[PGO] Differentiate Clang instrumentation and IR level instrumentation profiles

This patch uses one bit in profile version to differentiate Clang
instrumentation and IR level instrumentation profiles.

PGOInstrumenation generates a COMDAT variable __llvm_profile_raw_version so
that the compiler runtime can set the right profile kind.
PGOInstrumenation now checks this bit to make sure it's an IR level
instrumentation profile.

Differential Revision: http://reviews.llvm.org/D15540

llvm-svn: 260146

llvm/include/llvm/ProfileData/InstrProfData.inc

@@ -705,9 +705,11 @@ serializeValueProfDataFromRT(const ValueProfRuntimeRecord *Record,
  * 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

llvm/include/llvm/ProfileData/InstrProfReader.h

@@ -64,6 +64,7 @@ public:
   /// 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
@@ -118,6 +119,7 @@ private:
   std::unique_ptr<MemoryBuffer> DataBuffer;
   /// Iterator over the profile data.
   line_iterator Line;
+  bool IsIRLevelProfile;
 
   TextInstrProfReader(const TextInstrProfReader &) = delete;
   TextInstrProfReader &operator=(const TextInstrProfReader &) = delete;
@@ -125,11 +127,14 @@ private:
 
 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.
@@ -154,6 +159,10 @@ 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;
@@ -177,6 +186,9 @@ public:
   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());
@@ -292,6 +304,7 @@ struct InstrProfReaderIndexBase {
   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;
 };
 
@@ -323,7 +336,10 @@ public:
     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());
   }
@@ -348,7 +364,9 @@ private:
                                    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) {}
 

llvm/include/llvm/ProfileData/InstrProfWriter.h

@@ -30,10 +30,12 @@ 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;
 
@@ -55,6 +57,16 @@ public:
   /// 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);

llvm/lib/ProfileData/InstrProfReader.cpp

@@ -109,8 +109,26 @@ bool TextInstrProfReader::hasFormat(const MemoryBuffer &Buffer) {
                      [](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();
 }
 
@@ -293,7 +311,8 @@ void RawInstrProfReader<IntPtrT>::createSymtab(InstrProfSymtab &Symtab) {
 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);
@@ -470,10 +489,10 @@ data_type InstrProfLookupTrait::ReadData(StringRef K, const unsigned char *D,
       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);
@@ -490,7 +509,7 @@ data_type InstrProfLookupTrait::ReadData(StringRef K, const unsigned char *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();
@@ -603,7 +622,8 @@ std::error_code IndexedInstrProfReader::readHeader() {
 
   // 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);

llvm/lib/ProfileData/InstrProfWriter.cpp

@@ -142,7 +142,7 @@ public:
 }
 
 InstrProfWriter::InstrProfWriter(bool Sparse)
-    : Sparse(Sparse), FunctionData(),
+    : Sparse(Sparse), FunctionData(), ProfileKind(PF_Unknown),
       InfoObj(new InstrProfRecordWriterTrait()) {}
 
 InstrProfWriter::~InstrProfWriter() { delete InfoObj; }
@@ -230,6 +230,8 @@ void InstrProfWriter::writeImpl(ProfOStream &OS) {
   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;
@@ -336,6 +338,8 @@ void InstrProfWriter::writeRecordInText(const InstrProfRecord &Func,
 }
 
 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()))

llvm/lib/Transforms/Instrumentation/PGOInstrumentation.cpp

@@ -713,7 +713,22 @@ void PGOUseFunc::setBranchWeights() {
 }
 } // 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);
+  IRLevelVersionVariable->setComdat(
+      M.getOrInsertComdat(StringRef(INSTR_PROF_QUOTE(IR_LEVEL_PROF_VERSION_VAR))));
+}
+
 bool PGOInstrumentationGen::runOnModule(Module &M) {
+  createIRLevelProfileFlagVariable(M);
   for (auto &F : M) {
     if (F.isDeclaration())
       continue;
@@ -751,6 +766,13 @@ bool PGOInstrumentationUse::runOnModule(Module &M) {
                                           "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())

llvm/test/Transforms/PGOProfile/Inputs/branch1.proftext

@@ -1,3 +1,5 @@
+# :ir is the flag to indicate this is IR level profile.
+:ir
 test_br_1
 25571299074
 2

llvm/test/Transforms/PGOProfile/Inputs/branch2.proftext

@@ -1,3 +1,5 @@
+# :ir is the flag to indicate this is IR level profile.
+:ir
 test_br_2
 29667547796
 2

llvm/test/Transforms/PGOProfile/Inputs/criticaledge.proftext

@@ -1,3 +1,5 @@
+# :ir is the flag to indicate this is IR level profile.
+:ir
 test_criticalEdge
 82323253069
 8

llvm/test/Transforms/PGOProfile/Inputs/diag.proftext

@@ -1,3 +1,5 @@
+# :ir is the flag to indicate this is IR level profile.
+:ir
 foo
 12884999999
 1

llvm/test/Transforms/PGOProfile/Inputs/diag_FE.proftext

@@ -0,0 +1,5 @@
+foo
+12884999999
+1
+1
+

llvm/test/Transforms/PGOProfile/Inputs/landingpad.proftext

@@ -1,3 +1,5 @@
+# :ir is the flag to indicate this is IR level profile.
+:ir
 foo
 59130013419
 4

llvm/test/Transforms/PGOProfile/Inputs/loop1.proftext

@@ -1,3 +1,5 @@
+# :ir is the flag to indicate this is IR level profile.
+:ir
 test_simple_for
 34137660316
 2

llvm/test/Transforms/PGOProfile/Inputs/loop2.proftext

@@ -1,3 +1,5 @@
+# :ir is the flag to indicate this is IR level profile.
+:ir
 test_nested_for
 53929068288
 3

llvm/test/Transforms/PGOProfile/Inputs/switch.proftext

@@ -1,3 +1,5 @@
+# :ir is the flag to indicate this is IR level profile.
+:ir
 test_switch
 46200943743
 4

llvm/test/Transforms/PGOProfile/branch1.ll

@@ -4,6 +4,8 @@
 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_1 = private constant [9 x i8] c"test_br_1"
 
 define i32 @test_br_1(i32 %i) {

llvm/test/Transforms/PGOProfile/branch2.ll

@@ -4,6 +4,8 @@
 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) {

llvm/test/Transforms/PGOProfile/criticaledge.ll

@@ -4,6 +4,8 @@
 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"
 

llvm/test/Transforms/PGOProfile/diag_FE_profile.ll

@@ -0,0 +1,12 @@
+; 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
+}

llvm/test/Transforms/PGOProfile/landingpad.ll

@@ -6,6 +6,8 @@ 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"
 

llvm/test/Transforms/PGOProfile/loop1.ll

@@ -4,6 +4,8 @@
 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) {

llvm/test/Transforms/PGOProfile/loop2.ll

@@ -4,6 +4,8 @@
 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) {

llvm/test/Transforms/PGOProfile/single_bb.ll

@@ -2,6 +2,8 @@
 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() {

llvm/test/Transforms/PGOProfile/switch.ll

@@ -4,6 +4,8 @@
 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) {

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

@@ -128,6 +128,10 @@ static void mergeInstrProfile(const WeightedFileVector &Inputs,
       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.
@@ -269,6 +273,7 @@ static int showInstrProfile(std::string Filename, bool ShowCounts,
     exitWithErrorCode(EC, Filename);
 
   auto Reader = std::move(ReaderOrErr.get());
+  bool IsIRInstr = Reader->isIRLevelProfile();
   size_t ShownFunctions = 0;
   for (const auto &Func : *Reader) {
     bool Show =
@@ -295,8 +300,9 @@ static int showInstrProfile(std::string Filename, bool ShowCounts,
 
       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: "
@@ -304,8 +310,9 @@ static int showInstrProfile(std::string Filename, bool ShowCounts,
 
       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";
       }