[SampleProf] NFC. Expose reusable functionality in SampleProfile.

[mtrofin]

Summary

Exposing getOffset and findFunctionSamples as members of
SampleProfile. They are intimately tied to design choices of the
sample profile format - using offsets instead of line numbers, and
traversing inlined functions stack, respectively.

[davidxl]

lgtm

llvm/trunk/include/llvm/ProfileData/SampleProf.h

public:
   }
 
   /// Set the name of the function.
   void setName(StringRef FunctionName) { Name = FunctionName; }
 
   /// Return the function name.
   const StringRef &getName() const { return Name; }
 
+  /// Returns the line offset to the start line of the subprogram.
+  /// We assume that a single function will not exceed 65535 LOC.
+  static unsigned getOffset(const DILocation *DIL);
+
+  /// \brief Get the FunctionSamples of the inline instance where DIL originates
+  /// from.
+  ///
+  /// The FunctionSamples of the instruction (Machine or IR) associated to
+  /// \p DIL is the inlined instance in which that instruction is coming from.
+  /// We traverse the inline stack of that instruction, and match it with the
+  /// tree nodes in the profile.
+  ///
+  /// \param Inst Instruction to query.
+  ///
+  /// \returns the FunctionSamples pointer to the inlined instance.
+  const FunctionSamples *findFunctionSamples(const DILocation *DIL) const;
+
 private:
   /// Mangled name of the function.
   StringRef Name;
 
   /// Total number of samples collected inside this function.
   ///
   /// Samples are cumulative, they include all the samples collected
   /// inside this function and all its inlined callees.

llvm/trunk/lib/ProfileData/SampleProf.cpp

 //=-- SampleProf.cpp - Sample profiling format support --------------------===//
 //
 //                     The LLVM Compiler Infrastructure
 //
 // This file is distributed under the University of Illinois Open Source
 // License. See LICENSE.TXT for details.
 //
 //===----------------------------------------------------------------------===//
 //
 // This file contains common definitions used in the reading and writing of
 // sample profile data.
 //
 //===----------------------------------------------------------------------===//
 
+#include "llvm/IR/DebugInfoMetadata.h"
 #include "llvm/ProfileData/SampleProf.h"
 #include "llvm/Support/Compiler.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/ManagedStatic.h"
 #include "llvm/Support/raw_ostream.h"
 #include <string>
 #include <system_error>

 }
 
 raw_ostream &llvm::sampleprof::operator<<(raw_ostream &OS,
                                           const FunctionSamples &FS) {
   FS.print(OS);
   return OS;
 }
 
+unsigned FunctionSamples::getOffset(const DILocation *DIL) {
+  return (DIL->getLine() - DIL->getScope()->getSubprogram()->getLine()) &
+      0xffff;
+}
+
+const FunctionSamples *
+FunctionSamples::findFunctionSamples(const DILocation *DIL) const {
+  assert(DIL);
+  SmallVector<std::pair<LineLocation, StringRef>, 10> S;
+
+  const DILocation *PrevDIL = DIL;
+  for (DIL = DIL->getInlinedAt(); DIL; DIL = DIL->getInlinedAt()) {
+    S.push_back(std::make_pair(
+        LineLocation(getOffset(DIL), DIL->getBaseDiscriminator()),
+        PrevDIL->getScope()->getSubprogram()->getLinkageName()));
+    PrevDIL = DIL;
+  }
+  if (S.size() == 0)
+    return this;
+  const FunctionSamples *FS = this;
+  for (int i = S.size() - 1; i >= 0 && FS != nullptr; i--) {
+    FS = FS->findFunctionSamplesAt(S[i].first, S[i].second);
+  }
+  return FS;
+}
+
 #if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
 LLVM_DUMP_METHOD void FunctionSamples::dump() const { print(dbgs(), 0); }
 #endif

llvm/trunk/lib/Transforms/IPO/SampleProfile.cpp

protected:
   void findEquivalencesFor(BasicBlock *BB1, ArrayRef<BasicBlock *> Descendants,
                            DominatorTreeBase<BasicBlock, IsPostDom> *DomTree);
 
   void propagateWeights(Function &F);
   uint64_t visitEdge(Edge E, unsigned *NumUnknownEdges, Edge *UnknownEdge);
   void buildEdges(Function &F);
   bool propagateThroughEdges(Function &F, bool UpdateBlockCount);
   void computeDominanceAndLoopInfo(Function &F);
-  unsigned getOffset(const DILocation *DIL) const;
   void clearFunctionData();
 
   /// \brief Map basic blocks to their computed weights.
   ///
   /// The weight of a basic block is defined to be the maximum
   /// of all the instruction weights in that block.
   BlockWeightMap BlockWeights;
 
void SampleProfileLoader::clearFunctionData() {
   DT = nullptr;
   PDT = nullptr;
   LI = nullptr;
   Predecessors.clear();
   Successors.clear();
   CoverageTracker.clear();
 }
 
-/// Returns the line offset to the start line of the subprogram.
-/// We assume that a single function will not exceed 65535 LOC.
-unsigned SampleProfileLoader::getOffset(const DILocation *DIL) const {
-  return (DIL->getLine() - DIL->getScope()->getSubprogram()->getLine()) &
-         0xffff;
-}
-
 #ifndef NDEBUG
 /// \brief Print the weight of edge \p E on stream \p OS.
 ///
 /// \param OS  Stream to emit the output to.
 /// \param E  Edge to print.
 void SampleProfileLoader::printEdgeWeight(raw_ostream &OS, Edge E) {
   OS << "weight[" << E.first->getName() << "->" << E.second->getName()
      << "]: " << EdgeWeights[E] << "\n";
ErrorOr<uint64_t> SampleProfileLoader::getInstWeight(const Instruction &Inst) {
   // it means that the inlined callsite has no sample, thus the call
   // instruction should have 0 count.
   if ((isa<CallInst>(Inst) || isa<InvokeInst>(Inst)) &&
       !ImmutableCallSite(&Inst).isIndirectCall() &&
       findCalleeFunctionSamples(Inst))
     return 0;
 
   const DILocation *DIL = DLoc;
-  uint32_t LineOffset = getOffset(DIL);
+  uint32_t LineOffset = FunctionSamples::getOffset(DIL);
   uint32_t Discriminator = DIL->getBaseDiscriminator();
   ErrorOr<uint64_t> R = FS->findSamplesAt(LineOffset, Discriminator);
   if (R) {
     bool FirstMark =
         CoverageTracker.markSamplesUsed(FS, LineOffset, Discriminator, R.get());
     if (FirstMark) {
       ORE->emit([&]() {
         OptimizationRemarkAnalysis Remark(DEBUG_TYPE, "AppliedSamples", &Inst);
SampleProfileLoader::findCalleeFunctionSamples(const Instruction &Inst) const {
   if (const CallInst *CI = dyn_cast<CallInst>(&Inst))
     if (Function *Callee = CI->getCalledFunction())
       CalleeName = Callee->getName();
 
   const FunctionSamples *FS = findFunctionSamples(Inst);
   if (FS == nullptr)
     return nullptr;
 
-  return FS->findFunctionSamplesAt(
-      LineLocation(getOffset(DIL), DIL->getBaseDiscriminator()), CalleeName);
+  return FS->findFunctionSamplesAt(LineLocation(FunctionSamples::getOffset(DIL),
+                                                DIL->getBaseDiscriminator()),
+                                   CalleeName);
 }
 
 /// Returns a vector of FunctionSamples that are the indirect call targets
 /// of \p Inst. The vector is sorted by the total number of samples. Stores
 /// the total call count of the indirect call in \p Sum.
 std::vector<const FunctionSamples *>
 SampleProfileLoader::findIndirectCallFunctionSamples(
     const Instruction &Inst, uint64_t &Sum) const {
   const DILocation *DIL = Inst.getDebugLoc();
   std::vector<const FunctionSamples *> R;
 
   if (!DIL) {
     return R;
   }
 
   const FunctionSamples *FS = findFunctionSamples(Inst);
   if (FS == nullptr)
     return R;
 
-  uint32_t LineOffset = getOffset(DIL);
+  uint32_t LineOffset = FunctionSamples::getOffset(DIL);
   uint32_t Discriminator = DIL->getBaseDiscriminator();
 
   auto T = FS->findCallTargetMapAt(LineOffset, Discriminator);
   Sum = 0;
   if (T)
     for (const auto &T_C : T.get())
       Sum += T_C.second;
-  if (const FunctionSamplesMap *M = FS->findFunctionSamplesMapAt(
-          LineLocation(getOffset(DIL), DIL->getBaseDiscriminator()))) {
+  if (const FunctionSamplesMap *M = FS->findFunctionSamplesMapAt(LineLocation(
+          FunctionSamples::getOffset(DIL), DIL->getBaseDiscriminator()))) {
     if (M->empty())
       return R;
     for (const auto &NameFS : *M) {
       Sum += NameFS.second.getEntrySamples();
       R.push_back(&NameFS.second);
     }
     std::sort(R.begin(), R.end(),
               [](const FunctionSamples *L, const FunctionSamples *R) {

 /// \returns the FunctionSamples pointer to the inlined instance.
 const FunctionSamples *
 SampleProfileLoader::findFunctionSamples(const Instruction &Inst) const {
   SmallVector<std::pair<LineLocation, StringRef>, 10> S;
   const DILocation *DIL = Inst.getDebugLoc();
   if (!DIL)
     return Samples;
 
-  const DILocation *PrevDIL = DIL;
-  for (DIL = DIL->getInlinedAt(); DIL; DIL = DIL->getInlinedAt()) {
-    S.push_back(std::make_pair(
-        LineLocation(getOffset(DIL), DIL->getBaseDiscriminator()),
-        PrevDIL->getScope()->getSubprogram()->getLinkageName()));
-    PrevDIL = DIL;
-  }
-  if (S.size() == 0)
-    return Samples;
-  const FunctionSamples *FS = Samples;
-  for (int i = S.size() - 1; i >= 0 && FS != nullptr; i--) {
-    FS = FS->findFunctionSamplesAt(S[i].first, S[i].second);
-  }
-  return FS;
+  return Samples->findFunctionSamples(DIL);
 }
 
 bool SampleProfileLoader::inlineCallInstruction(Instruction *I) {
   assert(isa<CallInst>(I) || isa<InvokeInst>(I));
   CallSite CS(I);
   Function *CalledFunction = CS.getCalledFunction();
   assert(CalledFunction);
   DebugLoc DLoc = I->getDebugLoc();
if (BlockWeights[BB]) {
         if (!isa<CallInst>(I) && !isa<InvokeInst>(I))
           continue;
         CallSite CS(&I);
         if (!CS.getCalledFunction()) {
           const DebugLoc &DLoc = I.getDebugLoc();
           if (!DLoc)
             continue;
           const DILocation *DIL = DLoc;
-          uint32_t LineOffset = getOffset(DIL);
+          uint32_t LineOffset = FunctionSamples::getOffset(DIL);
           uint32_t Discriminator = DIL->getBaseDiscriminator();
 
           const FunctionSamples *FS = findFunctionSamples(I);
           if (!FS)
             continue;
           auto T = FS->findCallTargetMapAt(LineOffset, Discriminator);
           if (!T || T.get().empty())
             continue;