[PGO] Revisied patch: Differentiate Clang instrumentation and IR level instrumentation profiles

[xur]

Summary

The original review is: Differential Revision: http://reviews.llvm.org/D15540

I reverted the commit r260164 because it broke one darwin test in compile-rt/profile/

The reason for the breakage is Mach-O platform doesn’t support COMDATs. In this revised patch, I create a linkonce variable for the MachO platform and remain to create a comdat variable for other platforms.

I change the test Transform/PGOInstrumentation/branch1.ll to test linkonce variable creation.

Other part of the patch is the same.

Tested the patch in Marbook pro and Linux.

Thanks,

-Rong

[davidxl]

lib/Transforms/Instrumentation/PGOInstrumentation.cpp

729

Why not linkonceODR -- the version var generated in each TU needs to be the same.

733

Remove this comment line.

[xur]

uploaded the new patch integrated David's comments.

[t.p.northover]

Hi Rong,

Thanks for fixing the issue. I've checked on my local machines and I think this one works fine on Darwin.

Tim.

[davidxl]

lgtm

include/llvm/ProfileData/InstrProfData.inc

 #define INSTR_PROF_INDEX_VERSION 4
 /* Coverage mapping format vresion (start from 0). */
 #define INSTR_PROF_COVMAP_VERSION 1
 
 /* Profile version is always of type uint64_t. Reserve the upper 8 bits in the
  * version for other variants of profile. We set the lowest bit of the upper 8
  * bits (i.e. bit 56) to 1 to indicate if this is an IR-level instrumentaiton
  * generated profile, and 0 if this is a Clang FE generated profile.
  */
 #define VARIANT_MASKS_ALL 0xff00000000000000ULL
 #define GET_VERSION(V) ((V) & ~VARIANT_MASKS_ALL)
+#define VARIANT_MASK_IR_PROF (0x1ULL << 56)
+#define IR_LEVEL_PROF_VERSION_VAR __llvm_profile_raw_version
 
 /* Runtime section names and name strings.  */
 #define INSTR_PROF_DATA_SECT_NAME __llvm_prf_data
 #define INSTR_PROF_NAME_SECT_NAME __llvm_prf_names
 #define INSTR_PROF_CNTS_SECT_NAME __llvm_prf_cnts
 #define INSTR_PROF_COVMAP_SECT_NAME __llvm_covmap
 
 #define INSTR_PROF_DATA_SECT_NAME_STR                                          \

include/llvm/ProfileData/InstrProfReader.h

public:
 
   /// Read the header.  Required before reading first record.
   virtual std::error_code readHeader() = 0;
   /// Read a single record.
   virtual std::error_code readNextRecord(InstrProfRecord &Record) = 0;
   /// Iterator over profile data.
   InstrProfIterator begin() { return InstrProfIterator(this); }
   InstrProfIterator end() { return InstrProfIterator(); }
+  virtual bool isIRLevelProfile() const = 0;
 
   /// Return the PGO symtab. There are three different readers:
   /// Raw, Text, and Indexed profile readers. The first two types
   /// of readers are used only by llvm-profdata tool, while the indexed
   /// profile reader is also used by llvm-cov tool and the compiler (
   /// backend or frontend). Since creating PGO symtab can create
   /// significant runtime and memory overhead (as it touches data
   /// for the whole program), InstrProfSymtab for the indexed profile

 /// Each record consists of a function name, a function hash, a number of
 /// counters, and then each counter value, in that order.
 class TextInstrProfReader : public InstrProfReader {
 private:
   /// The profile data file contents.
   std::unique_ptr<MemoryBuffer> DataBuffer;
   /// Iterator over the profile data.
   line_iterator Line;
+  bool IsIRLevelProfile;
 
   TextInstrProfReader(const TextInstrProfReader &) = delete;
   TextInstrProfReader &operator=(const TextInstrProfReader &) = delete;
   std::error_code readValueProfileData(InstrProfRecord &Record);
 
 public:
   TextInstrProfReader(std::unique_ptr<MemoryBuffer> DataBuffer_)
-      : DataBuffer(std::move(DataBuffer_)), Line(*DataBuffer, true, '#') {}
+      : DataBuffer(std::move(DataBuffer_)), Line(*DataBuffer, true, '#'),
+        IsIRLevelProfile(false) {}
 
   /// Return true if the given buffer is in text instrprof format.
   static bool hasFormat(const MemoryBuffer &Buffer);
 
+  bool isIRLevelProfile() const override { return IsIRLevelProfile; }
+
   /// Read the header.
   std::error_code readHeader() override;
   /// Read a single record.
   std::error_code readNextRecord(InstrProfRecord &Record) override;
 
   InstrProfSymtab &getSymtab() override {
     assert(Symtab.get());
     return *Symtab.get();
   }
 };
 
 /// Reader for the raw instrprof binary format from runtime.
 ///
 /// This format is a raw memory dump of the instrumentation-baed profiling data
 /// from the runtime.  It has no index.
 ///
 /// Templated on the unsigned type whose size matches pointers on the platform
 /// that wrote the profile.
 template <class IntPtrT>
 class RawInstrProfReader : public InstrProfReader {
 private:
   /// The profile data file contents.
   std::unique_ptr<MemoryBuffer> DataBuffer;
   bool ShouldSwapBytes;
+  // The value of the version field of the raw profile data header. The lower 56
+  // bits specifies the format version and the most significant 8 bits specify
+  // the variant types of the profile.
+  uint64_t Version;
   uint64_t CountersDelta;
   uint64_t NamesDelta;
   const RawInstrProf::ProfileData<IntPtrT> *Data;
   const RawInstrProf::ProfileData<IntPtrT> *DataEnd;
   const uint64_t *CountersStart;
   const char *NamesStart;
   uint64_t NamesSize;
   const uint8_t *ValueDataStart;
   const char *ProfileEnd;
   uint32_t ValueKindLast;
   uint32_t CurValueDataSize;
 
   InstrProfRecord::ValueMapType FunctionPtrToNameMap;
 
   RawInstrProfReader(const RawInstrProfReader &) = delete;
   RawInstrProfReader &operator=(const RawInstrProfReader &) = delete;
 public:
   RawInstrProfReader(std::unique_ptr<MemoryBuffer> DataBuffer)
       : DataBuffer(std::move(DataBuffer)) { }
 
   static bool hasFormat(const MemoryBuffer &DataBuffer);
   std::error_code readHeader() override;
   std::error_code readNextRecord(InstrProfRecord &Record) override;
+  bool isIRLevelProfile() const override {
+    return (Version & VARIANT_MASK_IR_PROF) != 0;
+  }
 
   InstrProfSymtab &getSymtab() override {
     assert(Symtab.get());
     return *Symtab.get();
   }
 
 private:
   void createSymtab(InstrProfSymtab &Symtab);
struct InstrProfReaderIndexBase {
   // Read all the profile records with the key equal to FuncName
   virtual std::error_code getRecords(StringRef FuncName,
                                      ArrayRef<InstrProfRecord> &Data) = 0;
   virtual void advanceToNextKey() = 0;
   virtual bool atEnd() const = 0;
   virtual void setValueProfDataEndianness(support::endianness Endianness) = 0;
   virtual ~InstrProfReaderIndexBase() {}
   virtual uint64_t getVersion() const = 0;
+  virtual bool isIRLevelProfile() const = 0;
   virtual void populateSymtab(InstrProfSymtab &) = 0;
 };
 
 typedef OnDiskIterableChainedHashTable<InstrProfLookupTrait>
     OnDiskHashTableImplV3;
 
 template <typename HashTableImpl>
 class InstrProfReaderIndex : public InstrProfReaderIndexBase {
public:
   void advanceToNextKey() override { RecordIterator++; }
   bool atEnd() const override {
     return RecordIterator == HashTable->data_end();
   }
   void setValueProfDataEndianness(support::endianness Endianness) override {
     HashTable->getInfoObj().setValueProfDataEndianness(Endianness);
   }
   ~InstrProfReaderIndex() override {}
-  uint64_t getVersion() const override { return FormatVersion; }
+  uint64_t getVersion() const override { return GET_VERSION(FormatVersion); }
+  bool isIRLevelProfile() const override {
+    return (FormatVersion & VARIANT_MASK_IR_PROF) != 0;
+  }
   void populateSymtab(InstrProfSymtab &Symtab) override {
     Symtab.create(HashTable->keys());
   }
 };
 
 /// Reader for the indexed binary instrprof format.
 class IndexedInstrProfReader : public InstrProfReader {
 private:
   /// The profile data file contents.
   std::unique_ptr<MemoryBuffer> DataBuffer;
   /// The index into the profile data.
   std::unique_ptr<InstrProfReaderIndexBase> Index;
   /// Profile summary data.
   std::unique_ptr<ProfileSummary> Summary;
 
   IndexedInstrProfReader(const IndexedInstrProfReader &) = delete;
   IndexedInstrProfReader &operator=(const IndexedInstrProfReader &) = delete;
 
   // Read the profile summary. Return a pointer pointing to one byte past the
   // end of the summary data if it exists or the input \c Cur.
   const unsigned char *readSummary(IndexedInstrProf::ProfVersion Version,
                                    const unsigned char *Cur);
 
 public:
+  /// Return the profile version.
   uint64_t getVersion() const { return Index->getVersion(); }
+  bool isIRLevelProfile() const override { return Index->isIRLevelProfile(); }
   IndexedInstrProfReader(std::unique_ptr<MemoryBuffer> DataBuffer)
       : DataBuffer(std::move(DataBuffer)), Index(nullptr) {}
 
   /// Return true if the given buffer is in an indexed instrprof format.
   static bool hasFormat(const MemoryBuffer &DataBuffer);
 
   /// Read the file header.
   std::error_code readHeader() override;

include/llvm/ProfileData/InstrProfWriter.h

 
 /// Writer for instrumentation based profile data.
 class ProfOStream;
 class InstrProfRecordWriterTrait;
 
 class InstrProfWriter {
 public:
   typedef SmallDenseMap<uint64_t, InstrProfRecord, 1> ProfilingData;
+  enum ProfKind { PF_Unknown = 0, PF_FE, PF_IRLevel };
 
 private:
   bool Sparse;
   StringMap<ProfilingData> FunctionData;
+  ProfKind ProfileKind;
   // Use raw pointer here for the incomplete type object.
   InstrProfRecordWriterTrait *InfoObj;
 
 public:
   InstrProfWriter(bool Sparse = false);
   ~InstrProfWriter();
 
   /// Add function counts for the given function. If there are already counts
   /// for this function and the hash and number of counts match, each counter is
   /// summed. Optionally scale counts by \p Weight.
   std::error_code addRecord(InstrProfRecord &&I, uint64_t Weight = 1);
   /// Write the profile to \c OS
   void write(raw_fd_ostream &OS);
   /// Write the profile in text format to \c OS
   void writeText(raw_fd_ostream &OS);
   /// Write \c Record in text format to \c OS
   static void writeRecordInText(const InstrProfRecord &Record,
                                 InstrProfSymtab &Symtab, raw_fd_ostream &OS);
   /// Write the profile, returning the raw data. For testing.
   std::unique_ptr<MemoryBuffer> writeBuffer();
 
+  /// Set the ProfileKind. Report error if mixing FE and IR level profiles.
+  std::error_code setIsIRLevelProfile(bool IsIRLevel) {
+    if (ProfileKind == PF_Unknown) {
+      ProfileKind = IsIRLevel ? PF_IRLevel: PF_FE;
+      return instrprof_error::success;
+    }
+    return (IsIRLevel == (ProfileKind == PF_IRLevel)) ?
+           instrprof_error::success : instrprof_error::unsupported_version;
+  }
+
   // Internal interface for testing purpose only.
   void setValueProfDataEndianness(support::endianness Endianness);
   void setOutputSparse(bool Sparse);
 
 private:
   bool shouldEncodeData(const ProfilingData &PD);
   void writeImpl(ProfOStream &OS);
 };
 
 } // end namespace llvm
 
 #endif

lib/ProfileData/InstrProfReader.cpp

bool TextInstrProfReader::hasFormat(const MemoryBuffer &Buffer) {
   // 'reasonable' number of characters (up to profile magic size).
   size_t count = std::min(Buffer.getBufferSize(), sizeof(uint64_t));
   StringRef buffer = Buffer.getBufferStart();
   return count == 0 ||
          std::all_of(buffer.begin(), buffer.begin() + count,
                      [](char c) { return ::isprint(c) || ::isspace(c); });
 }
 
+// Read the profile variant flag from the header: ":FE" means this is a FE
+// generated profile. ":IR" means this is an IR level profile. Other strings
+// with a leading ':' will be reported an error format.
 std::error_code TextInstrProfReader::readHeader() {
   Symtab.reset(new InstrProfSymtab());
+  bool IsIRInstr = false;
+  if (!Line->startswith(":")) {
+    IsIRLevelProfile = false;
+    return success();
+  }
+  StringRef Str = (Line)->substr(1);
+  if (Str.equals_lower("ir"))
+    IsIRInstr = true;
+  else if (Str.equals_lower("fe"))
+    IsIRInstr = false;
+  else
+    return instrprof_error::bad_header;
+
+  ++Line;
+  IsIRLevelProfile = IsIRInstr;
   return success();
 }
 
 std::error_code
 TextInstrProfReader::readValueProfileData(InstrProfRecord &Record) {
 
 #define CHECK_LINE_END(Line)                                                   \
   if (Line.is_at_end())                                                        \
for (const RawInstrProf::ProfileData<IntPtrT> *I = Data; I != DataEnd; ++I) {
     Symtab.mapAddress(FPtr, I->NameRef);
   }
   Symtab.finalizeSymtab();
 }
 
 template <class IntPtrT>
 std::error_code
 RawInstrProfReader<IntPtrT>::readHeader(const RawInstrProf::Header &Header) {
-  if (swap(Header.Version) != RawInstrProf::Version)
+  Version = swap(Header.Version);
+  if (GET_VERSION(Version) != RawInstrProf::Version)
     return error(instrprof_error::unsupported_version);
 
   CountersDelta = swap(Header.CountersDelta);
   NamesDelta = swap(Header.NamesDelta);
   auto DataSize = swap(Header.DataSize);
   auto CountersSize = swap(Header.CountersSize);
   NamesSize = swap(Header.NamesSize);
   auto ValueDataSize = swap(Header.ValueDataSize);
data_type InstrProfLookupTrait::ReadData(StringRef K, const unsigned char *D,
   using namespace support;
   const unsigned char *End = D + N;
   while (D < End) {
     // Read hash.
     if (D + sizeof(uint64_t) >= End)
       return data_type();
     uint64_t Hash = endian::readNext<uint64_t, little, unaligned>(D);
 
-    // Initialize number of counters for FormatVersion == 1.
+    // Initialize number of counters for GET_VERSION(FormatVersion) == 1.
     uint64_t CountsSize = N / sizeof(uint64_t) - 1;
     // If format version is different then read the number of counters.
-    if (FormatVersion != IndexedInstrProf::ProfVersion::Version1) {
+    if (GET_VERSION(FormatVersion) != IndexedInstrProf::ProfVersion::Version1) {
       if (D + sizeof(uint64_t) > End)
         return data_type();
       CountsSize = endian::readNext<uint64_t, little, unaligned>(D);
     }
     // Read counter values.
     if (D + CountsSize * sizeof(uint64_t) > End)
       return data_type();
 
     CounterBuffer.clear();
     CounterBuffer.reserve(CountsSize);
     for (uint64_t J = 0; J < CountsSize; ++J)
       CounterBuffer.push_back(endian::readNext<uint64_t, little, unaligned>(D));
 
     DataBuffer.emplace_back(K, Hash, std::move(CounterBuffer));
 
     // Read value profiling data.
-    if (FormatVersion > IndexedInstrProf::ProfVersion::Version2 &&
+    if (GET_VERSION(FormatVersion) > IndexedInstrProf::ProfVersion::Version2 &&
         !readValueProfilingData(D, End)) {
       DataBuffer.clear();
       return data_type();
     }
   }
   return DataBuffer;
 }
 
std::error_code IndexedInstrProfReader::readHeader() {
 
   // Check the magic number.
   uint64_t Magic = endian::byte_swap<uint64_t, little>(Header->Magic);
   if (Magic != IndexedInstrProf::Magic)
     return error(instrprof_error::bad_magic);
 
   // Read the version.
   uint64_t FormatVersion = endian::byte_swap<uint64_t, little>(Header->Version);
-  if (FormatVersion > IndexedInstrProf::ProfVersion::CurrentVersion)
+  if (GET_VERSION(FormatVersion) >
+      IndexedInstrProf::ProfVersion::CurrentVersion)
     return error(instrprof_error::unsupported_version);
 
   Cur = readSummary((IndexedInstrProf::ProfVersion)FormatVersion, Cur);
 
   // Read the hash type and start offset.
   IndexedInstrProf::HashT HashType = static_cast<IndexedInstrProf::HashT>(
       endian::byte_swap<uint64_t, little>(Header->HashType));
   if (HashType > IndexedInstrProf::HashT::Last)

lib/ProfileData/InstrProfWriter.cpp

for (const auto &ProfileData : *V) {
       VDataPtr->swapBytesFromHost(ValueProfDataEndianness);
       Out.write((const char *)VDataPtr.get(), S);
     }
   }
 };
 }
 
 InstrProfWriter::InstrProfWriter(bool Sparse)
-    : Sparse(Sparse), FunctionData(),
+    : Sparse(Sparse), FunctionData(), ProfileKind(PF_Unknown),
       InfoObj(new InstrProfRecordWriterTrait()) {}
 
 InstrProfWriter::~InstrProfWriter() { delete InfoObj; }
 
 // Internal interface for testing purpose only.
 void InstrProfWriter::setValueProfDataEndianness(
     support::endianness Endianness) {
   InfoObj->ValueProfDataEndianness = Endianness;
void InstrProfWriter::writeImpl(ProfOStream &OS) {
   // Populate the hash table generator.
   for (const auto &I : FunctionData)
     if (shouldEncodeData(I.getValue()))
       Generator.insert(I.getKey(), &I.getValue());
   // Write the header.
   IndexedInstrProf::Header Header;
   Header.Magic = IndexedInstrProf::Magic;
   Header.Version = IndexedInstrProf::ProfVersion::CurrentVersion;
+  if (ProfileKind == PF_IRLevel)
+    Header.Version |= VARIANT_MASK_IR_PROF;
   Header.Unused = 0;
   Header.HashType = static_cast<uint64_t>(IndexedInstrProf::HashType);
   Header.HashOffset = 0;
   int N = sizeof(IndexedInstrProf::Header) / sizeof(uint64_t);
 
   // Only write out all the fields except 'HashOffset'. We need
   // to remember the offset of that field to allow back patching
   // later.
for (uint32_t S = 0; S < NS; S++) {
       }
     }
   }
 
   OS << "\n";
 }
 
 void InstrProfWriter::writeText(raw_fd_ostream &OS) {
+  if (ProfileKind == PF_IRLevel)
+    OS << "# IR level Instrumentation Flag\n:ir\n";
   InstrProfSymtab Symtab;
   for (const auto &I : FunctionData)
     if (shouldEncodeData(I.getValue()))
       Symtab.addFuncName(I.getKey());
   Symtab.finalizeSymtab();
 
   for (const auto &I : FunctionData)
     if (shouldEncodeData(I.getValue()))
       for (const auto &Func : I.getValue())
         writeRecordInText(Func.second, Symtab, OS);
 }

lib/Transforms/Instrumentation/PGOInstrumentation.cpp

 // The MST implementation is in Class CFGMST (CFGMST.h).
 //
 //===----------------------------------------------------------------------===//
 
 #include "CFGMST.h"
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/Statistic.h"
+#include "llvm/ADT/Triple.h"
 #include "llvm/Analysis/BlockFrequencyInfo.h"
 #include "llvm/Analysis/BranchProbabilityInfo.h"
 #include "llvm/Analysis/CFG.h"
 #include "llvm/IR/CallSite.h"
 #include "llvm/IR/DiagnosticInfo.h"
 #include "llvm/IR/IRBuilder.h"
 #include "llvm/IR/InstIterator.h"
 #include "llvm/IR/InstVisitor.h"
TI->setMetadata(llvm::LLVMContext::MD_prof,
                     MDB.createBranchWeights(Weights));
     DEBUG(dbgs() << "Weight is: ";
           for (const auto &W : Weights) { dbgs() << W << " "; }
           dbgs() << "\n";);
   }
 }
 } // end anonymous namespace
 
+// Create a COMDAT variable IR_LEVEL_PROF_VARNAME to make the runtime
+// aware this is an ir_level profile so it can set the version flag.
+static void createIRLevelProfileFlagVariable(Module &M) {
+  Type *IntTy64 = Type::getInt64Ty(M.getContext());
+  uint64_t ProfileVersion = (INSTR_PROF_RAW_VERSION | VARIANT_MASK_IR_PROF);
+  auto IRLevelVersionVariable =
+      new GlobalVariable(M, IntTy64, true, GlobalVariable::ExternalLinkage,
+                         Constant::getIntegerValue(IntTy64, APInt(64, ProfileVersion)),
+                         INSTR_PROF_QUOTE(IR_LEVEL_PROF_VERSION_VAR));
+  IRLevelVersionVariable->setVisibility(GlobalValue::DefaultVisibility);
+  Triple TT(M.getTargetTriple());
+  if (TT.isOSBinFormatMachO())
+    IRLevelVersionVariable->setLinkage(GlobalValue::LinkOnceAnyLinkage);
+  else
+    IRLevelVersionVariable->setComdat(
+        M.getOrInsertComdat(StringRef(INSTR_PROF_QUOTE(IR_LEVEL_PROF_VERSION_VAR))));
+/*  IRLevelVersionVariable->setLinkage(GlobalValue::WeakAnyLinkage); */
+}
+
 bool PGOInstrumentationGen::runOnModule(Module &M) {
+  createIRLevelProfileFlagVariable(M);
   for (auto &F : M) {
     if (F.isDeclaration())
       continue;
     BranchProbabilityInfo *BPI =
         &(getAnalysis<BranchProbabilityInfoWrapperPass>(F).getBPI());
     BlockFrequencyInfo *BFI =
         &(getAnalysis<BlockFrequencyInfoWrapperPass>(F).getBFI());
     instrumentOneFunc(F, &M, BPI, BFI);
bool PGOInstrumentationUse::runOnModule(Module &M) {
   }
 
   PGOReader = std::move(ReaderOrErr.get());
   if (!PGOReader) {
     Ctx.diagnose(DiagnosticInfoPGOProfile(ProfileFileName.data(),
                                           "Cannot get PGOReader"));
     return false;
   }
+  // TODO: might need to change the warning once the clang option is finalized.
+  if (!PGOReader->isIRLevelProfile()) {
+    Ctx.diagnose(DiagnosticInfoPGOProfile(
+        ProfileFileName.data(), "Not an IR level instrumentation profile"));
+    return false;
+  }
+
 
   for (auto &F : M) {
     if (F.isDeclaration())
       continue;
     BranchProbabilityInfo *BPI =
         &(getAnalysis<BranchProbabilityInfoWrapperPass>(F).getBPI());
     BlockFrequencyInfo *BFI =
         &(getAnalysis<BlockFrequencyInfoWrapperPass>(F).getBFI());
     PGOUseFunc Func(F, &M, BPI, BFI);
     setPGOCountOnFunc(Func, PGOReader.get());
   }
   return true;
 }

test/Transforms/PGOProfile/Inputs/branch1.proftext

+# :ir is the flag to indicate this is IR level profile.
+:ir
 test_br_1
 25571299074
 2
 3
 2
 

test/Transforms/PGOProfile/Inputs/branch2.proftext

+# :ir is the flag to indicate this is IR level profile.
+:ir
 test_br_2
 29667547796
 2
 1
 1
 

test/Transforms/PGOProfile/Inputs/criticaledge.proftext

+# :ir is the flag to indicate this is IR level profile.
+:ir
 test_criticalEdge
 82323253069
 8
 2
 1
 2
 2
 0

test/Transforms/PGOProfile/Inputs/diag.proftext

+# :ir is the flag to indicate this is IR level profile.
+:ir
 foo
 12884999999
 1
 1
 

test/Transforms/PGOProfile/Inputs/diag_FE.proftext

+foo
[phone]
+1
+1
+

test/Transforms/PGOProfile/Inputs/landingpad.proftext

+# :ir is the flag to indicate this is IR level profile.
+:ir
 foo
 59130013419
 4
 3
 1
 2
 0
 
 bar
 24868915205
 2
 1
 2
 

test/Transforms/PGOProfile/Inputs/loop1.proftext

+# :ir is the flag to indicate this is IR level profile.
+:ir
 test_simple_for
 34137660316
 2
 96
 4
 

test/Transforms/PGOProfile/Inputs/loop2.proftext

+# :ir is the flag to indicate this is IR level profile.
+:ir
 test_nested_for
 53929068288
 3
 33
 10
 6
 

test/Transforms/PGOProfile/Inputs/switch.proftext

+# :ir is the flag to indicate this is IR level profile.
+:ir
 test_switch
 46200943743
 4
 0
 5
 2
 3
 

test/Transforms/PGOProfile/branch1.ll

-; RUN: opt < %s -pgo-instr-gen -S | FileCheck %s --check-prefix=GEN
+; RUN: opt < %s -pgo-instr-gen -S | FileCheck %s --check-prefix=GEN --check-prefix=GEN-COMDAT
+; RUN: opt < %s -mtriple=x86_64-apple-darwin -pgo-instr-gen -S | FileCheck %s --check-prefix=GEN --check-prefix=GEN-DARWIN-LINKONCE
 ; RUN: llvm-profdata merge %S/Inputs/branch1.proftext -o %t.profdata
 ; RUN: opt < %s -pgo-instr-use -pgo-test-profile-file=%t.profdata -S | FileCheck %s --check-prefix=USE
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
+; GEN-DARWIN-LINKONCE: target triple = "x86_64-apple-darwin"
 
+; GEN-COMDAT: $__llvm_profile_raw_version = comdat any
+; GEN-COMDAT: @__llvm_profile_raw_version = constant i64 72057594037927939, comdat
+; GEN-DARWIN-LINKONCE: @__llvm_profile_raw_version = linkonce constant i64 72057594037927939
 ; GEN: @__profn_test_br_1 = private constant [9 x i8] c"test_br_1"
 
 define i32 @test_br_1(i32 %i) {
 entry:
 ; GEN: entry:
 ; GEN-NOT: llvm.instrprof.increment
   %cmp = icmp sgt i32 %i, 0
   br i1 %cmp, label %if.then, label %if.end

test/Transforms/PGOProfile/branch2.ll

 ; RUN: opt < %s -pgo-instr-gen -S | FileCheck %s --check-prefix=GEN
 ; RUN: llvm-profdata merge %S/Inputs/branch2.proftext -o %t.profdata
 ; RUN: opt < %s -pgo-instr-use -pgo-test-profile-file=%t.profdata -S | FileCheck %s --check-prefix=USE
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
+; GEN: $__llvm_profile_raw_version = comdat any
+; GEN: @__llvm_profile_raw_version = constant i64 72057594037927939, comdat
 ; GEN: @__profn_test_br_2 = private constant [9 x i8] c"test_br_2"
 
 define i32 @test_br_2(i32 %i) {
 entry:
 ; GEN: entry:
 ; GEN-NOT: llvm.instrprof.increment
   %cmp = icmp sgt i32 %i, 0
   br i1 %cmp, label %if.then, label %if.else

test/Transforms/PGOProfile/criticaledge.ll

 ; RUN: opt < %s -pgo-instr-gen -S | FileCheck %s --check-prefix=GEN
 ; RUN: llvm-profdata merge %S/Inputs/criticaledge.proftext -o %t.profdata
 ; RUN: opt < %s -pgo-instr-use -pgo-test-profile-file=%t.profdata -S | FileCheck %s --check-prefix=USE
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
+; GEN: $__llvm_profile_raw_version = comdat any
+; GEN: @__llvm_profile_raw_version = constant i64 72057594037927939, comdat
 ; GEN: @__profn_test_criticalEdge = private constant [17 x i8] c"test_criticalEdge"
 ; GEN: @__profn__stdin__bar = private constant [11 x i8] c"<stdin>:bar"
 
 define i32 @test_criticalEdge(i32 %i, i32 %j) {
 entry:
 ; CHECK: entry:
 ; GEN-NOT: call void @llvm.instrprof.increment
   switch i32 %i, label %sw.default [

test/Transforms/PGOProfile/diag_FE_profile.ll

+; RUN: llvm-profdata merge %S/Inputs/diag_FE.proftext -o %t.profdata
+; RUN: not opt < %s -pgo-instr-use -pgo-test-profile-file=%t.profdata -S  2>&1 | FileCheck %s
+
+; CHECK: Not an IR level instrumentation profile
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+define i32 @foo() {
+entry:
+  ret i32 0
+}

test/Transforms/PGOProfile/landingpad.ll

 ; RUN: opt < %s -pgo-instr-gen -S | FileCheck %s --check-prefix=GEN
 ; RUN: llvm-profdata merge %S/Inputs/landingpad.proftext -o %t.profdata
 ; RUN: opt < %s -pgo-instr-use -pgo-test-profile-file=%t.profdata -S | FileCheck %s --check-prefix=USE
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
 @val = global i32 0, align 4
 @_ZTIi = external constant i8*
+; GEN: $__llvm_profile_raw_version = comdat any
+; GEN: @__llvm_profile_raw_version = constant i64 72057594037927939, comdat
 ; GEN: @__profn_bar = private constant [3 x i8] c"bar"
 ; GEN: @__profn_foo = private constant [3 x i8] c"foo"
 
 define i32 @bar(i32 %i) {
 entry:
 ; GEN: entry:
 ; GEN-NOT: call void @llvm.instrprof.increment
   %rem = srem i32 %i, 3

test/Transforms/PGOProfile/loop1.ll

 ; RUN: opt < %s -pgo-instr-gen -S | FileCheck %s --check-prefix=GEN
 ; RUN: llvm-profdata merge %S/Inputs/loop1.proftext -o %t.profdata
 ; RUN: opt < %s -pgo-instr-use -pgo-test-profile-file=%t.profdata -S | FileCheck %s --check-prefix=USE
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
+; GEN: $__llvm_profile_raw_version = comdat any
+; GEN: @__llvm_profile_raw_version = constant i64 72057594037927939, comdat
 ; GEN: @__profn_test_simple_for = private constant [15 x i8] c"test_simple_for"
 
 define i32 @test_simple_for(i32 %n) {
 entry:
 ; GEN: entry:
 ; GEN-NOT: call void @llvm.instrprof.increment
   br label %for.cond
 

test/Transforms/PGOProfile/loop2.ll

 ; RUN: opt < %s -pgo-instr-gen -S | FileCheck %s --check-prefix=GEN
 ; RUN: llvm-profdata merge %S/Inputs/loop2.proftext -o %t.profdata
 ; RUN: opt < %s -pgo-instr-use -pgo-test-profile-file=%t.profdata -S | FileCheck %s --check-prefix=USE
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
+; GEN: $__llvm_profile_raw_version = comdat any
+; GEN: @__llvm_profile_raw_version = constant i64 72057594037927939, comdat
 ; GEN: @__profn_test_nested_for = private constant [15 x i8] c"test_nested_for"
 
 define i32 @test_nested_for(i32 %r, i32 %s) {
 entry:
 ; GEN: entry:
 ; GEN-NOT: call void @llvm.instrprof.increment
   br label %for.cond.outer
 

test/Transforms/PGOProfile/single_bb.ll

 ; RUN: opt < %s -pgo-instr-gen -S | FileCheck %s --check-prefix=GEN
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
+; GEN: $__llvm_profile_raw_version = comdat any
+; GEN: @__llvm_profile_raw_version = constant i64 72057594037927939, comdat
 ; GEN: @__profn_single_bb = private constant [9 x i8] c"single_bb"
 
 define i32 @single_bb() {
 entry:
 ; GEN: entry:
 ; GEN: call void @llvm.instrprof.increment(i8* getelementptr inbounds ([9 x i8], [9 x i8]* @__profn_single_bb, i32 0, i32 0), i64 12884901887, i32 1, i32 0)
   ret i32 0
 }

test/Transforms/PGOProfile/switch.ll

 ; RUN: opt < %s -pgo-instr-gen -S | FileCheck %s --check-prefix=GEN
 ; RUN: llvm-profdata merge %S/Inputs/switch.proftext -o %t.profdata
 ; RUN: opt < %s -pgo-instr-use -pgo-test-profile-file=%t.profdata -S | FileCheck %s --check-prefix=USE
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
+; GEN: $__llvm_profile_raw_version = comdat any
+; GEN: @__llvm_profile_raw_version = constant i64 72057594037927939, comdat
 ; GEN: @__profn_test_switch = private constant [11 x i8] c"test_switch"
 
 define void @test_switch(i32 %i) {
 entry:
 ; GEN: entry:
 ; GEN-NOT: call void @llvm.instrprof.increment
   switch i32 %i, label %sw.default [
     i32 1, label %sw.bb

tools/llvm-profdata/llvm-profdata.cpp

static void mergeInstrProfile(const WeightedFileVector &Inputs,
   InstrProfWriter Writer(OutputSparse);
   SmallSet<std::error_code, 4> WriterErrorCodes;
   for (const auto &Input : Inputs) {
     auto ReaderOrErr = InstrProfReader::create(Input.Filename);
     if (std::error_code ec = ReaderOrErr.getError())
       exitWithErrorCode(ec, Input.Filename);
 
     auto Reader = std::move(ReaderOrErr.get());
+    bool IsIRProfile = Reader->isIRLevelProfile();
+    if (Writer.setIsIRLevelProfile(IsIRProfile))
+      exitWithError("Merge IR generated profile with Clang generated profile.");
+
     for (auto &I : *Reader) {
       if (std::error_code EC = Writer.addRecord(std::move(I), Input.Weight)) {
         // Only show hint the first time an error occurs.
         bool firstTime = WriterErrorCodes.insert(EC).second;
         handleMergeWriterError(EC, Input.Filename, I.Name, firstTime);
       }
     }
     if (Reader->hasError())
static int showInstrProfile(std::string Filename, bool ShowCounts,
   if (ShowDetailedSummary && DetailedSummaryCutoffs.empty()) {
     Cutoffs = {800000, 900000, 950000, 990000, 999000, 999900, 999990};
   }
   ProfileSummary PS(Cutoffs);
   if (std::error_code EC = ReaderOrErr.getError())
     exitWithErrorCode(EC, Filename);
 
   auto Reader = std::move(ReaderOrErr.get());
+  bool IsIRInstr = Reader->isIRLevelProfile();
   size_t ShownFunctions = 0;
   for (const auto &Func : *Reader) {
     bool Show =
         ShowAllFunctions || (!ShowFunction.empty() &&
                              Func.Name.find(ShowFunction) != Func.Name.npos);
 
     bool doTextFormatDump = (Show && ShowCounts && TextFormat);
 
if (Show) {
 
       if (!ShownFunctions)
         OS << "Counters:\n";
 
       ++ShownFunctions;
 
       OS << "  " << Func.Name << ":\n"
          << "    Hash: " << format("0x%016" PRIx64, Func.Hash) << "\n"
-         << "    Counters: " << Func.Counts.size() << "\n"
-         << "    Function count: " << Func.Counts[0] << "\n";
+         << "    Counters: " << Func.Counts.size() << "\n";
+      if (!IsIRInstr)
+        OS << "    Function count: " << Func.Counts[0] << "\n";
 
       if (ShowIndirectCallTargets)
         OS << "    Indirect Call Site Count: "
            << Func.getNumValueSites(IPVK_IndirectCallTarget) << "\n";
 
       if (ShowCounts) {
         OS << "    Block counts: [";
-        for (size_t I = 1, E = Func.Counts.size(); I < E; ++I) {
-          OS << (I == 1 ? "" : ", ") << Func.Counts[I];
+        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) {
         InstrProfSymtab &Symtab = Reader->getSymtab();
         uint32_t NS = Func.getNumValueSites(IPVK_IndirectCallTarget);
         OS << "    Indirect Target Results: \n";