ops, CallOptions, dl).first;
 }
 
 SDValue DAGTypeLegalizer::SoftenFloatRes_FP_EXTEND(SDNode *N) {
+  bool IsStrict = N->isStrictFPOpcode();
   EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0));
-  SDValue Op = N->getOperand(0);
+  SDValue Op = N->getOperand(IsStrict ? 1 : 0);
+
+  SDValue Chain = IsStrict ? N->getOperand(0) : SDValue();
 
   // There's only a libcall for f16 -> f32, so proceed in two stages. Also, it's
   // entirely possible for both f16 and f32 to be legal, so use the fully
   // hard-float FP_EXTEND rather than FP16_TO_FP.
   if (Op.getValueType() == MVT::f16 && N->getValueType(0) != MVT::f32) {
+    if (IsStrict) {
+      Op = DAG.getNode(ISD::STRICT_FP_EXTEND, SDLoc(N),
+                       { MVT::f32, MVT::Other }, { Chain, Op });
+      Chain = Op.getValue(1);
+    } else {
       Op = DAG.getNode(ISD::FP_EXTEND, SDLoc(N), MVT::f32, Op);
+    }
+
     if (getTypeAction(MVT::f32) == TargetLowering::TypeSoftenFloat)
       AddToWorklist(Op.getNode());
   }
 
   if (getTypeAction(Op.getValueType()) == TargetLowering::TypePromoteFloat) {
     Op = GetPromotedFloat(Op);
     // If the promotion did the FP_EXTEND to the destination type for us,
     // there's nothing left to do here.
     if (Op.getValueType() == N->getValueType(0)) {
       return BitConvertToInteger(Op);
     }
   }
 
   RTLIB::Libcall LC = RTLIB::getFPEXT(Op.getValueType(), N->getValueType(0));
   assert(LC != RTLIB::UNKNOWN_LIBCALL && "Unsupported FP_EXTEND!");
   TargetLowering::MakeLibCallOptions CallOptions;
   EVT OpsVT[1] = { N->getOperand(0).getValueType() };
   CallOptions.setTypeListBeforeSoften(OpsVT, N->getValueType(0), true);
-  return TLI.makeLibCall(DAG, LC, NVT, Op, CallOptions, SDLoc(N)).first;
+  std::pair<SDValue, SDValue> Tmp = TLI.makeLibCall(DAG, LC, NVT, Op,
+                                                    CallOptions, SDLoc(N),
+                                                    Chain);
+  if (IsStrict)
+    ReplaceValueWith(SDValue(N, 1), Tmp.second);
+  return Tmp.first;
 }
 
 // FIXME: Should we just use 'normal' FP_EXTEND / FP_TRUNC instead of special
 // nodes?
 SDValue DAGTypeLegalizer::SoftenFloatRes_FP16_TO_FP(SDNode *N) {
   EVT MidVT = TLI.getTypeToTransformTo(*DAG.getContext(), MVT::f32);
   SDValue Op = N->getOperand(0);
   TargetLowering::MakeLibCallOptions CallOptions;
return SoftenFloatRes_Binary(N, GetFPLibCall(N->getValueType(0),
                                                RTLIB::POW_F32,
                                                RTLIB::POW_F64,
                                                RTLIB::POW_F80,
                                                RTLIB::POW_F128,
                                                RTLIB::POW_PPCF128));
 }
 
 SDValue DAGTypeLegalizer::SoftenFloatRes_FPOWI(SDNode *N) {
-  assert(N->getOperand(1).getValueType() == MVT::i32 &&
+  bool IsStrict = N->isStrictFPOpcode();
+  unsigned Offset = IsStrict ? 1 : 0;
+  assert(N->getOperand(1 + Offset).getValueType() == MVT::i32 &&
          "Unsupported power type!");
   RTLIB::Libcall LC = GetFPLibCall(N->getValueType(0),
                                    RTLIB::POWI_F32,
                                    RTLIB::POWI_F64,
                                    RTLIB::POWI_F80,
                                    RTLIB::POWI_F128,
                                    RTLIB::POWI_PPCF128);
   if (!TLI.getLibcallName(LC)) {
     // Some targets don't have a powi libcall; use pow instead.
     // FIXME: Implement this if some target needs it.
     DAG.getContext()->emitError("Don't know how to soften fpowi to fpow");
     return DAG.getUNDEF(N->getValueType(0));
   }
 
   EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0));
-  SDValue Ops[2] = { GetSoftenedFloat(N->getOperand(0)), N->getOperand(1) };
+  SDValue Ops[2] = { GetSoftenedFloat(N->getOperand(0 + Offset)),
+                     N->getOperand(1 + Offset) };
+  SDValue Chain = IsStrict ? N->getOperand(0) : SDValue();
   TargetLowering::MakeLibCallOptions CallOptions;
-  EVT OpsVT[2] = { N->getOperand(0).getValueType(),
-                   N->getOperand(1).getValueType() };
+  EVT OpsVT[2] = { N->getOperand(0 + Offset).getValueType(),
+                   N->getOperand(1 + Offset).getValueType() };
   CallOptions.setTypeListBeforeSoften(OpsVT, N->getValueType(0), true);
-  return TLI.makeLibCall(DAG, LC, NVT, Ops, CallOptions, SDLoc(N)).first;
+  std::pair<SDValue, SDValue> Tmp = TLI.makeLibCall(DAG, LC, NVT, Ops,
+                                                    CallOptions, SDLoc(N),
+                                                    Chain);
+  if (IsStrict)
+    ReplaceValueWith(SDValue(N, 1), Tmp.second);
+  return Tmp.first;
 }
 
 SDValue DAGTypeLegalizer::SoftenFloatRes_FREM(SDNode *N) {
   return SoftenFloatRes_Binary(N, GetFPLibCall(N->getValueType(0),
                                                RTLIB::REM_F32,
                                                RTLIB::REM_F64,
                                                RTLIB::REM_F80,
                                                RTLIB::REM_F128,
#ifndef NDEBUG
     N->dump(&DAG); dbgs() << "\n";
 #endif
     llvm_unreachable("Do not know how to soften this operator's operand!");
 
   case ISD::BITCAST:     Res = SoftenFloatOp_BITCAST(N); break;
   case ISD::BR_CC:       Res = SoftenFloatOp_BR_CC(N); break;
   case ISD::FP_EXTEND:   Res = SoftenFloatOp_FP_EXTEND(N); break;
   case ISD::FP_TO_FP16:  // Same as FP_ROUND for softening purposes
+  case ISD::STRICT_FP_ROUND:
   case ISD::FP_ROUND:    Res = SoftenFloatOp_FP_ROUND(N); break;
   case ISD::FP_TO_SINT:
   case ISD::FP_TO_UINT:  Res = SoftenFloatOp_FP_TO_XINT(N); break;
+  case ISD::STRICT_LROUND:
   case ISD::LROUND:      Res = SoftenFloatOp_LROUND(N); break;
+  case ISD::STRICT_LLROUND:
   case ISD::LLROUND:     Res = SoftenFloatOp_LLROUND(N); break;
+  case ISD::STRICT_LRINT:
   case ISD::LRINT:       Res = SoftenFloatOp_LRINT(N); break;
+  case ISD::STRICT_LLRINT:
   case ISD::LLRINT:      Res = SoftenFloatOp_LLRINT(N); break;
   case ISD::SELECT_CC:   Res = SoftenFloatOp_SELECT_CC(N); break;
   case ISD::SETCC:       Res = SoftenFloatOp_SETCC(N); break;
   case ISD::STORE:       Res = SoftenFloatOp_STORE(N, OpNo); break;
   case ISD::FCOPYSIGN:   Res = SoftenFloatOp_FCOPYSIGN(N); break;
   }
 
   // If the result is null, the sub-method took care of registering results etc.
SDValue DAGTypeLegalizer::SoftenFloatOp_FP_EXTEND(SDNode *N) {
   CallOptions.setTypeListBeforeSoften(OpsVT, N->getValueType(0), true);
   return TLI.makeLibCall(DAG, LC, RVT, Op, CallOptions, SDLoc(N)).first;
 }
 
 
 SDValue DAGTypeLegalizer::SoftenFloatOp_FP_ROUND(SDNode *N) {
   // We actually deal with the partially-softened FP_TO_FP16 node too, which
   // returns an i16 so doesn't meet the constraints necessary for FP_ROUND.
-  assert(N->getOpcode() == ISD::FP_ROUND || N->getOpcode() == ISD::FP_TO_FP16);
+  assert(N->getOpcode() == ISD::FP_ROUND || N->getOpcode() == ISD::FP_TO_FP16 ||
+         N->getOpcode() == ISD::STRICT_FP_ROUND);
 
-  EVT SVT = N->getOperand(0).getValueType();
+  bool IsStrict = N->isStrictFPOpcode();
+  SDValue Op = N->getOperand(IsStrict ? 1 : 0);
+  EVT SVT = Op.getValueType();
   EVT RVT = N->getValueType(0);
   EVT FloatRVT = N->getOpcode() == ISD::FP_TO_FP16 ? MVT::f16 : RVT;
 
   RTLIB::Libcall LC = RTLIB::getFPROUND(SVT, FloatRVT);
   assert(LC != RTLIB::UNKNOWN_LIBCALL && "Unsupported FP_ROUND libcall");
 
-  SDValue Op = GetSoftenedFloat(N->getOperand(0));
+  SDValue Chain = IsStrict ? N->getOperand(0) : SDValue();
+  Op = GetSoftenedFloat(Op);
   TargetLowering::MakeLibCallOptions CallOptions;
-  EVT OpsVT[1] = { N->getOperand(0).getValueType() };
-  CallOptions.setTypeListBeforeSoften(OpsVT, N->getValueType(0), true);
-  return TLI.makeLibCall(DAG, LC, RVT, Op, CallOptions, SDLoc(N)).first;
+  CallOptions.setTypeListBeforeSoften(SVT, RVT, true);
+  std::pair<SDValue, SDValue> Tmp = TLI.makeLibCall(DAG, LC, RVT, Op,
+                                                    CallOptions, SDLoc(N),
+                                                    Chain);
+  if (IsStrict) {
+    ReplaceValueWith(SDValue(N, 1), Tmp.second);
+    ReplaceValueWith(SDValue(N, 0), Tmp.first);
+    return SDValue();
+  }
+  return Tmp.first;
 }
 
 SDValue DAGTypeLegalizer::SoftenFloatOp_BR_CC(SDNode *N) {
   SDValue NewLHS = N->getOperand(2), NewRHS = N->getOperand(3);
   ISD::CondCode CCCode = cast<CondCodeSDNode>(N->getOperand(1))->get();
 
   EVT VT = NewLHS.getValueType();
   NewLHS = GetSoftenedFloat(NewLHS);
SDValue DAGTypeLegalizer::SoftenFloatOp_FCOPYSIGN(SDNode *N) {
   }
 
   RHS = DAG.getBitcast(LVT, RHS);
   return DAG.getNode(ISD::FCOPYSIGN, dl, LVT, LHS, RHS);
 }
 
 SDValue DAGTypeLegalizer::SoftenFloatOp_Unary(SDNode *N, RTLIB::Libcall LC) {
   EVT NVT = TLI.getTypeToTransformTo(*DAG.getContext(), N->getValueType(0));
-  SDValue Op = GetSoftenedFloat(N->getOperand(0));
+  bool IsStrict = N->isStrictFPOpcode();
+  unsigned Offset = IsStrict ? 1 : 0;
+  SDValue Op = GetSoftenedFloat(N->getOperand(0 + Offset));
+  SDValue Chain = IsStrict ? N->getOperand(0) : SDValue();
   TargetLowering::MakeLibCallOptions CallOptions;
-  EVT OpVT = N->getOperand(0).getValueType();
+  EVT OpVT = N->getOperand(0 + Offset).getValueType();
   CallOptions.setTypeListBeforeSoften(OpVT, N->getValueType(0), true);
-  return TLI.makeLibCall(DAG, LC, NVT, Op, CallOptions, SDLoc(N)).first;
+  std::pair<SDValue, SDValue> Tmp = TLI.makeLibCall(DAG, LC, NVT, Op,
+                                                    CallOptions, SDLoc(N),
+                                                    Chain);
+  if (IsStrict) {
+    ReplaceValueWith(SDValue(N, 1), Tmp.second);
+    ReplaceValueWith(SDValue(N, 0), Tmp.first);
+    return SDValue();
+  }
+
+  return Tmp.first;
 }
 
 SDValue DAGTypeLegalizer::SoftenFloatOp_LROUND(SDNode *N) {
-  EVT OpVT = N->getOperand(0).getValueType();
+  EVT OpVT = N->getOperand(N->isStrictFPOpcode() ? 1 : 0).getValueType();
   return SoftenFloatOp_Unary(N, GetFPLibCall(OpVT,
                                              RTLIB::LROUND_F32,
                                              RTLIB::LROUND_F64,
                                              RTLIB::LROUND_F80,
                                              RTLIB::LROUND_F128,
                                              RTLIB::LROUND_PPCF128));
 }
 
 SDValue DAGTypeLegalizer::SoftenFloatOp_LLROUND(SDNode *N) {
-  EVT OpVT = N->getOperand(0).getValueType();
+  EVT OpVT = N->getOperand(N->isStrictFPOpcode() ? 1 : 0).getValueType();
   return SoftenFloatOp_Unary(N, GetFPLibCall(OpVT,
                                              RTLIB::LLROUND_F32,
                                              RTLIB::LLROUND_F64,
                                              RTLIB::LLROUND_F80,
                                              RTLIB::LLROUND_F128,
                                              RTLIB::LLROUND_PPCF128));
 }
 
 SDValue DAGTypeLegalizer::SoftenFloatOp_LRINT(SDNode *N) {
-  EVT OpVT = N->getOperand(0).getValueType();
+  EVT OpVT = N->getOperand(N->isStrictFPOpcode() ? 1 : 0).getValueType();
   return SoftenFloatOp_Unary(N, GetFPLibCall(OpVT,
                                              RTLIB::LRINT_F32,
                                              RTLIB::LRINT_F64,
                                              RTLIB::LRINT_F80,
                                              RTLIB::LRINT_F128,
                                              RTLIB::LRINT_PPCF128));
 }
 
 SDValue DAGTypeLegalizer::SoftenFloatOp_LLRINT(SDNode *N) {
-  EVT OpVT = N->getOperand(0).getValueType();
+  EVT OpVT = N->getOperand(N->isStrictFPOpcode() ? 1 : 0).getValueType();
   return SoftenFloatOp_Unary(N, GetFPLibCall(OpVT,
                                              RTLIB::LLRINT_F32,
                                              RTLIB::LLRINT_F64,
                                              RTLIB::LLRINT_F80,
                                              RTLIB::LLRINT_F128,
                                              RTLIB::LLRINT_PPCF128));
 }
 

llvm/test/CodeGen/X86/fp128-libcalls-strict.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc < %s -O2 -mtriple=x86_64-linux-android -mattr=+mmx \
+; RUN: llc < %s -O2 -mtriple=x86_64-linux-android \
 ; RUN:     -enable-legalize-types-checking \
 ; RUN:     -disable-strictnode-mutation | FileCheck %s
-; RUN: llc < %s -O2 -mtriple=x86_64-linux-gnu -mattr=+mmx \
+; RUN: llc < %s -O2 -mtriple=x86_64-linux-gnu \
 ; RUN:     -enable-legalize-types-checking \
 ; RUN:     -disable-strictnode-mutation | FileCheck %s
+; RUN: llc < %s -O2 -mtriple=i686-linux-gnu -mattr=+sse2 \
+; RUN:     -enable-legalize-types-checking \
+; RUN:     -disable-strictnode-mutation | FileCheck %s --check-prefix=X86
 
 ; Check all soft floating point library function calls.
 
 define fp128 @add(fp128 %x, fp128 %y) nounwind strictfp {
 ; CHECK-LABEL: add:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq __addtf3
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: add:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    calll __addtf3
+; X86-NEXT:    addl $44, %esp
+; X86-NEXT:    movl (%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 8(%esi)
+; X86-NEXT:    movl %edx, 12(%esi)
+; X86-NEXT:    movl %eax, (%esi)
+; X86-NEXT:    movl %ecx, 4(%esi)
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    retl $4
 entry:
   %add = call fp128 @llvm.experimental.constrained.fadd.f128(fp128 %x, fp128 %y,  metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret fp128 %add
 }
 
 define fp128 @sub(fp128 %x, fp128 %y) nounwind strictfp {
 ; CHECK-LABEL: sub:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq __subtf3
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: sub:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    calll __subtf3
+; X86-NEXT:    addl $44, %esp
+; X86-NEXT:    movl (%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 8(%esi)
+; X86-NEXT:    movl %edx, 12(%esi)
+; X86-NEXT:    movl %eax, (%esi)
+; X86-NEXT:    movl %ecx, 4(%esi)
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    retl $4
 entry:
   %sub = call fp128 @llvm.experimental.constrained.fsub.f128(fp128 %x, fp128 %y,  metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret fp128 %sub
 }
 
 define fp128 @mul(fp128 %x, fp128 %y) nounwind strictfp {
 ; CHECK-LABEL: mul:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq __multf3
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: mul:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    calll __multf3
+; X86-NEXT:    addl $44, %esp
+; X86-NEXT:    movl (%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 8(%esi)
+; X86-NEXT:    movl %edx, 12(%esi)
+; X86-NEXT:    movl %eax, (%esi)
+; X86-NEXT:    movl %ecx, 4(%esi)
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    retl $4
 entry:
   %mul = call fp128 @llvm.experimental.constrained.fmul.f128(fp128 %x, fp128 %y,  metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret fp128 %mul
 }
 
 define fp128 @div(fp128 %x, fp128 %y) nounwind strictfp {
 ; CHECK-LABEL: div:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq __divtf3
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: div:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    calll __divtf3
+; X86-NEXT:    addl $44, %esp
+; X86-NEXT:    movl (%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 8(%esi)
+; X86-NEXT:    movl %edx, 12(%esi)
+; X86-NEXT:    movl %eax, (%esi)
+; X86-NEXT:    movl %ecx, 4(%esi)
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    retl $4
 entry:
   %div = call fp128 @llvm.experimental.constrained.fdiv.f128(fp128 %x, fp128 %y,  metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret fp128 %div
 }
 
 define fp128 @fma(fp128 %x, fp128 %y, fp128 %z) nounwind strictfp {
 ; CHECK-LABEL: fma:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq fmal
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: fma:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    calll fmal
+; X86-NEXT:    addl $60, %esp
+; X86-NEXT:    movl (%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 8(%esi)
+; X86-NEXT:    movl %edx, 12(%esi)
+; X86-NEXT:    movl %eax, (%esi)
+; X86-NEXT:    movl %ecx, 4(%esi)
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    retl $4
 entry:
   %fma = call fp128 @llvm.experimental.constrained.fma.f128(fp128 %x, fp128 %y,  fp128 %z, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret fp128 %fma
 }
 
 define fp128 @frem(fp128 %x, fp128 %y) nounwind strictfp {
 ; CHECK-LABEL: frem:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq fmodl
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: frem:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    calll fmodl
+; X86-NEXT:    addl $44, %esp
+; X86-NEXT:    movl (%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 8(%esi)
+; X86-NEXT:    movl %edx, 12(%esi)
+; X86-NEXT:    movl %eax, (%esi)
+; X86-NEXT:    movl %ecx, 4(%esi)
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    retl $4
 entry:
   %div = call fp128 @llvm.experimental.constrained.frem.f128(fp128 %x, fp128 %y,  metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret fp128 %div
 }
 
 define fp128 @ceil(fp128 %x) nounwind strictfp {
 ; CHECK-LABEL: ceil:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq ceill
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: ceil:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    calll ceill
+; X86-NEXT:    addl $28, %esp
+; X86-NEXT:    movl (%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 8(%esi)
+; X86-NEXT:    movl %edx, 12(%esi)
+; X86-NEXT:    movl %eax, (%esi)
+; X86-NEXT:    movl %ecx, 4(%esi)
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    retl $4
 entry:
   %ceil = call fp128 @llvm.experimental.constrained.ceil.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret fp128 %ceil
 }
 
 define fp128 @cos(fp128 %x) nounwind strictfp {
 ; CHECK-LABEL: cos:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq cosl
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: cos:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    calll cosl
+; X86-NEXT:    addl $28, %esp
+; X86-NEXT:    movl (%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 8(%esi)
+; X86-NEXT:    movl %edx, 12(%esi)
+; X86-NEXT:    movl %eax, (%esi)
+; X86-NEXT:    movl %ecx, 4(%esi)
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    retl $4
 entry:
   %cos = call fp128 @llvm.experimental.constrained.cos.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret fp128 %cos
 }
 
 define fp128 @exp(fp128 %x) nounwind strictfp {
 ; CHECK-LABEL: exp:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq expl
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: exp:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    calll expl
+; X86-NEXT:    addl $28, %esp
+; X86-NEXT:    movl (%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 8(%esi)
+; X86-NEXT:    movl %edx, 12(%esi)
+; X86-NEXT:    movl %eax, (%esi)
+; X86-NEXT:    movl %ecx, 4(%esi)
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    retl $4
 entry:
   %exp = call fp128 @llvm.experimental.constrained.exp.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret fp128 %exp
 }
 
 define fp128 @exp2(fp128 %x) nounwind strictfp {
 ; CHECK-LABEL: exp2:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq exp2l
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: exp2:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    calll exp2l
+; X86-NEXT:    addl $28, %esp
+; X86-NEXT:    movl (%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 8(%esi)
+; X86-NEXT:    movl %edx, 12(%esi)
+; X86-NEXT:    movl %eax, (%esi)
+; X86-NEXT:    movl %ecx, 4(%esi)
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    retl $4
 entry:
   %exp2 = call fp128 @llvm.experimental.constrained.exp2.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret fp128 %exp2
 }
 
 define fp128 @floor(fp128 %x) nounwind strictfp {
 ; CHECK-LABEL: floor:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq floorl
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: floor:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    calll floorl
+; X86-NEXT:    addl $28, %esp
+; X86-NEXT:    movl (%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 8(%esi)
+; X86-NEXT:    movl %edx, 12(%esi)
+; X86-NEXT:    movl %eax, (%esi)
+; X86-NEXT:    movl %ecx, 4(%esi)
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    retl $4
 entry:
   %floor = call fp128 @llvm.experimental.constrained.floor.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret fp128 %floor
 }
 
 define fp128 @log(fp128 %x) nounwind strictfp {
 ; CHECK-LABEL: log:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq logl
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: log:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    calll logl
+; X86-NEXT:    addl $28, %esp
+; X86-NEXT:    movl (%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 8(%esi)
+; X86-NEXT:    movl %edx, 12(%esi)
+; X86-NEXT:    movl %eax, (%esi)
+; X86-NEXT:    movl %ecx, 4(%esi)
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    retl $4
 entry:
   %log = call fp128 @llvm.experimental.constrained.log.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret fp128 %log
 }
 
 define fp128 @log10(fp128 %x) nounwind strictfp {
 ; CHECK-LABEL: log10:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq log10l
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: log10:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    calll log10l
+; X86-NEXT:    addl $28, %esp
+; X86-NEXT:    movl (%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 8(%esi)
+; X86-NEXT:    movl %edx, 12(%esi)
+; X86-NEXT:    movl %eax, (%esi)
+; X86-NEXT:    movl %ecx, 4(%esi)
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    retl $4
 entry:
   %log10 = call fp128 @llvm.experimental.constrained.log10.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret fp128 %log10
 }
 
 define fp128 @log2(fp128 %x) nounwind strictfp {
 ; CHECK-LABEL: log2:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq log2l
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: log2:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    calll log2l
+; X86-NEXT:    addl $28, %esp
+; X86-NEXT:    movl (%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 8(%esi)
+; X86-NEXT:    movl %edx, 12(%esi)
+; X86-NEXT:    movl %eax, (%esi)
+; X86-NEXT:    movl %ecx, 4(%esi)
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    retl $4
 entry:
   %log2 = call fp128 @llvm.experimental.constrained.log2.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret fp128 %log2
 }
 
 define fp128 @maxnum(fp128 %x, fp128 %y) nounwind strictfp {
 ; CHECK-LABEL: maxnum:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq fmaxl
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: maxnum:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    calll fmaxl
+; X86-NEXT:    addl $44, %esp
+; X86-NEXT:    movl (%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 8(%esi)
+; X86-NEXT:    movl %edx, 12(%esi)
+; X86-NEXT:    movl %eax, (%esi)
+; X86-NEXT:    movl %ecx, 4(%esi)
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    retl $4
 entry:
   %maxnum = call fp128 @llvm.experimental.constrained.maxnum.f128(fp128 %x, fp128 %y, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret fp128 %maxnum
 }
 
 define fp128 @minnum(fp128 %x, fp128 %y) nounwind strictfp {
 ; CHECK-LABEL: minnum:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq fminl
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: minnum:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    calll fminl
+; X86-NEXT:    addl $44, %esp
+; X86-NEXT:    movl (%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 8(%esi)
+; X86-NEXT:    movl %edx, 12(%esi)
+; X86-NEXT:    movl %eax, (%esi)
+; X86-NEXT:    movl %ecx, 4(%esi)
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    retl $4
 entry:
   %minnum = call fp128 @llvm.experimental.constrained.minnum.f128(fp128 %x, fp128 %y, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret fp128 %minnum
 }
 
 define fp128 @nearbyint(fp128 %x) nounwind strictfp {
 ; CHECK-LABEL: nearbyint:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq nearbyintl
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: nearbyint:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    calll nearbyintl
+; X86-NEXT:    addl $28, %esp
+; X86-NEXT:    movl (%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 8(%esi)
+; X86-NEXT:    movl %edx, 12(%esi)
+; X86-NEXT:    movl %eax, (%esi)
+; X86-NEXT:    movl %ecx, 4(%esi)
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    retl $4
 entry:
   %nearbyint = call fp128 @llvm.experimental.constrained.nearbyint.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret fp128 %nearbyint
 }
 
 define fp128 @pow(fp128 %x, fp128 %y) nounwind strictfp {
 ; CHECK-LABEL: pow:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq powl
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: pow:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    calll powl
+; X86-NEXT:    addl $44, %esp
+; X86-NEXT:    movl (%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 8(%esi)
+; X86-NEXT:    movl %edx, 12(%esi)
+; X86-NEXT:    movl %eax, (%esi)
+; X86-NEXT:    movl %ecx, 4(%esi)
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    retl $4
 entry:
   %pow = call fp128 @llvm.experimental.constrained.pow.f128(fp128 %x, fp128 %y, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret fp128 %pow
 }
 
 define fp128 @powi(fp128 %x, i32 %y) nounwind strictfp {
 ; CHECK-LABEL: powi:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq __powitf2
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: powi:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subl $8, %esp
+; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    calll __powitf2
+; X86-NEXT:    addl $28, %esp
+; X86-NEXT:    movl (%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 8(%esi)
+; X86-NEXT:    movl %edx, 12(%esi)
+; X86-NEXT:    movl %eax, (%esi)
+; X86-NEXT:    movl %ecx, 4(%esi)
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    retl $4
 entry:
   %powi = call fp128 @llvm.experimental.constrained.powi.f128(fp128 %x, i32 %y, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret fp128 %powi
 }
 
 define fp128 @rint(fp128 %x) nounwind strictfp {
 ; CHECK-LABEL: rint:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq rintl
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: rint:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    calll rintl
+; X86-NEXT:    addl $28, %esp
+; X86-NEXT:    movl (%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 8(%esi)
+; X86-NEXT:    movl %edx, 12(%esi)
+; X86-NEXT:    movl %eax, (%esi)
+; X86-NEXT:    movl %ecx, 4(%esi)
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    retl $4
 entry:
   %rint = call fp128 @llvm.experimental.constrained.rint.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret fp128 %rint
 }
 
 define fp128 @round(fp128 %x) nounwind strictfp {
 ; CHECK-LABEL: round:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq roundl
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: round:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    calll roundl
+; X86-NEXT:    addl $28, %esp
+; X86-NEXT:    movl (%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 8(%esi)
+; X86-NEXT:    movl %edx, 12(%esi)
+; X86-NEXT:    movl %eax, (%esi)
+; X86-NEXT:    movl %ecx, 4(%esi)
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    retl $4
 entry:
   %round = call fp128 @llvm.experimental.constrained.round.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret fp128 %round
 }
 
 define fp128 @sin(fp128 %x) nounwind strictfp {
 ; CHECK-LABEL: sin:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq sinl
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: sin:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    calll sinl
+; X86-NEXT:    addl $28, %esp
+; X86-NEXT:    movl (%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 8(%esi)
+; X86-NEXT:    movl %edx, 12(%esi)
+; X86-NEXT:    movl %eax, (%esi)
+; X86-NEXT:    movl %ecx, 4(%esi)
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    retl $4
 entry:
   %sin = call fp128 @llvm.experimental.constrained.sin.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret fp128 %sin
 }
 
 define fp128 @sqrt(fp128 %x) nounwind strictfp {
 ; CHECK-LABEL: sqrt:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq sqrtl
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: sqrt:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    calll sqrtl
+; X86-NEXT:    addl $28, %esp
+; X86-NEXT:    movl (%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 8(%esi)
+; X86-NEXT:    movl %edx, 12(%esi)
+; X86-NEXT:    movl %eax, (%esi)
+; X86-NEXT:    movl %ecx, 4(%esi)
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    retl $4
 entry:
   %sqrt = call fp128 @llvm.experimental.constrained.sqrt.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret fp128 %sqrt
 }
 
 define fp128 @trunc(fp128 %x) nounwind strictfp {
 ; CHECK-LABEL: trunc:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq truncl
 ; CHECK-NEXT:    popq %rax
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: trunc:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    pushl %edi
+; X86-NEXT:    pushl %esi
+; X86-NEXT:    subl $20, %esp
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %esi
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    leal {{[0-9]+}}(%esp), %eax
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl %eax
+; X86-NEXT:    calll truncl
+; X86-NEXT:    addl $28, %esp
+; X86-NEXT:    movl (%esp), %eax
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; X86-NEXT:    movl {{[0-9]+}}(%esp), %edi
+; X86-NEXT:    movl %edi, 8(%esi)
+; X86-NEXT:    movl %edx, 12(%esi)
+; X86-NEXT:    movl %eax, (%esi)
+; X86-NEXT:    movl %ecx, 4(%esi)
+; X86-NEXT:    movl %esi, %eax
+; X86-NEXT:    addl $20, %esp
+; X86-NEXT:    popl %esi
+; X86-NEXT:    popl %edi
+; X86-NEXT:    retl $4
 entry:
   %trunc = call fp128 @llvm.experimental.constrained.trunc.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret fp128 %trunc
 }
 
 define i32 @lrint(fp128 %x) nounwind strictfp {
 ; CHECK-LABEL: lrint:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq lrintl
 ; CHECK-NEXT:    popq %rcx
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: lrint:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    calll lrintl
+; X86-NEXT:    addl $28, %esp
+; X86-NEXT:    retl
 entry:
   %rint = call i32 @llvm.experimental.constrained.lrint.i32.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret i32 %rint
 }
 
 define i64 @llrint(fp128 %x) nounwind strictfp {
 ; CHECK-LABEL: llrint:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq llrintl
 ; CHECK-NEXT:    popq %rcx
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: llrint:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    calll llrintl
+; X86-NEXT:    addl $28, %esp
+; X86-NEXT:    retl
 entry:
   %rint = call i64 @llvm.experimental.constrained.llrint.i64.f128(fp128 %x, metadata !"round.dynamic", metadata !"fpexcept.strict") #0
   ret i64 %rint
 }
 
 define i32 @lround(fp128 %x) nounwind strictfp {
 ; CHECK-LABEL: lround:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq lroundl
 ; CHECK-NEXT:    popq %rcx
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: lround:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    calll lroundl
+; X86-NEXT:    addl $28, %esp
+; X86-NEXT:    retl
 entry:
   %round = call i32 @llvm.experimental.constrained.lround.i32.f128(fp128 %x, metadata !"fpexcept.strict") #0
   ret i32 %round
 }
 
 define i64 @llround(fp128 %x) nounwind strictfp {
 ; CHECK-LABEL: llround:
 ; CHECK:       # %bb.0: # %entry
 ; CHECK-NEXT:    pushq %rax
 ; CHECK-NEXT:    callq llroundl
 ; CHECK-NEXT:    popq %rcx
 ; CHECK-NEXT:    retq
+;
+; X86-LABEL: llround:
+; X86:       # %bb.0: # %entry
+; X86-NEXT:    subl $12, %esp
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    pushl {{[0-9]+}}(%esp)
+; X86-NEXT:    calll llroundl
+; X86-NEXT:    addl $28, %esp
+; X86-NEXT:    retl
 entry:
   %round = call i64 @llvm.experimental.constrained.llround.i64.f128(fp128 %x, metadata !"fpexcept.strict") #0
   ret i64 %round
 }
 
 attributes #0 = { strictfp }
 
 declare fp128 @llvm.experimental.constrained.fadd.f128(fp128, fp128, metadata, metadata)