[PGO][PGSO] Instrument the code gen / target passes.

[hjyamauchi]

Summary

Split off of D67120.

Add the profile guided size optimization instrumentation / queries in the code
gen or target passes. This doesn't enable the size optimizations in those passes
yet as they are currently disabled in shouldOptimizeForSize (for non-IR pass
queries).

A second try after reverted D71072.

[hjyamauchi]

The diff from D71072 is MachineOptimizationRemarkEmitter.h and AsmPrinter.cpp around line 1694.

--- a/llvm/include/llvm/CodeGen/MachineOptimizationRemarkEmitter.h
+++ b/llvm/include/llvm/CodeGen/MachineOptimizationRemarkEmitter.h
@@ -182,6 +182,10 @@ public:
     }
   }
 
+  MachineBlockFrequencyInfo *getBFI() {
+    return MBFI;
+  }
+
 private:
   MachineFunction &MF;
 
--- a/llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp
+++ b/llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp
@@ -1692,7 +1692,10 @@ void AsmPrinter::SetupMachineFunction(MachineFunction &MF) {
   ORE = &getAnalysis<MachineOptimizationRemarkEmitterPass>().getORE();
   PSI = &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
   MBFI = (PSI && PSI->hasProfileSummary()) ?
-         &getAnalysis<LazyMachineBlockFrequencyInfoPass>().getBFI() :
+         // ORE conditionally computes MBFI. If available, use it, otherwise
+         // request it.
+         (ORE->getBFI() ? ORE->getBFI() :
+          &getAnalysis<LazyMachineBlockFrequencyInfoPass>().getBFI()) :
          nullptr;
 }

[davidxl]

lgtm

llvm/include/llvm/CodeGen/AsmPrinter.h

 class DwarfDebug;
 class GCMetadataPrinter;
 class GCStrategy;
 class GlobalIndirectSymbol;
 class GlobalObject;
 class GlobalValue;
 class GlobalVariable;
 class MachineBasicBlock;
+class MachineBlockFrequencyInfo;
 class MachineConstantPoolValue;
 class MachineDominatorTree;
 class MachineFunction;
 class MachineInstr;
 class MachineJumpTableInfo;
 class MachineLoopInfo;
 class MachineModuleInfo;
 class MachineOptimizationRemarkEmitter;
 class MCAsmInfo;
 class MCCFIInstruction;
 struct MCCodePaddingContext;
 class MCContext;
 class MCExpr;
 class MCInst;
 class MCSection;
 class MCStreamer;
 class MCSubtargetInfo;
 class MCSymbol;
 class MCTargetOptions;
 class MDNode;
 class Module;
+class ProfileSummaryInfo;
 class raw_ostream;
 class RemarkStreamer;
 class StackMaps;
 class TargetLoweringObjectFile;
 class TargetMachine;
 
 /// This class is intended to be used as a driving class for all asm writers.
 class AsmPrinter : public MachineFunctionPass {
public:
   MachineDominatorTree *MDT = nullptr;
 
   /// This is a pointer to the current MachineLoopInfo.
   MachineLoopInfo *MLI = nullptr;
 
   /// Optimization remark emitter.
   MachineOptimizationRemarkEmitter *ORE;
 
+  MachineBlockFrequencyInfo *MBFI;
+
+  ProfileSummaryInfo *PSI;
+
   /// The symbol for the current function. This is recalculated at the beginning
   /// of each call to runOnMachineFunction().
   MCSymbol *CurrentFnSym = nullptr;
 
   /// The symbol for the current function descriptor on AIX. This is created
   /// at the beginning of each call to SetupMachineFunction().
   MCSymbol *CurrentFnDescSym = nullptr;
 

llvm/include/llvm/CodeGen/MachineOptimizationRemarkEmitter.h

if (MF.getFunction().getContext().getRemarkStreamer() ||
             .getContext()
             .getDiagHandlerPtr()
             ->isAnyRemarkEnabled()) {
       auto R = RemarkBuilder();
       emit((DiagnosticInfoOptimizationBase &)R);
     }
   }
 
+  MachineBlockFrequencyInfo *getBFI() {
+    return MBFI;
+  }
+
 private:
   MachineFunction &MF;
 
   /// MBFI is only set if hotness is requested.
   MachineBlockFrequencyInfo *MBFI;
 
   /// Compute hotness from IR value (currently assumed to be a block) if PGO is
   /// available.

llvm/include/llvm/CodeGen/TailDuplicator.h

 #include "llvm/ADT/SmallVector.h"
 #include "llvm/CodeGen/TargetInstrInfo.h"
 #include <utility>
 #include <vector>
 
 namespace llvm {
 
 class MachineBasicBlock;
+class MachineBlockFrequencyInfo;
 class MachineBranchProbabilityInfo;
 class MachineFunction;
 class MachineInstr;
 class MachineModuleInfo;
 class MachineRegisterInfo;
+class ProfileSummaryInfo;
 class TargetRegisterInfo;
 
 /// Utility class to perform tail duplication.
 class TailDuplicator {
   const TargetInstrInfo *TII;
   const TargetRegisterInfo *TRI;
   const MachineBranchProbabilityInfo *MBPI;
   const MachineModuleInfo *MMI;
   MachineRegisterInfo *MRI;
   MachineFunction *MF;
+  const MachineBlockFrequencyInfo *MBFI;
+  ProfileSummaryInfo *PSI;
   bool PreRegAlloc;
   bool LayoutMode;
   unsigned TailDupSize;
 
   // A list of virtual registers for which to update SSA form.
   SmallVector<unsigned, 16> SSAUpdateVRs;
 
   // For each virtual register in SSAUpdateVals keep a list of source virtual
public:
   /// @param MBPI - Branch Probability Info. Used to propagate correct
   ///     probabilities when modifying the CFG.
   /// @param LayoutMode - When true, don't use the existing layout to make
   ///     decisions.
   /// @param TailDupSize - Maxmimum size of blocks to tail-duplicate. Zero
   ///     default implies using the command line value TailDupSize.
   void initMF(MachineFunction &MF, bool PreRegAlloc,
               const MachineBranchProbabilityInfo *MBPI,
+              const MachineBlockFrequencyInfo *MBFI,
+              ProfileSummaryInfo *PSI,
               bool LayoutMode, unsigned TailDupSize = 0);
 
   bool tailDuplicateBlocks();
   static bool isSimpleBB(MachineBasicBlock *TailBB);
   bool shouldTailDuplicate(bool IsSimple, MachineBasicBlock &TailBB);
 
   /// Returns true if TailBB can successfully be duplicated into PredBB
   bool canTailDuplicate(MachineBasicBlock *TailBB, MachineBasicBlock *PredBB);

llvm/lib/CodeGen/AsmPrinter/AsmPrinter.cpp

 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/Statistic.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/ADT/Triple.h"
 #include "llvm/ADT/Twine.h"
 #include "llvm/Analysis/ConstantFolding.h"
 #include "llvm/Analysis/EHPersonalities.h"
 #include "llvm/Analysis/OptimizationRemarkEmitter.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
 #include "llvm/BinaryFormat/COFF.h"
 #include "llvm/BinaryFormat/Dwarf.h"
 #include "llvm/BinaryFormat/ELF.h"
 #include "llvm/CodeGen/GCMetadata.h"
 #include "llvm/CodeGen/GCMetadataPrinter.h"
 #include "llvm/CodeGen/GCStrategy.h"
+#include "llvm/CodeGen/LazyMachineBlockFrequencyInfo.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
+#include "llvm/CodeGen/MachineBlockFrequencyInfo.h"
 #include "llvm/CodeGen/MachineConstantPool.h"
 #include "llvm/CodeGen/MachineDominators.h"
 #include "llvm/CodeGen/MachineFrameInfo.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineInstr.h"
 #include "llvm/CodeGen/MachineInstrBundle.h"
 #include "llvm/CodeGen/MachineJumpTableInfo.h"
 #include "llvm/CodeGen/MachineLoopInfo.h"
 #include "llvm/CodeGen/MachineMemOperand.h"
 #include "llvm/CodeGen/MachineModuleInfo.h"
 #include "llvm/CodeGen/MachineModuleInfoImpls.h"
 #include "llvm/CodeGen/MachineOperand.h"
 #include "llvm/CodeGen/MachineOptimizationRemarkEmitter.h"
+#include "llvm/CodeGen/MachineSizeOpts.h"
 #include "llvm/CodeGen/StackMaps.h"
 #include "llvm/CodeGen/TargetFrameLowering.h"
 #include "llvm/CodeGen/TargetInstrInfo.h"
 #include "llvm/CodeGen/TargetLowering.h"
 #include "llvm/CodeGen/TargetOpcodes.h"
 #include "llvm/CodeGen/TargetRegisterInfo.h"
 #include "llvm/IR/BasicBlock.h"
 #include "llvm/IR/Comdat.h"

 }
 
 void AsmPrinter::getAnalysisUsage(AnalysisUsage &AU) const {
   AU.setPreservesAll();
   MachineFunctionPass::getAnalysisUsage(AU);
   AU.addRequired<MachineModuleInfoWrapperPass>();
   AU.addRequired<MachineOptimizationRemarkEmitterPass>();
   AU.addRequired<GCModuleInfo>();
+  AU.addRequired<LazyMachineBlockFrequencyInfoPass>();
+  AU.addRequired<ProfileSummaryInfoWrapperPass>();
 }
 
 bool AsmPrinter::doInitialization(Module &M) {
   auto *MMIWP = getAnalysisIfAvailable<MachineModuleInfoWrapperPass>();
   MMI = MMIWP ? &MMIWP->getMMI() : nullptr;
 
   // Initialize TargetLoweringObjectFile.
   const_cast<TargetLoweringObjectFile&>(getObjFileLowering())
void AsmPrinter::SetupMachineFunction(MachineFunction &MF) {
   if (needFuncLabelsForEHOrDebugInfo(MF, MMI) || NeedsLocalForSize ||
       MF.getTarget().Options.EmitStackSizeSection) {
     CurrentFnBegin = createTempSymbol("func_begin");
     if (NeedsLocalForSize)
       CurrentFnSymForSize = CurrentFnBegin;
   }
 
   ORE = &getAnalysis<MachineOptimizationRemarkEmitterPass>().getORE();
+  PSI = &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
+  MBFI = (PSI && PSI->hasProfileSummary()) ?
+         // ORE conditionally computes MBFI. If available, use it, otherwise
+         // request it.
+         (ORE->getBFI() ? ORE->getBFI() :
+          &getAnalysis<LazyMachineBlockFrequencyInfoPass>().getBFI()) :
+         nullptr;
 }
 
 namespace {
 
 // Keep track the alignment, constpool entries per Section.
   struct SectionCPs {
     MCSection *S;
     unsigned Alignment;
static void emitBasicBlockLoopComments(const MachineBasicBlock &MBB,
   OS << "Loop Header: Depth=" + Twine(Loop->getLoopDepth()) << '\n';
 
   PrintChildLoopComment(OS, Loop, AP.getFunctionNumber());
 }
 
 void AsmPrinter::setupCodePaddingContext(const MachineBasicBlock &MBB,
                                          MCCodePaddingContext &Context) const {
   assert(MF != nullptr && "Machine function must be valid");
+  bool OptForSize = MF->getFunction().hasOptSize() ||
+                    llvm::shouldOptimizeForSize(&MBB, PSI, MBFI);
   Context.IsPaddingActive = !MF->hasInlineAsm() &&
-                            !MF->getFunction().hasOptSize() &&
+                            !OptForSize &&
                             TM.getOptLevel() != CodeGenOpt::None;
   Context.IsBasicBlockReachableViaFallthrough =
       std::find(MBB.pred_begin(), MBB.pred_end(), MBB.getPrevNode()) !=
       MBB.pred_end();
   Context.IsBasicBlockReachableViaBranch =
       MBB.pred_size() > 0 && !isBlockOnlyReachableByFallthrough(&MBB);
 }
 

llvm/lib/CodeGen/BranchFolding.h

 
 class BasicBlock;
 class MachineBlockFrequencyInfo;
 class MachineBranchProbabilityInfo;
 class MachineFunction;
 class MachineLoopInfo;
 class MachineModuleInfo;
 class MachineRegisterInfo;
+class ProfileSummaryInfo;
 class raw_ostream;
 class TargetInstrInfo;
 class TargetRegisterInfo;
 
   class LLVM_LIBRARY_VISIBILITY BranchFolder {
   public:
     class MBFIWrapper;
 
     explicit BranchFolder(bool defaultEnableTailMerge,
                           bool CommonHoist,
                           MBFIWrapper &FreqInfo,
                           const MachineBranchProbabilityInfo &ProbInfo,
+                          ProfileSummaryInfo *PSI,
                           // Min tail length to merge. Defaults to commandline
                           // flag. Ignored for optsize.
                           unsigned MinTailLength = 0);
 
     /// Perhaps branch folding, tail merging and other CFG optimizations on the
     /// given function.  Block placement changes the layout and may create new
     /// tail merging opportunities.
     bool OptimizeFunction(MachineFunction &MF, const TargetInstrInfo *tii,
public:
       BlockFrequency getBlockFreq(const MachineBasicBlock *MBB) const;
       void setBlockFreq(const MachineBasicBlock *MBB, BlockFrequency F);
       raw_ostream &printBlockFreq(raw_ostream &OS,
                                   const MachineBasicBlock *MBB) const;
       raw_ostream &printBlockFreq(raw_ostream &OS,
                                   const BlockFrequency Freq) const;
       void view(const Twine &Name, bool isSimple = true);
       uint64_t getEntryFreq() const;
+      const MachineBlockFrequencyInfo &getMBFI() { return MBFI; }
 
     private:
       const MachineBlockFrequencyInfo &MBFI;
       DenseMap<const MachineBasicBlock *, BlockFrequency> MergedBBFreq;
     };
 
   private:
     MBFIWrapper &MBBFreqInfo;
     const MachineBranchProbabilityInfo &MBPI;
+    ProfileSummaryInfo *PSI;
 
     bool TailMergeBlocks(MachineFunction &MF);
     bool TryTailMergeBlocks(MachineBasicBlock* SuccBB,
                        MachineBasicBlock* PredBB,
                        unsigned MinCommonTailLength);
     void setCommonTailEdgeWeights(MachineBasicBlock &TailMBB);
 
     /// Delete the instruction OldInst and everything after it, replacing it

llvm/lib/CodeGen/BranchFolding.cpp

 #include "BranchFolding.h"
 #include "llvm/ADT/BitVector.h"
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/SmallSet.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/Statistic.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
 #include "llvm/CodeGen/Analysis.h"
 #include "llvm/CodeGen/LivePhysRegs.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineBlockFrequencyInfo.h"
 #include "llvm/CodeGen/MachineBranchProbabilityInfo.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineInstr.h"
 #include "llvm/CodeGen/MachineInstrBuilder.h"
 #include "llvm/CodeGen/MachineJumpTableInfo.h"
 #include "llvm/CodeGen/MachineLoopInfo.h"
 #include "llvm/CodeGen/MachineModuleInfo.h"
 #include "llvm/CodeGen/MachineOperand.h"
 #include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/CodeGen/MachineSizeOpts.h"
 #include "llvm/CodeGen/TargetInstrInfo.h"
 #include "llvm/CodeGen/TargetOpcodes.h"
 #include "llvm/CodeGen/TargetPassConfig.h"
 #include "llvm/CodeGen/TargetRegisterInfo.h"
 #include "llvm/CodeGen/TargetSubtargetInfo.h"
 #include "llvm/IR/DebugInfoMetadata.h"
 #include "llvm/IR/DebugLoc.h"
 #include "llvm/IR/Function.h"
public:
 
     explicit BranchFolderPass(): MachineFunctionPass(ID) {}
 
     bool runOnMachineFunction(MachineFunction &MF) override;
 
     void getAnalysisUsage(AnalysisUsage &AU) const override {
       AU.addRequired<MachineBlockFrequencyInfo>();
       AU.addRequired<MachineBranchProbabilityInfo>();
+      AU.addRequired<ProfileSummaryInfoWrapperPass>();
       AU.addRequired<TargetPassConfig>();
       MachineFunctionPass::getAnalysisUsage(AU);
     }
   };
 
 } // end anonymous namespace
 
 char BranchFolderPass::ID = 0;
bool BranchFolderPass::runOnMachineFunction(MachineFunction &MF) {
   TargetPassConfig *PassConfig = &getAnalysis<TargetPassConfig>();
   // TailMerge can create jump into if branches that make CFG irreducible for
   // HW that requires structurized CFG.
   bool EnableTailMerge = !MF.getTarget().requiresStructuredCFG() &&
                          PassConfig->getEnableTailMerge();
   BranchFolder::MBFIWrapper MBBFreqInfo(
       getAnalysis<MachineBlockFrequencyInfo>());
   BranchFolder Folder(EnableTailMerge, /*CommonHoist=*/true, MBBFreqInfo,
-                      getAnalysis<MachineBranchProbabilityInfo>());
+                      getAnalysis<MachineBranchProbabilityInfo>(),
+                      &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI());
   auto *MMIWP = getAnalysisIfAvailable<MachineModuleInfoWrapperPass>();
   return Folder.OptimizeFunction(
       MF, MF.getSubtarget().getInstrInfo(), MF.getSubtarget().getRegisterInfo(),
       MMIWP ? &MMIWP->getMMI() : nullptr);
 }
 
 BranchFolder::BranchFolder(bool defaultEnableTailMerge, bool CommonHoist,
                            MBFIWrapper &FreqInfo,
                            const MachineBranchProbabilityInfo &ProbInfo,
+                           ProfileSummaryInfo *PSI,
                            unsigned MinTailLength)
     : EnableHoistCommonCode(CommonHoist), MinCommonTailLength(MinTailLength),
-      MBBFreqInfo(FreqInfo), MBPI(ProbInfo) {
+      MBBFreqInfo(FreqInfo), MBPI(ProbInfo), PSI(PSI) {
   if (MinCommonTailLength == 0)
     MinCommonTailLength = TailMergeSize;
   switch (FlagEnableTailMerge) {
   case cl::BOU_UNSET: EnableTailMerge = defaultEnableTailMerge; break;
   case cl::BOU_TRUE: EnableTailMerge = true; break;
   case cl::BOU_FALSE: EnableTailMerge = false; break;
   }
 }

 ///                 thresholds apply to prevent undoing tail-duplication.
 static bool
 ProfitableToMerge(MachineBasicBlock *MBB1, MachineBasicBlock *MBB2,
                   unsigned MinCommonTailLength, unsigned &CommonTailLen,
                   MachineBasicBlock::iterator &I1,
                   MachineBasicBlock::iterator &I2, MachineBasicBlock *SuccBB,
                   MachineBasicBlock *PredBB,
                   DenseMap<const MachineBasicBlock *, int> &EHScopeMembership,
-                  bool AfterPlacement) {
+                  bool AfterPlacement,
+                  BranchFolder::MBFIWrapper &MBBFreqInfo,
+                  ProfileSummaryInfo *PSI) {
   // It is never profitable to tail-merge blocks from two different EH scopes.
   if (!EHScopeMembership.empty()) {
     auto EHScope1 = EHScopeMembership.find(MBB1);
     assert(EHScope1 != EHScopeMembership.end());
     auto EHScope2 = EHScopeMembership.find(MBB2);
     assert(EHScope2 != EHScopeMembership.end());
     if (EHScope1->second != EHScope2->second)
       return false;
ProfitableToMerge(MachineBasicBlock *MBB1, MachineBasicBlock *MBB2,
   if (EffectiveTailLen >= MinCommonTailLength)
     return true;
 
   // If we are optimizing for code size, 2 instructions in common is enough if
   // we don't have to split a block.  At worst we will be introducing 1 new
   // branch instruction, which is likely to be smaller than the 2
   // instructions that would be deleted in the merge.
   MachineFunction *MF = MBB1->getParent();
-  return EffectiveTailLen >= 2 && MF->getFunction().hasOptSize() &&
+  bool OptForSize =
+      MF->getFunction().hasOptSize() ||
+      (llvm::shouldOptimizeForSize(MBB1, PSI, &MBBFreqInfo.getMBFI()) &&
+       llvm::shouldOptimizeForSize(MBB2, PSI, &MBBFreqInfo.getMBFI()));
+  return EffectiveTailLen >= 2 && OptForSize &&
          (FullBlockTail1 || FullBlockTail2);
 }
 
 unsigned BranchFolder::ComputeSameTails(unsigned CurHash,
                                         unsigned MinCommonTailLength,
                                         MachineBasicBlock *SuccBB,
                                         MachineBasicBlock *PredBB) {
   unsigned maxCommonTailLength = 0U;
   SameTails.clear();
   MachineBasicBlock::iterator TrialBBI1, TrialBBI2;
   MPIterator HighestMPIter = std::prev(MergePotentials.end());
   for (MPIterator CurMPIter = std::prev(MergePotentials.end()),
                   B = MergePotentials.begin();
        CurMPIter != B && CurMPIter->getHash() == CurHash; --CurMPIter) {
     for (MPIterator I = std::prev(CurMPIter); I->getHash() == CurHash; --I) {
       unsigned CommonTailLen;
       if (ProfitableToMerge(CurMPIter->getBlock(), I->getBlock(),
                             MinCommonTailLength,
                             CommonTailLen, TrialBBI1, TrialBBI2,
                             SuccBB, PredBB,
                             EHScopeMembership,
-                            AfterBlockPlacement)) {
+                            AfterBlockPlacement, MBBFreqInfo, PSI)) {
         if (CommonTailLen > maxCommonTailLength) {
           SameTails.clear();
           maxCommonTailLength = CommonTailLen;
           HighestMPIter = CurMPIter;
           SameTails.push_back(SameTailElt(CurMPIter, TrialBBI1));
         }
         if (HighestMPIter == CurMPIter &&
             CommonTailLen == maxCommonTailLength)
if (MBB->succ_empty() && !PriorCond.empty() && !PriorFBB &&
           MadeChange = true;
           ++NumBranchOpts;
           return MadeChange;
         }
       }
     }
   }
 
-  if (!IsEmptyBlock(MBB) && MBB->pred_size() == 1 &&
-      MF.getFunction().hasOptSize()) {
+  bool OptForSize =
+      MF.getFunction().hasOptSize() ||
+      llvm::shouldOptimizeForSize(MBB, PSI, &MBBFreqInfo.getMBFI());
+  if (!IsEmptyBlock(MBB) && MBB->pred_size() == 1 && OptForSize) {
     // Changing "Jcc foo; foo: jmp bar;" into "Jcc bar;" might change the branch
     // direction, thereby defeating careful block placement and regressing
     // performance. Therefore, only consider this for optsize functions.
     MachineInstr &TailCall = *MBB->getFirstNonDebugInstr();
     if (TII->isUnconditionalTailCall(TailCall)) {
       MachineBasicBlock *Pred = *MBB->pred_begin();
       MachineBasicBlock *PredTBB = nullptr, *PredFBB = nullptr;
       SmallVector<MachineOperand, 4> PredCond;

llvm/lib/CodeGen/CodeGenPrepare.cpp

 #include "llvm/Support/MathExtras.h"
 #include "llvm/Support/raw_ostream.h"
 #include "llvm/Target/TargetMachine.h"
 #include "llvm/Target/TargetOptions.h"
 #include "llvm/Transforms/Utils/BasicBlockUtils.h"
 #include "llvm/Transforms/Utils/BypassSlowDivision.h"
 #include "llvm/Transforms/Utils/Local.h"
 #include "llvm/Transforms/Utils/SimplifyLibCalls.h"
+#include "llvm/Transforms/Utils/SizeOpts.h"
 #include <algorithm>
 #include <cassert>
 #include <cstdint>
 #include <iterator>
 #include <limits>
 #include <memory>
 #include <utility>
 #include <vector>
class CodeGenPrepare : public FunctionPass {
     const TargetSubtargetInfo *SubtargetInfo;
     const TargetLowering *TLI = nullptr;
     const TargetRegisterInfo *TRI;
     const TargetTransformInfo *TTI = nullptr;
     const TargetLibraryInfo *TLInfo;
     const LoopInfo *LI;
     std::unique_ptr<BlockFrequencyInfo> BFI;
     std::unique_ptr<BranchProbabilityInfo> BPI;
+    ProfileSummaryInfo *PSI;
 
     /// 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. The usage of WeakTrackingVH
class CodeGenPrepare : public FunctionPass {
     SmallSet<AssertingVH<Value>, 2> NewGEPBases;
 
     /// Map serial numbers to Large offset GEPs.
     DenseMap<AssertingVH<GetElementPtrInst>, int> LargeOffsetGEPID;
 
     /// Keep track of SExt promoted.
     ValueToSExts ValToSExtendedUses;
 
-    /// True if optimizing for size.
+    /// True if the function has the OptSize attribute.
     bool OptSize;
 
     /// DataLayout for the Function being processed.
     const DataLayout *DL = nullptr;
 
     /// Building the dominator tree can be expensive, so we only build it
     /// lazily and update it when required.
     std::unique_ptr<DominatorTree> DT;
if (auto *TPC = getAnalysisIfAvailable<TargetPassConfig>()) {
     TLI = SubtargetInfo->getTargetLowering();
     TRI = SubtargetInfo->getRegisterInfo();
   }
   TLInfo = &getAnalysis<TargetLibraryInfoWrapperPass>().getTLI(F);
   TTI = &getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
   LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
   BPI.reset(new BranchProbabilityInfo(F, *LI));
   BFI.reset(new BlockFrequencyInfo(F, *BPI, *LI));
+  PSI = &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
   OptSize = F.hasOptSize();
-
-  ProfileSummaryInfo *PSI =
-      &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
   if (ProfileGuidedSectionPrefix) {
     if (PSI->isFunctionHotInCallGraph(&F, *BFI))
       F.setSectionPrefix(".hot");
     else if (PSI->isFunctionColdInCallGraph(&F, *BFI))
       F.setSectionPrefix(".unlikely");
   }
 
   /// This optimization identifies DIV instructions that can be
   /// profitably bypassed and carried out with a shorter, faster divide.
   if (!OptSize && !PSI->hasHugeWorkingSetSize() && TLI &&
       TLI->isSlowDivBypassed()) {
     const DenseMap<unsigned int, unsigned int> &BypassWidths =
        TLI->getBypassSlowDivWidths();
     BasicBlock* BB = &*F.begin();
     while (BB != nullptr) {
       // bypassSlowDivision may create new BBs, but we don't want to reapply the
       // optimization to those blocks.
       BasicBlock* Next = BB->getNextNode();
+      // F.hasOptSize is already checked in the outer if statement.
+      if (!llvm::shouldOptimizeForSize(BB, PSI, BFI.get()))
         EverMadeChange |= bypassSlowDivision(BB, BypassWidths);
       BB = Next;
     }
   }
 
   // Eliminate blocks that contain only PHI nodes and an
   // unconditional branch.
   EverMadeChange |= eliminateMostlyEmptyBlocks(F);
 
if (MemIntrinsic *MI = dyn_cast<MemIntrinsic>(CI)) {
       }
     }
   }
 
   // If we have a cold call site, try to sink addressing computation into the
   // cold block.  This interacts with our handling for loads and stores to
   // ensure that we can fold all uses of a potential addressing computation
   // into their uses.  TODO: generalize this to work over profiling data
-  if (!OptSize && CI->hasFnAttr(Attribute::Cold))
+  bool OptForSize = OptSize || llvm::shouldOptimizeForSize(BB, PSI, BFI.get());
+  if (!OptForSize && CI->hasFnAttr(Attribute::Cold))
     for (auto &Arg : CI->arg_operands()) {
       if (!Arg->getType()->isPointerTy())
         continue;
       unsigned AS = Arg->getType()->getPointerAddressSpace();
       return optimizeMemoryInst(CI, Arg, Arg->getType(), AS);
     }
 
   IntrinsicInst *II = dyn_cast<IntrinsicInst>(CI);
class AddressingModeMatcher {
 
   // A GEP which has too large offset to be folded into the addressing mode.
   std::pair<AssertingVH<GetElementPtrInst>, int64_t> &LargeOffsetGEP;
 
   /// This is set to true when we should not do profitability checks.
   /// When true, IsProfitableToFoldIntoAddressingMode always returns true.
   bool IgnoreProfitability;
 
+  /// True if we are optimizing for size.
+  bool OptSize;
+
+  ProfileSummaryInfo *PSI;
+  BlockFrequencyInfo *BFI;
+
   AddressingModeMatcher(
       SmallVectorImpl<Instruction *> &AMI, const TargetLowering &TLI,
       const TargetRegisterInfo &TRI, Type *AT, unsigned AS, Instruction *MI,
       ExtAddrMode &AM, const SetOfInstrs &InsertedInsts,
       InstrToOrigTy &PromotedInsts, TypePromotionTransaction &TPT,
-      std::pair<AssertingVH<GetElementPtrInst>, int64_t> &LargeOffsetGEP)
+      std::pair<AssertingVH<GetElementPtrInst>, int64_t> &LargeOffsetGEP,
+      bool OptSize, ProfileSummaryInfo *PSI, BlockFrequencyInfo *BFI)
       : AddrModeInsts(AMI), TLI(TLI), TRI(TRI),
         DL(MI->getModule()->getDataLayout()), AccessTy(AT), AddrSpace(AS),
         MemoryInst(MI), AddrMode(AM), InsertedInsts(InsertedInsts),
-        PromotedInsts(PromotedInsts), TPT(TPT), LargeOffsetGEP(LargeOffsetGEP) {
+        PromotedInsts(PromotedInsts), TPT(TPT), LargeOffsetGEP(LargeOffsetGEP),
+        OptSize(OptSize), PSI(PSI), BFI(BFI) {
     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 TargetLowering &TLI, const TargetRegisterInfo &TRI,
         const SetOfInstrs &InsertedInsts, InstrToOrigTy &PromotedInsts,
         TypePromotionTransaction &TPT,
-        std::pair<AssertingVH<GetElementPtrInst>, int64_t> &LargeOffsetGEP) {
+        std::pair<AssertingVH<GetElementPtrInst>, int64_t> &LargeOffsetGEP,
+        bool OptSize, ProfileSummaryInfo *PSI, BlockFrequencyInfo *BFI) {
     ExtAddrMode Result;
 
     bool Success = AddressingModeMatcher(AddrModeInsts, TLI, TRI, AccessTy, AS,
                                          MemoryInst, Result, InsertedInsts,
-                                         PromotedInsts, TPT, LargeOffsetGEP)
+                                         PromotedInsts, TPT, LargeOffsetGEP,
+                                         OptSize, PSI, BFI)
                        .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 *Addr, unsigned Depth);

 
 /// 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 TargetLowering &TLI,
-    const TargetRegisterInfo &TRI, int SeenInsts = 0) {
+    const TargetRegisterInfo &TRI, bool OptSize, ProfileSummaryInfo *PSI,
+    BlockFrequencyInfo *BFI, int SeenInsts = 0) {
   // 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;
 
-  const bool OptSize = I->getFunction()->hasOptSize();
-
   // Loop over all the uses, recursively processing them.
   for (Use &U : I->uses()) {
     // Conservatively return true if we're seeing a large number or a deep chain
     // of users. This avoids excessive compilation times in pathological cases.
     if (SeenInsts++ >= MaxMemoryUsesToScan)
       return true;
 
     Instruction *UserI = cast<Instruction>(U.getUser());
if (AtomicCmpXchgInst *CmpX = dyn_cast<AtomicCmpXchgInst>(UserI)) {
         return true; // Storing addr, not into addr.
       MemoryUses.push_back(std::make_pair(CmpX, opNo));
       continue;
     }
 
     if (CallInst *CI = dyn_cast<CallInst>(UserI)) {
       // If this is a cold call, we can sink the addressing calculation into
       // the cold path.  See optimizeCallInst
-      if (!OptSize && CI->hasFnAttr(Attribute::Cold))
+      bool OptForSize = OptSize ||
+          llvm::shouldOptimizeForSize(CI->getParent(), PSI, BFI);
+      if (!OptForSize && CI->hasFnAttr(Attribute::Cold))
         continue;
 
       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, TLI, TRI))
         return true;
       continue;
     }
 
-    if (FindAllMemoryUses(UserI, MemoryUses, ConsideredInsts, TLI, TRI,
-                          SeenInsts))
+    if (FindAllMemoryUses(UserI, MemoryUses, ConsideredInsts, TLI, TRI, OptSize,
+                          PSI, BFI, SeenInsts))
       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 can have the address mode sunk into them,
   // we can remove the addressing mode and effectively trade one live register
   // for another (at worst.)  In this context, folding an addressing mode into
   // the use is just a particularly nice way of sinking it.
   SmallVector<std::pair<Instruction*,unsigned>, 16> MemoryUses;
   SmallPtrSet<Instruction*, 16> ConsideredInsts;
-  if (FindAllMemoryUses(I, MemoryUses, ConsideredInsts, TLI, TRI))
+  if (FindAllMemoryUses(I, MemoryUses, ConsideredInsts, TLI, TRI, OptSize,
+                        PSI, BFI))
     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 memory operation uses and see
   // if they could  *actually* fold the instruction.  The assumption is that
   // addressing modes are cheap and that duplicating the computation involved
   // many times is worthwhile, even on a fastpath. For sinking candidates
for (unsigned i = 0, e = MemoryUses.size(); i != e; ++i) {
     // *actually* cover the shared instruction.
     ExtAddrMode Result;
     std::pair<AssertingVH<GetElementPtrInst>, int64_t> LargeOffsetGEP(nullptr,
                                                                       0);
     TypePromotionTransaction::ConstRestorationPt LastKnownGood =
         TPT.getRestorationPoint();
     AddressingModeMatcher Matcher(
         MatchedAddrModeInsts, TLI, TRI, AddressAccessTy, AS, MemoryInst, Result,
-        InsertedInsts, PromotedInsts, TPT, LargeOffsetGEP);
+        InsertedInsts, PromotedInsts, TPT, LargeOffsetGEP, OptSize, PSI, BFI);
     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);
while (!worklist.empty()) {
     // For non-PHIs, determine the addressing mode being computed.  Note that
     // the result may differ depending on what other uses our candidate
     // addressing instructions might have.
     AddrModeInsts.clear();
     std::pair<AssertingVH<GetElementPtrInst>, int64_t> LargeOffsetGEP(nullptr,
                                                                       0);
     ExtAddrMode NewAddrMode = AddressingModeMatcher::Match(
         V, AccessTy, AddrSpace, MemoryInst, AddrModeInsts, *TLI, *TRI,
-        InsertedInsts, PromotedInsts, TPT, LargeOffsetGEP);
+        InsertedInsts, PromotedInsts, TPT, LargeOffsetGEP, OptSize, PSI,
+        BFI.get());
 
     GetElementPtrInst *GEP = LargeOffsetGEP.first;
     if (GEP && !NewGEPBases.count(GEP)) {
       // If splitting the underlying data structure can reduce the offset of a
       // GEP, collect the GEP.  Skip the GEPs that are the new bases of
       // previously split data structures.
       LargeOffsetGEPMap[GEP->getPointerOperand()].push_back(LargeOffsetGEP);
       if (LargeOffsetGEPID.find(GEP) == LargeOffsetGEPID.end())
bool CodeGenPrepare::optimizeShiftInst(BinaryOperator *Shift) {
   Shift->eraseFromParent();
   return true;
 }
 
 /// If we have a SelectInst that will likely profit from branch prediction,
 /// turn it into a branch.
 bool CodeGenPrepare::optimizeSelectInst(SelectInst *SI) {
   // If branch conversion isn't desirable, exit early.
-  if (DisableSelectToBranch || OptSize || !TLI)
+  if (DisableSelectToBranch ||
+      OptSize || llvm::shouldOptimizeForSize(SI->getParent(), PSI, BFI.get()) ||
+      !TLI)
     return false;
 
   // Find all consecutive select instructions that share the same condition.
   SmallVector<SelectInst *, 2> ASI;
   ASI.push_back(SI);
   for (BasicBlock::iterator It = ++BasicBlock::iterator(SI);
        It != SI->getParent()->end(); ++It) {
     SelectInst *I = dyn_cast<SelectInst>(&*It);

llvm/lib/CodeGen/ExpandMemCmp.cpp

 //===--- ExpandMemCmp.cpp - Expand memcmp() to load/stores ----------------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // This pass tries to expand memcmp() calls into optimally-sized loads and
 // compares for the target.
 //
 //===----------------------------------------------------------------------===//
 
 #include "llvm/ADT/Statistic.h"
 #include "llvm/Analysis/ConstantFolding.h"
+#include "llvm/Analysis/LazyBlockFrequencyInfo.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/Analysis/TargetTransformInfo.h"
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/CodeGen/TargetLowering.h"
 #include "llvm/CodeGen/TargetPassConfig.h"
 #include "llvm/CodeGen/TargetSubtargetInfo.h"
 #include "llvm/IR/IRBuilder.h"
 #include "llvm/InitializePasses.h"
+#include "llvm/Transforms/Utils/SizeOpts.h"
 
 using namespace llvm;
 
 #define DEBUG_TYPE "expandmemcmp"
 
 STATISTIC(NumMemCmpCalls, "Number of memcmp calls");
 STATISTIC(NumMemCmpNotConstant, "Number of memcmp calls without constant size");
 STATISTIC(NumMemCmpGreaterThanMax,

 ///  %47 = zext i8 %45 to i32
 ///  %48 = sub i32 %46, %47
 ///  br label %endblock
 /// endblock:                                         ; preds = %res_block,
 /// %loadbb3
 ///  %phi.res = phi i32 [ %48, %loadbb3 ], [ %11, %res_block ]
 ///  ret i32 %phi.res
 static bool expandMemCmp(CallInst *CI, const TargetTransformInfo *TTI,
-                         const TargetLowering *TLI, const DataLayout *DL) {
+                         const TargetLowering *TLI, const DataLayout *DL,
+                         ProfileSummaryInfo *PSI, BlockFrequencyInfo *BFI) {
   NumMemCmpCalls++;
 
   // Early exit from expansion if -Oz.
   if (CI->getFunction()->hasMinSize())
     return false;
 
   // Early exit from expansion if size is not a constant.
   ConstantInt *SizeCast = dyn_cast<ConstantInt>(CI->getArgOperand(2));
   if (!SizeCast) {
     NumMemCmpNotConstant++;
     return false;
   }
   const uint64_t SizeVal = SizeCast->getZExtValue();
 
   if (SizeVal == 0) {
     return false;
   }
   // TTI call to check if target would like to expand memcmp. Also, get the
   // available load sizes.
   const bool IsUsedForZeroCmp = isOnlyUsedInZeroEqualityComparison(CI);
-  auto Options = TTI->enableMemCmpExpansion(CI->getFunction()->hasOptSize(),
+  bool OptForSize = CI->getFunction()->hasOptSize() ||
+                    llvm::shouldOptimizeForSize(CI->getParent(), PSI, BFI);
+  auto Options = TTI->enableMemCmpExpansion(OptForSize,
                                             IsUsedForZeroCmp);
   if (!Options) return false;
 
   if (MemCmpEqZeroNumLoadsPerBlock.getNumOccurrences())
     Options.NumLoadsPerBlock = MemCmpEqZeroNumLoadsPerBlock;
 
-  if (CI->getFunction()->hasOptSize() &&
+  if (OptForSize &&
       MaxLoadsPerMemcmpOptSize.getNumOccurrences())
     Options.MaxNumLoads = MaxLoadsPerMemcmpOptSize;
 
-  if (!CI->getFunction()->hasOptSize() && MaxLoadsPerMemcmp.getNumOccurrences())
+  if (!OptForSize && MaxLoadsPerMemcmp.getNumOccurrences())
     Options.MaxNumLoads = MaxLoadsPerMemcmp;
 
   MemCmpExpansion Expansion(CI, SizeVal, Options, IsUsedForZeroCmp, *DL);
 
   // Don't expand if this will require more loads than desired by the target.
   if (Expansion.getNumLoads() == 0) {
     NumMemCmpGreaterThanMax++;
     return false;
bool runOnFunction(Function &F) override {
     }
     const TargetLowering* TL =
         TPC->getTM<TargetMachine>().getSubtargetImpl(F)->getTargetLowering();
 
     const TargetLibraryInfo *TLI =
         &getAnalysis<TargetLibraryInfoWrapperPass>().getTLI(F);
     const TargetTransformInfo *TTI =
         &getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
-    auto PA = runImpl(F, TLI, TTI, TL);
+    auto *PSI = &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
+    auto *BFI = (PSI && PSI->hasProfileSummary()) ?
+           &getAnalysis<LazyBlockFrequencyInfoPass>().getBFI() :
+           nullptr;
+    auto PA = runImpl(F, TLI, TTI, TL, PSI, BFI);
     return !PA.areAllPreserved();
   }
 
 private:
   void getAnalysisUsage(AnalysisUsage &AU) const override {
     AU.addRequired<TargetLibraryInfoWrapperPass>();
     AU.addRequired<TargetTransformInfoWrapperPass>();
+    AU.addRequired<ProfileSummaryInfoWrapperPass>();
+    LazyBlockFrequencyInfoPass::getLazyBFIAnalysisUsage(AU);
     FunctionPass::getAnalysisUsage(AU);
   }
 
   PreservedAnalyses runImpl(Function &F, const TargetLibraryInfo *TLI,
                             const TargetTransformInfo *TTI,
-                            const TargetLowering* TL);
+                            const TargetLowering* TL,
+                            ProfileSummaryInfo *PSI, BlockFrequencyInfo *BFI);
   // Returns true if a change was made.
   bool runOnBlock(BasicBlock &BB, const TargetLibraryInfo *TLI,
                   const TargetTransformInfo *TTI, const TargetLowering* TL,
-                  const DataLayout& DL);
+                  const DataLayout& DL, ProfileSummaryInfo *PSI,
+                  BlockFrequencyInfo *BFI);
 };
 
 bool ExpandMemCmpPass::runOnBlock(
     BasicBlock &BB, const TargetLibraryInfo *TLI,
     const TargetTransformInfo *TTI, const TargetLowering* TL,
-    const DataLayout& DL) {
+    const DataLayout& DL, ProfileSummaryInfo *PSI, BlockFrequencyInfo *BFI) {
   for (Instruction& I : BB) {
     CallInst *CI = dyn_cast<CallInst>(&I);
     if (!CI) {
       continue;
     }
     LibFunc Func;
     if (TLI->getLibFunc(ImmutableCallSite(CI), Func) &&
         (Func == LibFunc_memcmp || Func == LibFunc_bcmp) &&
-        expandMemCmp(CI, TTI, TL, &DL)) {
+        expandMemCmp(CI, TTI, TL, &DL, PSI, BFI)) {
       return true;
     }
   }
   return false;
 }
 
 
 PreservedAnalyses ExpandMemCmpPass::runImpl(
     Function &F, const TargetLibraryInfo *TLI, const TargetTransformInfo *TTI,
-    const TargetLowering* TL) {
+    const TargetLowering* TL, ProfileSummaryInfo *PSI,
+    BlockFrequencyInfo *BFI) {
   const DataLayout& DL = F.getParent()->getDataLayout();
   bool MadeChanges = false;
   for (auto BBIt = F.begin(); BBIt != F.end();) {
-    if (runOnBlock(*BBIt, TLI, TTI, TL, DL)) {
+    if (runOnBlock(*BBIt, TLI, TTI, TL, DL, PSI, BFI)) {
       MadeChanges = true;
       // If changes were made, restart the function from the beginning, since
       // the structure of the function was changed.
       BBIt = F.begin();
     } else {
       ++BBIt;
     }
   }
   return MadeChanges ? PreservedAnalyses::none() : PreservedAnalyses::all();
 }
 
 } // namespace
 
 char ExpandMemCmpPass::ID = 0;
 INITIALIZE_PASS_BEGIN(ExpandMemCmpPass, "expandmemcmp",
                       "Expand memcmp() to load/stores", false, false)
 INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
+INITIALIZE_PASS_DEPENDENCY(LazyBlockFrequencyInfoPass)
+INITIALIZE_PASS_DEPENDENCY(ProfileSummaryInfoWrapperPass)
 INITIALIZE_PASS_END(ExpandMemCmpPass, "expandmemcmp",
                     "Expand memcmp() to load/stores", false, false)
 
 FunctionPass *llvm::createExpandMemCmpPass() {
   return new ExpandMemCmpPass();
 }

llvm/lib/CodeGen/IfConversion.cpp

 #include "BranchFolding.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/ScopeExit.h"
 #include "llvm/ADT/SmallSet.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/SparseSet.h"
 #include "llvm/ADT/Statistic.h"
 #include "llvm/ADT/iterator_range.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
 #include "llvm/CodeGen/LivePhysRegs.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineBlockFrequencyInfo.h"
 #include "llvm/CodeGen/MachineBranchProbabilityInfo.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineInstr.h"
 #include "llvm/CodeGen/MachineInstrBuilder.h"
public:
     IfConverter(std::function<bool(const MachineFunction &)> Ftor = nullptr)
         : MachineFunctionPass(ID), PredicateFtor(std::move(Ftor)) {
       initializeIfConverterPass(*PassRegistry::getPassRegistry());
     }
 
     void getAnalysisUsage(AnalysisUsage &AU) const override {
       AU.addRequired<MachineBlockFrequencyInfo>();
       AU.addRequired<MachineBranchProbabilityInfo>();
+      AU.addRequired<ProfileSummaryInfoWrapperPass>();
       MachineFunctionPass::getAnalysisUsage(AU);
     }
 
     bool runOnMachineFunction(MachineFunction &MF) override;
 
     MachineFunctionProperties getRequiredProperties() const override {
       return MachineFunctionProperties().set(
           MachineFunctionProperties::Property::NoVRegs);

 } // end anonymous namespace
 
 char IfConverter::ID = 0;
 
 char &llvm::IfConverterID = IfConverter::ID;
 
 INITIALIZE_PASS_BEGIN(IfConverter, DEBUG_TYPE, "If Converter", false, false)
 INITIALIZE_PASS_DEPENDENCY(MachineBranchProbabilityInfo)
+INITIALIZE_PASS_DEPENDENCY(ProfileSummaryInfoWrapperPass)
 INITIALIZE_PASS_END(IfConverter, DEBUG_TYPE, "If Converter", false, false)
 
 bool IfConverter::runOnMachineFunction(MachineFunction &MF) {
   if (skipFunction(MF.getFunction()) || (PredicateFtor && !PredicateFtor(MF)))
     return false;
 
   const TargetSubtargetInfo &ST = MF.getSubtarget();
   TLI = ST.getTargetLowering();
   TII = ST.getInstrInfo();
   TRI = ST.getRegisterInfo();
   BranchFolder::MBFIWrapper MBFI(getAnalysis<MachineBlockFrequencyInfo>());
   MBPI = &getAnalysis<MachineBranchProbabilityInfo>();
+  ProfileSummaryInfo *PSI =
+      &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
   MRI = &MF.getRegInfo();
   SchedModel.init(&ST);
 
   if (!TII) return false;
 
   PreRegAlloc = MRI->isSSA();
 
   bool BFChange = false;
   if (!PreRegAlloc) {
     // Tail merge tend to expose more if-conversion opportunities.
-    BranchFolder BF(true, false, MBFI, *MBPI);
+    BranchFolder BF(true, false, MBFI, *MBPI, PSI);
     auto *MMIWP = getAnalysisIfAvailable<MachineModuleInfoWrapperPass>();
     BFChange = BF.OptimizeFunction(
         MF, TII, ST.getRegisterInfo(),
         MMIWP ? &MMIWP->getMMI() : nullptr);
   }
 
   LLVM_DEBUG(dbgs() << "\nIfcvt: function (" << ++FnNum << ") \'"
                     << MF.getName() << "\'");
if (!Change)
       break;
     MadeChange |= Change;
   }
 
   Tokens.clear();
   BBAnalysis.clear();
 
   if (MadeChange && IfCvtBranchFold) {
-    BranchFolder BF(false, false, MBFI, *MBPI);
+    BranchFolder BF(false, false, MBFI, *MBPI, PSI);
     auto *MMIWP = getAnalysisIfAvailable<MachineModuleInfoWrapperPass>();
     BF.OptimizeFunction(
         MF, TII, MF.getSubtarget().getRegisterInfo(),
         MMIWP ? &MMIWP->getMMI() : nullptr);
   }
 
   MadeChange |= BFChange;
   return MadeChange;

llvm/lib/CodeGen/MachineBlockPlacement.cpp

 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SetVector.h"
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/Statistic.h"
 #include "llvm/Analysis/BlockFrequencyInfoImpl.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineBlockFrequencyInfo.h"
 #include "llvm/CodeGen/MachineBranchProbabilityInfo.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineLoopInfo.h"
 #include "llvm/CodeGen/MachineModuleInfo.h"
 #include "llvm/CodeGen/MachinePostDominators.h"
+#include "llvm/CodeGen/MachineSizeOpts.h"
 #include "llvm/CodeGen/TailDuplicator.h"
 #include "llvm/CodeGen/TargetInstrInfo.h"
 #include "llvm/CodeGen/TargetLowering.h"
 #include "llvm/CodeGen/TargetPassConfig.h"
 #include "llvm/CodeGen/TargetSubtargetInfo.h"
 #include "llvm/IR/DebugLoc.h"
 #include "llvm/IR/Function.h"
 #include "llvm/InitializePasses.h"
class MachineBlockPlacement : public MachineFunctionPass {
   const TargetInstrInfo *TII;
 
   /// A handle to the target's lowering info.
   const TargetLoweringBase *TLI;
 
   /// A handle to the post dominator tree.
   MachinePostDominatorTree *MPDT;
 
+  ProfileSummaryInfo *PSI;
+
   /// Duplicator used to duplicate tails during placement.
   ///
   /// Placement decisions can open up new tail duplication opportunities, but
   /// since tail duplication affects placement decisions of later blocks, it
   /// must be done inline.
   TailDuplicator TailDup;
 
   /// Allocator and owner of BlockChain structures.
public:
   }
 
   void getAnalysisUsage(AnalysisUsage &AU) const override {
     AU.addRequired<MachineBranchProbabilityInfo>();
     AU.addRequired<MachineBlockFrequencyInfo>();
     if (TailDupPlacement)
       AU.addRequired<MachinePostDominatorTree>();
     AU.addRequired<MachineLoopInfo>();
+    AU.addRequired<ProfileSummaryInfoWrapperPass>();
     AU.addRequired<TargetPassConfig>();
     MachineFunctionPass::getAnalysisUsage(AU);
   }
 };
 
 } // end anonymous namespace
 
 char MachineBlockPlacement::ID = 0;
 
 char &llvm::MachineBlockPlacementID = MachineBlockPlacement::ID;
 
 INITIALIZE_PASS_BEGIN(MachineBlockPlacement, DEBUG_TYPE,
                       "Branch Probability Basic Block Placement", false, false)
 INITIALIZE_PASS_DEPENDENCY(MachineBranchProbabilityInfo)
 INITIALIZE_PASS_DEPENDENCY(MachineBlockFrequencyInfo)
 INITIALIZE_PASS_DEPENDENCY(MachinePostDominatorTree)
 INITIALIZE_PASS_DEPENDENCY(MachineLoopInfo)
+INITIALIZE_PASS_DEPENDENCY(ProfileSummaryInfoWrapperPass)
 INITIALIZE_PASS_END(MachineBlockPlacement, DEBUG_TYPE,
                     "Branch Probability Basic Block Placement", false, false)
 
 #ifndef NDEBUG
 /// Helper to print the name of a MBB.
 ///
 /// Only used by debug logging.
 static std::string getBlockName(const MachineBasicBlock *BB) {
MachineBlockPlacement::findBestLoopTop(const MachineLoop &L,
                                        const BlockFilterSet &LoopBlockSet) {
   // Placing the latch block before the header may introduce an extra branch
   // that skips this block the first time the loop is executed, which we want
   // to avoid when optimising for size.
   // FIXME: in theory there is a case that does not introduce a new branch,
   // i.e. when the layout predecessor does not fallthrough to the loop header.
   // In practice this never happens though: there always seems to be a preheader
   // that can fallthrough and that is also placed before the header.
-  if (F->getFunction().hasOptSize())
+  bool OptForSize = F->getFunction().hasOptSize() ||
+                    llvm::shouldOptimizeForSize(L.getHeader(), PSI,
+                                                &MBFI->getMBFI());
+  if (OptForSize)
     return L.getHeader();
 
   MachineBasicBlock *OldTop = nullptr;
   MachineBasicBlock *NewTop = L.getHeader();
   while (NewTop != OldTop) {
     OldTop = NewTop;
     NewTop = findBestLoopTopHelper(OldTop, L, LoopBlockSet);
     if (NewTop != OldTop)
for (MachineBasicBlock *ChainBB : FunctionChain) {
 
     // If the block is cold relative to its loop header, don't align it
     // regardless of what edges into the block exist.
     MachineBasicBlock *LoopHeader = L->getHeader();
     BlockFrequency LoopHeaderFreq = MBFI->getBlockFreq(LoopHeader);
     if (Freq < (LoopHeaderFreq * ColdProb))
       continue;
 
+    // If the global profiles indicates so, don't align it.
+    if (llvm::shouldOptimizeForSize(ChainBB, PSI, &MBFI->getMBFI()) &&
+        !TLI->alignLoopsWithOptSize())
+      continue;
+
     // Check for the existence of a non-layout predecessor which would benefit
     // from aligning this block.
     MachineBasicBlock *LayoutPred =
         &*std::prev(MachineFunction::iterator(ChainBB));
 
     // Force alignment if all the predecessors are jumps. We already checked
     // that the block isn't cold above.
     if (!LayoutPred->isSuccessor(ChainBB)) {
bool MachineBlockPlacement::runOnMachineFunction(MachineFunction &MF) {
   F = &MF;
   MBPI = &getAnalysis<MachineBranchProbabilityInfo>();
   MBFI = std::make_unique<BranchFolder::MBFIWrapper>(
       getAnalysis<MachineBlockFrequencyInfo>());
   MLI = &getAnalysis<MachineLoopInfo>();
   TII = MF.getSubtarget().getInstrInfo();
   TLI = MF.getSubtarget().getTargetLowering();
   MPDT = nullptr;
+  PSI = &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
 
   // Initialize PreferredLoopExit to nullptr here since it may never be set if
   // there are no MachineLoops.
   PreferredLoopExit = nullptr;
 
   assert(BlockToChain.empty() &&
          "BlockToChain map should be empty before starting placement.");
   assert(ComputedEdges.empty() &&
if (PassConfig->getOptLevel() >= CodeGenOpt::Aggressive) {
     // Do this unless only the regular threshold is explicitly set.
     if (TailDupPlacementThreshold.getNumOccurrences() == 0 ||
         TailDupPlacementAggressiveThreshold.getNumOccurrences() != 0)
       TailDupSize = TailDupPlacementAggressiveThreshold;
   }
 
   if (allowTailDupPlacement()) {
     MPDT = &getAnalysis<MachinePostDominatorTree>();
-    if (MF.getFunction().hasOptSize())
+    bool OptForSize = MF.getFunction().hasOptSize() ||
+                      llvm::shouldOptimizeForSize(&MF, PSI, &MBFI->getMBFI());
+    if (OptForSize)
       TailDupSize = 1;
     bool PreRegAlloc = false;
-    TailDup.initMF(MF, PreRegAlloc, MBPI, /* LayoutMode */ true, TailDupSize);
+    TailDup.initMF(MF, PreRegAlloc, MBPI, &MBFI->getMBFI(), PSI,
+                   /* LayoutMode */ true, TailDupSize);
     precomputeTriangleChains();
   }
 
   buildCFGChains();
 
   // Changing the layout can create new tail merging opportunities.
   // TailMerge can create jump into if branches that make CFG irreducible for
   // HW that requires structured CFG.
   bool EnableTailMerge = !MF.getTarget().requiresStructuredCFG() &&
                          PassConfig->getEnableTailMerge() &&
                          BranchFoldPlacement;
   // No tail merging opportunities if the block number is less than four.
   if (MF.size() > 3 && EnableTailMerge) {
     unsigned TailMergeSize = TailDupSize + 1;
     BranchFolder BF(/*EnableTailMerge=*/true, /*CommonHoist=*/false, *MBFI,
-                    *MBPI, TailMergeSize);
+                    *MBPI, PSI, TailMergeSize);
 
     auto *MMIWP = getAnalysisIfAvailable<MachineModuleInfoWrapperPass>();
     if (BF.OptimizeFunction(MF, TII, MF.getSubtarget().getRegisterInfo(),
                             MMIWP ? &MMIWP->getMMI() : nullptr, MLI,
                             /*AfterPlacement=*/true)) {
       // Redo the layout if tail merging creates/removes/moves blocks.
       BlockToChain.clear();
       ComputedEdges.clear();

llvm/lib/CodeGen/MachineCombiner.cpp

 //===---- MachineCombiner.cpp - Instcombining on SSA form machine code ----===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 // The machine combiner pass uses machine trace metrics to ensure the combined
 // instructions do not lengthen the critical path or the resource depth.
 //===----------------------------------------------------------------------===//
 
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/Statistic.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
+#include "llvm/CodeGen/LazyMachineBlockFrequencyInfo.h"
 #include "llvm/CodeGen/MachineDominators.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineLoopInfo.h"
 #include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/CodeGen/MachineSizeOpts.h"
 #include "llvm/CodeGen/MachineTraceMetrics.h"
 #include "llvm/CodeGen/Passes.h"
 #include "llvm/CodeGen/TargetInstrInfo.h"
 #include "llvm/CodeGen/TargetRegisterInfo.h"
 #include "llvm/CodeGen/TargetSchedule.h"
 #include "llvm/CodeGen/TargetSubtargetInfo.h"
 #include "llvm/InitializePasses.h"
 #include "llvm/Support/CommandLine.h"
class MachineCombiner : public MachineFunctionPass {
   const TargetSubtargetInfo *STI;
   const TargetInstrInfo *TII;
   const TargetRegisterInfo *TRI;
   MCSchedModel SchedModel;
   MachineRegisterInfo *MRI;
   MachineLoopInfo *MLI; // Current MachineLoopInfo
   MachineTraceMetrics *Traces;
   MachineTraceMetrics::Ensemble *MinInstr;
+  MachineBlockFrequencyInfo *MBFI;
+  ProfileSummaryInfo *PSI;
 
   TargetSchedModel TSchedModel;
 
   /// True if optimizing for code size.
   bool OptSize;
 
 public:
   static char ID;
   MachineCombiner() : MachineFunctionPass(ID) {
     initializeMachineCombinerPass(*PassRegistry::getPassRegistry());
   }
   void getAnalysisUsage(AnalysisUsage &AU) const override;
   bool runOnMachineFunction(MachineFunction &MF) override;
   StringRef getPassName() const override { return "Machine InstCombiner"; }
 
 private:
-  bool doSubstitute(unsigned NewSize, unsigned OldSize);
+  bool doSubstitute(unsigned NewSize, unsigned OldSize, bool OptForSize);
   bool combineInstructions(MachineBasicBlock *);
   MachineInstr *getOperandDef(const MachineOperand &MO);
   unsigned getDepth(SmallVectorImpl<MachineInstr *> &InsInstrs,
                     DenseMap<unsigned, unsigned> &InstrIdxForVirtReg,
                     MachineTraceMetrics::Trace BlockTrace);
   unsigned getLatency(MachineInstr *Root, MachineInstr *NewRoot,
                       MachineTraceMetrics::Trace BlockTrace);
   bool

 
 void MachineCombiner::getAnalysisUsage(AnalysisUsage &AU) const {
   AU.setPreservesCFG();
   AU.addPreserved<MachineDominatorTree>();
   AU.addRequired<MachineLoopInfo>();
   AU.addPreserved<MachineLoopInfo>();
   AU.addRequired<MachineTraceMetrics>();
   AU.addPreserved<MachineTraceMetrics>();
+  AU.addRequired<LazyMachineBlockFrequencyInfoPass>();
+  AU.addRequired<ProfileSummaryInfoWrapperPass>();
   MachineFunctionPass::getAnalysisUsage(AU);
 }
 
 MachineInstr *MachineCombiner::getOperandDef(const MachineOperand &MO) {
   MachineInstr *DefInstr = nullptr;
   // We need a virtual register definition.
   if (MO.isReg() && Register::isVirtualRegister(MO.getReg()))
     DefInstr = MRI->getUniqueVRegDef(MO.getReg());
LLVM_DEBUG(
           : dbgs() << "\t\t  As result it DOES NOT improve/preserve Resource "
                       "Length\n");
 
   return ResLenAfterCombine <= ResLenBeforeCombine;
 }
 
 /// \returns true when new instruction sequence should be generated
 /// independent if it lengthens critical path or not
-bool MachineCombiner::doSubstitute(unsigned NewSize, unsigned OldSize) {
-  if (OptSize && (NewSize < OldSize))
+bool MachineCombiner::doSubstitute(unsigned NewSize, unsigned OldSize,
+                                   bool OptForSize) {
+  if (OptForSize && (NewSize < OldSize))
     return true;
   if (!TSchedModel.hasInstrSchedModelOrItineraries())
     return true;
   return false;
 }
 
 /// Inserts InsInstrs and deletes DelInstrs. Incrementally updates instruction
 /// depths if requested.
bool MachineCombiner::combineInstructions(MachineBasicBlock *MBB) {
   // Check if the block is in a loop.
   const MachineLoop *ML = MLI->getLoopFor(MBB);
   if (!MinInstr)
     MinInstr = Traces->getEnsemble(MachineTraceMetrics::TS_MinInstrCount);
 
   SparseSet<LiveRegUnit> RegUnits;
   RegUnits.setUniverse(TRI->getNumRegUnits());
 
+  bool OptForSize = OptSize || llvm::shouldOptimizeForSize(MBB, PSI, MBFI);
+
   while (BlockIter != MBB->end()) {
     auto &MI = *BlockIter++;
     SmallVector<MachineCombinerPattern, 16> Patterns;
     // The motivating example is:
     //
     //     MUL  Other        MUL_op1 MUL_op2  Other
     //      \    /               \      |    /
     //      ADD/SUB      =>        MADD/MSUB
for (auto P : Patterns) {
         MinInstr->updateDepths(LastUpdate, BlockIter, RegUnits);
         LastUpdate = BlockIter;
       }
 
       // Substitute when we optimize for codesize and the new sequence has
       // fewer instructions OR
       // the new sequence neither lengthens the critical path nor increases
       // resource pressure.
-      if (SubstituteAlways || doSubstitute(NewInstCount, OldInstCount)) {
+      if (SubstituteAlways ||
+          doSubstitute(NewInstCount, OldInstCount, OptForSize)) {
         insertDeleteInstructions(MBB, MI, InsInstrs, DelInstrs, MinInstr,
                                  RegUnits, IncrementalUpdate);
         // Eagerly stop after the first pattern fires.
         Changed = true;
         break;
       } else {
         // For big basic blocks, we only compute the full trace the first time
         // we hit this. We do not invalidate the trace, but instead update the
bool MachineCombiner::runOnMachineFunction(MachineFunction &MF) {
   STI = &MF.getSubtarget();
   TII = STI->getInstrInfo();
   TRI = STI->getRegisterInfo();
   SchedModel = STI->getSchedModel();
   TSchedModel.init(STI);
   MRI = &MF.getRegInfo();
   MLI = &getAnalysis<MachineLoopInfo>();
   Traces = &getAnalysis<MachineTraceMetrics>();
+  PSI = &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
+  MBFI = (PSI && PSI->hasProfileSummary()) ?
+         &getAnalysis<LazyMachineBlockFrequencyInfoPass>().getBFI() :
+         nullptr;
   MinInstr = nullptr;
   OptSize = MF.getFunction().hasOptSize();
 
   LLVM_DEBUG(dbgs() << getPassName() << ": " << MF.getName() << '\n');
   if (!TII->useMachineCombiner()) {
     LLVM_DEBUG(
         dbgs()
         << "  Skipping pass: Target does not support machine combiner\n");

llvm/lib/CodeGen/SelectionDAG/SelectionDAGISel.cpp

 #include "llvm/ADT/SmallSet.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/Statistic.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/Analysis/AliasAnalysis.h"
 #include "llvm/Analysis/BranchProbabilityInfo.h"
 #include "llvm/Analysis/CFG.h"
 #include "llvm/Analysis/EHPersonalities.h"
+#include "llvm/Analysis/LazyBlockFrequencyInfo.h"
 #include "llvm/Analysis/LegacyDivergenceAnalysis.h"
 #include "llvm/Analysis/OptimizationRemarkEmitter.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/Analysis/TargetTransformInfo.h"
 #include "llvm/CodeGen/FastISel.h"
 #include "llvm/CodeGen/FunctionLoweringInfo.h"
 #include "llvm/CodeGen/GCMetadata.h"
 #include "llvm/CodeGen/ISDOpcodes.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineFrameInfo.h"
if (OptLevel != CodeGenOpt::None)
     AU.addRequired<AAResultsWrapperPass>();
   AU.addRequired<GCModuleInfo>();
   AU.addRequired<StackProtector>();
   AU.addPreserved<GCModuleInfo>();
   AU.addRequired<TargetLibraryInfoWrapperPass>();
   AU.addRequired<TargetTransformInfoWrapperPass>();
   if (UseMBPI && OptLevel != CodeGenOpt::None)
     AU.addRequired<BranchProbabilityInfoWrapperPass>();
+  AU.addRequired<ProfileSummaryInfoWrapperPass>();
+  LazyBlockFrequencyInfoPass::getLazyBFIAnalysisUsage(AU);
   MachineFunctionPass::getAnalysisUsage(AU);
 }
 
 /// SplitCriticalSideEffectEdges - Look for critical edges with a PHI value that
 /// may trap on it.  In this case we have to split the edge so that the path
 /// through the predecessor block that doesn't go to the phi block doesn't
 /// execute the possibly trapping instruction. If available, we pass domtree
 /// and loop info to be updated when we split critical edges. This is because
bool SelectionDAGISel::runOnMachineFunction(MachineFunction &mf) {
   RegInfo = &MF->getRegInfo();
   LibInfo = &getAnalysis<TargetLibraryInfoWrapperPass>().getTLI(Fn);
   GFI = Fn.hasGC() ? &getAnalysis<GCModuleInfo>().getFunctionInfo(Fn) : nullptr;
   ORE = std::make_unique<OptimizationRemarkEmitter>(&Fn);
   auto *DTWP = getAnalysisIfAvailable<DominatorTreeWrapperPass>();
   DominatorTree *DT = DTWP ? &DTWP->getDomTree() : nullptr;
   auto *LIWP = getAnalysisIfAvailable<LoopInfoWrapperPass>();
   LoopInfo *LI = LIWP ? &LIWP->getLoopInfo() : nullptr;
+  auto *PSI = &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
+  auto *BFI = (PSI && PSI->hasProfileSummary()) ?
+              &getAnalysis<LazyBlockFrequencyInfoPass>().getBFI() :
+              nullptr;
 
   LLVM_DEBUG(dbgs() << "\n\n\n=== " << Fn.getName() << "\n");
 
   SplitCriticalSideEffectEdges(const_cast<Function &>(Fn), DT, LI);
 
   CurDAG->init(*MF, *ORE, this, LibInfo,
-               getAnalysisIfAvailable<LegacyDivergenceAnalysis>(),
-               nullptr, nullptr);
+               getAnalysisIfAvailable<LegacyDivergenceAnalysis>(), PSI, BFI);
   FuncInfo->set(Fn, *MF, CurDAG);
   SwiftError->setFunction(*MF);
 
   // Now get the optional analyzes if we want to.
   // This is based on the possibly changed OptLevel (after optnone is taken
   // into account).  That's unfortunate but OK because it just means we won't
   // ask for passes that have been required anyway.
 

llvm/lib/CodeGen/TailDuplication.cpp

 //===- TailDuplication.cpp - Duplicate blocks into predecessors' tails ----===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 //
 /// \file This pass duplicates basic blocks ending in unconditional branches
 /// into the tails of their predecessors, using the TailDuplicator utility
 /// class.
 //
 //===----------------------------------------------------------------------===//
 
+#include "llvm/Analysis/ProfileSummaryInfo.h"
+#include "llvm/CodeGen/LazyMachineBlockFrequencyInfo.h"
 #include "llvm/CodeGen/MachineBranchProbabilityInfo.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineRegisterInfo.h"
 #include "llvm/CodeGen/Passes.h"
 #include "llvm/CodeGen/TailDuplicator.h"
 #include "llvm/InitializePasses.h"
 #include "llvm/Pass.h"

 public:
   TailDuplicateBase(char &PassID, bool PreRegAlloc)
     : MachineFunctionPass(PassID), PreRegAlloc(PreRegAlloc) {}
 
   bool runOnMachineFunction(MachineFunction &MF) override;
 
   void getAnalysisUsage(AnalysisUsage &AU) const override {
     AU.addRequired<MachineBranchProbabilityInfo>();
+    AU.addRequired<LazyMachineBlockFrequencyInfoPass>();
+    AU.addRequired<ProfileSummaryInfoWrapperPass>();
     MachineFunctionPass::getAnalysisUsage(AU);
   }
 };
 
 class TailDuplicate : public TailDuplicateBase {
 public:
   static char ID;
   TailDuplicate() : TailDuplicateBase(ID, false) {

 INITIALIZE_PASS(EarlyTailDuplicate, "early-tailduplication",
                 "Early Tail Duplication", false, false)
 
 bool TailDuplicateBase::runOnMachineFunction(MachineFunction &MF) {
   if (skipFunction(MF.getFunction()))
     return false;
 
   auto MBPI = &getAnalysis<MachineBranchProbabilityInfo>();
-  Duplicator.initMF(MF, PreRegAlloc, MBPI, /*LayoutMode=*/false);
+  auto *PSI = &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
+  auto *MBFI = (PSI && PSI->hasProfileSummary()) ?
+               &getAnalysis<LazyMachineBlockFrequencyInfoPass>().getBFI() :
+               nullptr;
+  Duplicator.initMF(MF, PreRegAlloc, MBPI, MBFI, PSI, /*LayoutMode=*/false);
 
   bool MadeChange = false;
   while (Duplicator.tailDuplicateBlocks())
     MadeChange = true;
 
   return MadeChange;
 }

llvm/lib/CodeGen/TailDuplicator.cpp

 #include "llvm/CodeGen/TailDuplicator.h"
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/DenseSet.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/SetVector.h"
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/Statistic.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineBranchProbabilityInfo.h"
+#include "llvm/CodeGen/MachineBlockFrequencyInfo.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineInstr.h"
 #include "llvm/CodeGen/MachineInstrBuilder.h"
 #include "llvm/CodeGen/MachineOperand.h"
 #include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/CodeGen/MachineSizeOpts.h"
 #include "llvm/CodeGen/MachineSSAUpdater.h"
 #include "llvm/CodeGen/TargetInstrInfo.h"
 #include "llvm/CodeGen/TargetRegisterInfo.h"
 #include "llvm/CodeGen/TargetSubtargetInfo.h"
 #include "llvm/IR/DebugLoc.h"
 #include "llvm/IR/Function.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Debug.h"
TailDupVerify("tail-dup-verify",
                   cl::desc("Verify sanity of PHI instructions during taildup"),
                   cl::init(false), cl::Hidden);
 
 static cl::opt<unsigned> TailDupLimit("tail-dup-limit", cl::init(~0U),
                                       cl::Hidden);
 
 void TailDuplicator::initMF(MachineFunction &MFin, bool PreRegAlloc,
                             const MachineBranchProbabilityInfo *MBPIin,
+                            const MachineBlockFrequencyInfo *MBFIin,
+                            ProfileSummaryInfo *PSIin,
                             bool LayoutModeIn, unsigned TailDupSizeIn) {
   MF = &MFin;
   TII = MF->getSubtarget().getInstrInfo();
   TRI = MF->getSubtarget().getRegisterInfo();
   MRI = &MF->getRegInfo();
   MMI = &MF->getMMI();
   MBPI = MBPIin;
+  MBFI = MBFIin;
+  PSI = PSIin;
   TailDupSize = TailDupSizeIn;
 
   assert(MBPI != nullptr && "Machine Branch Probability Info required");
 
   LayoutMode = LayoutModeIn;
   this->PreRegAlloc = PreRegAlloc;
 }
 
bool TailDuplicator::shouldTailDuplicate(bool IsSimple,
   // Don't try to tail-duplicate single-block loops.
   if (TailBB.isSuccessor(&TailBB))
     return false;
 
   // Set the limit on the cost to duplicate. When optimizing for size,
   // duplicate only one, because one branch instruction can be eliminated to
   // compensate for the duplication.
   unsigned MaxDuplicateCount;
-  if (TailDupSize == 0 &&
-      TailDuplicateSize.getNumOccurrences() == 0 &&
-      MF->getFunction().hasOptSize())
-    MaxDuplicateCount = 1;
-  else if (TailDupSize == 0)
+  bool OptForSize = MF->getFunction().hasOptSize() ||
+                    llvm::shouldOptimizeForSize(&TailBB, PSI, MBFI);
+  if (TailDupSize == 0)
     MaxDuplicateCount = TailDuplicateSize;
   else
     MaxDuplicateCount = TailDupSize;
+  if (OptForSize)
+    MaxDuplicateCount = 1;
 
   // If the block to be duplicated ends in an unanalyzable fallthrough, don't
   // duplicate it.
   // A similar check is necessary in MachineBlockPlacement to make sure pairs of
   // blocks with unanalyzable fallthrough get layed out contiguously.
   MachineBasicBlock *PredTBB = nullptr, *PredFBB = nullptr;
   SmallVector<MachineOperand, 4> PredCond;
   if (TII->analyzeBranch(TailBB, PredTBB, PredFBB, PredCond) &&

llvm/lib/Target/X86/X86FixupBWInsts.cpp

 /// targeted, or when optimizing for minimum code size.
 ///
 //===----------------------------------------------------------------------===//
 
 #include "X86.h"
 #include "X86InstrInfo.h"
 #include "X86Subtarget.h"
 #include "llvm/ADT/Statistic.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
+#include "llvm/CodeGen/LazyMachineBlockFrequencyInfo.h"
 #include "llvm/CodeGen/LivePhysRegs.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineInstrBuilder.h"
 #include "llvm/CodeGen/MachineLoopInfo.h"
 #include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/CodeGen/MachineSizeOpts.h"
 #include "llvm/CodeGen/Passes.h"
 #include "llvm/CodeGen/TargetInstrInfo.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/raw_ostream.h"
 using namespace llvm;
 
 #define FIXUPBW_DESC "X86 Byte/Word Instruction Fixup"
 #define FIXUPBW_NAME "x86-fixup-bw-insts"
public:
 
   StringRef getPassName() const override { return FIXUPBW_DESC; }
 
   FixupBWInstPass() : MachineFunctionPass(ID) { }
 
   void getAnalysisUsage(AnalysisUsage &AU) const override {
     AU.addRequired<MachineLoopInfo>(); // Machine loop info is used to
                                        // guide some heuristics.
+    AU.addRequired<ProfileSummaryInfoWrapperPass>();
+    AU.addRequired<LazyMachineBlockFrequencyInfoPass>();
     MachineFunctionPass::getAnalysisUsage(AU);
   }
 
   /// Loop over all of the basic blocks, replacing byte and word instructions by
   /// equivalent 32 bit instructions where performance or code size can be
   /// improved.
   bool runOnMachineFunction(MachineFunction &MF) override;
 
private:
   /// Local member for function's OptForSize attribute.
   bool OptForSize = false;
 
   /// Machine loop info used for guiding some heruistics.
   MachineLoopInfo *MLI = nullptr;
 
   /// Register Liveness information after the current instruction.
   LivePhysRegs LiveRegs;
+
+  ProfileSummaryInfo *PSI;
+  MachineBlockFrequencyInfo *MBFI;
 };
 char FixupBWInstPass::ID = 0;
 }
 
 INITIALIZE_PASS(FixupBWInstPass, FIXUPBW_NAME, FIXUPBW_DESC, false, false)
 
 FunctionPass *llvm::createX86FixupBWInsts() { return new FixupBWInstPass(); }
 
 bool FixupBWInstPass::runOnMachineFunction(MachineFunction &MF) {
   if (!FixupBWInsts || skipFunction(MF.getFunction()))
     return false;
 
   this->MF = &MF;
   TII = MF.getSubtarget<X86Subtarget>().getInstrInfo();
-  OptForSize = MF.getFunction().hasOptSize();
   MLI = &getAnalysis<MachineLoopInfo>();
+  PSI = &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
+  MBFI = (PSI && PSI->hasProfileSummary()) ?
+         &getAnalysis<LazyMachineBlockFrequencyInfoPass>().getBFI() :
+         nullptr;
   LiveRegs.init(TII->getRegisterInfo());
 
   LLVM_DEBUG(dbgs() << "Start X86FixupBWInsts\n";);
 
   // Process all basic blocks.
   for (auto &MBB : MF)
     processBasicBlock(MF, MBB);
 
void FixupBWInstPass::processBasicBlock(MachineFunction &MF,
   SmallVector<std::pair<MachineInstr *, MachineInstr *>, 8> MIReplacements;
 
   // Start computing liveness for this block. We iterate from the end to be able
   // to update this for each instruction.
   LiveRegs.clear();
   // We run after PEI, so we need to AddPristinesAndCSRs.
   LiveRegs.addLiveOuts(MBB);
 
+  OptForSize = MF.getFunction().hasOptSize() ||
+               llvm::shouldOptimizeForSize(&MBB, PSI, MBFI);
+
   for (auto I = MBB.rbegin(); I != MBB.rend(); ++I) {
     MachineInstr *MI = &*I;
 
     if (MachineInstr *NewMI = tryReplaceInstr(MI, MBB))
       MIReplacements.push_back(std::make_pair(MI, NewMI));
 
     // We're done with this instruction, update liveness for the next one.
     LiveRegs.stepBackward(*MI);

llvm/lib/Target/X86/X86OptimizeLEAs.cpp

 #include "X86.h"
 #include "X86InstrInfo.h"
 #include "X86Subtarget.h"
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/DenseMapInfo.h"
 #include "llvm/ADT/Hashing.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/Statistic.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
+#include "llvm/CodeGen/LazyMachineBlockFrequencyInfo.h"
 #include "llvm/CodeGen/MachineBasicBlock.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineInstr.h"
 #include "llvm/CodeGen/MachineInstrBuilder.h"
 #include "llvm/CodeGen/MachineOperand.h"
 #include "llvm/CodeGen/MachineRegisterInfo.h"
+#include "llvm/CodeGen/MachineSizeOpts.h"
 #include "llvm/CodeGen/TargetOpcodes.h"
 #include "llvm/CodeGen/TargetRegisterInfo.h"
 #include "llvm/IR/DebugInfoMetadata.h"
 #include "llvm/IR/DebugLoc.h"
 #include "llvm/IR/Function.h"
 #include "llvm/MC/MCInstrDesc.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Debug.h"
public:
 
   /// Loop over all of the basic blocks, replacing address
   /// calculations in load and store instructions, if it's already
   /// been calculated by LEA. Also, remove redundant LEAs.
   bool runOnMachineFunction(MachineFunction &MF) override;
 
   static char ID;
 
+  void getAnalysisUsage(AnalysisUsage &AU) const override {
+    AU.addRequired<ProfileSummaryInfoWrapperPass>();
+    AU.addRequired<LazyMachineBlockFrequencyInfoPass>();
+    MachineFunctionPass::getAnalysisUsage(AU);
+  }
+
 private:
   using MemOpMap = DenseMap<MemOpKey, SmallVector<MachineInstr *, 16>>;
 
   /// Returns a distance between two instructions inside one basic block.
   /// Negative result means, that instructions occur in reverse order.
   int calcInstrDist(const MachineInstr &First, const MachineInstr &Last);
 
   /// Choose the best \p LEA instruction from the \p List to replace
bool X86OptimizeLEAPass::runOnMachineFunction(MachineFunction &MF) {
   bool Changed = false;
 
   if (DisableX86LEAOpt || skipFunction(MF.getFunction()))
     return false;
 
   MRI = &MF.getRegInfo();
   TII = MF.getSubtarget<X86Subtarget>().getInstrInfo();
   TRI = MF.getSubtarget<X86Subtarget>().getRegisterInfo();
+  auto *PSI =
+      &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
+  auto *MBFI = (PSI && PSI->hasProfileSummary()) ?
+               &getAnalysis<LazyMachineBlockFrequencyInfoPass>().getBFI() :
+               nullptr;
 
   // Process all basic blocks.
   for (auto &MBB : MF) {
     MemOpMap LEAs;
     InstrPos.clear();
 
     // Find all LEA instructions in basic block.
     findLEAs(MBB, LEAs);
 
     // If current basic block has no LEAs, move on to the next one.
     if (LEAs.empty())
       continue;
 
     // Remove redundant LEA instructions.
     Changed |= removeRedundantLEAs(LEAs);
 
     // Remove redundant address calculations. Do it only for -Os/-Oz since only
     // a code size gain is expected from this part of the pass.
-    if (MF.getFunction().hasOptSize())
+    bool OptForSize = MF.getFunction().hasOptSize() ||
+                      llvm::shouldOptimizeForSize(&MBB, PSI, MBFI);
+    if (OptForSize)
       Changed |= removeRedundantAddrCalc(LEAs);
   }
 
   return Changed;
 }

llvm/lib/Target/X86/X86PadShortFunction.cpp

 //
 //===----------------------------------------------------------------------===//
 
 
 #include "X86.h"
 #include "X86InstrInfo.h"
 #include "X86Subtarget.h"
 #include "llvm/ADT/Statistic.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
+#include "llvm/CodeGen/LazyMachineBlockFrequencyInfo.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/MachineInstrBuilder.h"
+#include "llvm/CodeGen/MachineSizeOpts.h"
 #include "llvm/CodeGen/Passes.h"
 #include "llvm/CodeGen/TargetSchedule.h"
 #include "llvm/IR/Function.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/raw_ostream.h"
 
 using namespace llvm;
 
namespace {
 
   struct PadShortFunc : public MachineFunctionPass {
     static char ID;
     PadShortFunc() : MachineFunctionPass(ID)
                    , Threshold(4) {}
 
     bool runOnMachineFunction(MachineFunction &MF) override;
 
+    void getAnalysisUsage(AnalysisUsage &AU) const override {
+      AU.addRequired<ProfileSummaryInfoWrapperPass>();
+      AU.addRequired<LazyMachineBlockFrequencyInfoPass>();
+      MachineFunctionPass::getAnalysisUsage(AU);
+    }
+
     MachineFunctionProperties getRequiredProperties() const override {
       return MachineFunctionProperties().set(
           MachineFunctionProperties::Property::NoVRegs);
     }
 
     StringRef getPassName() const override {
       return "X86 Atom pad short functions";
     }
bool PadShortFunc::runOnMachineFunction(MachineFunction &MF) {
   if (MF.getFunction().hasOptSize())
     return false;
 
   if (!MF.getSubtarget<X86Subtarget>().padShortFunctions())
     return false;
 
   TSM.init(&MF.getSubtarget());
 
+  auto *PSI =
+      &getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
+  auto *MBFI = (PSI && PSI->hasProfileSummary()) ?
+               &getAnalysis<LazyMachineBlockFrequencyInfoPass>().getBFI() :
+               nullptr;
+
   // Search through basic blocks and mark the ones that have early returns
   ReturnBBs.clear();
   VisitedBBs.clear();
   findReturns(&MF.front());
 
   bool MadeChange = false;
 
   // Pad the identified basic blocks with NOOPs
   for (DenseMap<MachineBasicBlock*, unsigned int>::iterator I = ReturnBBs.begin();
        I != ReturnBBs.end(); ++I) {
     MachineBasicBlock *MBB = I->first;
     unsigned Cycles = I->second;
 
+    // Function::hasOptSize is already checked above.
+    bool OptForSize = llvm::shouldOptimizeForSize(MBB, PSI, MBFI);
+    if (OptForSize)
+      continue;
+
     if (Cycles < Threshold) {
       // BB ends in a return. Skip over any DBG_VALUE instructions
       // trailing the terminator.
       assert(MBB->size() > 0 &&
              "Basic block should contain at least a RET but is empty");
       MachineBasicBlock::iterator ReturnLoc = --MBB->end();
 
       while (ReturnLoc->isDebugInstr())

llvm/test/CodeGen/AArch64/O0-pipeline.ll

 ; RUN: llc -mtriple=arm64-- -O0 -debug-pass=Structure < %s -o /dev/null 2>&1 | grep -v "Verify generated machine code" | FileCheck %s
 
 ; REQUIRES: asserts
 
 ; CHECK-LABEL: Pass Arguments:
 ; CHECK-NEXT: Target Library Information
 ; CHECK-NEXT: Target Pass Configuration
 ; CHECK-NEXT: Machine Module Information
 ; CHECK-NEXT: Target Transform Information
 ; CHECK-NEXT: Type-Based Alias Analysis
 ; CHECK-NEXT: Scoped NoAlias Alias Analysis
 ; CHECK-NEXT: Assumption Cache Tracker
 ; CHECK-NEXT: Create Garbage Collector Module Metadata
+; CHECK-NEXT: Profile summary info
 ; CHECK-NEXT: Machine Branch Probability Analysis
 ; CHECK-NEXT:   ModulePass Manager
 ; CHECK-NEXT:     Pre-ISel Intrinsic Lowering
 ; CHECK-NEXT:     FunctionPass Manager
 ; CHECK-NEXT:       Expand Atomic instructions
 ; CHECK-NEXT:       Dominator Tree Construction
 ; CHECK-NEXT:       Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:       Module Verifier

 ; CHECK-NEXT:       AArch64PreLegalizerCombiner
 ; CHECK-NEXT:       Analysis containing CSE Info
 ; CHECK-NEXT:       Legalizer
 ; CHECK-NEXT:       RegBankSelect
 ; CHECK-NEXT:       Localizer
 ; CHECK-NEXT:       Analysis for ComputingKnownBits
 ; CHECK-NEXT:       InstructionSelect
 ; CHECK-NEXT:       ResetMachineFunction
+; CHECK-NEXT:       Dominator Tree Construction
+; CHECK-NEXT:       Natural Loop Information
+; CHECK-NEXT:       Lazy Branch Probability Analysis
+; CHECK-NEXT:       Lazy Block Frequency Analysis
 ; CHECK-NEXT:       AArch64 Instruction Selection
 ; CHECK-NEXT:       Finalize ISel and expand pseudo-instructions
 ; CHECK-NEXT:       Local Stack Slot Allocation
 ; CHECK-NEXT:       Eliminate PHI nodes for register allocation
 ; CHECK-NEXT:       Two-Address instruction pass
 ; CHECK-NEXT:       Fast Register Allocator
 ; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       Machine Optimization Remark Emitter

llvm/test/CodeGen/AArch64/O3-pipeline.ll

 ; RUN: llc -mtriple=arm64-- -O3 -debug-pass=Structure < %s -o /dev/null 2>&1 | grep -v "Verify generated machine code" | FileCheck %s
 
 ; REQUIRES: asserts
 
 ; CHECK-LABEL: Pass Arguments:
 ; CHECK-NEXT: Target Library Information
 ; CHECK-NEXT: Target Pass Configuration
 ; CHECK-NEXT: Machine Module Information
 ; CHECK-NEXT: Target Transform Information
 ; CHECK-NEXT: Assumption Cache Tracker
 ; CHECK-NEXT: Type-Based Alias Analysis
 ; CHECK-NEXT: Scoped NoAlias Alias Analysis
-; CHECK-NEXT: Create Garbage Collector Module Metadata
 ; CHECK-NEXT: Profile summary info
+; CHECK-NEXT: Create Garbage Collector Module Metadata
 ; CHECK-NEXT: Machine Branch Probability Analysis
 ; CHECK-NEXT:   ModulePass Manager
 ; CHECK-NEXT:     Pre-ISel Intrinsic Lowering
 ; CHECK-NEXT:     FunctionPass Manager
 ; CHECK-NEXT:       Expand Atomic instructions
 ; CHECK-NEXT:       Simplify the CFG
 ; CHECK-NEXT:       Dominator Tree Construction
 ; CHECK-NEXT:       Natural Loop Information
 ; CHECK-NEXT:       Lazy Branch Probability Analysis
 ; CHECK-NEXT:       Lazy Block Frequency Analysis
 ; CHECK-NEXT:       Optimization Remark Emitter
 ; CHECK-NEXT:       Scalar Evolution Analysis
 ; CHECK-NEXT:       Loop Data Prefetch
 ; CHECK-NEXT:       Falkor HW Prefetch Fix
 ; CHECK-NEXT:       Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:       Module Verifier
 ; CHECK-NEXT:       Canonicalize natural loops
 ; CHECK-NEXT:       Loop Pass Manager
 ; CHECK-NEXT:         Induction Variable Users
 ; CHECK-NEXT:         Loop Strength Reduction
 ; CHECK-NEXT:       Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:         Function Alias Analysis Results
 ; CHECK-NEXT:       Merge contiguous icmps into a memcmp
+; CHECK-NEXT:       Natural Loop Information
+; CHECK-NEXT:       Lazy Branch Probability Analysis
+; CHECK-NEXT:       Lazy Block Frequency Analysis
 ; CHECK-NEXT:       Expand memcmp() to load/stores
 ; CHECK-NEXT:       Lower Garbage Collection Instructions
 ; CHECK-NEXT:       Shadow Stack GC Lowering
 ; CHECK-NEXT:       Lower constant intrinsics
 ; CHECK-NEXT:       Remove unreachable blocks from the CFG
 ; CHECK-NEXT:       Dominator Tree Construction
 ; CHECK-NEXT:       Natural Loop Information
 ; CHECK-NEXT:       Branch Probability Analysis

 ; CHECK-NEXT:       Safe Stack instrumentation pass
 ; CHECK-NEXT:       Insert stack protectors
 ; CHECK-NEXT:       Module Verifier
 ; CHECK-NEXT:       Dominator Tree Construction
 ; CHECK-NEXT:       Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:       Function Alias Analysis Results
 ; CHECK-NEXT:       Natural Loop Information
 ; CHECK-NEXT:       Branch Probability Analysis
+; CHECK-NEXT:       Lazy Branch Probability Analysis
+; CHECK-NEXT:       Lazy Block Frequency Analysis
 ; CHECK-NEXT:       AArch64 Instruction Selection
 ; CHECK-NEXT:       MachineDominator Tree Construction
 ; CHECK-NEXT:       AArch64 Local Dynamic TLS Access Clean-up
 ; CHECK-NEXT:       Finalize ISel and expand pseudo-instructions
+; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       Early Tail Duplication
 ; CHECK-NEXT:       Optimize machine instruction PHIs
 ; CHECK-NEXT:       Slot index numbering
 ; CHECK-NEXT:       Merge disjoint stack slots
 ; CHECK-NEXT:       Local Stack Slot Allocation
 ; CHECK-NEXT:       Remove dead machine instructions
 ; CHECK-NEXT:       MachineDominator Tree Construction
 ; CHECK-NEXT:       AArch64 Condition Optimizer
 ; CHECK-NEXT:       Machine Natural Loop Construction
 ; CHECK-NEXT:       Machine Trace Metrics
 ; CHECK-NEXT:       AArch64 Conditional Compares
+; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       Machine InstCombiner
 ; CHECK-NEXT:       AArch64 Conditional Branch Tuning
 ; CHECK-NEXT:       Machine Trace Metrics
 ; CHECK-NEXT:       Early If-Conversion
 ; CHECK-NEXT:       AArch64 Store Pair Suppression
 ; CHECK-NEXT:       AArch64 SIMD instructions optimization pass
 ; CHECK-NEXT:       AArch64 Stack Tagging PreRA
 ; CHECK-NEXT:       MachineDominator Tree Construction

 ; CHECK-NEXT:       Machine Natural Loop Construction
 ; CHECK-NEXT:       Machine Block Frequency Analysis
 ; CHECK-NEXT:       MachinePostDominator Tree Construction
 ; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       Machine Optimization Remark Emitter
 ; CHECK-NEXT:       Shrink Wrapping analysis
 ; CHECK-NEXT:       Prologue/Epilogue Insertion & Frame Finalization
 ; CHECK-NEXT:       Control Flow Optimizer
+; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       Tail Duplication
 ; CHECK-NEXT:       Machine Copy Propagation Pass
 ; CHECK-NEXT:       Post-RA pseudo instruction expansion pass
 ; CHECK-NEXT:       AArch64 pseudo instruction expansion pass
 ; CHECK-NEXT:       AArch64 load / store optimization pass
 ; CHECK-NEXT:       AArch64 speculation hardening pass
 ; CHECK-NEXT:       MachineDominator Tree Construction
 ; CHECK-NEXT:       Machine Natural Loop Construction

llvm/test/CodeGen/ARM/O3-pipeline.ll

 ; CHECK-NEXT:      Canonicalize natural loops
 ; CHECK-NEXT:      Scalar Evolution Analysis
 ; CHECK-NEXT:      Loop Pass Manager
 ; CHECK-NEXT:        Induction Variable Users
 ; CHECK-NEXT:        Loop Strength Reduction
 ; CHECK-NEXT:      Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:      Function Alias Analysis Results
 ; CHECK-NEXT:      Merge contiguous icmps into a memcmp
+; CHECK-NEXT:      Natural Loop Information
+; CHECK-NEXT:      Lazy Branch Probability Analysis
+; CHECK-NEXT:      Lazy Block Frequency Analysis
 ; CHECK-NEXT:      Expand memcmp() to load/stores
 ; CHECK-NEXT:      Lower Garbage Collection Instructions
 ; CHECK-NEXT:      Shadow Stack GC Lowering
 ; CHECK-NEXT:      Lower constant intrinsics
 ; CHECK-NEXT:      Remove unreachable blocks from the CFG
 ; CHECK-NEXT:      Dominator Tree Construction
 ; CHECK-NEXT:      Natural Loop Information
 ; CHECK-NEXT:      Branch Probability Analysis

 ; CHECK-NEXT:      Safe Stack instrumentation pass
 ; CHECK-NEXT:      Insert stack protectors
 ; CHECK-NEXT:      Module Verifier
 ; CHECK-NEXT:      Dominator Tree Construction
 ; CHECK-NEXT:      Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:      Function Alias Analysis Results
 ; CHECK-NEXT:      Natural Loop Information
 ; CHECK-NEXT:      Branch Probability Analysis
+; CHECK-NEXT:      Lazy Branch Probability Analysis
+; CHECK-NEXT:      Lazy Block Frequency Analysis
 ; CHECK-NEXT:      ARM Instruction Selection
 ; CHECK-NEXT:      Finalize ISel and expand pseudo-instructions
+; CHECK-NEXT:      Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:      Early Tail Duplication
 ; CHECK-NEXT:      Optimize machine instruction PHIs
 ; CHECK-NEXT:      Slot index numbering
 ; CHECK-NEXT:      Merge disjoint stack slots
 ; CHECK-NEXT:      Local Stack Slot Allocation
 ; CHECK-NEXT:      Remove dead machine instructions
 ; CHECK-NEXT:      MachineDominator Tree Construction
 ; CHECK-NEXT:      Machine Natural Loop Construction

 ; CHECK-NEXT:      Machine Block Frequency Analysis
 ; CHECK-NEXT:      MachineDominator Tree Construction
 ; CHECK-NEXT:      MachinePostDominator Tree Construction
 ; CHECK-NEXT:      Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:      Machine Optimization Remark Emitter
 ; CHECK-NEXT:      Shrink Wrapping analysis
 ; CHECK-NEXT:      Prologue/Epilogue Insertion & Frame Finalization
 ; CHECK-NEXT:      Control Flow Optimizer
+; CHECK-NEXT:      Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:      Tail Duplication
 ; CHECK-NEXT:      Machine Copy Propagation Pass
 ; CHECK-NEXT:      Post-RA pseudo instruction expansion pass
 ; CHECK-NEXT:      ARM load / store optimization pass
 ; CHECK-NEXT:      ReachingDefAnalysis
 ; CHECK-NEXT:      ARM Execution Domain Fix
 ; CHECK-NEXT:      BreakFalseDeps
 ; CHECK-NEXT:      ARM pseudo instruction expansion pass

llvm/test/CodeGen/X86/O0-pipeline.ll

 ; When EXPENSIVE_CHECKS are enabled, the machine verifier appears between each
 ; pass. Ignore it with 'grep -v'.
 ; RUN: llc -mtriple=x86_64-- -O0 -debug-pass=Structure < %s -o /dev/null 2>&1 \
 ; RUN:   | grep -v 'Verify generated machine code' | FileCheck %s
 
 ; REQUIRES: asserts
 
 ; CHECK-LABEL: Pass Arguments:
 ; CHECK-NEXT: Target Library Information
 ; CHECK-NEXT: Target Pass Configuration
 ; CHECK-NEXT: Machine Module Information
 ; CHECK-NEXT: Target Transform Information
 ; CHECK-NEXT: Type-Based Alias Analysis
 ; CHECK-NEXT: Scoped NoAlias Alias Analysis
 ; CHECK-NEXT: Assumption Cache Tracker
 ; CHECK-NEXT: Create Garbage Collector Module Metadata
+; CHECK-NEXT: Profile summary info
 ; CHECK-NEXT: Machine Branch Probability Analysis
 ; CHECK-NEXT:   ModulePass Manager
 ; CHECK-NEXT:     Pre-ISel Intrinsic Lowering
 ; CHECK-NEXT:     FunctionPass Manager
 ; CHECK-NEXT:       Expand Atomic instructions
 ; CHECK-NEXT:       Dominator Tree Construction
 ; CHECK-NEXT:       Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:       Module Verifier
 ; CHECK-NEXT:       Lower Garbage Collection Instructions
 ; CHECK-NEXT:       Shadow Stack GC Lowering
 ; CHECK-NEXT:       Lower constant intrinsics
 ; CHECK-NEXT:       Remove unreachable blocks from the CFG
 ; CHECK-NEXT:       Instrument function entry/exit with calls to e.g. mcount() (post inlining)
 ; CHECK-NEXT:       Scalarize Masked Memory Intrinsics
 ; CHECK-NEXT:       Expand reduction intrinsics
 ; CHECK-NEXT:       Expand indirectbr instructions
 ; CHECK-NEXT:     Rewrite Symbols
 ; CHECK-NEXT:     FunctionPass Manager
 ; CHECK-NEXT:       Dominator Tree Construction
 ; CHECK-NEXT:       Exception handling preparation
 ; CHECK-NEXT:       Safe Stack instrumentation pass
 ; CHECK-NEXT:       Insert stack protectors
 ; CHECK-NEXT:       Module Verifier
+; CHECK-NEXT:       Dominator Tree Construction
+; CHECK-NEXT:       Natural Loop Information
+; CHECK-NEXT:       Lazy Branch Probability Analysis
+; CHECK-NEXT:       Lazy Block Frequency Analysis
 ; CHECK-NEXT:       X86 DAG->DAG Instruction Selection
 ; CHECK-NEXT:       X86 PIC Global Base Reg Initialization
 ; CHECK-NEXT:       Finalize ISel and expand pseudo-instructions
 ; CHECK-NEXT:       Local Stack Slot Allocation
 ; CHECK-NEXT:       X86 speculative load hardening
 ; CHECK-NEXT:       MachineDominator Tree Construction
 ; CHECK-NEXT:       X86 EFLAGS copy lowering
 ; CHECK-NEXT:       X86 WinAlloca Expander

llvm/test/CodeGen/X86/O3-pipeline.ll

 ; When EXPENSIVE_CHECKS are enabled, the machine verifier appears between each
 ; pass. Ignore it with 'grep -v'.
 ; RUN: llc -mtriple=x86_64-- -O3 -debug-pass=Structure < %s -o /dev/null 2>&1 \
 ; RUN:   | grep -v 'Verify generated machine code' | FileCheck %s
 
 ; REQUIRES: asserts
 
 ; CHECK-LABEL: Pass Arguments:
 ; CHECK-NEXT: Target Library Information
 ; CHECK-NEXT: Target Pass Configuration
 ; CHECK-NEXT: Machine Module Information
 ; CHECK-NEXT: Target Transform Information
 ; CHECK-NEXT: Type-Based Alias Analysis
 ; CHECK-NEXT: Scoped NoAlias Alias Analysis
 ; CHECK-NEXT: Assumption Cache Tracker
-; CHECK-NEXT: Create Garbage Collector Module Metadata
 ; CHECK-NEXT: Profile summary info
+; CHECK-NEXT: Create Garbage Collector Module Metadata
 ; CHECK-NEXT: Machine Branch Probability Analysis
 ; CHECK-NEXT:   ModulePass Manager
 ; CHECK-NEXT:     Pre-ISel Intrinsic Lowering
 ; CHECK-NEXT:     FunctionPass Manager
 ; CHECK-NEXT:       Expand Atomic instructions
 ; CHECK-NEXT:       Dominator Tree Construction
 ; CHECK-NEXT:       Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:       Module Verifier
 ; CHECK-NEXT:       Natural Loop Information
 ; CHECK-NEXT:       Canonicalize natural loops
 ; CHECK-NEXT:       Scalar Evolution Analysis
 ; CHECK-NEXT:       Loop Pass Manager
 ; CHECK-NEXT:         Induction Variable Users
 ; CHECK-NEXT:         Loop Strength Reduction
 ; CHECK-NEXT:       Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:         Function Alias Analysis Results
 ; CHECK-NEXT:       Merge contiguous icmps into a memcmp
+; CHECK-NEXT:       Natural Loop Information
+; CHECK-NEXT:       Lazy Branch Probability Analysis
+; CHECK-NEXT:       Lazy Block Frequency Analysis
 ; CHECK-NEXT:       Expand memcmp() to load/stores
 ; CHECK-NEXT:       Lower Garbage Collection Instructions
 ; CHECK-NEXT:       Shadow Stack GC Lowering
 ; CHECK-NEXT:       Lower constant intrinsics
 ; CHECK-NEXT:       Remove unreachable blocks from the CFG
 ; CHECK-NEXT:       Dominator Tree Construction
 ; CHECK-NEXT:       Natural Loop Information
 ; CHECK-NEXT:       Branch Probability Analysis

 ; CHECK-NEXT:       Safe Stack instrumentation pass
 ; CHECK-NEXT:       Insert stack protectors
 ; CHECK-NEXT:       Module Verifier
 ; CHECK-NEXT:       Dominator Tree Construction
 ; CHECK-NEXT:       Basic Alias Analysis (stateless AA impl)
 ; CHECK-NEXT:       Function Alias Analysis Results
 ; CHECK-NEXT:       Natural Loop Information
 ; CHECK-NEXT:       Branch Probability Analysis
+; CHECK-NEXT:       Lazy Branch Probability Analysis
+; CHECK-NEXT:       Lazy Block Frequency Analysis
 ; CHECK-NEXT:       X86 DAG->DAG Instruction Selection
 ; CHECK-NEXT:       MachineDominator Tree Construction
 ; CHECK-NEXT:       Local Dynamic TLS Access Clean-up
 ; CHECK-NEXT:       X86 PIC Global Base Reg Initialization
 ; CHECK-NEXT:        Finalize ISel and expand pseudo-instructions
 ; CHECK-NEXT:       X86 Domain Reassignment Pass
+; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       Early Tail Duplication
 ; CHECK-NEXT:       Optimize machine instruction PHIs
 ; CHECK-NEXT:       Slot index numbering
 ; CHECK-NEXT:       Merge disjoint stack slots
 ; CHECK-NEXT:       Local Stack Slot Allocation
 ; CHECK-NEXT:       Remove dead machine instructions
 ; CHECK-NEXT:       MachineDominator Tree Construction
 ; CHECK-NEXT:       Machine Natural Loop Construction
 ; CHECK-NEXT:       Machine Trace Metrics
 ; CHECK-NEXT:       Early If-Conversion
+; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       Machine InstCombiner
 ; CHECK-NEXT:       X86 cmov Conversion
 ; CHECK-NEXT:       MachineDominator Tree Construction
 ; CHECK-NEXT:       Machine Natural Loop Construction
 ; CHECK-NEXT:       Early Machine Loop Invariant Code Motion
 ; CHECK-NEXT:       MachineDominator Tree Construction
 ; CHECK-NEXT:       Machine Block Frequency Analysis
 ; CHECK-NEXT:       Machine Common Subexpression Elimination
 ; CHECK-NEXT:       MachinePostDominator Tree Construction
 ; CHECK-NEXT:       Machine code sinking
 ; CHECK-NEXT:       Peephole Optimizations
 ; CHECK-NEXT:       Remove dead machine instructions
 ; CHECK-NEXT:       Live Range Shrink
 ; CHECK-NEXT:       X86 Fixup SetCC
+; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       X86 LEA Optimize
 ; CHECK-NEXT:       X86 Optimize Call Frame
 ; CHECK-NEXT:       X86 Avoid Store Forwarding Block
 ; CHECK-NEXT:       X86 speculative load hardening
 ; CHECK-NEXT:       MachineDominator Tree Construction
 ; CHECK-NEXT:       X86 EFLAGS copy lowering
 ; CHECK-NEXT:       X86 WinAlloca Expander
 ; CHECK-NEXT:       Detect Dead Lanes

 ; CHECK-NEXT:       Machine Block Frequency Analysis
 ; CHECK-NEXT:       MachineDominator Tree Construction
 ; CHECK-NEXT:       MachinePostDominator Tree Construction
 ; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       Machine Optimization Remark Emitter
 ; CHECK-NEXT:       Shrink Wrapping analysis
 ; CHECK-NEXT:       Prologue/Epilogue Insertion & Frame Finalization
 ; CHECK-NEXT:       Control Flow Optimizer
+; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       Tail Duplication
 ; CHECK-NEXT:       Machine Copy Propagation Pass
 ; CHECK-NEXT:       Post-RA pseudo instruction expansion pass
 ; CHECK-NEXT:       X86 pseudo instruction expansion pass
 ; CHECK-NEXT:       MachineDominator Tree Construction
 ; CHECK-NEXT:       Machine Natural Loop Construction
 ; CHECK-NEXT:       Post RA top-down list latency scheduler
 ; CHECK-NEXT:       Analyze Machine Code For Garbage Collection
 ; CHECK-NEXT:       Machine Block Frequency Analysis
 ; CHECK-NEXT:       MachinePostDominator Tree Construction
 ; CHECK-NEXT:       Branch Probability Basic Block Placement
 ; CHECK-NEXT:       ReachingDefAnalysis
 ; CHECK-NEXT:       X86 Execution Dependency Fix
 ; CHECK-NEXT:       BreakFalseDeps
 ; CHECK-NEXT:       X86 Indirect Branch Tracking
 ; CHECK-NEXT:       X86 vzeroupper inserter
 ; CHECK-NEXT:       MachineDominator Tree Construction
 ; CHECK-NEXT:       Machine Natural Loop Construction
+; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       X86 Byte/Word Instruction Fixup
+; CHECK-NEXT:       Lazy Machine Block Frequency Analysis
 ; CHECK-NEXT:       X86 Atom pad short functions
 ; CHECK-NEXT:       X86 LEA Fixup
 ; CHECK-NEXT:       Compressing EVEX instrs to VEX encoding when possible
 ; CHECK-NEXT:       X86 Discriminate Memory Operands
 ; CHECK-NEXT:       X86 Insert Cache Prefetches
 ; CHECK-NEXT:       Contiguously Lay Out Funclets
 ; CHECK-NEXT:       StackMap Liveness Analysis
 ; CHECK-NEXT:       Live DEBUG_VALUE analysis