[flang] add option to generate runtime type info as external (#146071)

Reland #145901 with a fix for shared library builds.

So far flang generates runtime derived type info global definitions (as
opposed to declarations) for all the types used in the current
compilation unit even when the derived types are defined in other
compilation units. It is using linkonce_odr to achieve derived type
descriptor address "uniqueness" aspect needed to match two derived type
inside the runtime.

This comes at a big compile time cost because of all the extra globals
and their definitions in apps with many and complex derived types.

This patch adds and experimental option to only generate the rtti
definition for the types defined in the current compilation unit and to
only generate external declaration for the derived type descriptor
object of types defined elsewhere.

Note that objects compiled with this option are not compatible with
object files compiled without because files compiled without it may drop
the rtti for type they defined if it is not used in the compilation unit
because of the linkonce_odr aspect.

I am adding the option so that we can better measure the extra cost of
the current approach on apps and allow speeding up some compilation
where devirtualization does not matter (and the build config links to
all module file object anyway).

Author: jeanPerier

flang/include/flang/Evaluate/tools.h

@@ -1585,6 +1585,7 @@ bool IsExtensibleType(const DerivedTypeSpec *);
 bool IsSequenceOrBindCType(const DerivedTypeSpec *);
 bool IsBuiltinDerivedType(const DerivedTypeSpec *derived, const char *name);
 bool IsBuiltinCPtr(const Symbol &);
+bool IsFromBuiltinModule(const Symbol &);
 bool IsEventType(const DerivedTypeSpec *);
 bool IsLockType(const DerivedTypeSpec *);
 bool IsNotifyType(const DerivedTypeSpec *);

flang/include/flang/Lower/LoweringOptions.def

@@ -66,5 +66,9 @@ ENUM_LOWERINGOPT(RepackArraysWhole, unsigned, 1, 0)
 /// If true, CUDA Fortran runtime check is inserted.
 ENUM_LOWERINGOPT(CUDARuntimeCheck, unsigned, 1, 0)
 
+/// If true, do not generate definition for runtime type info global objects of
+/// derived types defined in other compilation units.
+ENUM_LOWERINGOPT(SkipExternalRttiDefinition, unsigned, 1, 0)
+
 #undef LOWERINGOPT
 #undef ENUM_LOWERINGOPT

flang/include/flang/Optimizer/CodeGen/CodeGen.h

@@ -39,6 +39,9 @@ struct FIRToLLVMPassOptions {
   // that such programs would crash at runtime if the derived type descriptors
   // are required by the runtime, so this is only an option to help debugging.
   bool ignoreMissingTypeDescriptors = false;
+  // Similar to ignoreMissingTypeDescriptors, but generate external declaration
+  // for the missing type descriptor globals instead.
+  bool skipExternalRttiDefinition = false;
 
   // Generate TBAA information for FIR types and memory accessing operations.
   bool applyTBAA = false;

flang/include/flang/Optimizer/Passes/CommandLineOpts.h

@@ -32,6 +32,19 @@ extern llvm::cl::opt<std::size_t> arrayStackAllocationThreshold;
 /// generated by the frontend.
 extern llvm::cl::opt<bool> ignoreMissingTypeDescriptors;
 
+/// Shared option in tools to only generate rtti static object definitions for
+/// derived types defined in the current compilation unit. Derived type
+/// descriptor object for types defined in other objects will only be declared
+/// as external. This also changes the linkage of rtti objects defined in the
+/// current compilation unit from linkonce_odr to external so that unused rtti
+/// objects are retained and can be accessed from other compilation units. This
+/// is an experimental option to explore compilation speed improvements and is
+/// an ABI breaking change because of the linkage change.
+/// It will also require linking against module file objects of modules defining
+/// only types (even for trivial types without type bound procedures, which
+/// differs from most compilers).
+extern llvm::cl::opt<bool> skipExternalRttiDefinition;
+
 /// Default optimization level used to create Flang pass pipeline is O0.
 extern llvm::OptimizationLevel defaultOptLevel;
 

flang/include/flang/Optimizer/Support/Utils.h

@@ -35,32 +35,6 @@ inline std::int64_t toInt(mlir::arith::ConstantOp cop) {
       .getSExtValue();
 }
 
-// Reconstruct binding tables for dynamic dispatch.
-using BindingTable = llvm::DenseMap<llvm::StringRef, unsigned>;
-using BindingTables = llvm::DenseMap<llvm::StringRef, BindingTable>;
-
-inline void buildBindingTables(BindingTables &bindingTables,
-                               mlir::ModuleOp mod) {
-
-  // The binding tables are defined in FIR after lowering inside fir.type_info
-  // operations. Go through each binding tables and store the procedure name and
-  // binding index for later use by the fir.dispatch conversion pattern.
-  for (auto typeInfo : mod.getOps<fir::TypeInfoOp>()) {
-    unsigned bindingIdx = 0;
-    BindingTable bindings;
-    if (typeInfo.getDispatchTable().empty()) {
-      bindingTables[typeInfo.getSymName()] = bindings;
-      continue;
-    }
-    for (auto dtEntry :
-         typeInfo.getDispatchTable().front().getOps<fir::DTEntryOp>()) {
-      bindings[dtEntry.getMethod()] = bindingIdx;
-      ++bindingIdx;
-    }
-    bindingTables[typeInfo.getSymName()] = bindings;
-  }
-}
-
 // Translate front-end KINDs for use in the IR and code gen.
 inline std::vector<fir::KindTy>
 fromDefaultKinds(const Fortran::common::IntrinsicTypeDefaultKinds &defKinds) {

flang/include/flang/Semantics/runtime-type-info.h

@@ -38,6 +38,10 @@ RuntimeDerivedTypeTables BuildRuntimeDerivedTypeTables(SemanticsContext &);
 /// to describe other derived types at runtime in flang descriptor.
 constexpr char typeInfoBuiltinModule[]{"__fortran_type_info"};
 
+/// Name of the builtin derived type in __fortran_type_inf that is used for
+/// derived type descriptors.
+constexpr char typeDescriptorTypeName[]{"derivedtype"};
+
 /// Name of the bindings descriptor component in the DerivedType type of the
 /// __Fortran_type_info module
 constexpr char bindingDescCompName[]{"binding"};

flang/lib/Evaluate/tools.cpp

@@ -2334,6 +2334,11 @@ bool IsBuiltinCPtr(const Symbol &symbol) {
   return false;
 }
 
+bool IsFromBuiltinModule(const Symbol &symbol) {
+  const Scope &scope{symbol.GetUltimate().owner()};
+  return IsSameModule(&scope, scope.context().GetBuiltinsScope());
+}
+
 bool IsIsoCType(const DerivedTypeSpec *derived) {
   return IsBuiltinDerivedType(derived, "c_ptr") ||
       IsBuiltinDerivedType(derived, "c_funptr");

flang/lib/Frontend/CompilerInvocation.cpp

@@ -14,6 +14,7 @@
 #include "flang/Frontend/CodeGenOptions.h"
 #include "flang/Frontend/PreprocessorOptions.h"
 #include "flang/Frontend/TargetOptions.h"
+#include "flang/Optimizer/Passes/CommandLineOpts.h"
 #include "flang/Semantics/semantics.h"
 #include "flang/Support/Fortran-features.h"
 #include "flang/Support/OpenMP-features.h"
@@ -1792,6 +1793,7 @@ void CompilerInvocation::setLoweringOptions() {
   // Lower TRANSPOSE as a runtime call under -O0.
   loweringOpts.setOptimizeTranspose(codegenOpts.OptimizationLevel > 0);
   loweringOpts.setUnderscoring(codegenOpts.Underscoring);
+  loweringOpts.setSkipExternalRttiDefinition(skipExternalRttiDefinition);
 
   const Fortran::common::LangOptions &langOptions = getLangOpts();
   loweringOpts.setIntegerWrapAround(langOptions.getSignedOverflowBehavior() ==

flang/lib/Lower/Bridge.cpp

@@ -262,6 +262,7 @@ class TypeInfoConverter {
   }
 
   void createTypeInfo(Fortran::lower::AbstractConverter &converter) {
+    createTypeInfoForTypeDescriptorBuiltinType(converter);
     while (!registeredTypeInfoA.empty()) {
       currentTypeInfoStack = &registeredTypeInfoB;
       for (const TypeInfo &info : registeredTypeInfoA)
@@ -277,10 +278,22 @@ class TypeInfoConverter {
 private:
   void createTypeInfoOpAndGlobal(Fortran::lower::AbstractConverter &converter,
                                  const TypeInfo &info) {
-    Fortran::lower::createRuntimeTypeInfoGlobal(converter, info.symbol.get());
+    if (!converter.getLoweringOptions().getSkipExternalRttiDefinition())
+      Fortran::lower::createRuntimeTypeInfoGlobal(converter, info.symbol.get());
     createTypeInfoOp(converter, info);
   }
 
+  void createTypeInfoForTypeDescriptorBuiltinType(
+      Fortran::lower::AbstractConverter &converter) {
+    if (registeredTypeInfoA.empty())
+      return;
+    auto builtinTypeInfoType = llvm::cast<fir::RecordType>(
+        converter.genType(registeredTypeInfoA[0].symbol.get()));
+    converter.getFirOpBuilder().createTypeInfoOp(
+        registeredTypeInfoA[0].loc, builtinTypeInfoType,
+        /*parentType=*/fir::RecordType{});
+  }
+
   void createTypeInfoOp(Fortran::lower::AbstractConverter &converter,
                         const TypeInfo &info) {
     fir::RecordType parentType{};

flang/lib/Lower/ConvertVariable.cpp

@@ -647,13 +647,19 @@ fir::GlobalOp Fortran::lower::defineGlobal(
 
 /// Return linkage attribute for \p var.
 static mlir::StringAttr
-getLinkageAttribute(fir::FirOpBuilder &builder,
+getLinkageAttribute(Fortran::lower::AbstractConverter &converter,
                     const Fortran::lower::pft::Variable &var) {
+  fir::FirOpBuilder &builder = converter.getFirOpBuilder();
   // Runtime type info for a same derived type is identical in each compilation
   // unit. It desired to avoid having to link against module that only define a
   // type. Therefore the runtime type info is generated everywhere it is needed
-  // with `linkonce_odr` LLVM linkage.
-  if (var.isRuntimeTypeInfoData())
+  // with `linkonce_odr` LLVM linkage (unless the skipExternalRttiDefinition
+  // option is set, in which case one will need to link against objects of
+  // modules defining types). Builtin objects rtti is always generated because
+  // the builtin module is currently not compiled or part of the runtime.
+  if (var.isRuntimeTypeInfoData() &&
+      (!converter.getLoweringOptions().getSkipExternalRttiDefinition() ||
+       Fortran::semantics::IsFromBuiltinModule(var.getSymbol())))
     return builder.createLinkOnceODRLinkage();
   if (var.isModuleOrSubmoduleVariable())
     return {}; // external linkage
@@ -673,7 +679,7 @@ static void instantiateGlobal(Fortran::lower::AbstractConverter &converter,
   fir::FirOpBuilder &builder = converter.getFirOpBuilder();
   std::string globalName = converter.mangleName(sym);
   mlir::Location loc = genLocation(converter, sym);
-  mlir::StringAttr linkage = getLinkageAttribute(builder, var);
+  mlir::StringAttr linkage = getLinkageAttribute(converter, var);
   fir::GlobalOp global;
   if (var.isModuleOrSubmoduleVariable()) {
     // A non-intrinsic module global is defined when lowering the module.
@@ -1265,7 +1271,7 @@ instantiateAggregateStore(Fortran::lower::AbstractConverter &converter,
   if (var.isGlobal()) {
     fir::GlobalOp global;
     auto &aggregate = var.getAggregateStore();
-    mlir::StringAttr linkage = getLinkageAttribute(builder, var);
+    mlir::StringAttr linkage = getLinkageAttribute(converter, var);
     if (var.isModuleOrSubmoduleVariable()) {
       // A module global was or will be defined when lowering the module. Emit
       // only a declaration if the global does not exist at that point.
@@ -2470,8 +2476,7 @@ void Fortran::lower::defineModuleVariable(
     AbstractConverter &converter, const Fortran::lower::pft::Variable &var) {
   // Use empty linkage for module variables, which makes them available
   // for use in another unit.
-  mlir::StringAttr linkage =
-      getLinkageAttribute(converter.getFirOpBuilder(), var);
+  mlir::StringAttr linkage = getLinkageAttribute(converter, var);
   if (!var.isGlobal())
     fir::emitFatalError(converter.getCurrentLocation(),
                         "attempting to lower module variable as local");
@@ -2606,10 +2611,9 @@ void Fortran::lower::createIntrinsicModuleGlobal(
 void Fortran::lower::createRuntimeTypeInfoGlobal(
     Fortran::lower::AbstractConverter &converter,
     const Fortran::semantics::Symbol &typeInfoSym) {
-  fir::FirOpBuilder &builder = converter.getFirOpBuilder();
   std::string globalName = converter.mangleName(typeInfoSym);
   auto var = Fortran::lower::pft::Variable(typeInfoSym, /*global=*/true);
-  mlir::StringAttr linkage = getLinkageAttribute(builder, var);
+  mlir::StringAttr linkage = getLinkageAttribute(converter, var);
   defineGlobal(converter, var, globalName, linkage);
 }