LLVM API Documentation

InlineCost.cpp

Go to the documentation of this file.
00001 //===- InlineCost.cpp - Cost analysis for inliner -------------------------===//
00002 //
00003 //                     The LLVM Compiler Infrastructure
00004 //
00005 // This file is distributed under the University of Illinois Open Source
00006 // License. See LICENSE.TXT for details.
00007 //
00008 //===----------------------------------------------------------------------===//
00009 //
00010 // This file implements inline cost analysis.
00011 //
00012 //===----------------------------------------------------------------------===//
00013 
00014 
00015 #include "llvm/Transforms/Utils/InlineCost.h"
00016 #include "llvm/Support/CallSite.h"
00017 #include "llvm/CallingConv.h"
00018 #include "llvm/IntrinsicInst.h"
00019 
00020 using namespace llvm;
00021 
00022 // CountCodeReductionForConstant - Figure out an approximation for how many
00023 // instructions will be constant folded if the specified value is constant.
00024 //
00025 unsigned InlineCostAnalyzer::FunctionInfo::
00026          CountCodeReductionForConstant(Value *V) {
00027   unsigned Reduction = 0;
00028   for (Value::use_iterator UI = V->use_begin(), E = V->use_end(); UI != E; ++UI)
00029     if (isa<BranchInst>(*UI))
00030       Reduction += 40;          // Eliminating a conditional branch is a big win
00031     else if (SwitchInst *SI = dyn_cast<SwitchInst>(*UI))
00032       // Eliminating a switch is a big win, proportional to the number of edges
00033       // deleted.
00034       Reduction += (SI->getNumSuccessors()-1) * 40;
00035     else if (CallInst *CI = dyn_cast<CallInst>(*UI)) {
00036       // Turning an indirect call into a direct call is a BIG win
00037       Reduction += CI->getCalledValue() == V ? 500 : 0;
00038     } else if (InvokeInst *II = dyn_cast<InvokeInst>(*UI)) {
00039       // Turning an indirect call into a direct call is a BIG win
00040       Reduction += II->getCalledValue() == V ? 500 : 0;
00041     } else {
00042       // Figure out if this instruction will be removed due to simple constant
00043       // propagation.
00044       Instruction &Inst = cast<Instruction>(**UI);
00045       
00046       // We can't constant propagate instructions which have effects or
00047       // read memory.
00048       //
00049       // FIXME: It would be nice to capture the fact that a load from a
00050       // pointer-to-constant-global is actually a *really* good thing to zap.
00051       // Unfortunately, we don't know the pointer that may get propagated here,
00052       // so we can't make this decision.
00053       if (Inst.mayReadFromMemory() || Inst.mayHaveSideEffects() ||
00054           isa<AllocationInst>(Inst))
00055         continue;
00056 
00057       bool AllOperandsConstant = true;
00058       for (unsigned i = 0, e = Inst.getNumOperands(); i != e; ++i)
00059         if (!isa<Constant>(Inst.getOperand(i)) && Inst.getOperand(i) != V) {
00060           AllOperandsConstant = false;
00061           break;
00062         }
00063 
00064       if (AllOperandsConstant) {
00065         // We will get to remove this instruction...
00066         Reduction += 7;
00067 
00068         // And any other instructions that use it which become constants
00069         // themselves.
00070         Reduction += CountCodeReductionForConstant(&Inst);
00071       }
00072     }
00073 
00074   return Reduction;
00075 }
00076 
00077 // CountCodeReductionForAlloca - Figure out an approximation of how much smaller
00078 // the function will be if it is inlined into a context where an argument
00079 // becomes an alloca.
00080 //
00081 unsigned InlineCostAnalyzer::FunctionInfo::
00082          CountCodeReductionForAlloca(Value *V) {
00083   if (!isa<PointerType>(V->getType())) return 0;  // Not a pointer
00084   unsigned Reduction = 0;
00085   for (Value::use_iterator UI = V->use_begin(), E = V->use_end(); UI != E;++UI){
00086     Instruction *I = cast<Instruction>(*UI);
00087     if (isa<LoadInst>(I) || isa<StoreInst>(I))
00088       Reduction += 10;
00089     else if (GetElementPtrInst *GEP = dyn_cast<GetElementPtrInst>(I)) {
00090       // If the GEP has variable indices, we won't be able to do much with it.
00091       if (!GEP->hasAllConstantIndices())
00092         Reduction += CountCodeReductionForAlloca(GEP)+15;
00093     } else {
00094       // If there is some other strange instruction, we're not going to be able
00095       // to do much if we inline this.
00096       return 0;
00097     }
00098   }
00099 
00100   return Reduction;
00101 }
00102 
00103 /// analyzeFunction - Fill in the current structure with information gleaned
00104 /// from the specified function.
00105 void InlineCostAnalyzer::FunctionInfo::analyzeFunction(Function *F) {
00106   unsigned NumInsts = 0, NumBlocks = 0, NumVectorInsts = 0;
00107 
00108   // Look at the size of the callee.  Each basic block counts as 20 units, and
00109   // each instruction counts as 5.
00110   for (Function::const_iterator BB = F->begin(), E = F->end(); BB != E; ++BB) {
00111     for (BasicBlock::const_iterator II = BB->begin(), E = BB->end();
00112          II != E; ++II) {
00113       if (isa<PHINode>(II)) continue;           // PHI nodes don't count.
00114 
00115       // Special handling for calls.
00116       if (isa<CallInst>(II) || isa<InvokeInst>(II)) {
00117         if (isa<DbgInfoIntrinsic>(II))
00118           continue;  // Debug intrinsics don't count as size.
00119         
00120         CallSite CS = CallSite::get(const_cast<Instruction*>(&*II));
00121         
00122         // If this function contains a call to setjmp or _setjmp, never inline
00123         // it.  This is a hack because we depend on the user marking their local
00124         // variables as volatile if they are live across a setjmp call, and they
00125         // probably won't do this in callers.
00126         if (Function *F = CS.getCalledFunction())
00127           if (F->isDeclaration() && 
00128               (F->getName() == "setjmp" || F->getName() == "_setjmp")) {
00129             NeverInline = true;
00130             return;
00131           }
00132 
00133         // Calls often compile into many machine instructions.  Bump up their
00134         // cost to reflect this.
00135         if (!isa<IntrinsicInst>(II))
00136           NumInsts += 5;
00137       }
00138       
00139       if (const AllocaInst *AI = dyn_cast<AllocaInst>(II)) {
00140         if (!AI->isStaticAlloca())
00141           this->usesDynamicAlloca = true;
00142       }
00143 
00144       if (isa<ExtractElementInst>(II) || isa<VectorType>(II->getType()))
00145         ++NumVectorInsts; 
00146       
00147       // Noop casts, including ptr <-> int,  don't count.
00148       if (const CastInst *CI = dyn_cast<CastInst>(II)) {
00149         if (CI->isLosslessCast() || isa<IntToPtrInst>(CI) || 
00150             isa<PtrToIntInst>(CI))
00151           continue;
00152       } else if (const GetElementPtrInst *GEPI =
00153                  dyn_cast<GetElementPtrInst>(II)) {
00154         // If a GEP has all constant indices, it will probably be folded with
00155         // a load/store.
00156         if (GEPI->hasAllConstantIndices())
00157           continue;
00158       }
00159       
00160       ++NumInsts;
00161     }
00162 
00163     ++NumBlocks;
00164   }
00165 
00166   this->NumBlocks      = NumBlocks;
00167   this->NumInsts       = NumInsts;
00168   this->NumVectorInsts = NumVectorInsts;
00169 
00170   // Check out all of the arguments to the function, figuring out how much
00171   // code can be eliminated if one of the arguments is a constant.
00172   for (Function::arg_iterator I = F->arg_begin(), E = F->arg_end(); I != E; ++I)
00173     ArgumentWeights.push_back(ArgInfo(CountCodeReductionForConstant(I),
00174                                       CountCodeReductionForAlloca(I)));
00175 }
00176 
00177 
00178 
00179 // getInlineCost - The heuristic used to determine if we should inline the
00180 // function call or not.
00181 //
00182 InlineCost InlineCostAnalyzer::getInlineCost(CallSite CS,
00183                                SmallPtrSet<const Function *, 16> &NeverInline) {
00184   Instruction *TheCall = CS.getInstruction();
00185   Function *Callee = CS.getCalledFunction();
00186   Function *Caller = TheCall->getParent()->getParent();
00187 
00188       // Don't inline functions which can be redefined at link-time to mean
00189       // something else.
00190    if (Callee->mayBeOverridden() ||
00191        // Don't inline functions marked noinline.
00192        Callee->hasFnAttr(Attribute::NoInline) || NeverInline.count(Callee))
00193     return llvm::InlineCost::getNever();
00194 
00195   // InlineCost - This value measures how good of an inline candidate this call
00196   // site is to inline.  A lower inline cost make is more likely for the call to
00197   // be inlined.  This value may go negative.
00198   //
00199   int InlineCost = 0;
00200   
00201   // If there is only one call of the function, and it has internal linkage,
00202   // make it almost guaranteed to be inlined.
00203   //
00204   if (Callee->hasLocalLinkage() && Callee->hasOneUse())
00205     InlineCost -= 15000;
00206   
00207   // If this function uses the coldcc calling convention, prefer not to inline
00208   // it.
00209   if (Callee->getCallingConv() == CallingConv::Cold)
00210     InlineCost += 2000;
00211   
00212   // If the instruction after the call, or if the normal destination of the
00213   // invoke is an unreachable instruction, the function is noreturn.  As such,
00214   // there is little point in inlining this.
00215   if (InvokeInst *II = dyn_cast<InvokeInst>(TheCall)) {
00216     if (isa<UnreachableInst>(II->getNormalDest()->begin()))
00217       InlineCost += 10000;
00218   } else if (isa<UnreachableInst>(++BasicBlock::iterator(TheCall)))
00219     InlineCost += 10000;
00220   
00221   // Get information about the callee...
00222   FunctionInfo &CalleeFI = CachedFunctionInfo[Callee];
00223   
00224   // If we haven't calculated this information yet, do so now.
00225   if (CalleeFI.NumBlocks == 0)
00226     CalleeFI.analyzeFunction(Callee);
00227 
00228   // If we should never inline this, return a huge cost.
00229   if (CalleeFI.NeverInline)
00230     return InlineCost::getNever();
00231 
00232   // FIXME: It would be nice to kill off CalleeFI.NeverInline. Then we
00233   // could move this up and avoid computing the FunctionInfo for
00234   // things we are going to just return always inline for. This
00235   // requires handling setjmp somewhere else, however.
00236   if (!Callee->isDeclaration() && Callee->hasFnAttr(Attribute::AlwaysInline))
00237     return InlineCost::getAlways();
00238     
00239   if (CalleeFI.usesDynamicAlloca) {
00240     // Get infomation about the caller...
00241     FunctionInfo &CallerFI = CachedFunctionInfo[Caller];
00242 
00243     // If we haven't calculated this information yet, do so now.
00244     if (CallerFI.NumBlocks == 0)
00245       CallerFI.analyzeFunction(Caller);
00246 
00247     // Don't inline a callee with dynamic alloca into a caller without them.
00248     // Functions containing dynamic alloca's are inefficient in various ways;
00249     // don't create more inefficiency.
00250     if (!CallerFI.usesDynamicAlloca)
00251       return InlineCost::getNever();
00252   }
00253 
00254   // Add to the inline quality for properties that make the call valuable to
00255   // inline.  This includes factors that indicate that the result of inlining
00256   // the function will be optimizable.  Currently this just looks at arguments
00257   // passed into the function.
00258   //
00259   unsigned ArgNo = 0;
00260   for (CallSite::arg_iterator I = CS.arg_begin(), E = CS.arg_end();
00261        I != E; ++I, ++ArgNo) {
00262     // Each argument passed in has a cost at both the caller and the callee
00263     // sides.  This favors functions that take many arguments over functions
00264     // that take few arguments.
00265     InlineCost -= 20;
00266     
00267     // If this is a function being passed in, it is very likely that we will be
00268     // able to turn an indirect function call into a direct function call.
00269     if (isa<Function>(I))
00270       InlineCost -= 100;
00271     
00272     // If an alloca is passed in, inlining this function is likely to allow
00273     // significant future optimization possibilities (like scalar promotion, and
00274     // scalarization), so encourage the inlining of the function.
00275     //
00276     else if (isa<AllocaInst>(I)) {
00277       if (ArgNo < CalleeFI.ArgumentWeights.size())
00278         InlineCost -= CalleeFI.ArgumentWeights[ArgNo].AllocaWeight;
00279       
00280       // If this is a constant being passed into the function, use the argument
00281       // weights calculated for the callee to determine how much will be folded
00282       // away with this information.
00283     } else if (isa<Constant>(I)) {
00284       if (ArgNo < CalleeFI.ArgumentWeights.size())
00285         InlineCost -= CalleeFI.ArgumentWeights[ArgNo].ConstantWeight;
00286     }
00287   }
00288   
00289   // Now that we have considered all of the factors that make the call site more
00290   // likely to be inlined, look at factors that make us not want to inline it.
00291   
00292   // Don't inline into something too big, which would make it bigger.
00293   //
00294   InlineCost += Caller->size()/15;
00295   
00296   // Look at the size of the callee. Each instruction counts as 5.
00297   InlineCost += CalleeFI.NumInsts*5;
00298 
00299   return llvm::InlineCost::get(InlineCost);
00300 }
00301 
00302 // getInlineFudgeFactor - Return a > 1.0 factor if the inliner should use a
00303 // higher threshold to determine if the function call should be inlined.
00304 float InlineCostAnalyzer::getInlineFudgeFactor(CallSite CS) {
00305   Function *Callee = CS.getCalledFunction();
00306   
00307   // Get information about the callee...
00308   FunctionInfo &CalleeFI = CachedFunctionInfo[Callee];
00309   
00310   // If we haven't calculated this information yet, do so now.
00311   if (CalleeFI.NumBlocks == 0)
00312     CalleeFI.analyzeFunction(Callee);
00313 
00314   float Factor = 1.0f;
00315   // Single BB functions are often written to be inlined.
00316   if (CalleeFI.NumBlocks == 1)
00317     Factor += 0.5f;
00318 
00319   // Be more aggressive if the function contains a good chunk (if it mades up
00320   // at least 10% of the instructions) of vector instructions.
00321   if (CalleeFI.NumVectorInsts > CalleeFI.NumInsts/2)
00322     Factor += 2.0f;
00323   else if (CalleeFI.NumVectorInsts > CalleeFI.NumInsts/10)
00324     Factor += 1.5f;
00325   return Factor;
00326 }