Add an optional arg to include/exclude synthetic profile when query hasProfileData

[davidxl]

Summary

The arg is defaulted to false as most of the users of the interface checks for branch probability data.

Synthetic profile propagation is not on by default, so this patch has no effect on default compilations.

[eraman]

include/llvm/IR/Function.h

310

To me
return EC.hasValue() && (IncludeSynthetic || !EC.isSynthetic()) looks cleaner and readable, but I'll leave it to you.

[davidxl]

Updated the patch to include more APIs.

[eraman]

Instead of passing a boolean, would it be better to pass ProfileCountType enum? Right now it doesn't make a difference as there are only two valid profile count types, but if that set expands, we could make them like bitmasks and then get a subset match.

[davidxl]

It is tempting to use enum in this case, however I don't see possible extension to the type (in forseable future), so perhaps keep this way.

[davidxl]

Update related interfaces in ProfileSummaryInfo.

include/llvm/Analysis/BlockFrequencyInfo.h

   /// means that we should not rely on the value itself, but only on the
   /// comparison to the other block frequencies. We do this to avoid using of
   /// floating points.
   BlockFrequency getBlockFreq(const BasicBlock *BB) const;
 
   /// Returns the estimated profile count of \p BB.
   /// This computes the relative block frequency of \p BB and multiplies it by
   /// the enclosing function's count (if available) and returns the value.
-  Optional<uint64_t> getBlockProfileCount(const BasicBlock *BB) const;
+  Optional<uint64_t> getBlockProfileCount(const BasicBlock *BB,
+                                          bool AllowSynthetic = false) const;
 
   /// Returns the estimated profile count of \p Freq.
   /// This uses the frequency \p Freq and multiplies it by
   /// the enclosing function's count (if available) and returns the value.
   Optional<uint64_t> getProfileCountFromFreq(uint64_t Freq) const;
 
   /// Returns true if \p BB is an irreducible loop header
   /// block. Otherwise false.

include/llvm/Analysis/BlockFrequencyInfoImpl.h

 
   virtual raw_ostream &print(raw_ostream &OS) const { return OS; }
   void dump() const { print(dbgs()); }
 
   Scaled64 getFloatingBlockFreq(const BlockNode &Node) const;
 
   BlockFrequency getBlockFreq(const BlockNode &Node) const;
   Optional<uint64_t> getBlockProfileCount(const Function &F,
-                                          const BlockNode &Node) const;
+                                          const BlockNode &Node,
+                                          bool AllowSynthetic = false) const;
   Optional<uint64_t> getProfileCountFromFreq(const Function &F,
-                                             uint64_t Freq) const;
+                                             uint64_t Freq,
+                                             bool AllowSynthetic = false) const;
   bool isIrrLoopHeader(const BlockNode &Node);
 
   void setBlockFreq(const BlockNode &Node, uint64_t Freq);
 
   raw_ostream &printBlockFreq(raw_ostream &OS, const BlockNode &Node) const;
   raw_ostream &printBlockFreq(raw_ostream &OS,
                               const BlockFrequency &Freq) const;
 

 
   using BlockFrequencyInfoImplBase::getEntryFreq;
 
   BlockFrequency getBlockFreq(const BlockT *BB) const {
     return BlockFrequencyInfoImplBase::getBlockFreq(getNode(BB));
   }
 
   Optional<uint64_t> getBlockProfileCount(const Function &F,
-                                          const BlockT *BB) const {
-    return BlockFrequencyInfoImplBase::getBlockProfileCount(F, getNode(BB));
+                                          const BlockT *BB,
+                                          bool AllowSynthetic = false) const {
+    return BlockFrequencyInfoImplBase::getBlockProfileCount(F, getNode(BB),
+                                                            AllowSynthetic);
   }
 
   Optional<uint64_t> getProfileCountFromFreq(const Function &F,
-                                             uint64_t Freq) const {
-    return BlockFrequencyInfoImplBase::getProfileCountFromFreq(F, Freq);
+                                             uint64_t Freq,
+                                             bool AllowSynthetic = false) const {
+    return BlockFrequencyInfoImplBase::getProfileCountFromFreq(F, Freq,
+                                                               AllowSynthetic);
   }
 
   bool isIrrLoopHeader(const BlockT *BB) {
     return BlockFrequencyInfoImplBase::isIrrLoopHeader(getNode(BB));
   }
 
   void setBlockFreq(const BlockT *BB, uint64_t Freq);
 

include/llvm/IR/Function.h

                      const DenseSet<GlobalValue::GUID> *Imports = nullptr);
 
   /// A convenience wrapper for setting entry count
   void setEntryCount(uint64_t Count, ProfileCountType Type = PCT_Real,
                      const DenseSet<GlobalValue::GUID> *Imports = nullptr);
 
   /// Get the entry count for this function.
   ///
-  /// Entry count is the number of times the function was executed based on
-  /// pgo data.
-  ProfileCount getEntryCount() const;
+  /// Entry count is the number of times the function was executed.
+  /// When AllowSynthetic is false, only pgo_data will be returned.
+  ProfileCount getEntryCount(bool AllowSynthetic = false) const;
 
   /// Return true if the function is annotated with profile data.
   ///
   /// Presence of entry counts from a profile run implies the function has
-  /// profile annotations.
-  bool hasProfileData() const { return getEntryCount().hasValue(); }
+  /// profile annotations. If IncludeSynthetic is false, only return true
+  /// when the profile data is real.
+  bool hasProfileData(bool IncludeSynthetic = false) const {
+    return getEntryCount(IncludeSynthetic).hasValue();
+  }
 
   /// Returns the set of GUIDs that needs to be imported to the function for
   /// sample PGO, to enable the same inlines as the profiled optimized binary.
   DenseSet<GlobalValue::GUID> getImportGUIDs() const;
 
   /// Set the section prefix for this function.
   void setSectionPrefix(StringRef Prefix);
 

lib/Analysis/BlockFrequencyInfo.cpp

   }
 }
 
 BlockFrequency BlockFrequencyInfo::getBlockFreq(const BasicBlock *BB) const {
   return BFI ? BFI->getBlockFreq(BB) : 0;
 }
 
 Optional<uint64_t>
-BlockFrequencyInfo::getBlockProfileCount(const BasicBlock *BB) const {
+BlockFrequencyInfo::getBlockProfileCount(const BasicBlock *BB,
+                                         bool AllowSynthetic) const {
   if (!BFI)
     return None;
 
-  return BFI->getBlockProfileCount(*getFunction(), BB);
+  return BFI->getBlockProfileCount(*getFunction(), BB, AllowSynthetic);
 }
 
 Optional<uint64_t>
 BlockFrequencyInfo::getProfileCountFromFreq(uint64_t Freq) const {
   if (!BFI)
     return None;
   return BFI->getProfileCountFromFreq(*getFunction(), Freq);
 }

lib/Analysis/BlockFrequencyInfoImpl.cpp

 BlockFrequencyInfoImplBase::getBlockFreq(const BlockNode &Node) const {
   if (!Node.isValid())
     return 0;
   return Freqs[Node.Index].Integer;
 }
 
 Optional<uint64_t>
 BlockFrequencyInfoImplBase::getBlockProfileCount(const Function &F,
-                                                 const BlockNode &Node) const {
-  return getProfileCountFromFreq(F, getBlockFreq(Node).getFrequency());
+                                                 const BlockNode &Node,
+                                                 bool AllowSynthetic) const {
+  return getProfileCountFromFreq(F, getBlockFreq(Node).getFrequency(),
+                                 AllowSynthetic);
 }
 
 Optional<uint64_t>
 BlockFrequencyInfoImplBase::getProfileCountFromFreq(const Function &F,
-                                                    uint64_t Freq) const {
-  auto EntryCount = F.getEntryCount();
+                                                    uint64_t Freq,
+                                                    bool AllowSynthetic) const {
+  auto EntryCount = F.getEntryCount(AllowSynthetic);
   if (!EntryCount)
     return None;
   // Use 128 bit APInt to do the arithmetic to avoid overflow.
   APInt BlockCount(128, EntryCount.getCount());
   APInt BlockFreq(128, Freq);
   APInt EntryFreq(128, getEntryFreq());
   BlockCount *= BlockFreq;
   // Rounded division of BlockCount by EntryFreq. Since EntryFreq is unsigned

lib/IR/Function.cpp

       MDB.createFunctionEntryCount(Count.getCount(), Count.isSynthetic(), S));
 }
 
 void Function::setEntryCount(uint64_t Count, Function::ProfileCountType Type,
                              const DenseSet<GlobalValue::GUID> *Imports) {
   setEntryCount(ProfileCount(Count, Type), Imports);
 }
 
-ProfileCount Function::getEntryCount() const {
+ProfileCount Function::getEntryCount(bool AllowSynthetic) const {
   MDNode *MD = getMetadata(LLVMContext::MD_prof);
   if (MD && MD->getOperand(0))
     if (MDString *MDS = dyn_cast<MDString>(MD->getOperand(0))) {
       if (MDS->getString().equals("function_entry_count")) {
         ConstantInt *CI = mdconst::extract<ConstantInt>(MD->getOperand(1));
         uint64_t Count = CI->getValue().getZExtValue();
         // A value of -1 is used for SamplePGO when there were no samples.
         // Treat this the same as unknown.
         if (Count == (uint64_t)-1)
           return ProfileCount::getInvalid();
         return ProfileCount(Count, PCT_Real);
-      } else if (MDS->getString().equals("synthetic_function_entry_count")) {
+      } else if (AllowSynthetic &&
+                 MDS->getString().equals("synthetic_function_entry_count")) {
         ConstantInt *CI = mdconst::extract<ConstantInt>(MD->getOperand(1));
         uint64_t Count = CI->getValue().getZExtValue();
         return ProfileCount(Count, PCT_Synthetic);
       }
     }
   return ProfileCount::getInvalid();
 }