Add hasProfileData() to check if a function has profile data. NFC.

Summary:
This replaces calls to getEntryCount().hasValue() with hasProfileData
that does the same thing. This refactoring is useful to do before adding
synthetic function entry counts but also a useful cleanup IMO even
otherwise. I have used hasProfileData instead of hasRealProfileData as
David had earlier suggested since I think profile implies "real" and I
use the phrase "synthetic entry count" and not "synthetic profile count"
but I am fine calling it hasRealProfileData if you prefer.

Reviewers: davidxl, silvas

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D41461

llvm-svn: 321331

include/llvm/IR/Function.h

@@ -248,6 +248,12 @@ public:
   /// pgo data.
   Optional<uint64_t> getEntryCount() 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(); }
+
   /// 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;

lib/Analysis/ModuleSummaryAnalysis.cpp

@@ -454,7 +454,7 @@ ModuleSummaryIndex llvm::buildModuleSummaryIndex(
     std::unique_ptr<BlockFrequencyInfo> BFIPtr;
     if (GetBFICallback)
       BFI = GetBFICallback(F);
-    else if (F.getEntryCount().hasValue()) {
+    else if (F.hasProfileData()) {
       LoopInfo LI{DominatorTree(const_cast<Function &>(F))};
       BranchProbabilityInfo BPI{F, LI};
       BFIPtr = llvm::make_unique<BlockFrequencyInfo>(F, BPI, LI);

lib/Analysis/ProfileSummaryInfo.cpp

@@ -251,7 +251,7 @@ bool ProfileSummaryInfo::isColdCallSite(const CallSite &CS,
   // If there is no profile for the caller, and we know the profile is
   // accurate, we consider the callsite as cold.
   return (hasSampleProfile() &&
-          (CS.getCaller()->getEntryCount() || ProfileSampleAccurate ||
+          (CS.getCaller()->hasProfileData() || ProfileSampleAccurate ||
            CS.getCaller()->hasFnAttribute("profile-sample-accurate")));
 }
 

lib/Bitcode/Writer/BitcodeWriter.cpp

@@ -3371,7 +3371,7 @@ void ModuleBitcodeWriterBase::writePerModuleFunctionSummaryRecord(
   for (auto &RI : FS->refs())
     NameVals.push_back(VE.getValueID(RI.getValue()));
 
-  bool HasProfileData = F.getEntryCount().hasValue();
+  bool HasProfileData = F.hasProfileData();
   for (auto &ECI : FS->calls()) {
     NameVals.push_back(getValueId(ECI.first));
     if (HasProfileData)

lib/CodeGen/MachineBlockPlacement.cpp

@@ -1235,7 +1235,7 @@ void MachineBlockPlacement::precomputeTriangleChains() {
 // When profile is available, we need to handle the triangle-shape CFG.
 static BranchProbability getLayoutSuccessorProbThreshold(
       const MachineBasicBlock *BB) {
-  if (!BB->getParent()->getFunction().getEntryCount())
+  if (!BB->getParent()->getFunction().hasProfileData())
     return BranchProbability(StaticLikelyProb, 100);
   if (BB->succ_size() == 2) {
     const MachineBasicBlock *Succ1 = *BB->succ_begin();
@@ -2178,7 +2178,7 @@ MachineBlockPlacement::collectLoopBlockSet(const MachineLoop &L) {
   // will be merged into the first outer loop chain for which this block is not
   // cold anymore. This needs precise profile data and we only do this when
   // profile data is available.
-  if (F->getFunction().getEntryCount() || ForceLoopColdBlock) {
+  if (F->getFunction().hasProfileData() || ForceLoopColdBlock) {
     BlockFrequency LoopFreq(0);
     for (auto LoopPred : L.getHeader()->predecessors())
       if (!L.contains(LoopPred))
@@ -2220,7 +2220,7 @@ void MachineBlockPlacement::buildLoopChains(const MachineLoop &L) {
   // for better layout.
   bool RotateLoopWithProfile =
       ForcePreciseRotationCost ||
-      (PreciseRotationCost && F->getFunction().getEntryCount());
+      (PreciseRotationCost && F->getFunction().hasProfileData());
 
   // First check to see if there is an obviously preferable top block for the
   // loop. This will default to the header, but may end up as one of the

lib/Transforms/IPO/PartialInlining.cpp

@@ -710,7 +710,7 @@ PartialInlinerImpl::computeOutliningInfo(Function *F) {
 
 // Check if there is PGO data or user annoated branch data:
 static bool hasProfileData(Function *F, FunctionOutliningInfo *OI) {
-  if (F->getEntryCount())
+  if (F->hasProfileData())
     return true;
   // Now check if any of the entry block has MD_prof data:
   for (auto *E : OI->Entries) {
@@ -1274,7 +1274,7 @@ std::pair<bool, Function *> PartialInlinerImpl::unswitchFunction(Function *F) {
 
   // Only try to outline cold regions if we have a profile summary, which
   // implies we have profiling information.
-  if (PSI->hasProfileSummary() && F->getEntryCount().hasValue() &&
+  if (PSI->hasProfileSummary() && F->hasProfileData() &&
       !DisableMultiRegionPartialInline) {
     std::unique_ptr<FunctionOutliningMultiRegionInfo> OMRI =
         computeOutliningColdRegionsInfo(F);
@@ -1380,10 +1380,10 @@ bool PartialInlinerImpl::tryPartialInline(FunctionCloner &Cloner) {
                             Cloner.ClonedFunc->user_end());
 
   DenseMap<User *, uint64_t> CallSiteToProfCountMap;
-  if (Cloner.OrigFunc->getEntryCount())
+  auto CalleeEntryCount = Cloner.OrigFunc->getEntryCount();
+  if (CalleeEntryCount)
     computeCallsiteToProfCountMap(Cloner.ClonedFunc, CallSiteToProfCountMap);
 
-  auto CalleeEntryCount = Cloner.OrigFunc->getEntryCount();
   uint64_t CalleeEntryCountV = (CalleeEntryCount ? *CalleeEntryCount : 0);
 
   bool AnyInline = false;

lib/Transforms/Scalar/JumpThreading.cpp

@@ -282,7 +282,7 @@ bool JumpThreading::runOnFunction(Function &F) {
   auto AA = &getAnalysis<AAResultsWrapperPass>().getAAResults();
   std::unique_ptr<BlockFrequencyInfo> BFI;
   std::unique_ptr<BranchProbabilityInfo> BPI;
-  bool HasProfileData = F.getEntryCount().hasValue();
+  bool HasProfileData = F.hasProfileData();
   if (HasProfileData) {
     LoopInfo LI{DominatorTree(F)};
     BPI.reset(new BranchProbabilityInfo(F, LI, TLI));
@@ -307,8 +307,7 @@ PreservedAnalyses JumpThreadingPass::run(Function &F,
 
   std::unique_ptr<BlockFrequencyInfo> BFI;
   std::unique_ptr<BranchProbabilityInfo> BPI;
-  bool HasProfileData = F.getEntryCount().hasValue();
-  if (HasProfileData) {
+  if (F.hasProfileData()) {
     LoopInfo LI{DominatorTree(F)};
     BPI.reset(new BranchProbabilityInfo(F, LI, &TLI));
     BFI.reset(new BlockFrequencyInfo(F, *BPI, LI));

lib/Transforms/Scalar/LoopSink.cpp

@@ -247,7 +247,7 @@ static bool sinkLoopInvariantInstructions(Loop &L, AAResults &AA, LoopInfo &LI,
 
   // Enable LoopSink only when runtime profile is available.
   // With static profile, the sinking decision may be sub-optimal.
-  if (!Preheader->getParent()->getEntryCount())
+  if (!Preheader->getParent()->hasProfileData())
     return false;
 
   const BlockFrequency PreheaderFreq = BFI.getBlockFreq(Preheader);

lib/Transforms/Scalar/LoopUnrollPass.cpp

@@ -882,7 +882,7 @@ static bool computeUnrollCount(
   }
   
   // Check if the runtime trip count is too small when profile is available.
-  if (L->getHeader()->getParent()->getEntryCount()) {
+  if (L->getHeader()->getParent()->hasProfileData()) {
     if (auto ProfileTripCount = getLoopEstimatedTripCount(L)) {
       if (*ProfileTripCount < FlatLoopTripCountThreshold)
         return false;

lib/Transforms/Utils/LoopUnrollPeel.cpp

@@ -203,7 +203,7 @@ void llvm::computePeelCount(Loop *L, unsigned LoopSize,
   // hit the peeled section.
   // We only do this in the presence of profile information, since otherwise
   // our estimates of the trip count are not reliable enough.
-  if (UP.AllowPeeling && L->getHeader()->getParent()->getEntryCount()) {
+  if (UP.AllowPeeling && L->getHeader()->getParent()->hasProfileData()) {
     Optional<unsigned> PeelCount = getLoopEstimatedTripCount(L);
     if (!PeelCount)
       return;