[clang][AST] Improve AST Reader/Writer memory footprint

Reduce memory footprint of AST Reader/Writer:
1. Adjust internal data containers' element type.
2. Switch to set for deduplication of deferred diags.

Differential Revision: https://reviews.llvm.org/D101793

clang/include/clang/Sema/ExternalSemaSource.h

@@ -199,8 +199,8 @@ public:
   /// and variable decls which may cause deferred diags. Note that this routine
   /// may be invoked multiple times; the external source should take care not to
   /// introduce the same declarations repeatedly.
-  virtual void ReadDeclsToCheckForDeferredDiags(
-      llvm::SmallVector<Decl *, 4> &Decls) {}
+  virtual void
+  ReadDeclsToCheckForDeferredDiags(llvm::SmallSetVector<Decl *, 4> &Decls) {}
 
   /// \copydoc Sema::CorrectTypo
   /// \note LookupKind must correspond to a valid Sema::LookupNameKind

clang/include/clang/Sema/MultiplexExternalSemaSource.h

@@ -337,7 +337,7 @@ public:
   /// may be invoked multiple times; the external source should take care not to
   /// introduce the same declarations repeatedly.
   void ReadDeclsToCheckForDeferredDiags(
-      llvm::SmallVector<Decl *, 4> &Decls) override;
+      llvm::SmallSetVector<Decl *, 4> &Decls) override;
 
   /// \copydoc ExternalSemaSource::CorrectTypo
   /// \note Returns the first nonempty correction.

clang/include/clang/Sema/Sema.h

@@ -1786,7 +1786,7 @@ public:
   private:
     /// Function or variable declarations to be checked for whether the deferred
     /// diagnostics should be emitted.
-    SmallVector<Decl *, 4> DeclsToCheckForDeferredDiags;
+    llvm::SmallSetVector<Decl *, 4> DeclsToCheckForDeferredDiags;
 
   public:
   // Emit all deferred diagnostics.

clang/include/clang/Serialization/ASTReader.h

@@ -767,21 +767,21 @@ private:
   /// This contains the data loaded from all EAGERLY_DESERIALIZED_DECLS blocks
   /// in the chain. The referenced declarations are deserialized and passed to
   /// the consumer eagerly.
-  SmallVector<uint64_t, 16> EagerlyDeserializedDecls;
+  SmallVector<serialization::DeclID, 16> EagerlyDeserializedDecls;
 
   /// The IDs of all tentative definitions stored in the chain.
   ///
   /// Sema keeps track of all tentative definitions in a TU because it has to
   /// complete them and pass them on to CodeGen. Thus, tentative definitions in
   /// the PCH chain must be eagerly deserialized.
-  SmallVector<uint64_t, 16> TentativeDefinitions;
+  SmallVector<serialization::DeclID, 16> TentativeDefinitions;
 
   /// The IDs of all CXXRecordDecls stored in the chain whose VTables are
   /// used.
   ///
   /// CodeGen has to emit VTables for these records, so they have to be eagerly
   /// deserialized.
-  SmallVector<uint64_t, 64> VTableUses;
+  SmallVector<serialization::DeclID, 64> VTableUses;
 
   /// A snapshot of the pending instantiations in the chain.
   ///
@@ -789,7 +789,7 @@ private:
   /// end of the TU. It consists of a pair of values for every pending
   /// instantiation where the first value is the ID of the decl and the second
   /// is the instantiation location.
-  SmallVector<uint64_t, 64> PendingInstantiations;
+  SmallVector<serialization::DeclID, 64> PendingInstantiations;
 
   //@}
 
@@ -799,24 +799,24 @@ private:
 
   /// A snapshot of Sema's unused file-scoped variable tracking, for
   /// generating warnings.
-  SmallVector<uint64_t, 16> UnusedFileScopedDecls;
+  SmallVector<serialization::DeclID, 16> UnusedFileScopedDecls;
 
   /// A list of all the delegating constructors we've seen, to diagnose
   /// cycles.
-  SmallVector<uint64_t, 4> DelegatingCtorDecls;
+  SmallVector<serialization::DeclID, 4> DelegatingCtorDecls;
 
   /// Method selectors used in a @selector expression. Used for
   /// implementation of -Wselector.
-  SmallVector<uint64_t, 64> ReferencedSelectorsData;
+  SmallVector<serialization::SelectorID, 64> ReferencedSelectorsData;
 
   /// A snapshot of Sema's weak undeclared identifier tracking, for
   /// generating warnings.
-  SmallVector<uint64_t, 64> WeakUndeclaredIdentifiers;
+  SmallVector<serialization::IdentifierID, 64> WeakUndeclaredIdentifiers;
 
   /// The IDs of type aliases for ext_vectors that exist in the chain.
   ///
   /// Used by Sema for finding sugared names for ext_vectors in diagnostics.
-  SmallVector<uint64_t, 4> ExtVectorDecls;
+  SmallVector<serialization::DeclID, 4> ExtVectorDecls;
 
   //@}
 
@@ -827,7 +827,7 @@ private:
   /// The IDs of all potentially unused typedef names in the chain.
   ///
   /// Sema tracks these to emit warnings.
-  SmallVector<uint64_t, 16> UnusedLocalTypedefNameCandidates;
+  SmallVector<serialization::DeclID, 16> UnusedLocalTypedefNameCandidates;
 
   /// Our current depth in #pragma cuda force_host_device begin/end
   /// macros.
@@ -836,18 +836,18 @@ private:
   /// The IDs of the declarations Sema stores directly.
   ///
   /// Sema tracks a few important decls, such as namespace std, directly.
-  SmallVector<uint64_t, 4> SemaDeclRefs;
+  SmallVector<serialization::DeclID, 4> SemaDeclRefs;
 
   /// The IDs of the types ASTContext stores directly.
   ///
   /// The AST context tracks a few important types, such as va_list, directly.
-  SmallVector<uint64_t, 16> SpecialTypes;
+  SmallVector<serialization::TypeID, 16> SpecialTypes;
 
   /// The IDs of CUDA-specific declarations ASTContext stores directly.
   ///
   /// The AST context tracks a few important decls, currently cudaConfigureCall,
   /// directly.
-  SmallVector<uint64_t, 2> CUDASpecialDeclRefs;
+  SmallVector<serialization::DeclID, 2> CUDASpecialDeclRefs;
 
   /// The floating point pragma option settings.
   SmallVector<uint64_t, 1> FPPragmaOptions;
@@ -896,11 +896,11 @@ private:
   llvm::DenseMap<const Decl *, std::set<std::string>> OpenCLDeclExtMap;
 
   /// A list of the namespaces we've seen.
-  SmallVector<uint64_t, 4> KnownNamespaces;
+  SmallVector<serialization::DeclID, 4> KnownNamespaces;
 
   /// A list of undefined decls with internal linkage followed by the
   /// SourceLocation of a matching ODR-use.
-  SmallVector<uint64_t, 8> UndefinedButUsed;
+  SmallVector<serialization::DeclID, 8> UndefinedButUsed;
 
   /// Delete expressions to analyze at the end of translation unit.
   SmallVector<uint64_t, 8> DelayedDeleteExprs;
@@ -912,8 +912,7 @@ private:
   /// The IDs of all decls to be checked for deferred diags.
   ///
   /// Sema tracks these to emit deferred diags.
-  SmallVector<uint64_t, 4> DeclsToCheckForDeferredDiags;
-
+  llvm::SmallSetVector<serialization::DeclID, 4> DeclsToCheckForDeferredDiags;
 
 public:
   struct ImportedSubmodule {
@@ -2016,7 +2015,7 @@ public:
       llvm::SmallSetVector<const TypedefNameDecl *, 4> &Decls) override;
 
   void ReadDeclsToCheckForDeferredDiags(
-      llvm::SmallVector<Decl *, 4> &Decls) override;
+      llvm::SmallSetVector<Decl *, 4> &Decls) override;
 
   void ReadReferencedSelectors(
            SmallVectorImpl<std::pair<Selector, SourceLocation>> &Sels) override;

clang/include/clang/Serialization/ASTWriter.h

@@ -402,8 +402,8 @@ private:
   /// headers. The declarations themselves are stored as declaration
   /// IDs, since they will be written out to an EAGERLY_DESERIALIZED_DECLS
   /// record.
-  SmallVector<uint64_t, 16> EagerlyDeserializedDecls;
-  SmallVector<uint64_t, 16> ModularCodegenDecls;
+  SmallVector<serialization::DeclID, 16> EagerlyDeserializedDecls;
+  SmallVector<serialization::DeclID, 16> ModularCodegenDecls;
 
   /// DeclContexts that have received extensions since their serialized
   /// form.

clang/lib/Sema/MultiplexExternalSemaSource.cpp

@@ -268,7 +268,7 @@ void MultiplexExternalSemaSource::ReadExtVectorDecls(
 }
 
 void MultiplexExternalSemaSource::ReadDeclsToCheckForDeferredDiags(
-    llvm::SmallVector<Decl *, 4> &Decls) {
+    llvm::SmallSetVector<Decl *, 4> &Decls) {
   for(size_t i = 0; i < Sources.size(); ++i)
     Sources[i]->ReadDeclsToCheckForDeferredDiags(Decls);
 }

clang/lib/Sema/SemaDecl.cpp

@@ -12539,7 +12539,7 @@ void Sema::AddInitializerToDecl(Decl *RealDecl, Expr *Init, bool DirectInit) {
   }
 
   if (LangOpts.OpenMP && VDecl->isFileVarDecl())
-    DeclsToCheckForDeferredDiags.push_back(VDecl);
+    DeclsToCheckForDeferredDiags.insert(VDecl);
   CheckCompleteVariableDeclaration(VDecl);
 }
 
@@ -14773,7 +14773,7 @@ Decl *Sema::ActOnFinishFunctionBody(Decl *dcl, Stmt *Body,
     auto ES = getEmissionStatus(FD);
     if (ES == Sema::FunctionEmissionStatus::Emitted ||
         ES == Sema::FunctionEmissionStatus::Unknown)
-      DeclsToCheckForDeferredDiags.push_back(FD);
+      DeclsToCheckForDeferredDiags.insert(FD);
   }
 
   return dcl;

clang/lib/Serialization/ASTReader.cpp

@@ -3810,7 +3810,7 @@ ASTReader::ReadASTBlock(ModuleFile &F, unsigned ClientLoadCapabilities) {
 
     case DECLS_TO_CHECK_FOR_DEFERRED_DIAGS:
       for (unsigned I = 0, N = Record.size(); I != N; ++I)
-        DeclsToCheckForDeferredDiags.push_back(getGlobalDeclID(F, Record[I]));
+        DeclsToCheckForDeferredDiags.insert(getGlobalDeclID(F, Record[I]));
       break;
     }
   }
@@ -8333,18 +8333,15 @@ void ASTReader::ReadUnusedLocalTypedefNameCandidates(
 }
 
 void ASTReader::ReadDeclsToCheckForDeferredDiags(
-    llvm::SmallVector<Decl *, 4> &Decls) {
-  for (unsigned I = 0, N = DeclsToCheckForDeferredDiags.size(); I != N;
-       ++I) {
-    auto *D = dyn_cast_or_null<Decl>(
-        GetDecl(DeclsToCheckForDeferredDiags[I]));
+    llvm::SmallSetVector<Decl *, 4> &Decls) {
+  for (auto I : DeclsToCheckForDeferredDiags) {
+    auto *D = dyn_cast_or_null<Decl>(GetDecl(I));
     if (D)
-      Decls.push_back(D);
+      Decls.insert(D);
   }
   DeclsToCheckForDeferredDiags.clear();
 }
 
-
 void ASTReader::ReadReferencedSelectors(
        SmallVectorImpl<std::pair<Selector, SourceLocation>> &Sels) {
   if (ReferencedSelectorsData.empty())

clang/lib/Serialization/ASTWriter.cpp

@@ -4667,9 +4667,9 @@ ASTFileSignature ASTWriter::WriteASTCore(Sema &SemaRef, StringRef isysroot,
   }
 
   // Build a record containing all of the DeclsToCheckForDeferredDiags.
-  RecordData DeclsToCheckForDeferredDiags;
+  SmallVector<serialization::DeclID, 64> DeclsToCheckForDeferredDiags;
   for (auto *D : SemaRef.DeclsToCheckForDeferredDiags)
-    AddDeclRef(D, DeclsToCheckForDeferredDiags);
+    DeclsToCheckForDeferredDiags.push_back(GetDeclRef(D));
 
   RecordData DeclUpdatesOffsetsRecord;