[CodeGenPrepare] Don't call getSubtargetImpl quite as often

[loladiro]

Summary

While profiling LLVM's memory allocation, I noticed that getSubtargetImpl was called quite often (and it allocates heap memory by doing string operations). This simple change to cache the TargetLowering/TargetRegisterInfo in CodeGenPrepare reduces the total number of allocations in my test compile by about 3%

[arsenm]

LGTM

[dblaikie]

+echristo, who did a bunch of this subtarget stuff, in case he has some
extra insight (and/or just so he knows in case other similar things come up)

[echristo]

LGTM. Thanks!

-eric

[echristo]

Alternately, btw, you can just cache the STI in the pass as well btw. Either works for me.

-eric

[Eugene.Zelenko]

Looks like patch was not committed.

[arsenm]

ping to commit this?

[echristo]

Still looks good to me.

[arsenm]

Patch looks obsolete

lib/CodeGen/CodeGenPrepare.cpp

 typedef SmallPtrSet<Instruction *, 16> SetOfInstrs;
 typedef PointerIntPair<Type *, 1, bool> TypeIsSExt;
 typedef DenseMap<Instruction *, TypeIsSExt> InstrToOrigTy;
 class TypePromotionTransaction;
 
   class CodeGenPrepare : public FunctionPass {
     const TargetMachine *TM;
     const TargetLowering *TLI;
+    const TargetRegisterInfo *TRI;
     const TargetTransformInfo *TTI;
     const TargetLibraryInfo *TLInfo;
 
+    /// Cache UseAA for the current function from the subtarget
+    bool UseAA;
+
     /// As we scan instructions optimizing them, this is the next instruction
     /// to optimize. Transforms that can invalidate this should update it.
     BasicBlock::iterator CurInstIterator;
 
     /// Keeps track of non-local addresses that have been sunk into a block.
     /// This allows us to avoid inserting duplicate code for blocks with
     /// multiple load/stores of the same address.
     ValueMap<Value*, Value*> SunkAddrs;
bool CodeGenPrepare::runOnFunction(Function &F) {
   DL = &F.getParent()->getDataLayout();
 
   bool EverMadeChange = false;
   // Clear per function information.
   InsertedInsts.clear();
   PromotedInsts.clear();
 
   ModifiedDT = false;
-  if (TM)
-    TLI = TM->getSubtargetImpl(F)->getTargetLowering();
+  if (TM) {
+    auto *STI = TM->getSubtargetImpl(F);
+    TLI = STI->getTargetLowering();
+    TRI = STI->getRegisterInfo();
+    UseAA = STI->useAA();
+  }
   TLInfo = &getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();
   TTI = &getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
   OptSize = F.optForSize();
 
   /// This optimization identifies DIV instructions that can be
   /// profitably bypassed and carried out with a shorter, faster divide.
   if (!OptSize && TLI && TLI->isSlowDivBypassed()) {
     const DenseMap<unsigned int, unsigned int> &BypassWidths =
void TypePromotionTransaction::rollback(
   }
 }
 
 /// \brief A helper class for matching addressing modes.
 ///
 /// This encapsulates the logic for matching the target-legal addressing modes.
 class AddressingModeMatcher {
   SmallVectorImpl<Instruction*> &AddrModeInsts;
-  const TargetMachine &TM;
   const TargetLowering &TLI;
+  const TargetRegisterInfo &TRI;
   const DataLayout &DL;
 
   /// AccessTy/MemoryInst - This is the type for the access (e.g. double) and
   /// the memory instruction that we're computing this address for.
   Type *AccessTy;
   unsigned AddrSpace;
   Instruction *MemoryInst;
 
   /// This is the addressing mode that we're building up. This is
   /// part of the return value of this addressing mode matching stuff.
   ExtAddrMode &AddrMode;
 
   /// The instructions inserted by other CodeGenPrepare optimizations.
   const SetOfInstrs &InsertedInsts;
   /// A map from the instructions to their type before promotion.
   InstrToOrigTy &PromotedInsts;
   /// The ongoing transaction where every action should be registered.
   TypePromotionTransaction &TPT;
 
   /// This is set to true when we should not do profitability checks.
   /// When true, IsProfitableToFoldIntoAddressingMode always returns true.
   bool IgnoreProfitability;
 
   AddressingModeMatcher(SmallVectorImpl<Instruction *> &AMI,
-                        const TargetMachine &TM, Type *AT, unsigned AS,
+                        const TargetLowering *TLI,
+                        const TargetRegisterInfo *TRI, Type *AT, unsigned AS,
                         Instruction *MI, ExtAddrMode &AM,
                         const SetOfInstrs &InsertedInsts,
                         InstrToOrigTy &PromotedInsts,
                         TypePromotionTransaction &TPT)
-      : AddrModeInsts(AMI), TM(TM),
-        TLI(*TM.getSubtargetImpl(*MI->getParent()->getParent())
-                 ->getTargetLowering()),
+      : AddrModeInsts(AMI), TLI(*TLI), TRI(*TRI),
         DL(MI->getModule()->getDataLayout()), AccessTy(AT), AddrSpace(AS),
         MemoryInst(MI), AddrMode(AM), InsertedInsts(InsertedInsts),
         PromotedInsts(PromotedInsts), TPT(TPT) {
     IgnoreProfitability = false;
   }
 public:
 
   /// Find the maximal addressing mode that a load/store of V can fold,
   /// give an access type of AccessTy.  This returns a list of involved
   /// instructions in AddrModeInsts.
   /// \p InsertedInsts The instructions inserted by other CodeGenPrepare
   /// optimizations.
   /// \p PromotedInsts maps the instructions to their type before promotion.
   /// \p The ongoing transaction where every action should be registered.
-  static ExtAddrMode Match(Value *V, Type *AccessTy, unsigned AS,
-                           Instruction *MemoryInst,
-                           SmallVectorImpl<Instruction*> &AddrModeInsts,
-                           const TargetMachine &TM,
-                           const SetOfInstrs &InsertedInsts,
-                           InstrToOrigTy &PromotedInsts,
-                           TypePromotionTransaction &TPT) {
+  static ExtAddrMode
+  Match(Value *V, Type *AccessTy, unsigned AS, Instruction *MemoryInst,
+        SmallVectorImpl<Instruction *> &AddrModeInsts,
+        const TargetLowering *TLI, const TargetRegisterInfo *TRI,
+        const SetOfInstrs &InsertedInsts, InstrToOrigTy &PromotedInsts,
     ExtAddrMode Result;
 
-    bool Success = AddressingModeMatcher(AddrModeInsts, TM, AccessTy, AS,
-                                         MemoryInst, Result, InsertedInsts,
-                                         PromotedInsts, TPT).matchAddr(V, 0);
+    bool Success =
+        AddressingModeMatcher(AddrModeInsts, TLI, TRI, AccessTy, AS, MemoryInst,
+                              Result, InsertedInsts, PromotedInsts, TPT)
+            .matchAddr(V, 0);
     (void)Success; assert(Success && "Couldn't select *anything*?");
     return Result;
   }
 private:
   bool matchScaledValue(Value *ScaleReg, int64_t Scale, unsigned Depth);
   bool matchAddr(Value *V, unsigned Depth);
   bool matchOperationAddr(User *Operation, unsigned Opcode, unsigned Depth,
                           bool *MovedAway = nullptr);
bool AddressingModeMatcher::matchAddr(Value *Addr, unsigned Depth) {
   // Couldn't match.
   TPT.rollback(LastKnownGood);
   return false;
 }
 
 /// Check to see if all uses of OpVal by the specified inline asm call are due
 /// to memory operands. If so, return true, otherwise return false.
 static bool IsOperandAMemoryOperand(CallInst *CI, InlineAsm *IA, Value *OpVal,
-                                    const TargetMachine &TM) {
+                                    const TargetLowering *TLI,
+                                    const TargetRegisterInfo *TRI) {
   const Function *F = CI->getParent()->getParent();
-  const TargetLowering *TLI = TM.getSubtargetImpl(*F)->getTargetLowering();
-  const TargetRegisterInfo *TRI = TM.getSubtargetImpl(*F)->getRegisterInfo();
   TargetLowering::AsmOperandInfoVector TargetConstraints =
       TLI->ParseConstraints(F->getParent()->getDataLayout(), TRI,
                             ImmutableCallSite(CI));
   for (unsigned i = 0, e = TargetConstraints.size(); i != e; ++i) {
     TargetLowering::AsmOperandInfo &OpInfo = TargetConstraints[i];
 
     // Compute the constraint code and ConstraintType to use.
     TLI->ComputeConstraintToUse(OpInfo, SDValue());

 }
 
 /// Recursively walk all the uses of I until we find a memory use.
 /// If we find an obviously non-foldable instruction, return true.
 /// Add the ultimately found memory instructions to MemoryUses.
 static bool FindAllMemoryUses(
     Instruction *I,
     SmallVectorImpl<std::pair<Instruction *, unsigned>> &MemoryUses,
-    SmallPtrSetImpl<Instruction *> &ConsideredInsts, const TargetMachine &TM) {
+    SmallPtrSetImpl<Instruction *> &ConsideredInsts, const TargetLowering *TLI,
+    const TargetRegisterInfo *TRI) {
   // If we already considered this instruction, we're done.
   if (!ConsideredInsts.insert(I).second)
     return false;
 
   // If this is an obviously unfoldable instruction, bail out.
   if (!MightBeFoldableInst(I))
     return true;
 
if (StoreInst *SI = dyn_cast<StoreInst>(UserI)) {
       continue;
     }
 
     if (CallInst *CI = dyn_cast<CallInst>(UserI)) {
       InlineAsm *IA = dyn_cast<InlineAsm>(CI->getCalledValue());
       if (!IA) return true;
 
       // If this is a memory operand, we're cool, otherwise bail out.
-      if (!IsOperandAMemoryOperand(CI, IA, I, TM))
+      if (!IsOperandAMemoryOperand(CI, IA, I, TLI, TRI))
         return true;
       continue;
     }
 
-    if (FindAllMemoryUses(UserI, MemoryUses, ConsideredInsts, TM))
+    if (FindAllMemoryUses(UserI, MemoryUses, ConsideredInsts, TLI, TRI))
       return true;
   }
 
   return false;
 }
 
 /// Return true if Val is already known to be live at the use site that we're
 /// folding it into. If so, there is no cost to include it in the addressing
if (!BaseReg && !ScaledReg)
     return true;
 
   // If all uses of this instruction are ultimately load/store/inlineasm's,
   // check to see if their addressing modes will include this instruction.  If
   // so, we can fold it into all uses, so it doesn't matter if it has multiple
   // uses.
   SmallVector<std::pair<Instruction*,unsigned>, 16> MemoryUses;
   SmallPtrSet<Instruction*, 16> ConsideredInsts;
-  if (FindAllMemoryUses(I, MemoryUses, ConsideredInsts, TM))
+  if (FindAllMemoryUses(I, MemoryUses, ConsideredInsts, &TLI, &TRI))
     return false;  // Has a non-memory, non-foldable use!
 
   // Now that we know that all uses of this instruction are part of a chain of
   // computation involving only operations that could theoretically be folded
   // into a memory use, loop over each of these uses and see if they could
   // *actually* fold the instruction.
   SmallVector<Instruction*, 32> MatchedAddrModeInsts;
   for (unsigned i = 0, e = MemoryUses.size(); i != e; ++i) {
for (unsigned i = 0, e = MemoryUses.size(); i != e; ++i) {
     unsigned AS = AddrTy->getAddressSpace();
 
     // Do a match against the root of this address, ignoring profitability. This
     // will tell us if the addressing mode for the memory operation will
     // *actually* cover the shared instruction.
     ExtAddrMode Result;
     TypePromotionTransaction::ConstRestorationPt LastKnownGood =
         TPT.getRestorationPoint();
-    AddressingModeMatcher Matcher(MatchedAddrModeInsts, TM, AddressAccessTy, AS,
-                                  MemoryInst, Result, InsertedInsts,
-                                  PromotedInsts, TPT);
+    AddressingModeMatcher Matcher(MatchedAddrModeInsts, &TLI, &TRI,
+                                  AddressAccessTy, AS, MemoryInst, Result,
+                                  InsertedInsts, PromotedInsts, TPT);
     Matcher.IgnoreProfitability = true;
     bool Success = Matcher.matchAddr(Address, 0);
     (void)Success; assert(Success && "Couldn't select *anything*?");
 
     // The match was to check the profitability, the changes made are not
     // part of the original matcher. Therefore, they should be dropped
     // otherwise the original matcher will not present the right state.
     TPT.rollback(LastKnownGood);
if (PHINode *P = dyn_cast<PHINode>(V)) {
       for (Value *IncValue : P->incoming_values())
         worklist.push_back(IncValue);
       continue;
     }
 
     // For non-PHIs, determine the addressing mode being computed.
     SmallVector<Instruction*, 16> NewAddrModeInsts;
     ExtAddrMode NewAddrMode = AddressingModeMatcher::Match(
-      V, AccessTy, AddrSpace, MemoryInst, NewAddrModeInsts, *TM,
+        V, AccessTy, AddrSpace, MemoryInst, NewAddrModeInsts, TLI, TRI,
         InsertedInsts, PromotedInsts, TPT);
 
     // This check is broken into two cases with very similar code to avoid using
     // getNumUses() as much as possible. Some values have a lot of uses, so
     // calling getNumUses() unconditionally caused a significant compile-time
     // regression.
     if (!Consensus) {
       Consensus = V;
       AddrMode = NewAddrMode;
bool CodeGenPrepare::optimizeMemoryInst(Instruction *MemoryInst, Value *Addr,
   // computation.
   Value *&SunkAddr = SunkAddrs[Addr];
   if (SunkAddr) {
     DEBUG(dbgs() << "CGP: Reusing nonlocal addrmode: " << AddrMode << " for "
                  << *MemoryInst << "\n");
     if (SunkAddr->getType() != Addr->getType())
       SunkAddr = Builder.CreateBitCast(SunkAddr, Addr->getType());
   } else if (AddrSinkUsingGEPs ||
-             (!AddrSinkUsingGEPs.getNumOccurrences() && TM &&
-              TM->getSubtargetImpl(*MemoryInst->getParent()->getParent())
-                  ->useAA())) {
+             (!AddrSinkUsingGEPs.getNumOccurrences() && UseAA)) {
     // By default, we use the GEP-based method when AA is used later. This
     // prevents new inttoptr/ptrtoint pairs from degrading AA capabilities.
     DEBUG(dbgs() << "CGP: SINKING nonlocal addrmode: " << AddrMode << " for "
                  << *MemoryInst << "\n");
     Type *IntPtrTy = DL->getIntPtrType(Addr->getType());
     Value *ResultPtr = nullptr, *ResultIndex = nullptr;
 
     // First, find the pointer.
bool CodeGenPrepare::optimizeMemoryInst(Instruction *MemoryInst, Value *Addr,
   return true;
 }
 
 /// If there are any memory operands, use OptimizeMemoryInst to sink their
 /// address computing into the block when possible / profitable.
 bool CodeGenPrepare::optimizeInlineAsmInst(CallInst *CS) {
   bool MadeChange = false;
 
-  const TargetRegisterInfo *TRI =
-      TM->getSubtargetImpl(*CS->getParent()->getParent())->getRegisterInfo();
   TargetLowering::AsmOperandInfoVector TargetConstraints =
       TLI->ParseConstraints(*DL, TRI, CS);
   unsigned ArgNo = 0;
   for (unsigned i = 0, e = TargetConstraints.size(); i != e; ++i) {
     TargetLowering::AsmOperandInfo &OpInfo = TargetConstraints[i];
 
     // Compute the constraint code and ConstraintType to use.
     TLI->ComputeConstraintToUse(OpInfo, SDValue());