Introduce additional abbreviations into the AST writer for

DeclRefExprs, IntegerLiterals, and others, reducing Cocoa PCH size by
~1% and C++ header size by ~2.5%. From Jonathan Turner!

llvm-svn: 132528

clang/include/clang/Serialization/ASTBitCodes.h

@@ -514,6 +514,9 @@ namespace clang {
     /// NUM_PREDEF_TYPE_IDs.
     const unsigned NUM_PREDEF_TYPE_IDS = 100;
 
+    /// \brief The number of allowed abbreviations in bits
+    const unsigned NUM_ALLOWED_ABBREVS_SIZE = 4;
+
     /// \brief Record codes for each kind of type.
     ///
     /// These constants describe the type records that can occur within a

clang/include/clang/Serialization/ASTWriter.h

@@ -342,6 +342,12 @@ private:
   unsigned DeclContextLexicalAbbrev;
   unsigned DeclContextVisibleLookupAbbrev;
   unsigned UpdateVisibleAbbrev;
+  unsigned DeclRefExprAbbrev;
+  unsigned CharacterLiteralAbbrev;
+  unsigned DeclRecordAbbrev;
+  unsigned IntegerLiteralAbbrev;
+  unsigned EnumConstantDeclAbbrev;
+
   void WriteDeclsBlockAbbrevs();
   void WriteDecl(ASTContext &Context, Decl *D);
 
@@ -569,7 +575,12 @@ public:
   unsigned getOpaqueValueID(OpaqueValueExpr *e);
 
   unsigned getParmVarDeclAbbrev() const { return ParmVarDeclAbbrev; }
-
+  unsigned getDeclRefExprAbbrev() const { return DeclRefExprAbbrev; }
+  unsigned getCharacterLiteralAbbrev() const { return CharacterLiteralAbbrev; }
+  unsigned getDeclRecordAbbrev() const { return DeclRecordAbbrev; }
+  unsigned getIntegerLiteralAbbrev() const { return IntegerLiteralAbbrev; }
+  unsigned getEnumConstantDeclAbbrev() const { return EnumConstantDeclAbbrev; }
+  
   bool hasChain() const { return Chain; }
 
   // ASTDeserializationListener implementation

clang/lib/Serialization/ASTWriter.cpp

@@ -889,13 +889,14 @@ void ASTWriter::WriteBlockInfoBlock() {
   RECORD(DECL_INDIRECTFIELD);
   RECORD(DECL_EXPANDED_NON_TYPE_TEMPLATE_PARM_PACK);
   
+  // Statements and Exprs can occur in the Decls and Types block.
+  AddStmtsExprs(Stream, Record);
+
   BLOCK(PREPROCESSOR_DETAIL_BLOCK);
   RECORD(PPD_MACRO_INSTANTIATION);
   RECORD(PPD_MACRO_DEFINITION);
   RECORD(PPD_INCLUSION_DIRECTIVE);
   
-  // Statements and Exprs can occur in the Decls and Types block.
-  AddStmtsExprs(Stream, Record);
 #undef RECORD
 #undef BLOCK
   Stream.ExitBlock();
@@ -2700,8 +2701,13 @@ ASTWriter::ASTWriter(llvm::BitstreamWriter &Stream)
     NextSelectorID(FirstSelectorID), FirstMacroID(1), NextMacroID(FirstMacroID),
     CollectedStmts(&StmtsToEmit),
     NumStatements(0), NumMacros(0), NumLexicalDeclContexts(0),
-    NumVisibleDeclContexts(0), FirstCXXBaseSpecifiersID(1),
-    NextCXXBaseSpecifiersID(1)
+    NumVisibleDeclContexts(0),
+    FirstCXXBaseSpecifiersID(1), NextCXXBaseSpecifiersID(1),
+    ParmVarDeclAbbrev(0), DeclContextLexicalAbbrev(0),
+    DeclContextVisibleLookupAbbrev(0), UpdateVisibleAbbrev(0),
+    DeclRefExprAbbrev(0), CharacterLiteralAbbrev(0),
+    DeclRecordAbbrev(0), IntegerLiteralAbbrev(0),
+    EnumConstantDeclAbbrev(0)
 {
 }
 
@@ -2867,7 +2873,7 @@ void ASTWriter::WriteASTCore(Sema &SemaRef, MemorizeStatCalls *StatCalls,
 
   // Keep writing types and declarations until all types and
   // declarations have been written.
-  Stream.EnterSubblock(DECLTYPES_BLOCK_ID, 3);
+  Stream.EnterSubblock(DECLTYPES_BLOCK_ID, NUM_ALLOWED_ABBREVS_SIZE);
   WriteDeclsBlockAbbrevs();
   while (!DeclTypesToEmit.empty()) {
     DeclOrType DOT = DeclTypesToEmit.front();
@@ -3097,7 +3103,7 @@ void ASTWriter::WriteASTChain(Sema &SemaRef, MemorizeStatCalls *StatCalls,
     AddDeclRef(SemaRef.getStdBadAlloc(), SemaDeclRefs);
   }
 
-  Stream.EnterSubblock(DECLTYPES_BLOCK_ID, 3);
+  Stream.EnterSubblock(DECLTYPES_BLOCK_ID, NUM_ALLOWED_ABBREVS_SIZE);
   WriteDeclsBlockAbbrevs();
   for (DeclsToRewriteTy::iterator
          I = DeclsToRewrite.begin(), E = DeclsToRewrite.end(); I != E; ++I)
@@ -3209,7 +3215,7 @@ void ASTWriter::WriteDeclUpdatesBlocks() {
     return;
 
   RecordData OffsetsRecord;
-  Stream.EnterSubblock(DECL_UPDATES_BLOCK_ID, 3);
+  Stream.EnterSubblock(DECL_UPDATES_BLOCK_ID, NUM_ALLOWED_ABBREVS_SIZE);
   for (DeclUpdateMap::iterator
          I = DeclUpdates.begin(), E = DeclUpdates.end(); I != E; ++I) {
     const Decl *D = I->first;

clang/lib/Serialization/ASTWriterDecl.cpp

@@ -213,6 +213,21 @@ void ASTDeclWriter::VisitRecordDecl(RecordDecl *D) {
   Record.push_back(D->hasFlexibleArrayMember());
   Record.push_back(D->isAnonymousStructOrUnion());
   Record.push_back(D->hasObjectMember());
+
+  if (!D->hasAttrs() &&
+      !D->isImplicit() &&
+      !D->isUsed(false) &&
+      D->getPCHLevel() == 0 &&
+      !D->hasExtInfo() &&
+      D->RedeclLink.getNext() == D &&
+      !D->isInvalidDecl() &&
+      !D->isReferenced() &&
+      D->getAccess() == AS_none &&
+      !CXXRecordDecl::classofKind(D->getKind()) &&
+      D->getDeclName().getNameKind() == DeclarationName::Identifier)
+
+    AbbrevToUse = Writer.getDeclRecordAbbrev();
+
   Code = serialization::DECL_RECORD;
 }
 
@@ -227,6 +242,20 @@ void ASTDeclWriter::VisitEnumConstantDecl(EnumConstantDecl *D) {
   if (D->getInitExpr())
     Writer.AddStmt(D->getInitExpr());
   Writer.AddAPSInt(D->getInitVal(), Record);
+
+  if (!D->getInitExpr() &&
+      !D->isInvalidDecl() &&
+      !D->hasAttrs() &&
+      !D->isImplicit() &&
+      !D->isUsed(false) &&
+      !D->isReferenced() &&
+      D->getAccess() == AS_none &&
+      D->getPCHLevel() == 0 &&
+      D->getDeclName().getNameKind() == DeclarationName::Identifier &&
+      D->getInitVal().getBitWidth() == 32 
+      )
+    AbbrevToUse = Writer.getEnumConstantDeclAbbrev();
+
   Code = serialization::DECL_ENUM_CONSTANT;
 }
 
@@ -1149,10 +1178,12 @@ void ASTDeclWriter::VisitRedeclarable(Redeclarable<T> *D) {
 
 void ASTWriter::WriteDeclsBlockAbbrevs() {
   using namespace llvm;
-  // Abbreviation for DECL_PARM_VAR.
-  BitCodeAbbrev *Abv = new BitCodeAbbrev();
-  Abv->Add(BitCodeAbbrevOp(serialization::DECL_PARM_VAR));
 
+  BitCodeAbbrev *Abv;
+
+  // Abbreviation for DECL_ENUM_CONSTANT
+  Abv = new BitCodeAbbrev();  
+  Abv->Add(BitCodeAbbrevOp(serialization::DECL_ENUM_CONSTANT));
   // Decl
   Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // DeclContext
   Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // LexicalDeclContext
@@ -1164,7 +1195,71 @@ void ASTWriter::WriteDeclsBlockAbbrevs() {
   Abv->Add(BitCodeAbbrevOp(0));                       // isReferenced
   Abv->Add(BitCodeAbbrevOp(AS_none));                 // C++ AccessSpecifier
   Abv->Add(BitCodeAbbrevOp(0));                       // PCH level
+  // NamedDecl
+  Abv->Add(BitCodeAbbrevOp(0));                       // NameKind = Identifier
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // Name
+  // ValueDecl
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // Type
+  // EnumConstantDecl
+  Abv->Add(BitCodeAbbrevOp(0));                       // getInitExpr
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); //isUnsigned
+  Abv->Add(BitCodeAbbrevOp(32));                      // Bit Width
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // Value
+  EnumConstantDeclAbbrev = Stream.EmitAbbrev(Abv);
 
+  // Abbreviation for DECL_RECORD
+  Abv = new BitCodeAbbrev();
+  Abv->Add(BitCodeAbbrevOp(serialization::DECL_RECORD));
+  // Decl
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // DeclContext
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // LexicalDeclContext
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // Location
+  Abv->Add(BitCodeAbbrevOp(0));                       // isInvalidDecl (!?)
+  Abv->Add(BitCodeAbbrevOp(0));                       // HasAttrs
+  Abv->Add(BitCodeAbbrevOp(0));                       // isImplicit
+  Abv->Add(BitCodeAbbrevOp(0));                       // isUsed
+  Abv->Add(BitCodeAbbrevOp(0));                       // isReferenced
+  Abv->Add(BitCodeAbbrevOp(AS_none));                 // C++ AccessSpecifier
+  Abv->Add(BitCodeAbbrevOp(0));                       // PCH level
+  // NamedDecl
+  Abv->Add(BitCodeAbbrevOp(0));                       // NameKind = Identifier
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // Name
+  // TypeDecl
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // Source Location
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // Type Ref
+  // Redeclarable
+  Abv->Add(BitCodeAbbrevOp(0));                         // No redeclaration
+  // TagDecl
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6));   // IdentifierNamespace
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6));   // getTagKind
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); // isDefinition
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); // EmbeddedInDeclarator
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6));   // SourceLocation
+  Abv->Add(BitCodeAbbrevOp(0));                         // hasExtInfo
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6));   // TypedefNameAnonDecl
+  // RecordDecl
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); // FlexibleArrayMember
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); // AnonymousStructUnion
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); // hasObjectMember
+  // DC
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6));   // LexicalOffset
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6));   // VisibleOffset
+  DeclRecordAbbrev = Stream.EmitAbbrev(Abv);
+
+  // Abbreviation for DECL_PARM_VAR
+  Abv = new BitCodeAbbrev();
+  Abv->Add(BitCodeAbbrevOp(serialization::DECL_PARM_VAR));
+  // Decl
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // DeclContext
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // LexicalDeclContext
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // Location
+  Abv->Add(BitCodeAbbrevOp(0));                       // isInvalidDecl (!?)
+  Abv->Add(BitCodeAbbrevOp(0));                       // HasAttrs
+  Abv->Add(BitCodeAbbrevOp(0));                       // isImplicit
+  Abv->Add(BitCodeAbbrevOp(0));                       // isUsed
+  Abv->Add(BitCodeAbbrevOp(0));                       // isReferenced
+  Abv->Add(BitCodeAbbrevOp(AS_none));                 // C++ AccessSpecifier
+  Abv->Add(BitCodeAbbrevOp(0));                       // PCH level
   // NamedDecl
   Abv->Add(BitCodeAbbrevOp(0));                       // NameKind = Identifier
   Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // Name
@@ -1193,9 +1288,61 @@ void ASTWriter::WriteDeclsBlockAbbrevs() {
   Abv->Add(BitCodeAbbrevOp(0));                       // KNRPromoted
   Abv->Add(BitCodeAbbrevOp(0));                       // HasInheritedDefaultArg
   Abv->Add(BitCodeAbbrevOp(0));                   // HasUninstantiatedDefaultArg
-
   ParmVarDeclAbbrev = Stream.EmitAbbrev(Abv);
 
+  // Abbreviation for EXPR_DECL_REF
+  Abv = new BitCodeAbbrev();
+  Abv->Add(BitCodeAbbrevOp(serialization::EXPR_DECL_REF));
+  //Stmt
+  //Expr
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // Type
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); //IsTypeDependent
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); //IsValueDependent
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); //UnexpandedParamPack
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 3)); //GetValueKind
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 3)); //GetObjectKind
+  //DeclRefExpr
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); //HasQualifier
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); //GetDeclFound
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); //ExplicitTemplateArgs
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // DeclRef
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // Location
+  DeclRefExprAbbrev = Stream.EmitAbbrev(Abv);
+
+  // Abbreviation for EXPR_INTEGER_LITERAL
+  Abv = new BitCodeAbbrev();
+  Abv->Add(BitCodeAbbrevOp(serialization::EXPR_INTEGER_LITERAL));
+  //Stmt
+  //Expr
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // Type
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); //IsTypeDependent
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); //IsValueDependent
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); //UnexpandedParamPack
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 3)); //GetValueKind
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 3)); //GetObjectKind
+  //Integer Literal
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // Location
+  Abv->Add(BitCodeAbbrevOp(32));                      // Bit Width
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // Value
+  IntegerLiteralAbbrev = Stream.EmitAbbrev(Abv);
+
+  // Abbreviation for EXPR_CHARACTER_LITERAL
+  Abv = new BitCodeAbbrev();
+  Abv->Add(BitCodeAbbrevOp(serialization::EXPR_CHARACTER_LITERAL));
+  //Stmt
+  //Expr
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // Type
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); //IsTypeDependent
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); //IsValueDependent
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); //UnexpandedParamPack
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 3)); //GetValueKind
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 3)); //GetObjectKind
+  //CharacterLiteral
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // getValue
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::VBR, 6)); // Location
+  Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Fixed, 1)); //IsWide
+  CharacterLiteralAbbrev = Stream.EmitAbbrev(Abv);
+
   Abv = new BitCodeAbbrev();
   Abv->Add(BitCodeAbbrevOp(serialization::DECL_CONTEXT_LEXICAL));
   Abv->Add(BitCodeAbbrevOp(BitCodeAbbrevOp::Blob));

clang/lib/Serialization/ASTWriterStmt.cpp

@@ -30,6 +30,7 @@ namespace clang {
 
   public:
     serialization::StmtCode Code;
+    unsigned AbbrevToUse;
 
     ASTStmtWriter(ASTWriter &Writer, ASTWriter::RecordData &Record)
       : Writer(Writer), Record(Record) { }
@@ -392,6 +393,14 @@ void ASTStmtWriter::VisitDeclRefExpr(DeclRefExpr *E) {
     Record.push_back(NumTemplateArgs);
   }
 
+  DeclarationName::NameKind nk = (E->getDecl()->getDeclName().getNameKind());
+
+  if ((!E->hasExplicitTemplateArgs()) && (!E->hasQualifier()) &&
+      (E->getDecl() == E->getFoundDecl()) &&
+      nk == DeclarationName::Identifier) {
+    AbbrevToUse = Writer.getDeclRefExprAbbrev();
+  }
+
   if (E->hasQualifier())
     Writer.AddNestedNameSpecifierLoc(E->getQualifierLoc(), Record);
 
@@ -411,6 +420,11 @@ void ASTStmtWriter::VisitIntegerLiteral(IntegerLiteral *E) {
   VisitExpr(E);
   Writer.AddSourceLocation(E->getLocation(), Record);
   Writer.AddAPInt(E->getValue(), Record);
+
+  if (E->getValue().getBitWidth() == 32) {
+    AbbrevToUse = Writer.getIntegerLiteralAbbrev();
+  }
+
   Code = serialization::EXPR_INTEGER_LITERAL;
 }
 
@@ -449,6 +463,9 @@ void ASTStmtWriter::VisitCharacterLiteral(CharacterLiteral *E) {
   Record.push_back(E->getValue());
   Writer.AddSourceLocation(E->getLocation(), Record);
   Record.push_back(E->isWide());
+
+  AbbrevToUse = Writer.getCharacterLiteralAbbrev();
+
   Code = serialization::EXPR_CHARACTER_LITERAL;
 }
 
@@ -1460,6 +1477,7 @@ void ASTWriter::WriteSubStmt(Stmt *S) {
   CollectedStmts = &SubStmts;
 
   Writer.Code = serialization::STMT_NULL_PTR;
+  Writer.AbbrevToUse = 0;
   Writer.Visit(S);
   
 #ifndef NDEBUG
@@ -1481,7 +1499,7 @@ void ASTWriter::WriteSubStmt(Stmt *S) {
   while (!SubStmts.empty())
     WriteSubStmt(SubStmts.pop_back_val());
   
-  Stream.EmitRecord(Writer.Code, Record);
+  Stream.EmitRecord(Writer.Code, Record, Writer.AbbrevToUse);
 }
 
 /// \brief Flush all of the statements that have been added to the