Refactor profile summary support code. NFC.

[eraman]

Summary

Summary computation is not just for instrumented profiling and so I have moved the ProfileSummary class to ProfileCommon.h (named so to allow code unrelated to summary but common to instrumented and sampled profiling to be placed there)

[davidxl]

lgtm

llvm/trunk/include/llvm/ProfileData/InstrProf.h

 #ifndef LLVM_PROFILEDATA_INSTRPROF_H
 #define LLVM_PROFILEDATA_INSTRPROF_H
 
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/ADT/StringSet.h"
 #include "llvm/IR/GlobalValue.h"
 #include "llvm/ProfileData/InstrProfData.inc"
+#include "llvm/ProfileData/ProfileCommon.h"
 #include "llvm/Support/Endian.h"
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/ErrorOr.h"
 #include "llvm/Support/MD5.h"
 #include "llvm/Support/MathExtras.h"
 #include <cstdint>
 #include <list>
 #include <map>

 uint32_t getValueProfDataSizeRT(const ValueProfRuntimeRecord *Record);
 
 /* Return a ValueProfData instance that stores the data collected at runtime. */
 ValueProfData *
 serializeValueProfDataFromRT(const ValueProfRuntimeRecord *Record,
                              ValueProfData *Dst);
 
 namespace IndexedInstrProf {
-struct Summary;
-}
-
-///// Profile summary computation ////
-// The 'show' command displays richer summary of the profile data. The profile
-// summary is one or more (Cutoff, MinBlockCount, NumBlocks) triplets. Given a
-// target execution count percentile, we compute the minimum number of blocks
-// needed to reach this target and the minimum execution count of these blocks.
-struct ProfileSummaryEntry {
-  uint32_t Cutoff;        ///< The required percentile of total execution count.
-  uint64_t MinBlockCount; ///< The minimum execution count for this percentile.
-  uint64_t NumBlocks;     ///< Number of blocks >= the minumum execution count.
-  ProfileSummaryEntry(uint32_t TheCutoff, uint64_t TheMinBlockCount,
-                      uint64_t TheNumBlocks)
-      : Cutoff(TheCutoff), MinBlockCount(TheMinBlockCount),
-        NumBlocks(TheNumBlocks) {}
-};
-
-class ProfileSummary {
-  // We keep track of the number of times a count appears in the profile and
-  // keep the map sorted in the descending order of counts.
-  std::map<uint64_t, uint32_t, std::greater<uint64_t>> CountFrequencies;
-  std::vector<ProfileSummaryEntry> DetailedSummary;
-  std::vector<uint32_t> DetailedSummaryCutoffs;
-  // Sum of all counts.
-  uint64_t TotalCount;
-  uint64_t MaxBlockCount, MaxInternalBlockCount, MaxFunctionCount;
-  uint32_t NumBlocks, NumFunctions;
-  inline void addCount(uint64_t Count, bool IsEntry);
-
-public:
-  static const int Scale = 1000000;
-  ProfileSummary(std::vector<uint32_t> Cutoffs)
-      : DetailedSummaryCutoffs(Cutoffs), TotalCount(0), MaxBlockCount(0),
-        MaxInternalBlockCount(0), MaxFunctionCount(0), NumBlocks(0),
-        NumFunctions(0) {}
-  ProfileSummary(const IndexedInstrProf::Summary &S);
-  inline void addRecord(const InstrProfRecord &);
-  inline std::vector<ProfileSummaryEntry> &getDetailedSummary();
-  void computeDetailedSummary();
-  uint32_t getNumBlocks() { return NumBlocks; }
-  uint64_t getTotalCount() { return TotalCount; }
-  uint32_t getNumFunctions() { return NumFunctions; }
-  uint64_t getMaxFunctionCount() { return MaxFunctionCount; }
-  uint64_t getMaxBlockCount() { return MaxBlockCount; }
-  uint64_t getMaxInternalBlockCount() { return MaxInternalBlockCount; }
-};
-
-// This is called when a count is seen in the profile.
-void ProfileSummary::addCount(uint64_t Count, bool IsEntry) {
-  TotalCount += Count;
-  if (Count > MaxBlockCount)
-    MaxBlockCount = Count;
-  if (!IsEntry && Count > MaxInternalBlockCount)
-    MaxInternalBlockCount = Count;
-  NumBlocks++;
-  CountFrequencies[Count]++;
-}
-
-void ProfileSummary::addRecord(const InstrProfRecord &R) {
-  NumFunctions++;
-  if (R.Counts[0] > MaxFunctionCount)
-    MaxFunctionCount = R.Counts[0];
-
-  for (size_t I = 0, E = R.Counts.size(); I < E; ++I)
-    addCount(R.Counts[I], (I == 0));
-}
-
-std::vector<ProfileSummaryEntry> &ProfileSummary::getDetailedSummary() {
-  if (!DetailedSummaryCutoffs.empty() && DetailedSummary.empty())
-    computeDetailedSummary();
-  return DetailedSummary;
-}
-
-namespace IndexedInstrProf {
 
 enum class HashT : uint32_t {
   MD5,
 
   Last = MD5
 };
 
 static inline uint64_t MD5Hash(StringRef Str) {

llvm/trunk/include/llvm/ProfileData/ProfileCommon.h

+//===-- ProfileCommon.h - Common profiling APIs. ----------------*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file contains data structures and functions common to both instrumented
+// and sample profiling.
+//
+//===----------------------------------------------------------------------===//
+
+#include <cstdint>
+#include <map>
+#include <vector>
+
+#ifndef LLVM_PROFILEDATA_PROFILE_COMMON_H
+#define LLVM_PROFILEDATA_PROFILE_COMMON_H
+
+namespace llvm {
+namespace IndexedInstrProf {
+struct Summary;
+}
+class InstrProfRecord;
+///// Profile summary computation ////
+// The 'show' command displays richer summary of the profile data. The profile
+// summary is one or more (Cutoff, MinBlockCount, NumBlocks) triplets. Given a
+// target execution count percentile, we compute the minimum number of blocks
+// needed to reach this target and the minimum execution count of these blocks.
+struct ProfileSummaryEntry {
+  uint32_t Cutoff;        ///< The required percentile of total execution count.
+  uint64_t MinBlockCount; ///< The minimum execution count for this percentile.
+  uint64_t NumBlocks;     ///< Number of blocks >= the minumum execution count.
+  ProfileSummaryEntry(uint32_t TheCutoff, uint64_t TheMinBlockCount,
+                      uint64_t TheNumBlocks)
+      : Cutoff(TheCutoff), MinBlockCount(TheMinBlockCount),
+        NumBlocks(TheNumBlocks) {}
+};
+
+class ProfileSummary {
+  // We keep track of the number of times a count appears in the profile and
+  // keep the map sorted in the descending order of counts.
+  std::map<uint64_t, uint32_t, std::greater<uint64_t>> CountFrequencies;
+  std::vector<ProfileSummaryEntry> DetailedSummary;
+  std::vector<uint32_t> DetailedSummaryCutoffs;
+  // Sum of all counts.
+  uint64_t TotalCount;
+  uint64_t MaxBlockCount, MaxInternalBlockCount, MaxFunctionCount;
+  uint32_t NumBlocks, NumFunctions;
+  inline void addCount(uint64_t Count, bool IsEntry);
+
+public:
+  static const int Scale = 1000000;
+  ProfileSummary(std::vector<uint32_t> Cutoffs)
+      : DetailedSummaryCutoffs(Cutoffs), TotalCount(0), MaxBlockCount(0),
+        MaxInternalBlockCount(0), MaxFunctionCount(0), NumBlocks(0),
+        NumFunctions(0) {}
+  ProfileSummary(const IndexedInstrProf::Summary &S);
+  void addRecord(const InstrProfRecord &);
+  inline std::vector<ProfileSummaryEntry> &getDetailedSummary();
+  void computeDetailedSummary();
+  uint32_t getNumBlocks() { return NumBlocks; }
+  uint64_t getTotalCount() { return TotalCount; }
+  uint32_t getNumFunctions() { return NumFunctions; }
+  uint64_t getMaxFunctionCount() { return MaxFunctionCount; }
+  uint64_t getMaxBlockCount() { return MaxBlockCount; }
+  uint64_t getMaxInternalBlockCount() { return MaxInternalBlockCount; }
+};
+
+// This is called when a count is seen in the profile.
+void ProfileSummary::addCount(uint64_t Count, bool IsEntry) {
+  TotalCount += Count;
+  if (Count > MaxBlockCount)
+    MaxBlockCount = Count;
+  if (!IsEntry && Count > MaxInternalBlockCount)
+    MaxInternalBlockCount = Count;
+  NumBlocks++;
+  CountFrequencies[Count]++;
+}
+
+std::vector<ProfileSummaryEntry> &ProfileSummary::getDetailedSummary() {
+  if (!DetailedSummaryCutoffs.empty() && DetailedSummary.empty())
+    computeDetailedSummary();
+  return DetailedSummary;
+}
+
+} // end namespace llvm
+#endif

llvm/trunk/lib/ProfileData/CMakeLists.txt

 add_llvm_library(LLVMProfileData
   InstrProf.cpp
   InstrProfReader.cpp
   InstrProfWriter.cpp
   CoverageMapping.cpp
   CoverageMappingWriter.cpp
   CoverageMappingReader.cpp
+  ProfileSummary.cpp
   SampleProf.cpp
   SampleProfReader.cpp
   SampleProfWriter.cpp
 
   ADDITIONAL_HEADER_DIRS
   ${LLVM_MAIN_INCLUDE_DIR}/llvm/ProfileData
 
   DEPENDS
   intrinsics_gen
   )

llvm/trunk/lib/ProfileData/InstrProf.cpp

for (unsigned I = 3; I < NOps; I += 2) {
     if (!Value || !Count)
       return false;
     ValueData[ActualNumValueData].Value = Value->getZExtValue();
     ValueData[ActualNumValueData].Count = Count->getZExtValue();
     ActualNumValueData++;
   }
   return true;
 }
-
-// The argument to this method is a vector of cutoff percentages and the return
-// value is a vector of (Cutoff, MinBlockCount, NumBlocks) triplets.
-void ProfileSummary::computeDetailedSummary() {
-  if (DetailedSummaryCutoffs.empty())
-    return;
-  auto Iter = CountFrequencies.begin();
-  auto End = CountFrequencies.end();
-  std::sort(DetailedSummaryCutoffs.begin(), DetailedSummaryCutoffs.end());
-
-  uint32_t BlocksSeen = 0;
-  uint64_t CurrSum = 0, Count = 0;
-
-  for (uint32_t Cutoff : DetailedSummaryCutoffs) {
-    assert(Cutoff <= 999999);
-    APInt Temp(128, TotalCount);
-    APInt N(128, Cutoff);
-    APInt D(128, ProfileSummary::Scale);
-    Temp *= N;
-    Temp = Temp.sdiv(D);
-    uint64_t DesiredCount = Temp.getZExtValue();
-    assert(DesiredCount <= TotalCount);
-    while (CurrSum < DesiredCount && Iter != End) {
-      Count = Iter->first;
-      uint32_t Freq = Iter->second;
-      CurrSum += (Count * Freq);
-      BlocksSeen += Freq;
-      Iter++;
-    }
-    assert(CurrSum >= DesiredCount);
-    ProfileSummaryEntry PSE = {Cutoff, Count, BlocksSeen};
-    DetailedSummary.push_back(PSE);
-  }
-}
-
-ProfileSummary::ProfileSummary(const IndexedInstrProf::Summary &S)
-    : TotalCount(S.get(IndexedInstrProf::Summary::TotalBlockCount)),
-      MaxBlockCount(S.get(IndexedInstrProf::Summary::MaxBlockCount)),
-      MaxInternalBlockCount(
-          S.get(IndexedInstrProf::Summary::MaxInternalBlockCount)),
-      MaxFunctionCount(S.get(IndexedInstrProf::Summary::MaxFunctionCount)),
-      NumBlocks(S.get(IndexedInstrProf::Summary::TotalNumBlocks)),
-      NumFunctions(S.get(IndexedInstrProf::Summary::TotalNumFunctions)) {
-  for (unsigned I = 0; I < S.NumCutoffEntries; I++) {
-    const IndexedInstrProf::Summary::Entry &Ent = S.getEntry(I);
-    DetailedSummary.emplace_back((uint32_t)Ent.Cutoff, Ent.MinBlockCount,
-                                 Ent.NumBlocks);
-  }
-}
-
 } // end namespace llvm

llvm/trunk/lib/ProfileData/ProfileSummary.cpp

+//=-- Profilesummary.cpp - Profile summary computation ----------------------=//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file contains support for computing profile summary data.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/ProfileData/ProfileCommon.h"
+#include "llvm/ProfileData/InstrProf.h"
+
+using namespace llvm;
+
+void ProfileSummary::addRecord(const InstrProfRecord &R) {
+  NumFunctions++;
+  if (R.Counts[0] > MaxFunctionCount)
+    MaxFunctionCount = R.Counts[0];
+
+  for (size_t I = 0, E = R.Counts.size(); I < E; ++I)
+    addCount(R.Counts[I], (I == 0));
+}
+
+// The argument to this method is a vector of cutoff percentages and the return
+// value is a vector of (Cutoff, MinBlockCount, NumBlocks) triplets.
+void ProfileSummary::computeDetailedSummary() {
+  if (DetailedSummaryCutoffs.empty())
+    return;
+  auto Iter = CountFrequencies.begin();
+  auto End = CountFrequencies.end();
+  std::sort(DetailedSummaryCutoffs.begin(), DetailedSummaryCutoffs.end());
+
+  uint32_t BlocksSeen = 0;
+  uint64_t CurrSum = 0, Count = 0;
+
+  for (uint32_t Cutoff : DetailedSummaryCutoffs) {
+    assert(Cutoff <= 999999);
+    APInt Temp(128, TotalCount);
+    APInt N(128, Cutoff);
+    APInt D(128, ProfileSummary::Scale);
+    Temp *= N;
+    Temp = Temp.sdiv(D);
+    uint64_t DesiredCount = Temp.getZExtValue();
+    assert(DesiredCount <= TotalCount);
+    while (CurrSum < DesiredCount && Iter != End) {
+      Count = Iter->first;
+      uint32_t Freq = Iter->second;
+      CurrSum += (Count * Freq);
+      BlocksSeen += Freq;
+      Iter++;
+    }
+    assert(CurrSum >= DesiredCount);
+    ProfileSummaryEntry PSE = {Cutoff, Count, BlocksSeen};
+    DetailedSummary.push_back(PSE);
+  }
+}
+
+ProfileSummary::ProfileSummary(const IndexedInstrProf::Summary &S)
+    : TotalCount(S.get(IndexedInstrProf::Summary::TotalBlockCount)),
+      MaxBlockCount(S.get(IndexedInstrProf::Summary::MaxBlockCount)),
+      MaxInternalBlockCount(
+          S.get(IndexedInstrProf::Summary::MaxInternalBlockCount)),
+      MaxFunctionCount(S.get(IndexedInstrProf::Summary::MaxFunctionCount)),
+      NumBlocks(S.get(IndexedInstrProf::Summary::TotalNumBlocks)),
+      NumFunctions(S.get(IndexedInstrProf::Summary::TotalNumFunctions)) {
+  for (unsigned I = 0; I < S.NumCutoffEntries; I++) {
+    const IndexedInstrProf::Summary::Entry &Ent = S.getEntry(I);
+    DetailedSummary.emplace_back((uint32_t)Ent.Cutoff, Ent.MinBlockCount,
+                                 Ent.NumBlocks);
+  }
+}

llvm/trunk/tools/llvm-profdata/llvm-profdata.cpp

 //===----------------------------------------------------------------------===//
 
 #include "llvm/ADT/SmallSet.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/StringRef.h"
 #include "llvm/IR/LLVMContext.h"
 #include "llvm/ProfileData/InstrProfReader.h"
 #include "llvm/ProfileData/InstrProfWriter.h"
+#include "llvm/ProfileData/ProfileCommon.h"
 #include "llvm/ProfileData/SampleProfReader.h"
 #include "llvm/ProfileData/SampleProfWriter.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Errc.h"
 #include "llvm/Support/FileSystem.h"
 #include "llvm/Support/Format.h"
 #include "llvm/Support/ManagedStatic.h"
 #include "llvm/Support/MemoryBuffer.h"