[PGO] Refactor the valule profile dumping function for ease of adding other profile kind

[xur]

Summary

This is split off
https://reviews.llvm.org/D28965

Refactor the dumping function so that we can add other value profile kind easily.

[davidxl]

tools/llvm-profdata/llvm-profdata.cpp

559

Better to extract the driver loop into a common function, eg: traverseAllValueSites, and then pass a lambda/callback to do different things such as collect stats or dumping.

[xur]

tools/llvm-profdata/llvm-profdata.cpp

559

it's hard to use a lambda function here as I need to function pointers with captures. I pass all the necessary data variables as the parameters instead.

[davidxl]

lgtm

test/tools/llvm-profdata/value-prof.proftext

 0
 2
 foo:100
 foo2:1000
 1
 foo2:20000
 
 #ICTXT: Indirect Call Site Count: 3
-#ICTXT-NEXT:    Indirect Target Results: 
+#ICTXT-NEXT:    Indirect Target Results:
 #ICTXT-NEXT:  [ 1, foo, 100 ]
 #ICTXT-NEXT:  [ 1, foo2, 1000 ]
 #ICTXT-NEXT:  [ 2, foo2, 20000 ]
 
 #IC: Indirect Call Site Count: 3
-#IC-NEXT:    Indirect Target Results: 
+#IC-NEXT:    Indirect Target Results:
 #IC-NEXT: [ 1, foo2, 1000 ]
 #IC-NEXT: [ 1, foo, 100 ]
 #IC-NEXT: [ 2, foo2, 20000 ]
 
 #ICTEXT: foo:100
 #ICTEXT-NEXT: foo2:1000
 #ICTEXT-NEXT: 1
 #ICTEXT-NEXT: foo2:20000
 #
 
 bar
 # Func Hash:
 10
 # Num Counters:
 2
 # Counter Values:
 999000
 359800
 
-#ICSUM: Total Number of Indirect Call Sites : 3
-#ICSUM: Total Number of Sites With Values : 2
-#ICSUM: Total Number of Profiled Values : 3
+#ICSUM: Statistics for indirect call sites profile:
+#ICSUM: Total number of sites: 3
+#ICSUM: Total number of sites with values: 2
+#ICSUM: Total number of profiled values: 3
 #ICSUM: NumTargets, SiteCount
-#ICSUM  1, 1
-#ICSUM  2, 1
-
+#ICSUM    1, 1
+#ICSUM    2, 1

tools/llvm-profdata/llvm-profdata.cpp

if (ProfileKind == instr)
     mergeInstrProfile(WeightedInputs, OutputFilename, OutputFormat,
                       OutputSparse, NumThreads);
   else
     mergeSampleProfile(WeightedInputs, OutputFilename, OutputFormat);
 
   return 0;
 }
 
+typedef struct ValueSitesStats {
+  ValueSitesStats()
+      : TotalNumValueSites(0), TotalNumValueSitesWithValueProfile(0),
+        TotalNumValues(0) {}
+  uint64_t TotalNumValueSites;
+  uint64_t TotalNumValueSitesWithValueProfile;
+  uint64_t TotalNumValues;
+  std::vector<unsigned> ValueSitesHistogram;
+} ValueSitesStats;
+
+static void CollectValueSitesStats(const InstrProfRecord &Func, uint32_t VK,
+                                   ValueSitesStats &Stats) {
+  uint32_t NS = Func.getNumValueSites(VK);
+  Stats.TotalNumValueSites += NS;
+  for (size_t I = 0; I < NS; ++I) {
+    uint32_t NV = Func.getNumValueDataForSite(VK, I);
+    std::unique_ptr<InstrProfValueData[]> VD = Func.getValueForSite(VK, I);
+    Stats.TotalNumValues += NV;
+    if (NV) {
+      Stats.TotalNumValueSitesWithValueProfile++;
+      if (NV > Stats.ValueSitesHistogram.size())
+        Stats.ValueSitesHistogram.resize(NV, 0);
+      Stats.ValueSitesHistogram[NV - 1]++;
+    }
+  }
+}
+
+static void ShowValueSitesStats(raw_fd_ostream &OS, uint32_t VK,
+                                ValueSitesStats &Stats) {
+  OS << "  Total number of sites: " << Stats.TotalNumValueSites << "\n";
+  OS << "  Total number of sites with values: "
+     << Stats.TotalNumValueSitesWithValueProfile << "\n";
+  OS << "  Total number of profiled values: " << Stats.TotalNumValues << "\n";
+
+  OS << "  Value sites histogram:\n\tNumTargets, SiteCount\n";
+  for (unsigned I = 0; I < Stats.ValueSitesHistogram.size(); I++) {
+    if (Stats.ValueSitesHistogram[I] > 0)
+      OS << "\t" << I + 1 << ", " << Stats.ValueSitesHistogram[I] << "\n";
+  }
+}
+
 static int showInstrProfile(const std::string &Filename, bool ShowCounts,
                             bool ShowIndirectCallTargets,
                             bool ShowDetailedSummary,
                             std::vector<uint32_t> DetailedSummaryCutoffs,
                             bool ShowAllFunctions,
                             const std::string &ShowFunction, bool TextFormat,
                             raw_fd_ostream &OS) {
   auto ReaderOrErr = InstrProfReader::create(Filename);
   std::vector<uint32_t> Cutoffs = std::move(DetailedSummaryCutoffs);
   if (ShowDetailedSummary && Cutoffs.empty()) {
     Cutoffs = {800000, 900000, 950000, 990000, 999000, 999900, 999990};
   }
   InstrProfSummaryBuilder Builder(std::move(Cutoffs));
   if (Error E = ReaderOrErr.takeError())
     exitWithError(std::move(E), Filename);
 
   auto Reader = std::move(ReaderOrErr.get());
   bool IsIRInstr = Reader->isIRLevelProfile();
   size_t ShownFunctions = 0;
-  uint64_t TotalNumValueSites = 0;
-  uint64_t TotalNumValueSitesWithValueProfile = 0;
-  uint64_t TotalNumValues = 0;
-  std::vector<unsigned> ICHistogram;
+  int NumVPKind = IPVK_Last - IPVK_First + 1;
+  std::vector<ValueSitesStats> VPStats(NumVPKind);
   for (const auto &Func : *Reader) {
     bool Show =
         ShowAllFunctions || (!ShowFunction.empty() &&
                              Func.Name.find(ShowFunction) != Func.Name.npos);
 
     bool doTextFormatDump = (Show && ShowCounts && TextFormat);
 
     if (doTextFormatDump) {
if (Show) {
         size_t Start = (IsIRInstr ? 0 : 1);
         for (size_t I = Start, E = Func.Counts.size(); I < E; ++I) {
           OS << (I == Start ? "" : ", ") << Func.Counts[I];
         }
         OS << "]\n";
       }
 
       if (ShowIndirectCallTargets) {
+        CollectValueSitesStats(Func, IPVK_IndirectCallTarget,
+                               VPStats[IPVK_IndirectCallTarget]);
+        OS << "    Indirect Target Results:\n";
         InstrProfSymtab &Symtab = Reader->getSymtab();
         uint32_t NS = Func.getNumValueSites(IPVK_IndirectCallTarget);
-        OS << "    Indirect Target Results: \n";
-        TotalNumValueSites += NS;
         for (size_t I = 0; I < NS; ++I) {
           uint32_t NV = Func.getNumValueDataForSite(IPVK_IndirectCallTarget, I);
           std::unique_ptr<InstrProfValueData[]> VD =
               Func.getValueForSite(IPVK_IndirectCallTarget, I);
-          TotalNumValues += NV;
-          if (NV) {
-            TotalNumValueSitesWithValueProfile++;
-            if (NV > ICHistogram.size())
-              ICHistogram.resize(NV, 0);
-            ICHistogram[NV - 1]++;
-          }
           for (uint32_t V = 0; V < NV; V++) {
             OS << "\t[ " << I << ", ";
             OS << Symtab.getFuncName(VD[V].Value) << ", " << VD[V].Count
                << " ]\n";
           }
         }
       }
     }
   }
   if (Reader->hasError())
     exitWithError(Reader->getError(), Filename);
 
   if (ShowCounts && TextFormat)
     return 0;
   std::unique_ptr<ProfileSummary> PS(Builder.getSummary());
   if (ShowAllFunctions || !ShowFunction.empty())
     OS << "Functions shown: " << ShownFunctions << "\n";
   OS << "Total functions: " << PS->getNumFunctions() << "\n";
   OS << "Maximum function count: " << PS->getMaxFunctionCount() << "\n";
   OS << "Maximum internal block count: " << PS->getMaxInternalCount() << "\n";
   if (ShownFunctions && ShowIndirectCallTargets) {
-    OS << "Total Number of Indirect Call Sites : " << TotalNumValueSites
-       << "\n";
-    OS << "Total Number of Sites With Values : "
-       << TotalNumValueSitesWithValueProfile << "\n";
-    OS << "Total Number of Profiled Values : " << TotalNumValues << "\n";
-
-    OS << "IC Value histogram : \n\tNumTargets, SiteCount\n";
-    for (unsigned I = 0; I < ICHistogram.size(); I++) {
-      OS << "\t" << I + 1 << ", " << ICHistogram[I] << "\n";
-    }
+    OS << "Statistics for indirect call sites profile:\n";
+    ShowValueSitesStats(OS, IPVK_IndirectCallTarget,
+                        VPStats[IPVK_IndirectCallTarget]);
   }
 
   if (ShowDetailedSummary) {
     OS << "Detailed summary:\n";
     OS << "Total number of blocks: " << PS->getNumCounts() << "\n";
     OS << "Total count: " << PS->getTotalCount() << "\n";
     for (auto Entry : PS->getDetailedSummary()) {
       OS << Entry.NumCounts << " blocks with count >= " << Entry.MinCount