SamplePGO - Sort samples by source location when emitting as text.

When dumping function samples or writing them out as text format, it
helps if the samples are emitted sorted by source location. The sorting
of the maps is a bit slow, so we only do it on demand.

llvm-svn: 253568

llvm/include/llvm/ProfileData/SampleProf.h

@@ -77,6 +77,10 @@ struct LineLocation {
   LineLocation(uint32_t L, uint32_t D) : LineOffset(L), Discriminator(D) {}
   void print(raw_ostream &OS) const;
   void dump() const;
+  bool operator<(const LineLocation &O) const {
+    return LineOffset < O.LineOffset ||
+           (LineOffset == O.LineOffset && Discriminator < O.Discriminator);
+  }
 
   uint32_t LineOffset;
   uint32_t Discriminator;
@@ -335,6 +339,29 @@ private:
 
 raw_ostream &operator<<(raw_ostream &OS, const FunctionSamples &FS);
 
+/// Sort a LocationT->SampleT map by LocationT.
+///
+/// It produces a sorted list of <LocationT, SampleT> records by ascending
+/// order of LocationT.
+template <class LocationT, class SampleT> class SampleSorter {
+public:
+  typedef detail::DenseMapPair<LocationT, SampleT> SamplesWithLoc;
+  typedef SmallVector<const SamplesWithLoc *, 20> SamplesWithLocList;
+
+  SampleSorter(const DenseMap<LocationT, SampleT> &Samples) {
+    for (const auto &I : Samples)
+      V.push_back(&I);
+    std::stable_sort(V.begin(), V.end(),
+                     [](const SamplesWithLoc *A, const SamplesWithLoc *B) {
+                       return A->first < B->first;
+                     });
+  }
+  const SamplesWithLocList &get() const { return V; }
+
+private:
+  SamplesWithLocList V;
+};
+
 } // end namespace sampleprof
 
 } // end namespace llvm

llvm/lib/ProfileData/SampleProf.cpp

@@ -108,15 +108,18 @@ void FunctionSamples::print(raw_ostream &OS, unsigned Indent) const {
   OS << TotalSamples << ", " << TotalHeadSamples << ", " << BodySamples.size()
      << " sampled lines\n";
 
-  for (const auto &SI : BodySamples) {
+  SampleSorter<LineLocation, SampleRecord> SortedBodySamples(BodySamples);
+  for (const auto &SI : SortedBodySamples.get()) {
     OS.indent(Indent);
-    OS << SI.first << ": " << SI.second;
+    OS << SI->first << ": " << SI->second;
   }
 
-  for (const auto &CS : CallsiteSamples) {
+  SampleSorter<CallsiteLocation, FunctionSamples> SortedCallsiteSamples(
+      CallsiteSamples);
+  for (const auto &CS : SortedCallsiteSamples.get()) {
     OS.indent(Indent);
-    OS << CS.first << ": ";
-    CS.second.print(OS, Indent + 2);
+    OS << CS->first << ": ";
+    CS->second.print(OS, Indent + 2);
   }
 }
 

llvm/lib/ProfileData/SampleProfWriter.cpp

@@ -32,7 +32,7 @@ using namespace llvm;
 /// \brief Write samples to a text file.
 ///
 /// Note: it may be tempting to implement this in terms of
-/// FunctionSamples::dump().  Please don't.  The dump functionality is intended
+/// FunctionSamples::print().  Please don't.  The dump functionality is intended
 /// for debugging and has no specified form.
 ///
 /// The format used here is more structured and deliberate because
@@ -44,9 +44,10 @@ std::error_code SampleProfileWriterText::write(StringRef FName,
     OS << ":" << S.getHeadSamples();
   OS << "\n";
 
-  for (const auto &I : S.getBodySamples()) {
-    LineLocation Loc = I.first;
-    const SampleRecord &Sample = I.second;
+  SampleSorter<LineLocation, SampleRecord> SortedSamples(S.getBodySamples());
+  for (const auto &I : SortedSamples.get()) {
+    LineLocation Loc = I->first;
+    const SampleRecord &Sample = I->second;
     OS.indent(Indent + 1);
     if (Loc.Discriminator == 0)
       OS << Loc.LineOffset << ": ";
@@ -60,10 +61,12 @@ std::error_code SampleProfileWriterText::write(StringRef FName,
     OS << "\n";
   }
 
+  SampleSorter<CallsiteLocation, FunctionSamples> SortedCallsiteSamples(
+      S.getCallsiteSamples());
   Indent += 1;
-  for (const auto &I : S.getCallsiteSamples()) {
-    CallsiteLocation Loc = I.first;
-    const FunctionSamples &CalleeSamples = I.second;
+  for (const auto &I : SortedCallsiteSamples.get()) {
+    CallsiteLocation Loc = I->first;
+    const FunctionSamples &CalleeSamples = I->second;
     OS.indent(Indent);
     if (Loc.Discriminator == 0)
       OS << Loc.LineOffset << ": ";

llvm/test/tools/llvm-profdata/gcc-gcov-sample-profile.test

@@ -11,8 +11,8 @@ RUN: llvm-profdata show --sample %p/Inputs/gcc-sample-profile.gcov | FileCheck %
 SHOW1: Function: main: 364084, 0, 6 sampled lines
 SHOW1: 2.3: inlined callee: _Z3fool: 243786, 0, 3 sampled lines
 SHOW1:   1.3: inlined callee: _Z3bari: 0, 0, 2 sampled lines
-SHOW1:   1.8: inlined callee: _Z3bari: 0, 0, 2 sampled lines
 SHOW1:   1.7: inlined callee: _Z3bari: 98558, 0, 2 sampled lines
+SHOW1:   1.8: inlined callee: _Z3bari: 0, 0, 2 sampled lines
 
 2- Convert the profile to text encoding and check that they are both
    identical.

llvm/test/tools/llvm-profdata/inline-samples.test

@@ -10,9 +10,9 @@ RUN: llvm-profdata show --sample %t.profbin | FileCheck %s --check-prefix=SHOW1
 SHOW1: Function: main: 366846, 0, 6 sampled lines
 SHOW1: 2.3: inlined callee: _Z3fool: 246044, 0, 3 sampled lines
 SHOW1:   1.3: inlined callee: _Z3bari: 0, 0, 2 sampled lines
-SHOW1:   1.8: inlined callee: _Z3bari: 0, 0, 2 sampled lines
 SHOW1:   1.7: inlined callee: _Z3bari: 99492, 0, 2 sampled lines
 SHOW1:     1.2: 46732
+SHOW1:   1.8: inlined callee: _Z3bari: 0, 0, 2 sampled lines
 
 3- Convert the binary profile to text encoding and check that they are both
    identical.