Refactor InlinCost.cpp in preparation for estimated speedup heuristic.

[eraman]

Summary

This includes the following refactoring that is useful for a subsequent patch that adds a new inlining heuristic:

• Factor out the code in instruction visitors that checks if an instruction evaluates to a constant.
• Add a method to accumulate the cost of inlining.
• Make isGEPOffsetConstant (which is called once) into a lambda.
• Move a block of code in visitSwitchInst to a lambda.

Some of these may not make much sense standalone, but are useful for the subsequent patch (to be posted shortly)

[chandlerc]

Can you split this into separate patches that do a single refactoring? (Especially considering you have the breakdown in your descirption...) That would make it easier to review for me.

lib/Analysis/InlineCost.cpp

402–404

Of all of these, this one seems the one that doesn't really make sense on its own. I'd rather this be part of the change where it starts to make sense rather than a seemingly bad code smell being added because of some subsequent change.

[eraman]

In D30059#679384, @chandlerc wrote:

Can you split this into separate patches that do a single refactoring? (Especially considering you have the breakdown in your descirption...) That would make it easier to review for me.

Ok, will do.

lib/Analysis/InlineCost.cpp

402–404

Ok

lib/Analysis/InlineCost.cpp

class CallAnalyzer : public InstVisitor<CallAnalyzer, bool> {
   // Custom simplification helper routines.
   bool isAllocaDerivedArg(Value *V);
   bool lookupSROAArgAndCost(Value *V, Value *&Arg,
                             DenseMap<Value *, int>::iterator &CostIt);
   void disableSROA(DenseMap<Value *, int>::iterator CostIt);
   void disableSROA(Value *V);
   void accumulateSROACost(DenseMap<Value *, int>::iterator CostIt,
                           int InstructionCost);
-  bool isGEPOffsetConstant(GetElementPtrInst &GEP);
+  void accumulateCost(int InstructionCost);
   bool isGEPFree(GetElementPtrInst &GEP);
   bool accumulateGEPOffset(GEPOperator &GEP, APInt &Offset);
   bool simplifyCallSite(Function *F, CallSite CS);
   ConstantInt *stripAndComputeInBoundsConstantOffsets(Value *&V);
 
   /// Return true if the given argument to the function being considered for
   /// inlining has the given attribute set either at the call site or the
   /// function declaration.  Primarily used to inspect call site specific
class CallAnalyzer : public InstVisitor<CallAnalyzer, bool> {
   bool visitReturnInst(ReturnInst &RI);
   bool visitBranchInst(BranchInst &BI);
   bool visitSwitchInst(SwitchInst &SI);
   bool visitIndirectBrInst(IndirectBrInst &IBI);
   bool visitResumeInst(ResumeInst &RI);
   bool visitCleanupReturnInst(CleanupReturnInst &RI);
   bool visitCatchReturnInst(CatchReturnInst &RI);
   bool visitUnreachableInst(UnreachableInst &I);
+  /// Simplify \p I if its operands are constants and update SimplifiedValues.
+  /// Transfom is a lambda specific to instruction type that evaluates the
+  /// instruction when all the operands are constants.
+  bool
+  simplifyInstruction(Instruction &I,
+                      function_ref<Constant *(ArrayRef<Constant *>)> Evaluate);
 
 public:
   CallAnalyzer(const TargetTransformInfo &TTI,
                std::function<AssumptionCache &(Function &)> &GetAssumptionCache,
                Optional<function_ref<BlockFrequencyInfo &(Function &)>> &GetBFI,
                ProfileSummaryInfo *PSI, Function &Callee, CallSite CSArg,
                const InlineParams &Params)
       : TTI(TTI), GetAssumptionCache(GetAssumptionCache), GetBFI(GetBFI),

 
 /// \brief Accumulate the given cost for a particular SROA candidate.
 void CallAnalyzer::accumulateSROACost(DenseMap<Value *, int>::iterator CostIt,
                                       int InstructionCost) {
   CostIt->second += InstructionCost;
   SROACostSavings += InstructionCost;
 }
 
-/// \brief Check whether a GEP's indices are all constant.
-///
-/// Respects any simplified values known during the analysis of this callsite.
-bool CallAnalyzer::isGEPOffsetConstant(GetElementPtrInst &GEP) {
-  for (User::op_iterator I = GEP.idx_begin(), E = GEP.idx_end(); I != E; ++I)
-    if (!isa<Constant>(*I) && !SimplifiedValues.lookup(*I))
-      return false;
-
-  return true;
-}
-
 /// \brief Accumulate a constant GEP offset into an APInt if possible.
 ///
 /// Returns false if unable to compute the offset for any reason. Respects any
 /// simplified values known during the analysis of this callsite.
 bool CallAnalyzer::accumulateGEPOffset(GEPOperator &GEP, APInt &Offset) {
   const DataLayout &DL = F.getParent()->getDataLayout();
   unsigned IntPtrWidth = DL.getPointerSizeInBits();
   assert(IntPtrWidth == Offset.getBitWidth());
bool CallAnalyzer::visitPHI(PHINode &I) {
   // FIXME: We need to propagate SROA *disabling* through phi nodes, even
   // though we don't want to propagate it's bonuses. The idea is to disable
   // SROA if it *might* be used in an inappropriate manner.
 
   // Phi nodes are always zero-cost.
   return true;
 }
 
+void CallAnalyzer::accumulateCost(int InstructionCost) {
+  Cost += InstructionCost;
+}
+
 bool CallAnalyzer::visitGetElementPtr(GetElementPtrInst &I) {
   Value *SROAArg;
   DenseMap<Value *, int>::iterator CostIt;
   bool SROACandidate =
       lookupSROAArgAndCost(I.getPointerOperand(), SROAArg, CostIt);
 
   // Try to fold GEPs of constant-offset call site argument pointers. This
   // requires target data and inbounds GEPs.
if (BaseAndOffset.first) {
       // all-constant indexed.
       if (SROACandidate)
         SROAArgValues[&I] = SROAArg;
 
       return true;
     }
   }
 
+  // Lambda to check whether a GEP's indices are all constant.
+  auto isGEPOffsetConstant = [&](GetElementPtrInst &GEP) {
+    for (User::op_iterator I = GEP.idx_begin(), E = GEP.idx_end(); I != E; ++I)
+      if (!isa<Constant>(*I) && !SimplifiedValues.lookup(*I))
+        return false;
+    return true;
+  };
+
   if (isGEPOffsetConstant(I)) {
     if (SROACandidate)
       SROAArgValues[&I] = SROAArg;
 
     // Constant GEPs are modeled as free.
     return true;
   }
 
   // Variable GEPs will require math and will disable SROA.
   if (SROACandidate)
     disableSROA(CostIt);
   return isGEPFree(I);
 }
 
-bool CallAnalyzer::visitBitCast(BitCastInst &I) {
-  // Propagate constants through bitcasts.
-  Constant *COp = dyn_cast<Constant>(I.getOperand(0));
+bool CallAnalyzer::simplifyInstruction(
+    Instruction &I, function_ref<Constant *(ArrayRef<Constant *>)> Evaluate) {
+  Constant *COps[2];
+  int N = 0;
+  for (Value *Op : I.operands()) {
+    Constant *COp = dyn_cast<Constant>(Op);
     if (!COp)
-    COp = SimplifiedValues.lookup(I.getOperand(0));
-  if (COp)
-    if (Constant *C = ConstantExpr::getBitCast(COp, I.getType())) {
-      SimplifiedValues[&I] = C;
-      return true;
-    }
+      COp = SimplifiedValues.lookup(Op);
+    if (!COp)
+      return false;
+    COps[N++] = COp;
+  }
+  if (auto *C = Evaluate(COps)) {
+  return false;
+}
+
+bool CallAnalyzer::visitBitCast(BitCastInst &I) {
+  // Propagate constants through bitcasts.
+  auto Evaluate = [&](ArrayRef<Constant *> COps) -> Constant * {
+    return ConstantExpr::getBitCast(COps[0], I.getType());
+  };
+  if (simplifyInstruction(I, Evaluate))
+    return true;
 
   // Track base/offsets through casts
   std::pair<Value *, APInt> BaseAndOffset =
       ConstantOffsetPtrs.lookup(I.getOperand(0));
   // Casts don't change the offset, just wrap it up.
   if (BaseAndOffset.first)
     ConstantOffsetPtrs[&I] = BaseAndOffset;
 
   // Also look for SROA candidates here.
   Value *SROAArg;
   DenseMap<Value *, int>::iterator CostIt;
   if (lookupSROAArgAndCost(I.getOperand(0), SROAArg, CostIt))
     SROAArgValues[&I] = SROAArg;
 
   // Bitcasts are always zero cost.
   return true;
 }
 
 bool CallAnalyzer::visitPtrToInt(PtrToIntInst &I) {
   // Propagate constants through ptrtoint.
-  Constant *COp = dyn_cast<Constant>(I.getOperand(0));
-  if (!COp)
-    COp = SimplifiedValues.lookup(I.getOperand(0));
-  if (COp)
-    if (Constant *C = ConstantExpr::getPtrToInt(COp, I.getType())) {
-      SimplifiedValues[&I] = C;
-      return true;
-    }
+  auto Evaluate = [&](ArrayRef<Constant *> COps) -> Constant * {
+    return ConstantExpr::getPtrToInt(COps[0], I.getType());
+  };
+  if (simplifyInstruction(I, Evaluate))
 
   // Track base/offset pairs when converted to a plain integer provided the
   // integer is large enough to represent the pointer.
   unsigned IntegerSize = I.getType()->getScalarSizeInBits();
   const DataLayout &DL = F.getParent()->getDataLayout();
   if (IntegerSize >= DL.getPointerSizeInBits()) {
     std::pair<Value *, APInt> BaseAndOffset =
         ConstantOffsetPtrs.lookup(I.getOperand(0));
bool CallAnalyzer::visitPtrToInt(PtrToIntInst &I) {
   if (lookupSROAArgAndCost(I.getOperand(0), SROAArg, CostIt))
     SROAArgValues[&I] = SROAArg;
 
   return TargetTransformInfo::TCC_Free == TTI.getUserCost(&I);
 }
 
 bool CallAnalyzer::visitIntToPtr(IntToPtrInst &I) {
   // Propagate constants through ptrtoint.
-  Constant *COp = dyn_cast<Constant>(I.getOperand(0));
-  if (!COp)
-    COp = SimplifiedValues.lookup(I.getOperand(0));
-  if (COp)
-    if (Constant *C = ConstantExpr::getIntToPtr(COp, I.getType())) {
-      SimplifiedValues[&I] = C;
-      return true;
-    }
+  auto Evaluate = [&](ArrayRef<Constant *> COps) -> Constant * {
+    return ConstantExpr::getIntToPtr(COps[0], I.getType());
+  };
+  if (simplifyInstruction(I, Evaluate))
 
   // Track base/offset pairs when round-tripped through a pointer without
   // modifications provided the integer is not too large.
   Value *Op = I.getOperand(0);
   unsigned IntegerSize = Op->getType()->getScalarSizeInBits();
   const DataLayout &DL = F.getParent()->getDataLayout();
   if (IntegerSize <= DL.getPointerSizeInBits()) {
     std::pair<Value *, APInt> BaseAndOffset = ConstantOffsetPtrs.lookup(Op);
     if (BaseAndOffset.first)
       ConstantOffsetPtrs[&I] = BaseAndOffset;
   }
 
   // "Propagate" SROA here in the same manner as we do for ptrtoint above.
   Value *SROAArg;
   DenseMap<Value *, int>::iterator CostIt;
   if (lookupSROAArgAndCost(Op, SROAArg, CostIt))
     SROAArgValues[&I] = SROAArg;
 
   return TargetTransformInfo::TCC_Free == TTI.getUserCost(&I);
 }
 
 bool CallAnalyzer::visitCastInst(CastInst &I) {
   // Propagate constants through ptrtoint.
-  Constant *COp = dyn_cast<Constant>(I.getOperand(0));
-  if (!COp)
-    COp = SimplifiedValues.lookup(I.getOperand(0));
-  if (COp)
-    if (Constant *C = ConstantExpr::getCast(I.getOpcode(), COp, I.getType())) {
-      SimplifiedValues[&I] = C;
-      return true;
-    }
+  auto Evaluate = [&](ArrayRef<Constant *> COps) -> Constant * {
+    return ConstantExpr::getCast(I.getOpcode(), COps[0], I.getType());
+  };
+  if (simplifyInstruction(I, Evaluate))
 
   // Disable SROA in the face of arbitrary casts we don't whitelist elsewhere.
   disableSROA(I.getOperand(0));
 
   return TargetTransformInfo::TCC_Free == TTI.getUserCost(&I);
 }
 
 bool CallAnalyzer::visitUnaryInstruction(UnaryInstruction &I) {
   Value *Operand = I.getOperand(0);
-  Constant *COp = dyn_cast<Constant>(Operand);
-  if (!COp)
-    COp = SimplifiedValues.lookup(Operand);
-  if (COp) {
+  auto Evaluate = [&](ArrayRef<Constant *> COps) -> Constant * {
     const DataLayout &DL = F.getParent()->getDataLayout();
-    if (Constant *C = ConstantFoldInstOperands(&I, COp, DL)) {
-      SimplifiedValues[&I] = C;
-      return true;
-    }
-  }
+    return ConstantFoldInstOperands(&I, COps[0], DL);
+  };
+  if (simplifyInstruction(I, Evaluate))
 
   // Disable any SROA on the argument to arbitrary unary operators.
   disableSROA(Operand);
 
   return false;
 }
 
 bool CallAnalyzer::paramHasAttr(Argument *A, Attribute::AttrKind Attr) {
void CallAnalyzer::updateThreshold(CallSite CS, Function &Callee) {
   else if (Caller->optForSize())
     Threshold = MinIfValid(Threshold, Params.OptSizeThreshold);
 
   // Adjust the threshold based on inlinehint attribute and profile based
   // hotness information if the caller does not have MinSize attribute.
   if (!Caller->optForMinSize()) {
     if (Callee.hasFnAttribute(Attribute::InlineHint))
       Threshold = MaxIfValid(Threshold, Params.HintThreshold);
-    if (PSI) {
-      BlockFrequencyInfo *CallerBFI = GetBFI ? &((*GetBFI)(*Caller)) : nullptr;
+    if (PSI) {
       if (PSI->isHotCallSite(CS, CallerBFI)) {
         DEBUG(dbgs() << "Hot callsite.\n");
         Threshold = MaxIfValid(Threshold, Params.HotCallSiteThreshold);
       } else if (PSI->isFunctionEntryHot(&Callee)) {
         DEBUG(dbgs() << "Hot callee.\n");
         // If callsite hotness can not be determined, we may still know
         // that the callee is hot and treat it as a weaker hint for threshold
         // increase.
void CallAnalyzer::updateThreshold(CallSite CS, Function &Callee) {
   // Finally, take the target-specific inlining threshold multiplier into
   // account.
   Threshold *= TTI.getInliningThresholdMultiplier();
 }
 
 bool CallAnalyzer::visitCmpInst(CmpInst &I) {
   Value *LHS = I.getOperand(0), *RHS = I.getOperand(1);
   // First try to handle simplified comparisons.
-  if (!isa<Constant>(LHS))
-    if (Constant *SimpleLHS = SimplifiedValues.lookup(LHS))
-      LHS = SimpleLHS;
-  if (!isa<Constant>(RHS))
-    if (Constant *SimpleRHS = SimplifiedValues.lookup(RHS))
-      RHS = SimpleRHS;
-  if (Constant *CLHS = dyn_cast<Constant>(LHS)) {
-    if (Constant *CRHS = dyn_cast<Constant>(RHS))
-      if (Constant *C =
-              ConstantExpr::getCompare(I.getPredicate(), CLHS, CRHS)) {
-        SimplifiedValues[&I] = C;
-        return true;
-      }
-  }
+  auto Evaluate = [&](ArrayRef<Constant *> COps) -> Constant * {
+    return ConstantExpr::getCompare(I.getPredicate(), COps[0], COps[1]);
+  };
+  if (simplifyInstruction(I, Evaluate))
 
   if (I.getOpcode() == Instruction::FCmp)
     return false;
 
   // Otherwise look for a comparison between constant offset pointers with
   // a common base.
   Value *LHSBase, *RHSBase;
   APInt LHSOffset, RHSOffset;
bool CallAnalyzer::visitSub(BinaryOperator &I) {
 
   // Otherwise, fall back to the generic logic for simplifying and handling
   // instructions.
   return Base::visitSub(I);
 }
 
 bool CallAnalyzer::visitBinaryOperator(BinaryOperator &I) {
   Value *LHS = I.getOperand(0), *RHS = I.getOperand(1);
-  const DataLayout &DL = F.getParent()->getDataLayout();
-  if (!isa<Constant>(LHS))
-    if (Constant *SimpleLHS = SimplifiedValues.lookup(LHS))
-      LHS = SimpleLHS;
-  if (!isa<Constant>(RHS))
-    if (Constant *SimpleRHS = SimplifiedValues.lookup(RHS))
-      RHS = SimpleRHS;
+  auto Evaluate = [&](ArrayRef<Constant *> COps) -> Constant * {
     Value *SimpleV = nullptr;
+    const DataLayout &DL = F.getParent()->getDataLayout();
     if (auto FI = dyn_cast<FPMathOperator>(&I))
-    SimpleV =
-        SimplifyFPBinOp(I.getOpcode(), LHS, RHS, FI->getFastMathFlags(), DL);
+      SimpleV = SimplifyFPBinOp(I.getOpcode(), COps[0], COps[1],
+                                FI->getFastMathFlags(), DL);
     else
-    SimpleV = SimplifyBinOp(I.getOpcode(), LHS, RHS, DL);
+      SimpleV = SimplifyBinOp(I.getOpcode(), COps[0], COps[1], DL);
+    return dyn_cast_or_null<Constant>(SimpleV);
+  };
 
-  if (Constant *C = dyn_cast_or_null<Constant>(SimpleV)) {
-    SimplifiedValues[&I] = C;
+  if (simplifyInstruction(I, Evaluate))
     return true;
-  }
 
   // Disable any SROA on arguments to arbitrary, unsimplified binary operators.
   disableSROA(LHS);
   disableSROA(RHS);
 
   return false;
 }
 
if (lookupSROAArgAndCost(I.getPointerOperand(), SROAArg, CostIt)) {
     disableSROA(CostIt);
   }
 
   return false;
 }
 
 bool CallAnalyzer::visitExtractValue(ExtractValueInst &I) {
   // Constant folding for extract value is trivial.
-  Constant *C = dyn_cast<Constant>(I.getAggregateOperand());
-  if (!C)
-    C = SimplifiedValues.lookup(I.getAggregateOperand());
-  if (C) {
-    SimplifiedValues[&I] = ConstantExpr::getExtractValue(C, I.getIndices());
+  auto Evaluate = [&](ArrayRef<Constant *> COps) -> Constant * {
+    return ConstantExpr::getExtractValue(COps[0], I.getIndices());
+  };
+  if (simplifyInstruction(I, Evaluate))
     return true;
-  }
 
   // SROA can look through these but give them a cost.
   return false;
 }
 
 bool CallAnalyzer::visitInsertValue(InsertValueInst &I) {
   // Constant folding for insert value is trivial.
-  Constant *AggC = dyn_cast<Constant>(I.getAggregateOperand());
-  if (!AggC)
-    AggC = SimplifiedValues.lookup(I.getAggregateOperand());
-  Constant *InsertedC = dyn_cast<Constant>(I.getInsertedValueOperand());
-  if (!InsertedC)
-    InsertedC = SimplifiedValues.lookup(I.getInsertedValueOperand());
-  if (AggC && InsertedC) {
-    SimplifiedValues[&I] =
-        ConstantExpr::getInsertValue(AggC, InsertedC, I.getIndices());
+  auto Evaluate = [&](ArrayRef<Constant *> COps) -> Constant * {
+    return ConstantExpr::getInsertValue(/*AggregateOperand*/ COps[0],
+                                        /*InsertedValueOperand*/ COps[1],
+                                        I.getIndices());
+  };
+  if (simplifyInstruction(I, Evaluate))
     return true;
-  }
 
   // SROA can look through these but give them a cost.
   return false;
 }
 
 /// \brief Try to simplify a call site.
 ///
 /// Takes a concrete function and callsite and tries to actually simplify it by
 /// analyzing the arguments and call itself with instsimplify. Returns true if
 /// it has simplified the callsite to some other entity (a constant), making it
 /// free.
 bool CallAnalyzer::simplifyCallSite(Function *F, CallSite CS) {
   // FIXME: Using the instsimplify logic directly for this is inefficient
   // because we have to continually rebuild the argument list even when no
   // simplifications can be performed. Until that is fixed with remapping
   // inside of instsimplify, directly constant fold calls here.
   if (!canConstantFoldCallTo(F))
     return false;
-
   // Try to re-map the arguments to constants.
   SmallVector<Constant *, 4> ConstantArgs;
   ConstantArgs.reserve(CS.arg_size());
   for (CallSite::arg_iterator I = CS.arg_begin(), E = CS.arg_end(); I != E;
        ++I) {
     Constant *C = dyn_cast<Constant>(*I);
     if (!C)
       C = dyn_cast_or_null<Constant>(SimplifiedValues.lookup(*I));
if (Function *F = CS.getCalledFunction()) {
     // FIXME: Lift this into part of the InstVisitor.
     if (IntrinsicInst *II = dyn_cast<IntrinsicInst>(CS.getInstruction())) {
       switch (II->getIntrinsicID()) {
       default:
         return Base::visitCallSite(CS);
 
       case Intrinsic::load_relative:
         // This is normally lowered to 4 LLVM instructions.
-        Cost += 3 * InlineConstants::InstrCost;
+        accumulateCost(3 * InlineConstants::InstrCost);
         return false;
 
       case Intrinsic::memset:
       case Intrinsic::memcpy:
       case Intrinsic::memmove:
         // SROA can usually chew through these intrinsics, but they aren't free.
         return false;
       case Intrinsic::localescape:
         HasFrameEscape = true;
         return false;
       }
     }
 
     if (F == CS.getInstruction()->getParent()->getParent()) {
       // This flag will fully abort the analysis, so don't bother with anything
       // else.
       IsRecursiveCall = true;
       return false;
     }
 
     if (TTI.isLoweredToCall(F)) {
       // We account for the average 1 instruction per call argument setup
       // here.
-      Cost += CS.arg_size() * InlineConstants::InstrCost;
+      accumulateCost(CS.arg_size() * InlineConstants::InstrCost);
 
       // Everything other than inline ASM will also have a significant cost
       // merely from making the call.
       if (!isa<InlineAsm>(CS.getCalledValue()))
-        Cost += InlineConstants::CallPenalty;
+        accumulateCost(InlineConstants::CallPenalty);
     }
 
     return Base::visitCallSite(CS);
   }
 
   // Otherwise we're in a very special case -- an indirect function call. See
   // if we can be particularly clever about this.
   Value *Callee = CS.getCalledValue();
 
   // First, pay the price of the argument setup. We account for the average
   // 1 instruction per call argument setup here.
-  Cost += CS.arg_size() * InlineConstants::InstrCost;
+  accumulateCost(CS.arg_size() * InlineConstants::InstrCost);
 
   // Next, check if this happens to be an indirect function call to a known
   // function in this inline context. If not, we've done all we can.
   Function *F = dyn_cast_or_null<Function>(SimplifiedValues.lookup(Callee));
   if (!F)
     return Base::visitCallSite(CS);
 
   // If we have a constant that we are calling as a function, we can peer
return BI.isUnconditional() || isa<ConstantInt>(BI.getCondition()) ||
              SimplifiedValues.lookup(BI.getCondition()));
 }
 
 bool CallAnalyzer::visitSwitchInst(SwitchInst &SI) {
   // We model unconditional switches as free, see the comments on handling
   // branches.
   if (isa<ConstantInt>(SI.getCondition()))
     return true;
-  if (Value *V = SimplifiedValues.lookup(SI.getCondition()))
-    if (isa<ConstantInt>(V))
-      return true;
 
-  // Otherwise, we need to accumulate a cost proportional to the number of
+  auto SwitchInstCost = [](SwitchInst &SI) {
+    // We need to compute a cost proportional to the number of
     // distinct successor blocks. This fan-out in the CFG cannot be represented
     // for free even if we can represent the core switch as a jumptable that
     // takes a single instruction.
     //
     // NB: We convert large switches which are just used to initialize large phi
     // nodes to lookup tables instead in simplify-cfg, so this shouldn't prevent
     // inlining those. It will prevent inlining in cases where the optimization
     // does not (yet) fire.
     SmallPtrSet<BasicBlock *, 8> SuccessorBlocks;
     SuccessorBlocks.insert(SI.getDefaultDest());
     for (auto I = SI.case_begin(), E = SI.case_end(); I != E; ++I)
       SuccessorBlocks.insert(I.getCaseSuccessor());
+
     // Add cost corresponding to the number of distinct destinations. The first
     // we model as free because of fallthrough.
-  Cost += (SuccessorBlocks.size() - 1) * InlineConstants::InstrCost;
+    return (SuccessorBlocks.size() - 1) * InlineConstants::InstrCost;
+  };
+
+  if (Value *V = SimplifiedValues.lookup(SI.getCondition()))
+    if (isa<ConstantInt>(V))
+      return true;
+
+  accumulateCost(SwitchInstCost(SI));
   return false;
 }
 
 bool CallAnalyzer::visitIndirectBrInst(IndirectBrInst &IBI) {
   // We never want to inline functions that contain an indirectbr.  This is
   // incorrect because all the blockaddress's (in static global initializers
   // for example) would be referring to the original function, and this
   // indirect jump would jump from the inlined copy of the function into the
if (I->getType()->isFloatingPointTy()) {
         Attribute Attr = F.getFnAttribute("use-soft-float");
         StringRef Val = Attr.getValueAsString();
         if (Val == "true")
           hasSoftFloatAttr = true;
       }
 
       if (TTI.getFPOpCost(I->getType()) == TargetTransformInfo::TCC_Expensive ||
           hasSoftFloatAttr)
-        Cost += InlineConstants::CallPenalty;
+        accumulateCost(InlineConstants::CallPenalty);
     }
 
     // If the instruction simplified to a constant, there is no cost to this
     // instruction. Visit the instructions using our InstVisitor to account for
     // all of the per-instruction logic. The visit tree returns true if we
     // consumed the instruction in any way, and false if the instruction's base
     // cost should count against inlining.
     if (Base::visit(&*I))
       ++NumInstructionsSimplified;
     else
-      Cost += InlineConstants::InstrCost;
+      accumulateCost(InlineConstants::InstrCost);
 
     // If the visit this instruction detected an uninlinable pattern, abort.
     if (IsRecursiveCall || ExposesReturnsTwice || HasDynamicAlloca ||
         HasIndirectBr || HasFrameEscape)
       return false;
 
     // If the caller is a recursive function then we don't want to inline
     // functions which allocate a lot of stack space because it would increase
if (CS.isByValArgument(I)) {
       // If it generates more than 8 stores it is likely to be expanded as an
       // inline memcpy so we take that as an upper bound. Otherwise we assume
       // one load and one store per word copied.
       // FIXME: The maxStoresPerMemcpy setting from the target should be used
       // here instead of a magic number of 8, but it's not available via
       // DataLayout.
       NumStores = std::min(NumStores, 8U);
 
-      Cost -= 2 * NumStores * InlineConstants::InstrCost;
+      accumulateCost(-2 * NumStores * InlineConstants::InstrCost);
     } else {
       // For non-byval arguments subtract off one instruction per call
       // argument.
-      Cost -= InlineConstants::InstrCost;
+      accumulateCost(-InlineConstants::InstrCost);
     }
   }
   // The call instruction also disappears after inlining.
-  Cost -= InlineConstants::InstrCost + InlineConstants::CallPenalty;
-  
+  accumulateCost(-InlineConstants::InstrCost - InlineConstants::CallPenalty);
   // If there is only one call of the function, and it has internal linkage,
   // the cost of inlining it drops dramatically.
   bool OnlyOneCallAndLocalLinkage =
       F.hasLocalLinkage() && F.hasOneUse() && &F == CS.getCalledFunction();
   if (OnlyOneCallAndLocalLinkage)
     Cost -= InlineConstants::LastCallToStaticBonus;
 
   // If this function uses the coldcc calling convention, prefer not to inline
   // it.
   if (F.getCallingConv() == CallingConv::Cold)
-    Cost += InlineConstants::ColdccPenalty;
+    accumulateCost(InlineConstants::ColdccPenalty);
 
   // Check if we're done. This can happen due to bonuses and penalties.
   if (Cost > Threshold)
     return false;
 
   if (F.empty())
     return true;