LLVM API Documentation

PromoteMemoryToRegister.cpp

Go to the documentation of this file.
00001 //===- PromoteMemoryToRegister.cpp - Convert allocas to registers ---------===//
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 promotes memory references to be register references.  It promotes
00011 // alloca instructions which only have loads and stores as uses.  An alloca is
00012 // transformed by using dominator frontiers to place PHI nodes, then traversing
00013 // the function in depth-first order to rewrite loads and stores as appropriate.
00014 // This is just the standard SSA construction algorithm to construct "pruned"
00015 // SSA form.
00016 //
00017 //===----------------------------------------------------------------------===//
00018 
00019 #define DEBUG_TYPE "mem2reg"
00020 #include "llvm/Transforms/Utils/PromoteMemToReg.h"
00021 #include "llvm/Constants.h"
00022 #include "llvm/DerivedTypes.h"
00023 #include "llvm/Function.h"
00024 #include "llvm/Instructions.h"
00025 #include "llvm/IntrinsicInst.h"
00026 #include "llvm/LLVMContext.h"
00027 #include "llvm/Analysis/Dominators.h"
00028 #include "llvm/Analysis/AliasSetTracker.h"
00029 #include "llvm/ADT/DenseMap.h"
00030 #include "llvm/ADT/SmallPtrSet.h"
00031 #include "llvm/ADT/SmallVector.h"
00032 #include "llvm/ADT/Statistic.h"
00033 #include "llvm/ADT/STLExtras.h"
00034 #include "llvm/Support/CFG.h"
00035 #include "llvm/Support/Compiler.h"
00036 #include <algorithm>
00037 using namespace llvm;
00038 
00039 STATISTIC(NumLocalPromoted, "Number of alloca's promoted within one block");
00040 STATISTIC(NumSingleStore,   "Number of alloca's promoted with a single store");
00041 STATISTIC(NumDeadAlloca,    "Number of dead alloca's removed");
00042 STATISTIC(NumPHIInsert,     "Number of PHI nodes inserted");
00043 
00044 // Provide DenseMapInfo for all pointers.
00045 namespace llvm {
00046 template<>
00047 struct DenseMapInfo<std::pair<BasicBlock*, unsigned> > {
00048   typedef std::pair<BasicBlock*, unsigned> EltTy;
00049   static inline EltTy getEmptyKey() {
00050     return EltTy(reinterpret_cast<BasicBlock*>(-1), ~0U);
00051   }
00052   static inline EltTy getTombstoneKey() {
00053     return EltTy(reinterpret_cast<BasicBlock*>(-2), 0U);
00054   }
00055   static unsigned getHashValue(const std::pair<BasicBlock*, unsigned> &Val) {
00056     return DenseMapInfo<void*>::getHashValue(Val.first) + Val.second*2;
00057   }
00058   static bool isEqual(const EltTy &LHS, const EltTy &RHS) {
00059     return LHS == RHS;
00060   }
00061   static bool isPod() { return true; }
00062 };
00063 }
00064 
00065 /// isAllocaPromotable - Return true if this alloca is legal for promotion.
00066 /// This is true if there are only loads and stores to the alloca.
00067 ///
00068 bool llvm::isAllocaPromotable(const AllocaInst *AI) {
00069   // FIXME: If the memory unit is of pointer or integer type, we can permit
00070   // assignments to subsections of the memory unit.
00071 
00072   // Only allow direct and non-volatile loads and stores...
00073   for (Value::use_const_iterator UI = AI->use_begin(), UE = AI->use_end();
00074        UI != UE; ++UI)     // Loop over all of the uses of the alloca
00075     if (const LoadInst *LI = dyn_cast<LoadInst>(*UI)) {
00076       if (LI->isVolatile())
00077         return false;
00078     } else if (const StoreInst *SI = dyn_cast<StoreInst>(*UI)) {
00079       if (SI->getOperand(0) == AI)
00080         return false;   // Don't allow a store OF the AI, only INTO the AI.
00081       if (SI->isVolatile())
00082         return false;
00083     } else if (const BitCastInst *BC = dyn_cast<BitCastInst>(*UI)) {
00084       // A bitcast that does not feed into debug info inhibits promotion.
00085       if (!BC->hasOneUse() || !isa<DbgInfoIntrinsic>(*BC->use_begin()))
00086         return false;
00087       // If the only use is by debug info, this alloca will not exist in
00088       // non-debug code, so don't try to promote; this ensures the same
00089       // codegen with debug info.  Otherwise, debug info should not
00090       // inhibit promotion (but we must examine other uses).
00091       if (AI->hasOneUse())
00092         return false;
00093     } else {
00094       return false;
00095     }
00096 
00097   return true;
00098 }
00099 
00100 namespace {
00101   struct AllocaInfo;
00102 
00103   // Data package used by RenamePass()
00104   class VISIBILITY_HIDDEN RenamePassData {
00105   public:
00106     typedef std::vector<Value *> ValVector;
00107     
00108     RenamePassData() {}
00109     RenamePassData(BasicBlock *B, BasicBlock *P,
00110                    const ValVector &V) : BB(B), Pred(P), Values(V) {}
00111     BasicBlock *BB;
00112     BasicBlock *Pred;
00113     ValVector Values;
00114     
00115     void swap(RenamePassData &RHS) {
00116       std::swap(BB, RHS.BB);
00117       std::swap(Pred, RHS.Pred);
00118       Values.swap(RHS.Values);
00119     }
00120   };
00121   
00122   /// LargeBlockInfo - This assigns and keeps a per-bb relative ordering of
00123   /// load/store instructions in the block that directly load or store an alloca.
00124   ///
00125   /// This functionality is important because it avoids scanning large basic
00126   /// blocks multiple times when promoting many allocas in the same block.
00127   class VISIBILITY_HIDDEN LargeBlockInfo {
00128     /// InstNumbers - For each instruction that we track, keep the index of the
00129     /// instruction.  The index starts out as the number of the instruction from
00130     /// the start of the block.
00131     DenseMap<const Instruction *, unsigned> InstNumbers;
00132   public:
00133     
00134     /// isInterestingInstruction - This code only looks at accesses to allocas.
00135     static bool isInterestingInstruction(const Instruction *I) {
00136       return (isa<LoadInst>(I) && isa<AllocaInst>(I->getOperand(0))) ||
00137              (isa<StoreInst>(I) && isa<AllocaInst>(I->getOperand(1)));
00138     }
00139     
00140     /// getInstructionIndex - Get or calculate the index of the specified
00141     /// instruction.
00142     unsigned getInstructionIndex(const Instruction *I) {
00143       assert(isInterestingInstruction(I) &&
00144              "Not a load/store to/from an alloca?");
00145       
00146       // If we already have this instruction number, return it.
00147       DenseMap<const Instruction *, unsigned>::iterator It = InstNumbers.find(I);
00148       if (It != InstNumbers.end()) return It->second;
00149       
00150       // Scan the whole block to get the instruction.  This accumulates
00151       // information for every interesting instruction in the block, in order to
00152       // avoid gratuitus rescans.
00153       const BasicBlock *BB = I->getParent();
00154       unsigned InstNo = 0;
00155       for (BasicBlock::const_iterator BBI = BB->begin(), E = BB->end();
00156            BBI != E; ++BBI)
00157         if (isInterestingInstruction(BBI))
00158           InstNumbers[BBI] = InstNo++;
00159       It = InstNumbers.find(I);
00160       
00161       assert(It != InstNumbers.end() && "Didn't insert instruction?");
00162       return It->second;
00163     }
00164     
00165     void deleteValue(const Instruction *I) {
00166       InstNumbers.erase(I);
00167     }
00168     
00169     void clear() {
00170       InstNumbers.clear();
00171     }
00172   };
00173 
00174   struct VISIBILITY_HIDDEN PromoteMem2Reg {
00175     /// Allocas - The alloca instructions being promoted.
00176     ///
00177     std::vector<AllocaInst*> Allocas;
00178     DominatorTree &DT;
00179     DominanceFrontier &DF;
00180 
00181     /// AST - An AliasSetTracker object to update.  If null, don't update it.
00182     ///
00183     AliasSetTracker *AST;
00184     
00185     LLVMContext &Context;
00186 
00187     /// AllocaLookup - Reverse mapping of Allocas.
00188     ///
00189     std::map<AllocaInst*, unsigned>  AllocaLookup;
00190 
00191     /// NewPhiNodes - The PhiNodes we're adding.
00192     ///
00193     DenseMap<std::pair<BasicBlock*, unsigned>, PHINode*> NewPhiNodes;
00194     
00195     /// PhiToAllocaMap - For each PHI node, keep track of which entry in Allocas
00196     /// it corresponds to.
00197     DenseMap<PHINode*, unsigned> PhiToAllocaMap;
00198     
00199     /// PointerAllocaValues - If we are updating an AliasSetTracker, then for
00200     /// each alloca that is of pointer type, we keep track of what to copyValue
00201     /// to the inserted PHI nodes here.
00202     ///
00203     std::vector<Value*> PointerAllocaValues;
00204 
00205     /// Visited - The set of basic blocks the renamer has already visited.
00206     ///
00207     SmallPtrSet<BasicBlock*, 16> Visited;
00208 
00209     /// BBNumbers - Contains a stable numbering of basic blocks to avoid
00210     /// non-determinstic behavior.
00211     DenseMap<BasicBlock*, unsigned> BBNumbers;
00212 
00213     /// BBNumPreds - Lazily compute the number of predecessors a block has.
00214     DenseMap<const BasicBlock*, unsigned> BBNumPreds;
00215   public:
00216     PromoteMem2Reg(const std::vector<AllocaInst*> &A, DominatorTree &dt,
00217                    DominanceFrontier &df, AliasSetTracker *ast,
00218                    LLVMContext &C)
00219       : Allocas(A), DT(dt), DF(df), AST(ast), Context(C) {}
00220 
00221     void run();
00222 
00223     /// properlyDominates - Return true if I1 properly dominates I2.
00224     ///
00225     bool properlyDominates(Instruction *I1, Instruction *I2) const {
00226       if (InvokeInst *II = dyn_cast<InvokeInst>(I1))
00227         I1 = II->getNormalDest()->begin();
00228       return DT.properlyDominates(I1->getParent(), I2->getParent());
00229     }
00230     
00231     /// dominates - Return true if BB1 dominates BB2 using the DominatorTree.
00232     ///
00233     bool dominates(BasicBlock *BB1, BasicBlock *BB2) const {
00234       return DT.dominates(BB1, BB2);
00235     }
00236 
00237   private:
00238     void RemoveFromAllocasList(unsigned &AllocaIdx) {
00239       Allocas[AllocaIdx] = Allocas.back();
00240       Allocas.pop_back();
00241       --AllocaIdx;
00242     }
00243 
00244     unsigned getNumPreds(const BasicBlock *BB) {
00245       unsigned &NP = BBNumPreds[BB];
00246       if (NP == 0)
00247         NP = std::distance(pred_begin(BB), pred_end(BB))+1;
00248       return NP-1;
00249     }
00250 
00251     void DetermineInsertionPoint(AllocaInst *AI, unsigned AllocaNum,
00252                                  AllocaInfo &Info);
00253     void ComputeLiveInBlocks(AllocaInst *AI, AllocaInfo &Info, 
00254                              const SmallPtrSet<BasicBlock*, 32> &DefBlocks,
00255                              SmallPtrSet<BasicBlock*, 32> &LiveInBlocks);
00256     
00257     void RewriteSingleStoreAlloca(AllocaInst *AI, AllocaInfo &Info,
00258                                   LargeBlockInfo &LBI);
00259     void PromoteSingleBlockAlloca(AllocaInst *AI, AllocaInfo &Info,
00260                                   LargeBlockInfo &LBI);
00261 
00262     
00263     void RenamePass(BasicBlock *BB, BasicBlock *Pred,
00264                     RenamePassData::ValVector &IncVals,
00265                     std::vector<RenamePassData> &Worklist);
00266     bool QueuePhiNode(BasicBlock *BB, unsigned AllocaIdx, unsigned &Version,
00267                       SmallPtrSet<PHINode*, 16> &InsertedPHINodes);
00268   };
00269   
00270   struct AllocaInfo {
00271     std::vector<BasicBlock*> DefiningBlocks;
00272     std::vector<BasicBlock*> UsingBlocks;
00273     
00274     StoreInst  *OnlyStore;
00275     BasicBlock *OnlyBlock;
00276     bool OnlyUsedInOneBlock;
00277     
00278     Value *AllocaPointerVal;
00279     
00280     void clear() {
00281       DefiningBlocks.clear();
00282       UsingBlocks.clear();
00283       OnlyStore = 0;
00284       OnlyBlock = 0;
00285       OnlyUsedInOneBlock = true;
00286       AllocaPointerVal = 0;
00287     }
00288     
00289     /// AnalyzeAlloca - Scan the uses of the specified alloca, filling in our
00290     /// ivars.
00291     void AnalyzeAlloca(AllocaInst *AI) {
00292       clear();
00293 
00294       // As we scan the uses of the alloca instruction, keep track of stores,
00295       // and decide whether all of the loads and stores to the alloca are within
00296       // the same basic block.
00297       for (Value::use_iterator U = AI->use_begin(), E = AI->use_end();
00298            U != E;)  {
00299         Instruction *User = cast<Instruction>(*U);
00300         ++U;
00301         if (BitCastInst *BC = dyn_cast<BitCastInst>(User)) {
00302           // Remove any uses of this alloca in DbgInfoInstrinsics.
00303           assert(BC->hasOneUse() && "Unexpected alloca uses!");
00304           DbgInfoIntrinsic *DI = cast<DbgInfoIntrinsic>(*BC->use_begin());
00305           DI->eraseFromParent();
00306           BC->eraseFromParent();
00307           continue;
00308         } 
00309         else if (StoreInst *SI = dyn_cast<StoreInst>(User)) {
00310           // Remember the basic blocks which define new values for the alloca
00311           DefiningBlocks.push_back(SI->getParent());
00312           AllocaPointerVal = SI->getOperand(0);
00313           OnlyStore = SI;
00314         } else {
00315           LoadInst *LI = cast<LoadInst>(User);
00316           // Otherwise it must be a load instruction, keep track of variable
00317           // reads.
00318           UsingBlocks.push_back(LI->getParent());
00319           AllocaPointerVal = LI;
00320         }
00321         
00322         if (OnlyUsedInOneBlock) {
00323           if (OnlyBlock == 0)
00324             OnlyBlock = User->getParent();
00325           else if (OnlyBlock != User->getParent())
00326             OnlyUsedInOneBlock = false;
00327         }
00328       }
00329     }
00330   };
00331 }  // end of anonymous namespace
00332 
00333 
00334 void PromoteMem2Reg::run() {
00335   Function &F = *DF.getRoot()->getParent();
00336 
00337   if (AST) PointerAllocaValues.resize(Allocas.size());
00338 
00339   AllocaInfo Info;
00340   LargeBlockInfo LBI;
00341 
00342   for (unsigned AllocaNum = 0; AllocaNum != Allocas.size(); ++AllocaNum) {
00343     AllocaInst *AI = Allocas[AllocaNum];
00344 
00345     assert(isAllocaPromotable(AI) &&
00346            "Cannot promote non-promotable alloca!");
00347     assert(AI->getParent()->getParent() == &F &&
00348            "All allocas should be in the same function, which is same as DF!");
00349 
00350     if (AI->use_empty()) {
00351       // If there are no uses of the alloca, just delete it now.
00352       if (AST) AST->deleteValue(AI);
00353       AI->eraseFromParent();
00354 
00355       // Remove the alloca from the Allocas list, since it has been processed
00356       RemoveFromAllocasList(AllocaNum);
00357       ++NumDeadAlloca;
00358       continue;
00359     }
00360     
00361     // Calculate the set of read and write-locations for each alloca.  This is
00362     // analogous to finding the 'uses' and 'definitions' of each variable.
00363     Info.AnalyzeAlloca(AI);
00364 
00365     // If there is only a single store to this value, replace any loads of
00366     // it that are directly dominated by the definition with the value stored.
00367     if (Info.DefiningBlocks.size() == 1) {
00368       RewriteSingleStoreAlloca(AI, Info, LBI);
00369 
00370       // Finally, after the scan, check to see if the store is all that is left.
00371       if (Info.UsingBlocks.empty()) {
00372         // Remove the (now dead) store and alloca.
00373         Info.OnlyStore->eraseFromParent();
00374         LBI.deleteValue(Info.OnlyStore);
00375 
00376         if (AST) AST->deleteValue(AI);
00377         AI->eraseFromParent();
00378         LBI.deleteValue(AI);
00379         
00380         // The alloca has been processed, move on.
00381         RemoveFromAllocasList(AllocaNum);
00382         
00383         ++NumSingleStore;
00384         continue;
00385       }
00386     }
00387     
00388     // If the alloca is only read and written in one basic block, just perform a
00389     // linear sweep over the block to eliminate it.
00390     if (Info.OnlyUsedInOneBlock) {
00391       PromoteSingleBlockAlloca(AI, Info, LBI);
00392       
00393       // Finally, after the scan, check to see if the stores are all that is
00394       // left.
00395       if (Info.UsingBlocks.empty()) {
00396         
00397         // Remove the (now dead) stores and alloca.
00398         while (!AI->use_empty()) {
00399           StoreInst *SI = cast<StoreInst>(AI->use_back());
00400           SI->eraseFromParent();
00401           LBI.deleteValue(SI);
00402         }
00403         
00404         if (AST) AST->deleteValue(AI);
00405         AI->eraseFromParent();
00406         LBI.deleteValue(AI);
00407         
00408         // The alloca has been processed, move on.
00409         RemoveFromAllocasList(AllocaNum);
00410         
00411         ++NumLocalPromoted;
00412         continue;
00413       }
00414     }
00415     
00416     // If we haven't computed a numbering for the BB's in the function, do so
00417     // now.
00418     if (BBNumbers.empty()) {
00419       unsigned ID = 0;
00420       for (Function::iterator I = F.begin(), E = F.end(); I != E; ++I)
00421         BBNumbers[I] = ID++;
00422     }
00423 
00424     // If we have an AST to keep updated, remember some pointer value that is
00425     // stored into the alloca.
00426     if (AST)
00427       PointerAllocaValues[AllocaNum] = Info.AllocaPointerVal;
00428     
00429     // Keep the reverse mapping of the 'Allocas' array for the rename pass.
00430     AllocaLookup[Allocas[AllocaNum]] = AllocaNum;
00431 
00432     // At this point, we're committed to promoting the alloca using IDF's, and
00433     // the standard SSA construction algorithm.  Determine which blocks need PHI
00434     // nodes and see if we can optimize out some work by avoiding insertion of
00435     // dead phi nodes.
00436     DetermineInsertionPoint(AI, AllocaNum, Info);
00437   }
00438 
00439   if (Allocas.empty())
00440     return; // All of the allocas must have been trivial!
00441 
00442   LBI.clear();
00443   
00444   
00445   // Set the incoming values for the basic block to be null values for all of
00446   // the alloca's.  We do this in case there is a load of a value that has not
00447   // been stored yet.  In this case, it will get this null value.
00448   //
00449   RenamePassData::ValVector Values(Allocas.size());
00450   for (unsigned i = 0, e = Allocas.size(); i != e; ++i)
00451     Values[i] = UndefValue::get(Allocas[i]->getAllocatedType());
00452 
00453   // Walks all basic blocks in the function performing the SSA rename algorithm
00454   // and inserting the phi nodes we marked as necessary
00455   //
00456   std::vector<RenamePassData> RenamePassWorkList;
00457   RenamePassWorkList.push_back(RenamePassData(F.begin(), 0, Values));
00458   while (!RenamePassWorkList.empty()) {
00459     RenamePassData RPD;
00460     RPD.swap(RenamePassWorkList.back());
00461     RenamePassWorkList.pop_back();
00462     // RenamePass may add new worklist entries.
00463     RenamePass(RPD.BB, RPD.Pred, RPD.Values, RenamePassWorkList);
00464   }
00465   
00466   // The renamer uses the Visited set to avoid infinite loops.  Clear it now.
00467   Visited.clear();
00468 
00469   // Remove the allocas themselves from the function.
00470   for (unsigned i = 0, e = Allocas.size(); i != e; ++i) {
00471     Instruction *A = Allocas[i];
00472 
00473     // If there are any uses of the alloca instructions left, they must be in
00474     // sections of dead code that were not processed on the dominance frontier.
00475     // Just delete the users now.
00476     //
00477     if (!A->use_empty())
00478       A->replaceAllUsesWith(UndefValue::get(A->getType()));
00479     if (AST) AST->deleteValue(A);
00480     A->eraseFromParent();
00481   }
00482 
00483   
00484   // Loop over all of the PHI nodes and see if there are any that we can get
00485   // rid of because they merge all of the same incoming values.  This can
00486   // happen due to undef values coming into the PHI nodes.  This process is
00487   // iterative, because eliminating one PHI node can cause others to be removed.
00488   bool EliminatedAPHI = true;
00489   while (EliminatedAPHI) {
00490     EliminatedAPHI = false;
00491     
00492     for (DenseMap<std::pair<BasicBlock*, unsigned>, PHINode*>::iterator I =
00493            NewPhiNodes.begin(), E = NewPhiNodes.end(); I != E;) {
00494       PHINode *PN = I->second;
00495       
00496       // If this PHI node merges one value and/or undefs, get the value.
00497       if (Value *V = PN->hasConstantValue(true)) {
00498         if (!isa<Instruction>(V) ||
00499             properlyDominates(cast<Instruction>(V), PN)) {
00500           if (AST && isa<PointerType>(PN->getType()))
00501             AST->deleteValue(PN);
00502           PN->replaceAllUsesWith(V);
00503           PN->eraseFromParent();
00504           NewPhiNodes.erase(I++);
00505           EliminatedAPHI = true;
00506           continue;
00507         }
00508       }
00509       ++I;
00510     }
00511   }
00512   
00513   // At this point, the renamer has added entries to PHI nodes for all reachable
00514   // code.  Unfortunately, there may be unreachable blocks which the renamer
00515   // hasn't traversed.  If this is the case, the PHI nodes may not
00516   // have incoming values for all predecessors.  Loop over all PHI nodes we have
00517   // created, inserting undef values if they are missing any incoming values.
00518   //
00519   for (DenseMap<std::pair<BasicBlock*, unsigned>, PHINode*>::iterator I =
00520          NewPhiNodes.begin(), E = NewPhiNodes.end(); I != E; ++I) {
00521     // We want to do this once per basic block.  As such, only process a block
00522     // when we find the PHI that is the first entry in the block.
00523     PHINode *SomePHI = I->second;
00524     BasicBlock *BB = SomePHI->getParent();
00525     if (&BB->front() != SomePHI)
00526       continue;
00527 
00528     // Only do work here if there the PHI nodes are missing incoming values.  We
00529     // know that all PHI nodes that were inserted in a block will have the same
00530     // number of incoming values, so we can just check any of them.
00531     if (SomePHI->getNumIncomingValues() == getNumPreds(BB))
00532       continue;
00533 
00534     // Get the preds for BB.
00535     SmallVector<BasicBlock*, 16> Preds(pred_begin(BB), pred_end(BB));
00536     
00537     // Ok, now we know that all of the PHI nodes are missing entries for some
00538     // basic blocks.  Start by sorting the incoming predecessors for efficient
00539     // access.
00540     std::sort(Preds.begin(), Preds.end());
00541     
00542     // Now we loop through all BB's which have entries in SomePHI and remove
00543     // them from the Preds list.
00544     for (unsigned i = 0, e = SomePHI->getNumIncomingValues(); i != e; ++i) {
00545       // Do a log(n) search of the Preds list for the entry we want.
00546       SmallVector<BasicBlock*, 16>::iterator EntIt =
00547         std::lower_bound(Preds.begin(), Preds.end(),
00548                          SomePHI->getIncomingBlock(i));
00549       assert(EntIt != Preds.end() && *EntIt == SomePHI->getIncomingBlock(i)&&
00550              "PHI node has entry for a block which is not a predecessor!");
00551 
00552       // Remove the entry
00553       Preds.erase(EntIt);
00554     }
00555 
00556     // At this point, the blocks left in the preds list must have dummy
00557     // entries inserted into every PHI nodes for the block.  Update all the phi
00558     // nodes in this block that we are inserting (there could be phis before
00559     // mem2reg runs).
00560     unsigned NumBadPreds = SomePHI->getNumIncomingValues();
00561     BasicBlock::iterator BBI = BB->begin();
00562     while ((SomePHI = dyn_cast<PHINode>(BBI++)) &&
00563            SomePHI->getNumIncomingValues() == NumBadPreds) {
00564       Value *UndefVal = UndefValue::get(SomePHI->getType());
00565       for (unsigned pred = 0, e = Preds.size(); pred != e; ++pred)
00566         SomePHI->addIncoming(UndefVal, Preds[pred]);
00567     }
00568   }
00569         
00570   NewPhiNodes.clear();
00571 }
00572 
00573 
00574 /// ComputeLiveInBlocks - Determine which blocks the value is live in.  These
00575 /// are blocks which lead to uses.  Knowing this allows us to avoid inserting
00576 /// PHI nodes into blocks which don't lead to uses (thus, the inserted phi nodes
00577 /// would be dead).
00578 void PromoteMem2Reg::
00579 ComputeLiveInBlocks(AllocaInst *AI, AllocaInfo &Info, 
00580                     const SmallPtrSet<BasicBlock*, 32> &DefBlocks,
00581                     SmallPtrSet<BasicBlock*, 32> &LiveInBlocks) {
00582   
00583   // To determine liveness, we must iterate through the predecessors of blocks
00584   // where the def is live.  Blocks are added to the worklist if we need to
00585   // check their predecessors.  Start with all the using blocks.
00586   SmallVector<BasicBlock*, 64> LiveInBlockWorklist;
00587   LiveInBlockWorklist.insert(LiveInBlockWorklist.end(), 
00588                              Info.UsingBlocks.begin(), Info.UsingBlocks.end());
00589   
00590   // If any of the using blocks is also a definition block, check to see if the
00591   // definition occurs before or after the use.  If it happens before the use,
00592   // the value isn't really live-in.
00593   for (unsigned i = 0, e = LiveInBlockWorklist.size(); i != e; ++i) {
00594     BasicBlock *BB = LiveInBlockWorklist[i];
00595     if (!DefBlocks.count(BB)) continue;
00596     
00597     // Okay, this is a block that both uses and defines the value.  If the first
00598     // reference to the alloca is a def (store), then we know it isn't live-in.
00599     for (BasicBlock::iterator I = BB->begin(); ; ++I) {
00600       if (StoreInst *SI = dyn_cast<StoreInst>(I)) {
00601         if (SI->getOperand(1) != AI) continue;
00602         
00603         // We found a store to the alloca before a load.  The alloca is not
00604         // actually live-in here.
00605         LiveInBlockWorklist[i] = LiveInBlockWorklist.back();
00606         LiveInBlockWorklist.pop_back();
00607         --i, --e;
00608         break;
00609       } else if (LoadInst *LI = dyn_cast<LoadInst>(I)) {
00610         if (LI->getOperand(0) != AI) continue;
00611         
00612         // Okay, we found a load before a store to the alloca.  It is actually
00613         // live into this block.
00614         break;
00615       }
00616     }
00617   }
00618   
00619   // Now that we have a set of blocks where the phi is live-in, recursively add
00620   // their predecessors until we find the full region the value is live.
00621   while (!LiveInBlockWorklist.empty()) {
00622     BasicBlock *BB = LiveInBlockWorklist.pop_back_val();
00623     
00624     // The block really is live in here, insert it into the set.  If already in
00625     // the set, then it has already been processed.
00626     if (!LiveInBlocks.insert(BB))
00627       continue;
00628     
00629     // Since the value is live into BB, it is either defined in a predecessor or
00630     // live into it to.  Add the preds to the worklist unless they are a
00631     // defining block.
00632     for (pred_iterator PI = pred_begin(BB), E = pred_end(BB); PI != E; ++PI) {
00633       BasicBlock *P = *PI;
00634       
00635       // The value is not live into a predecessor if it defines the value.
00636       if (DefBlocks.count(P))
00637         continue;
00638       
00639       // Otherwise it is, add to the worklist.
00640       LiveInBlockWorklist.push_back(P);
00641     }
00642   }
00643 }
00644 
00645 /// DetermineInsertionPoint - At this point, we're committed to promoting the
00646 /// alloca using IDF's, and the standard SSA construction algorithm.  Determine
00647 /// which blocks need phi nodes and see if we can optimize out some work by
00648 /// avoiding insertion of dead phi nodes.
00649 void PromoteMem2Reg::DetermineInsertionPoint(AllocaInst *AI, unsigned AllocaNum,
00650                                              AllocaInfo &Info) {
00651 
00652   // Unique the set of defining blocks for efficient lookup.
00653   SmallPtrSet<BasicBlock*, 32> DefBlocks;
00654   DefBlocks.insert(Info.DefiningBlocks.begin(), Info.DefiningBlocks.end());
00655 
00656   // Determine which blocks the value is live in.  These are blocks which lead
00657   // to uses.
00658   SmallPtrSet<BasicBlock*, 32> LiveInBlocks;
00659   ComputeLiveInBlocks(AI, Info, DefBlocks, LiveInBlocks);
00660 
00661   // Compute the locations where PhiNodes need to be inserted.  Look at the
00662   // dominance frontier of EACH basic-block we have a write in.
00663   unsigned CurrentVersion = 0;
00664   SmallPtrSet<PHINode*, 16> InsertedPHINodes;
00665   std::vector<std::pair<unsigned, BasicBlock*> > DFBlocks;
00666   while (!Info.DefiningBlocks.empty()) {
00667     BasicBlock *BB = Info.DefiningBlocks.back();
00668     Info.DefiningBlocks.pop_back();
00669     
00670     // Look up the DF for this write, add it to defining blocks.
00671     DominanceFrontier::const_iterator it = DF.find(BB);
00672     if (it == DF.end()) continue;
00673     
00674     const DominanceFrontier::DomSetType &S = it->second;
00675     
00676     // In theory we don't need the indirection through the DFBlocks vector.
00677     // In practice, the order of calling QueuePhiNode would depend on the
00678     // (unspecified) ordering of basic blocks in the dominance frontier,
00679     // which would give PHI nodes non-determinstic subscripts.  Fix this by
00680     // processing blocks in order of the occurance in the function.
00681     for (DominanceFrontier::DomSetType::const_iterator P = S.begin(),
00682          PE = S.end(); P != PE; ++P) {
00683       // If the frontier block is not in the live-in set for the alloca, don't
00684       // bother processing it.
00685       if (!LiveInBlocks.count(*P))
00686         continue;
00687       
00688       DFBlocks.push_back(std::make_pair(BBNumbers[*P], *P));
00689     }
00690     
00691     // Sort by which the block ordering in the function.
00692     if (DFBlocks.size() > 1)
00693       std::sort(DFBlocks.begin(), DFBlocks.end());
00694     
00695     for (unsigned i = 0, e = DFBlocks.size(); i != e; ++i) {
00696       BasicBlock *BB = DFBlocks[i].second;
00697       if (QueuePhiNode(BB, AllocaNum, CurrentVersion, InsertedPHINodes))
00698         Info.DefiningBlocks.push_back(BB);
00699     }
00700     DFBlocks.clear();
00701   }
00702 }
00703 
00704 /// RewriteSingleStoreAlloca - If there is only a single store to this value,
00705 /// replace any loads of it that are directly dominated by the definition with
00706 /// the value stored.
00707 void PromoteMem2Reg::RewriteSingleStoreAlloca(AllocaInst *AI,
00708                                               AllocaInfo &Info,
00709                                               LargeBlockInfo &LBI) {
00710   StoreInst *OnlyStore = Info.OnlyStore;
00711   bool StoringGlobalVal = !isa<Instruction>(OnlyStore->getOperand(0));
00712   BasicBlock *StoreBB = OnlyStore->getParent();
00713   int StoreIndex = -1;
00714 
00715   // Clear out UsingBlocks.  We will reconstruct it here if needed.
00716   Info.UsingBlocks.clear();
00717   
00718   for (Value::use_iterator UI = AI->use_begin(), E = AI->use_end(); UI != E; ) {
00719     Instruction *UserInst = cast<Instruction>(*UI++);
00720     if (!isa<LoadInst>(UserInst)) {
00721       assert(UserInst == OnlyStore && "Should only have load/stores");
00722       continue;
00723     }
00724     LoadInst *LI = cast<LoadInst>(UserInst);
00725     
00726     // Okay, if we have a load from the alloca, we want to replace it with the
00727     // only value stored to the alloca.  We can do this if the value is
00728     // dominated by the store.  If not, we use the rest of the mem2reg machinery
00729     // to insert the phi nodes as needed.
00730     if (!StoringGlobalVal) {  // Non-instructions are always dominated.
00731       if (LI->getParent() == StoreBB) {
00732         // If we have a use that is in the same block as the store, compare the
00733         // indices of the two instructions to see which one came first.  If the
00734         // load came before the store, we can't handle it.
00735         if (StoreIndex == -1)
00736           StoreIndex = LBI.getInstructionIndex(OnlyStore);
00737 
00738         if (unsigned(StoreIndex) > LBI.getInstructionIndex(LI)) {
00739           // Can't handle this load, bail out.
00740           Info.UsingBlocks.push_back(StoreBB);
00741           continue;
00742         }
00743         
00744       } else if (LI->getParent() != StoreBB &&
00745                  !dominates(StoreBB, LI->getParent())) {
00746         // If the load and store are in different blocks, use BB dominance to
00747         // check their relationships.  If the store doesn't dom the use, bail
00748         // out.
00749         Info.UsingBlocks.push_back(LI->getParent());
00750         continue;
00751       }
00752     }
00753     
00754     // Otherwise, we *can* safely rewrite this load.
00755     LI->replaceAllUsesWith(OnlyStore->getOperand(0));
00756     if (AST && isa<PointerType>(LI->getType()))
00757       AST->deleteValue(LI);
00758     LI->eraseFromParent();
00759     LBI.deleteValue(LI);
00760   }
00761 }
00762 
00763 namespace {
00764 
00765 /// StoreIndexSearchPredicate - This is a helper predicate used to search by the
00766 /// first element of a pair.
00767 struct StoreIndexSearchPredicate {
00768   bool operator()(const std::pair<unsigned, StoreInst*> &LHS,
00769                   const std::pair<unsigned, StoreInst*> &RHS) {
00770     return LHS.first < RHS.first;
00771   }
00772 };
00773 
00774 }
00775 
00776 /// PromoteSingleBlockAlloca - Many allocas are only used within a single basic
00777 /// block.  If this is the case, avoid traversing the CFG and inserting a lot of
00778 /// potentially useless PHI nodes by just performing a single linear pass over
00779 /// the basic block using the Alloca.
00780 ///
00781 /// If we cannot promote this alloca (because it is read before it is written),
00782 /// return true.  This is necessary in cases where, due to control flow, the
00783 /// alloca is potentially undefined on some control flow paths.  e.g. code like
00784 /// this is potentially correct:
00785 ///
00786 ///   for (...) { if (c) { A = undef; undef = B; } }
00787 ///
00788 /// ... so long as A is not used before undef is set.
00789 ///
00790 void PromoteMem2Reg::PromoteSingleBlockAlloca(AllocaInst *AI, AllocaInfo &Info,
00791                                               LargeBlockInfo &LBI) {
00792   // The trickiest case to handle is when we have large blocks. Because of this,
00793   // this code is optimized assuming that large blocks happen.  This does not
00794   // significantly pessimize the small block case.  This uses LargeBlockInfo to
00795   // make it efficient to get the index of various operations in the block.
00796   
00797   // Clear out UsingBlocks.  We will reconstruct it here if needed.
00798   Info.UsingBlocks.clear();
00799   
00800   // Walk the use-def list of the alloca, getting the locations of all stores.
00801   typedef SmallVector<std::pair<unsigned, StoreInst*>, 64> StoresByIndexTy;
00802   StoresByIndexTy StoresByIndex;
00803   
00804   for (Value::use_iterator UI = AI->use_begin(), E = AI->use_end();
00805        UI != E; ++UI) 
00806     if (StoreInst *SI = dyn_cast<StoreInst>(*UI))
00807       StoresByIndex.push_back(std::make_pair(LBI.getInstructionIndex(SI), SI));
00808 
00809   // If there are no stores to the alloca, just replace any loads with undef.
00810   if (StoresByIndex.empty()) {
00811     for (Value::use_iterator UI = AI->use_begin(), E = AI->use_end(); UI != E;) 
00812       if (LoadInst *LI = dyn_cast<LoadInst>(*UI++)) {
00813         LI->replaceAllUsesWith(UndefValue::get(LI->getType()));
00814         if (AST && isa<PointerType>(LI->getType()))
00815           AST->deleteValue(LI);
00816         LBI.deleteValue(LI);
00817         LI->eraseFromParent();
00818       }
00819     return;
00820   }
00821   
00822   // Sort the stores by their index, making it efficient to do a lookup with a
00823   // binary search.
00824   std::sort(StoresByIndex.begin(), StoresByIndex.end());
00825   
00826   // Walk all of the loads from this alloca, replacing them with the nearest
00827   // store above them, if any.
00828   for (Value::use_iterator UI = AI->use_begin(), E = AI->use_end(); UI != E;) {
00829     LoadInst *LI = dyn_cast<LoadInst>(*UI++);
00830     if (!LI) continue;
00831     
00832     unsigned LoadIdx = LBI.getInstructionIndex(LI);
00833     
00834     // Find the nearest store that has a lower than this load. 
00835     StoresByIndexTy::iterator I = 
00836       std::lower_bound(StoresByIndex.begin(), StoresByIndex.end(),
00837                        std::pair<unsigned, StoreInst*>(LoadIdx, 0),
00838                        StoreIndexSearchPredicate());
00839     
00840     // If there is no store before this load, then we can't promote this load.
00841     if (I == StoresByIndex.begin()) {
00842       // Can't handle this load, bail out.
00843       Info.UsingBlocks.push_back(LI->getParent());
00844       continue;
00845     }
00846       
00847     // Otherwise, there was a store before this load, the load takes its value.
00848     --I;
00849     LI->replaceAllUsesWith(I->second->getOperand(0));
00850     if (AST && isa<PointerType>(LI->getType()))
00851       AST->deleteValue(LI);
00852     LI->eraseFromParent();
00853     LBI.deleteValue(LI);
00854   }
00855 }
00856 
00857 
00858 // QueuePhiNode - queues a phi-node to be added to a basic-block for a specific
00859 // Alloca returns true if there wasn't already a phi-node for that variable
00860 //
00861 bool PromoteMem2Reg::QueuePhiNode(BasicBlock *BB, unsigned AllocaNo,
00862                                   unsigned &Version,
00863                                   SmallPtrSet<PHINode*, 16> &InsertedPHINodes) {
00864   // Look up the basic-block in question.
00865   PHINode *&PN = NewPhiNodes[std::make_pair(BB, AllocaNo)];
00866 
00867   // If the BB already has a phi node added for the i'th alloca then we're done!
00868   if (PN) return false;
00869 
00870   // Create a PhiNode using the dereferenced type... and add the phi-node to the
00871   // BasicBlock.
00872   PN = PHINode::Create(Allocas[AllocaNo]->getAllocatedType(),
00873                        Allocas[AllocaNo]->getName() + "." + Twine(Version++), 
00874                        BB->begin());
00875   ++NumPHIInsert;
00876   PhiToAllocaMap[PN] = AllocaNo;
00877   PN->reserveOperandSpace(getNumPreds(BB));
00878   
00879   InsertedPHINodes.insert(PN);
00880 
00881   if (AST && isa<PointerType>(PN->getType()))
00882     AST->copyValue(PointerAllocaValues[AllocaNo], PN);
00883 
00884   return true;
00885 }
00886 
00887 // RenamePass - Recursively traverse the CFG of the function, renaming loads and
00888 // stores to the allocas which we are promoting.  IncomingVals indicates what
00889 // value each Alloca contains on exit from the predecessor block Pred.
00890 //
00891 void PromoteMem2Reg::RenamePass(BasicBlock *BB, BasicBlock *Pred,
00892                                 RenamePassData::ValVector &IncomingVals,
00893                                 std::vector<RenamePassData> &Worklist) {
00894 NextIteration:
00895   // If we are inserting any phi nodes into this BB, they will already be in the
00896   // block.
00897   if (PHINode *APN = dyn_cast<PHINode>(BB->begin())) {
00898     // If we have PHI nodes to update, compute the number of edges from Pred to
00899     // BB.
00900     if (PhiToAllocaMap.count(APN)) {
00901       // We want to be able to distinguish between PHI nodes being inserted by
00902       // this invocation of mem2reg from those phi nodes that already existed in
00903       // the IR before mem2reg was run.  We determine that APN is being inserted
00904       // because it is missing incoming edges.  All other PHI nodes being
00905       // inserted by this pass of mem2reg will have the same number of incoming
00906       // operands so far.  Remember this count.
00907       unsigned NewPHINumOperands = APN->getNumOperands();
00908       
00909       unsigned NumEdges = 0;
00910       for (succ_iterator I = succ_begin(Pred), E = succ_end(Pred); I != E; ++I)
00911         if (*I == BB)
00912           ++NumEdges;
00913       assert(NumEdges && "Must be at least one edge from Pred to BB!");
00914       
00915       // Add entries for all the phis.
00916       BasicBlock::iterator PNI = BB->begin();
00917       do {
00918         unsigned AllocaNo = PhiToAllocaMap[APN];
00919         
00920         // Add N incoming values to the PHI node.
00921         for (unsigned i = 0; i != NumEdges; ++i)
00922           APN->addIncoming(IncomingVals[AllocaNo], Pred);
00923         
00924         // The currently active variable for this block is now the PHI.
00925         IncomingVals[AllocaNo] = APN;
00926         
00927         // Get the next phi node.
00928         ++PNI;
00929         APN = dyn_cast<PHINode>(PNI);
00930         if (APN == 0) break;
00931         
00932         // Verify that it is missing entries.  If not, it is not being inserted
00933         // by this mem2reg invocation so we want to ignore it.
00934       } while (APN->getNumOperands() == NewPHINumOperands);
00935     }
00936   }
00937   
00938   // Don't revisit blocks.
00939   if (!Visited.insert(BB)) return;
00940 
00941   for (BasicBlock::iterator II = BB->begin(); !isa<TerminatorInst>(II); ) {
00942     Instruction *I = II++; // get the instruction, increment iterator
00943 
00944     if (LoadInst *LI = dyn_cast<LoadInst>(I)) {
00945       AllocaInst *Src = dyn_cast<AllocaInst>(LI->getPointerOperand());
00946       if (!Src) continue;
00947   
00948       std::map<AllocaInst*, unsigned>::iterator AI = AllocaLookup.find(Src);
00949       if (AI == AllocaLookup.end()) continue;
00950 
00951       Value *V = IncomingVals[AI->second];
00952 
00953       // Anything using the load now uses the current value.
00954       LI->replaceAllUsesWith(V);
00955       if (AST && isa<PointerType>(LI->getType()))
00956         AST->deleteValue(LI);
00957       BB->getInstList().erase(LI);
00958     } else if (StoreInst *SI = dyn_cast<StoreInst>(I)) {
00959       // Delete this instruction and mark the name as the current holder of the
00960       // value
00961       AllocaInst *Dest = dyn_cast<AllocaInst>(SI->getPointerOperand());
00962       if (!Dest) continue;
00963       
00964       std::map<AllocaInst *, unsigned>::iterator ai = AllocaLookup.find(Dest);
00965       if (ai == AllocaLookup.end())
00966         continue;
00967       
00968       // what value were we writing?
00969       IncomingVals[ai->second] = SI->getOperand(0);
00970       BB->getInstList().erase(SI);
00971     }
00972   }
00973 
00974   // 'Recurse' to our successors.
00975   succ_iterator I = succ_begin(BB), E = succ_end(BB);
00976   if (I == E) return;
00977 
00978   // Keep track of the successors so we don't visit the same successor twice
00979   SmallPtrSet<BasicBlock*, 8> VisitedSuccs;
00980 
00981   // Handle the first successor without using the worklist.
00982   VisitedSuccs.insert(*I);
00983   Pred = BB;
00984   BB = *I;
00985   ++I;
00986 
00987   for (; I != E; ++I)
00988     if (VisitedSuccs.insert(*I))
00989       Worklist.push_back(RenamePassData(*I, Pred, IncomingVals));
00990 
00991   goto NextIteration;
00992 }
00993 
00994 /// PromoteMemToReg - Promote the specified list of alloca instructions into
00995 /// scalar registers, inserting PHI nodes as appropriate.  This function makes
00996 /// use of DominanceFrontier information.  This function does not modify the CFG
00997 /// of the function at all.  All allocas must be from the same function.
00998 ///
00999 /// If AST is specified, the specified tracker is updated to reflect changes
01000 /// made to the IR.
01001 ///
01002 void llvm::PromoteMemToReg(const std::vector<AllocaInst*> &Allocas,
01003                            DominatorTree &DT, DominanceFrontier &DF,
01004                            LLVMContext &Context, AliasSetTracker *AST) {
01005   // If there is nothing to do, bail out...
01006   if (Allocas.empty()) return;
01007 
01008   PromoteMem2Reg(Allocas, DT, DF, AST, Context).run();
01009 }