Sample profiles - Add a name table to the binary encoding.

Binary encoded profiles used to encode all function names inline at
every reference.  This is clearly suboptimal in terms of space.  This
patch fixes this by adding a name table to the header of the file.

llvm-svn: 250241

3 files changed, 94 insertions, 21 deletions

diff --git a/llvm/lib/ProfileData/SampleProf.cpp b/llvm/lib/ProfileData/SampleProf.cpp
index 027fa81790b..c6960ba4bd9 100644
--- a/llvm/lib/ProfileData/SampleProf.cpp
+++ b/llvm/lib/ProfileData/SampleProf.cpp
@@ -38,6 +38,10 @@ class SampleProfErrorCategoryType : public std::error_category {
       return "Malformed profile data";
     case sampleprof_error::unrecognized_format:
       return "Unrecognized profile encoding format";
+    case sampleprof_error::unsupported_writing_format:
+      return "Profile encoding format unsupported for writing operations";
+    case sampleprof_error::truncated_name_table:
+      return "Truncated function name table";
     case sampleprof_error::not_implemented:
       return "Unimplemented feature";
     }
diff --git a/llvm/lib/ProfileData/SampleProfReader.cpp b/llvm/lib/ProfileData/SampleProfReader.cpp
index c620d4ca84a..a058274e8ee 100644
--- a/llvm/lib/ProfileData/SampleProfReader.cpp
+++ b/llvm/lib/ProfileData/SampleProfReader.cpp
@@ -378,6 +378,16 @@ ErrorOr<StringRef> SampleProfileReaderBinary::readString() {
   return Str;
 }
 
+ErrorOr<StringRef> SampleProfileReaderBinary::readStringFromTable() {
+  std::error_code EC;
+  auto Idx = readNumber<unsigned>();
+  if (std::error_code EC = Idx.getError())
+    return EC;
+  if (*Idx >= NameTable.size())
+    return sampleprof_error::truncated_name_table;
+  return NameTable[*Idx];
+}
+
 std::error_code
 SampleProfileReaderBinary::readProfile(FunctionSamples &FProfile) {
   auto Val = readNumber<unsigned>();
@@ -413,7 +423,7 @@ SampleProfileReaderBinary::readProfile(FunctionSamples &FProfile) {
       return EC;
 
     for (unsigned J = 0; J < *NumCalls; ++J) {
-      auto CalledFunction(readString());
+      auto CalledFunction(readStringFromTable());
       if (std::error_code EC = CalledFunction.getError())
         return EC;
 
@@ -442,7 +452,7 @@ SampleProfileReaderBinary::readProfile(FunctionSamples &FProfile) {
     if (std::error_code EC = Discriminator.getError())
       return EC;
 
-    auto FName(readString());
+    auto FName(readStringFromTable());
     if (std::error_code EC = FName.getError())
       return EC;
 
@@ -457,7 +467,7 @@ SampleProfileReaderBinary::readProfile(FunctionSamples &FProfile) {
 
 std::error_code SampleProfileReaderBinary::read() {
   while (!at_eof()) {
-    auto FName(readString());
+    auto FName(readStringFromTable());
     if (std::error_code EC = FName.getError())
       return EC;
 
@@ -489,6 +499,18 @@ std::error_code SampleProfileReaderBinary::readHeader() {
   else if (*Version != SPVersion())
     return sampleprof_error::unsupported_version;
 
+  // Read the name table.
+  auto Size = readNumber<size_t>();
+  if (std::error_code EC = Size.getError())
+    return EC;
+  NameTable.reserve(*Size);
+  for (size_t I = 0; I < *Size; ++I) {
+    auto Name(readString());
+    if (std::error_code EC = Name.getError())
+      return EC;
+    NameTable.push_back(*Name);
+  }
+
   return sampleprof_error::success;
 }
 
diff --git a/llvm/lib/ProfileData/SampleProfWriter.cpp b/llvm/lib/ProfileData/SampleProfWriter.cpp
index 6be884b13e0..d3001aac3f6 100644
--- a/llvm/lib/ProfileData/SampleProfWriter.cpp
+++ b/llvm/lib/ProfileData/SampleProfWriter.cpp
@@ -30,7 +30,8 @@ using namespace llvm::sampleprof;
 using namespace llvm;
 
 /// \brief Write samples to a text file.
-bool SampleProfileWriterText::write(StringRef FName, const FunctionSamples &S) {
+std::error_code SampleProfileWriterText::write(StringRef FName,
+                                               const FunctionSamples &S) {
   OS << FName << ":" << S.getTotalSamples();
   if (Indent == 0)
     OS << ":" << S.getHeadSamples();
@@ -61,31 +62,74 @@ bool SampleProfileWriterText::write(StringRef FName, const FunctionSamples &S) {
       OS << Loc.LineOffset << ": ";
     else
       OS << Loc.LineOffset << "." << Loc.Discriminator << ": ";
-    write(Loc.CalleeName, CalleeSamples);
+    if (std::error_code EC = write(Loc.CalleeName, CalleeSamples))
+      return EC;
   }
   Indent -= 1;
 
-  return true;
+  return sampleprof_error::success;
 }
 
-SampleProfileWriterBinary::SampleProfileWriterBinary(StringRef F,
-                                                     std::error_code &EC)
-    : SampleProfileWriter(F, EC, sys::fs::F_None) {
-  if (EC)
-    return;
+std::error_code SampleProfileWriterBinary::writeNameIdx(StringRef FName) {
+  const auto &ret = NameTable.find(FName);
+  if (ret == NameTable.end())
+    return sampleprof_error::truncated_name_table;
+  encodeULEB128(ret->second, OS);
+  return sampleprof_error::success;
+}
+
+void SampleProfileWriterBinary::addName(StringRef FName) {
+  auto NextIdx = NameTable.size();
+  NameTable.insert(std::make_pair(FName, NextIdx));
+}
+
+void SampleProfileWriterBinary::addNames(const FunctionSamples &S) {
+  // Add all the names in indirect call targets.
+  for (const auto &I : S.getBodySamples()) {
+    const SampleRecord &Sample = I.second;
+    for (const auto &J : Sample.getCallTargets())
+      addName(J.first());
+  }
+
+  // Recursively add all the names for inlined callsites.
+  for (const auto &J : S.getCallsiteSamples()) {
+    CallsiteLocation Loc = J.first;
+    const FunctionSamples &CalleeSamples = J.second;
+    addName(Loc.CalleeName);
+    addNames(CalleeSamples);
+  }
+}
 
-  // Write the file header.
+std::error_code SampleProfileWriterBinary::writeHeader(
+    const StringMap<FunctionSamples> &ProfileMap) {
+  // Write file magic identifier.
   encodeULEB128(SPMagic(), OS);
   encodeULEB128(SPVersion(), OS);
+
+  // Generate the name table for all the functions referenced in the profile.
+  for (const auto &I : ProfileMap) {
+    addName(I.first());
+    addNames(I.second);
+  }
+
+  // Write out the name table.
+  encodeULEB128(NameTable.size(), OS);
+  for (auto N : NameTable) {
+    OS << N.first;
+    encodeULEB128(0, OS);
+  }
+
+  return sampleprof_error::success;
 }
 
 /// \brief Write samples to a binary file.
 ///
 /// \returns true if the samples were written successfully, false otherwise.
-bool SampleProfileWriterBinary::write(StringRef FName,
-                                      const FunctionSamples &S) {
-  OS << FName;
-  encodeULEB128(0, OS);
+std::error_code SampleProfileWriterBinary::write(StringRef FName,
+                                                 const FunctionSamples &S) {
+  if (std::error_code EC = writeNameIdx(FName))
+    return EC;
+
   encodeULEB128(S.getTotalSamples(), OS);
   encodeULEB128(S.getHeadSamples(), OS);
   encodeULEB128(S.getBodySamples().size(), OS);
@@ -99,10 +143,10 @@ bool SampleProfileWriterBinary::write(StringRef FName,
     encodeULEB128(Sample.getSamples(), OS);
     encodeULEB128(Sample.getCallTargets().size(), OS);
     for (const auto &J : Sample.getCallTargets()) {
-      std::string Callee = J.first();
+      StringRef Callee = J.first();
       unsigned CalleeSamples = J.second;
-      OS << Callee;
-      encodeULEB128(0, OS);
+      if (std::error_code EC = writeNameIdx(Callee))
+        return EC;
       encodeULEB128(CalleeSamples, OS);
     }
   }
@@ -114,10 +158,11 @@ bool SampleProfileWriterBinary::write(StringRef FName,
     const FunctionSamples &CalleeSamples = J.second;
     encodeULEB128(Loc.LineOffset, OS);
     encodeULEB128(Loc.Discriminator, OS);
-    write(Loc.CalleeName, CalleeSamples);
+    if (std::error_code EC = write(Loc.CalleeName, CalleeSamples))
+      return EC;
   }
 
-  return true;
+  return sampleprof_error::success;
 }
 
 /// \brief Create a sample profile writer based on the specified format.
@@ -138,6 +183,8 @@ SampleProfileWriter::create(StringRef Filename, SampleProfileFormat Format) {
     Writer.reset(new SampleProfileWriterBinary(Filename, EC));
   else if (Format == SPF_Text)
     Writer.reset(new SampleProfileWriterText(Filename, EC));
+  else if (Format == SPF_GCC)
+    EC = sampleprof_error::unsupported_writing_format;
   else
     EC = sampleprof_error::unrecognized_format;