Write the identifier offsets array into the PCH file as a blob, so

that the PCH reader does not have to decode the VBR encoding at PCH
load time.

Also, reduce the size of the identifier offsets from 64 bits down to
32 bits. The identifier table itself isn't going to grow to more than
4GB :)

Overall, this results in a 13% speedup in the Cocoa-prefixed "Hello,
World" benchmark.

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@70063 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/clang/Frontend/PCHReader.h b/include/clang/Frontend/PCHReader.h
index fe23185bed7168b97d6121747ae2d373c3f37de0..0c8520ceb44fa5db27dc60a8b32e610475163c1a 100644 (file)
--- a/include/clang/Frontend/PCHReader.h
+++ b/include/clang/Frontend/PCHReader.h
@@ -121,21 +121,28 @@ private:
 
   /// \brief Actual data for the on-disk hash table.
   ///
-  /// FIXME: This will eventually go away.
+  // This pointer points into a memory buffer, where the on-disk hash
+  // table for identifiers actually lives.
   const char *IdentifierTableData;
 
   /// \brief A pointer to an on-disk hash table of opaque type
   /// IdentifierHashTable.
   void *IdentifierLookupTable;
 
-  /// \brief String data for identifiers, indexed by the identifier ID
-  /// minus one.
+  /// \brief Offsets into the identifier table data.
   ///
-  /// Each element in this array is either an offset into
-  /// IdentifierTable that contains the string data (if the lowest bit
-  /// is set, in which case the offset is shifted left by one) or is
-  /// an IdentifierInfo* that has already been resolved.
-  llvm::SmallVector<uint64_t, 16> IdentifierData;
+  /// This array is indexed by the identifier ID (-1), and provides
+  /// the offset into IdentifierTableData where the string data is
+  /// stored.
+  const uint32_t *IdentifierOffsets;
+
+  /// \brief A vector containing identifiers that have already been
+  /// loaded.
+  ///
+  /// If the pointer at index I is non-NULL, then it refers to the
+  /// IdentifierInfo for the identifier with ID=I+1 that has already
+  /// been loaded.
+  std::vector<IdentifierInfo *> IdentifiersLoaded;
 
   /// \brief A pointer to an on-disk hash table of opaque type
   /// PCHMethodPoolLookupTable.
@@ -256,6 +263,7 @@ public:
   explicit PCHReader(Preprocessor &PP, ASTContext &Context) 
     : SemaObj(0), PP(PP), Context(Context), Consumer(0),
       IdentifierTableData(0), IdentifierLookupTable(0),
+      IdentifierOffsets(0),
       MethodPoolLookupTable(0), MethodPoolLookupTableData(0),
       TotalSelectorsInMethodPool(0), SelectorOffsets(0),
       TotalNumSelectors(0), NumStatementsRead(0), NumMacrosRead(0),
@@ -349,7 +357,7 @@ public:
   virtual std::pair<ObjCMethodList, ObjCMethodList> 
     ReadMethodPool(Selector Sel);
 
-  void SetIdentifierInfo(unsigned ID, const IdentifierInfo *II);
+  void SetIdentifierInfo(unsigned ID, IdentifierInfo *II);
 
   /// \brief Report a diagnostic.
   DiagnosticBuilder Diag(unsigned DiagID);

diff --git a/include/clang/Frontend/PCHWriter.h b/include/clang/Frontend/PCHWriter.h
index 41f8ad4af54a3f9d160bf0a92317c08ca8ae217b..a597d68ee3d8dee205878f76f2abfb6a88983fb9 100644 (file)
--- a/include/clang/Frontend/PCHWriter.h
+++ b/include/clang/Frontend/PCHWriter.h
@@ -95,18 +95,18 @@ private:
   llvm::DenseMap<const IdentifierInfo *, pch::IdentID> IdentifierIDs;
   
   /// \brief Offsets of each of the identifier IDs into the identifier
-  /// table, shifted left by one bit with the low bit set.
-  llvm::SmallVector<uint64_t, 16> IdentifierOffsets;
+  /// table.
+  std::vector<uint32_t> IdentifierOffsets;
 
   /// \brief Map that provides the ID numbers of each Selector.
   llvm::DenseMap<Selector, pch::SelectorID> SelectorIDs;
   
   /// \brief Offset of each selector within the method pool/selector
   /// table, indexed by the Selector ID (-1).
-  llvm::SmallVector<uint32_t, 16> SelectorOffsets;
+  std::vector<uint32_t> SelectorOffsets;
 
   /// \brief A vector of all Selectors (ordered by ID).
-  llvm::SmallVector<Selector, 16> SelVector;
+  std::vector<Selector> SelVector;
   
   /// \brief Offsets of each of the macro identifiers into the
   /// bitstream.

diff --git a/lib/Frontend/PCHReader.cpp b/lib/Frontend/PCHReader.cpp
index 897a0e77135d3d1785f985536068ca6248523574..005436dccf2eacfdc619d5214e5606612310d707 100644 (file)
--- a/lib/Frontend/PCHReader.cpp
+++ b/lib/Frontend/PCHReader.cpp
@@ -1837,28 +1837,23 @@ PCHReader::ReadPCHBlock(uint64_t &PreprocessorBlockOffset) {
 
     case pch::IDENTIFIER_TABLE:
       IdentifierTableData = BlobStart;
-      IdentifierLookupTable 
-        = PCHIdentifierLookupTable::Create(
+      if (Record[0]) {
+        IdentifierLookupTable 
+          = PCHIdentifierLookupTable::Create(
                         (const unsigned char *)IdentifierTableData + Record[0],
                         (const unsigned char *)IdentifierTableData, 
                         PCHIdentifierLookupTrait(*this));
-      PP.getIdentifierTable().setExternalIdentifierLookup(this);
+        PP.getIdentifierTable().setExternalIdentifierLookup(this);
+      }
       break;
 
     case pch::IDENTIFIER_OFFSET:
-      if (!IdentifierData.empty()) {
+      if (!IdentifiersLoaded.empty()) {
         Error("Duplicate IDENTIFIER_OFFSET record in PCH file");
         return Failure;
       }
-      IdentifierData.swap(Record);
-#ifndef NDEBUG
-      for (unsigned I = 0, N = IdentifierData.size(); I != N; ++I) {
-        if ((IdentifierData[I] & 0x01) == 0) {
-          Error("Malformed identifier table in the precompiled header");
-          return Failure;
-        }
-      }
-#endif
+      IdentifierOffsets = (const uint32_t *)BlobStart;
+      IdentifiersLoaded.resize(Record[0]);
       break;
 
     case pch::EXTERNAL_DEFINITIONS:
@@ -2710,22 +2705,20 @@ void PCHReader::StartTranslationUnit(ASTConsumer *Consumer) {
 void PCHReader::PrintStats() {
   std::fprintf(stderr, "*** PCH Statistics:\n");
 
-  unsigned NumTypesLoaded = 
-    TypesLoaded.size() - std::count(TypesLoaded.begin(), TypesLoaded.end(),
-                                    (Type *)0);
-  unsigned NumDeclsLoaded = 
-    DeclsLoaded.size() - std::count(DeclsLoaded.begin(), DeclsLoaded.end(),
-                                    (Decl *)0);
-  unsigned NumIdentifiersLoaded = 0;
-  for (unsigned I = 0; I < IdentifierData.size(); ++I) {
-    if ((IdentifierData[I] & 0x01) == 0)
-      ++NumIdentifiersLoaded;
-  }
-  unsigned NumSelectorsLoaded = 0;
-  for (unsigned I = 0; I < SelectorsLoaded.size(); ++I) {
-    if (SelectorsLoaded[I].getAsOpaquePtr())
-      ++NumSelectorsLoaded;
-  }
+  unsigned NumTypesLoaded 
+    = TypesLoaded.size() - std::count(TypesLoaded.begin(), TypesLoaded.end(),
+                                      (Type *)0);
+  unsigned NumDeclsLoaded
+    = DeclsLoaded.size() - std::count(DeclsLoaded.begin(), DeclsLoaded.end(),
+                                      (Decl *)0);
+  unsigned NumIdentifiersLoaded
+    = IdentifiersLoaded.size() - std::count(IdentifiersLoaded.begin(),
+                                            IdentifiersLoaded.end(),
+                                            (IdentifierInfo *)0);
+  unsigned NumSelectorsLoaded 
+    = SelectorsLoaded.size() - std::count(SelectorsLoaded.begin(),
+                                          SelectorsLoaded.end(),
+                                          Selector());
 
   if (!TypesLoaded.empty())
     std::fprintf(stderr, "  %u/%u types read (%f%%)\n",
@@ -2735,10 +2728,10 @@ void PCHReader::PrintStats() {
     std::fprintf(stderr, "  %u/%u declarations read (%f%%)\n",
                  NumDeclsLoaded, (unsigned)DeclsLoaded.size(),
                  ((float)NumDeclsLoaded/DeclsLoaded.size() * 100));
-  if (!IdentifierData.empty())
+  if (!IdentifiersLoaded.empty())
     std::fprintf(stderr, "  %u/%u identifiers read (%f%%)\n",
-                 NumIdentifiersLoaded, (unsigned)IdentifierData.size(),
-                 ((float)NumIdentifiersLoaded/IdentifierData.size() * 100));
+                 NumIdentifiersLoaded, (unsigned)IdentifiersLoaded.size(),
+                 ((float)NumIdentifiersLoaded/IdentifiersLoaded.size() * 100));
   if (TotalNumSelectors)
     std::fprintf(stderr, "  %u/%u selectors read (%f%%)\n",
                  NumSelectorsLoaded, TotalNumSelectors,
@@ -2832,27 +2825,28 @@ PCHReader::ReadMethodPool(Selector Sel) {
   return *Pos;
 }
 
-void PCHReader::SetIdentifierInfo(unsigned ID, const IdentifierInfo *II) {
+void PCHReader::SetIdentifierInfo(unsigned ID, IdentifierInfo *II) {
   assert(ID && "Non-zero identifier ID required");
-  IdentifierData[ID - 1] = reinterpret_cast<uint64_t>(II);
+  assert(ID <= IdentifiersLoaded.size() && "Identifier ID out of range");
+  IdentifiersLoaded[ID - 1] = II;
 }
 
 IdentifierInfo *PCHReader::DecodeIdentifierInfo(unsigned ID) {
   if (ID == 0)
     return 0;
   
-  if (!IdentifierTableData || IdentifierData.empty()) {
+  if (!IdentifierTableData || IdentifiersLoaded.empty()) {
     Error("No identifier table in PCH file");
     return 0;
   }
   
-  if (IdentifierData[ID - 1] & 0x01) {
-    uint64_t Offset = IdentifierData[ID - 1] >> 1;
-    IdentifierData[ID - 1] = reinterpret_cast<uint64_t>(
-                               &Context.Idents.get(IdentifierTableData + Offset));
+  if (!IdentifiersLoaded[ID - 1]) {
+    uint32_t Offset = IdentifierOffsets[ID - 1];
+    IdentifiersLoaded[ID - 1] 
+      = &Context.Idents.get(IdentifierTableData + Offset);
   }
   
-  return reinterpret_cast<IdentifierInfo *>(IdentifierData[ID - 1]);
+  return IdentifiersLoaded[ID - 1];
 }
 
 Selector PCHReader::DecodeSelector(unsigned ID) {

diff --git a/lib/Frontend/PCHWriter.cpp b/lib/Frontend/PCHWriter.cpp
index 91ddbf41826da55bd9bc97427e3b5603c8a9104b..4ac836419eb836d307fe84d5b96d0cfe72b840dd 100644 (file)
--- a/lib/Frontend/PCHWriter.cpp
+++ b/lib/Frontend/PCHWriter.cpp
@@ -2119,7 +2119,18 @@ void PCHWriter::WriteIdentifierTable(Preprocessor &PP) {
   }
 
   // Write the offsets table for identifier IDs.
-  Stream.EmitRecord(pch::IDENTIFIER_OFFSET, IdentifierOffsets);
+  BitCodeAbbrev *Abbrev = new BitCodeAbbrev();
+  Abbrev->Add(BitCodeAbbrevOp(pch::IDENTIFIER_OFFSET));
+  Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 32)); // # of identifiers
+  Abbrev->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Blob));
+  unsigned IdentifierOffsetAbbrev = Stream.EmitAbbrev(Abbrev);
+
+  RecordData Record;
+  Record.push_back(pch::IDENTIFIER_OFFSET);
+  Record.push_back(IdentifierOffsets.size());
+  Stream.EmitRecordWithBlob(IdentifierOffsetAbbrev, Record,
+                            (const char *)&IdentifierOffsets.front(),
+                            IdentifierOffsets.size() * sizeof(uint32_t));
 }
 
 /// \brief Write a record containing the given attributes.
@@ -2253,7 +2264,7 @@ void PCHWriter::AddString(const std::string &Str, RecordData &Record) {
 /// \brief Note that the identifier II occurs at the given offset
 /// within the identifier table.
 void PCHWriter::SetIdentifierOffset(const IdentifierInfo *II, uint32_t Offset) {
-  IdentifierOffsets[IdentifierIDs[II] - 1] = (Offset << 1) | 0x01;
+  IdentifierOffsets[IdentifierIDs[II] - 1] = Offset;
 }
 
 /// \brief Note that the selector Sel occurs at the given offset