[flang] add option to generate runtime type info as external (#145901)

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/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/Lower/Bridge.cpp

@@ -52,6 +52,7 @@
 #include "flang/Optimizer/Dialect/FIROps.h"
 #include "flang/Optimizer/Dialect/Support/FIRContext.h"
 #include "flang/Optimizer/HLFIR/HLFIROps.h"
+#include "flang/Optimizer/Passes/CommandLineOpts.h"
 #include "flang/Optimizer/Support/DataLayout.h"
 #include "flang/Optimizer/Support/FatalError.h"
 #include "flang/Optimizer/Support/InternalNames.h"
@@ -262,6 +263,7 @@ class TypeInfoConverter {
   }
 
   void createTypeInfo(Fortran::lower::AbstractConverter &converter) {
+    createTypeInfoForTypeDescriptorBuiltinType(converter);
     while (!registeredTypeInfoA.empty()) {
       currentTypeInfoStack = &registeredTypeInfoB;
       for (const TypeInfo &info : registeredTypeInfoA)
@@ -277,10 +279,22 @@ class TypeInfoConverter {
 private:
   void createTypeInfoOpAndGlobal(Fortran::lower::AbstractConverter &converter,
                                  const TypeInfo &info) {
-    Fortran::lower::createRuntimeTypeInfoGlobal(converter, info.symbol.get());
+    if (!::skipExternalRttiDefinition)
+      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

@@ -38,6 +38,7 @@
 #include "flang/Optimizer/Dialect/FIROps.h"
 #include "flang/Optimizer/Dialect/Support/FIRContext.h"
 #include "flang/Optimizer/HLFIR/HLFIROps.h"
+#include "flang/Optimizer/Passes/CommandLineOpts.h"
 #include "flang/Optimizer/Support/FatalError.h"
 #include "flang/Optimizer/Support/InternalNames.h"
 #include "flang/Optimizer/Support/Utils.h"
@@ -652,8 +653,13 @@ getLinkageAttribute(fir::FirOpBuilder &builder,
   // 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() &&
+      (!::skipExternalRttiDefinition ||
+       Fortran::semantics::IsFromBuiltinModule(var.getSymbol())))
     return builder.createLinkOnceODRLinkage();
   if (var.isModuleOrSubmoduleVariable())
     return {}; // external linkage

flang/lib/Optimizer/CodeGen/CodeGen.cpp

@@ -1294,6 +1294,51 @@ genCUFAllocDescriptor(mlir::Location loc,
       .getResult();
 }
 
+/// Get the address of the type descriptor global variable that was created by
+/// lowering for derived type \p recType.
+template <typename ModOpTy>
+static mlir::Value
+getTypeDescriptor(ModOpTy mod, mlir::ConversionPatternRewriter &rewriter,
+                  mlir::Location loc, fir::RecordType recType,
+                  const fir::FIRToLLVMPassOptions &options) {
+  std::string name =
+      options.typeDescriptorsRenamedForAssembly
+          ? fir::NameUniquer::getTypeDescriptorAssemblyName(recType.getName())
+          : fir::NameUniquer::getTypeDescriptorName(recType.getName());
+  mlir::Type llvmPtrTy = ::getLlvmPtrType(mod.getContext());
+  if (auto global = mod.template lookupSymbol<fir::GlobalOp>(name))
+    return rewriter.create<mlir::LLVM::AddressOfOp>(loc, llvmPtrTy,
+                                                    global.getSymName());
+  // The global may have already been translated to LLVM.
+  if (auto global = mod.template lookupSymbol<mlir::LLVM::GlobalOp>(name))
+    return rewriter.create<mlir::LLVM::AddressOfOp>(loc, llvmPtrTy,
+                                                    global.getSymName());
+  // Type info derived types do not have type descriptors since they are the
+  // types defining type descriptors.
+  if (options.ignoreMissingTypeDescriptors ||
+      fir::NameUniquer::belongsToModule(
+          name, Fortran::semantics::typeInfoBuiltinModule))
+    return rewriter.create<mlir::LLVM::ZeroOp>(loc, llvmPtrTy);
+
+  if (!options.skipExternalRttiDefinition)
+    fir::emitFatalError(loc,
+                        "runtime derived type info descriptor was not "
+                        "generated and skipExternalRttiDefinition and "
+                        "ignoreMissingTypeDescriptors options are not set");
+
+  // Rtti for a derived type defined in another compilation unit and for which
+  // rtti was not defined in lowering because of the skipExternalRttiDefinition
+  // option. Generate the object declaration now.
+  auto insertPt = rewriter.saveInsertionPoint();
+  rewriter.setInsertionPoint(mod.getBody(), mod.getBody()->end());
+  mlir::LLVM::GlobalOp global = rewriter.create<mlir::LLVM::GlobalOp>(
+      loc, llvmPtrTy, /*constant=*/true, mlir::LLVM::Linkage::External, name,
+      mlir::Attribute());
+  rewriter.restoreInsertionPoint(insertPt);
+  return rewriter.create<mlir::LLVM::AddressOfOp>(loc, llvmPtrTy,
+                                                  global.getSymName());
+}
+
 /// Common base class for embox to descriptor conversion.
 template <typename OP>
 struct EmboxCommonConversion : public fir::FIROpConversion<OP> {
@@ -1406,36 +1451,6 @@ struct EmboxCommonConversion : public fir::FIROpConversion<OP> {
                        stride);
   }
 
-  /// Get the address of the type descriptor global variable that was created by
-  /// lowering for derived type \p recType.
-  template <typename ModOpTy>
-  mlir::Value
-  getTypeDescriptor(ModOpTy mod, mlir::ConversionPatternRewriter &rewriter,
-                    mlir::Location loc, fir::RecordType recType) const {
-    std::string name =
-        this->options.typeDescriptorsRenamedForAssembly
-            ? fir::NameUniquer::getTypeDescriptorAssemblyName(recType.getName())
-            : fir::NameUniquer::getTypeDescriptorName(recType.getName());
-    mlir::Type llvmPtrTy = ::getLlvmPtrType(mod.getContext());
-    if (auto global = mod.template lookupSymbol<fir::GlobalOp>(name)) {
-      return rewriter.create<mlir::LLVM::AddressOfOp>(loc, llvmPtrTy,
-                                                      global.getSymName());
-    }
-    if (auto global = mod.template lookupSymbol<mlir::LLVM::GlobalOp>(name)) {
-      // The global may have already been translated to LLVM.
-      return rewriter.create<mlir::LLVM::AddressOfOp>(loc, llvmPtrTy,
-                                                      global.getSymName());
-    }
-    // Type info derived types do not have type descriptors since they are the
-    // types defining type descriptors.
-    if (!this->options.ignoreMissingTypeDescriptors &&
-        !fir::NameUniquer::belongsToModule(
-            name, Fortran::semantics::typeInfoBuiltinModule))
-      fir::emitFatalError(
-          loc, "runtime derived type info descriptor was not generated");
-    return rewriter.create<mlir::LLVM::ZeroOp>(loc, llvmPtrTy);
-  }
-
   template <typename ModOpTy>
   mlir::Value populateDescriptor(mlir::Location loc, ModOpTy mod,
                                  fir::BaseBoxType boxTy, mlir::Type inputType,
@@ -1500,16 +1515,17 @@ struct EmboxCommonConversion : public fir::FIROpConversion<OP> {
           mlir::Type innerType = fir::unwrapInnerType(inputType);
           if (innerType && mlir::isa<fir::RecordType>(innerType)) {
             auto recTy = mlir::dyn_cast<fir::RecordType>(innerType);
-            typeDesc = getTypeDescriptor(mod, rewriter, loc, recTy);
+            typeDesc =
+                getTypeDescriptor(mod, rewriter, loc, recTy, this->options);
           } else {
             // Unlimited polymorphic type descriptor with no record type. Set
             // type descriptor address to a clean state.
             typeDesc = rewriter.create<mlir::LLVM::ZeroOp>(
                 loc, ::getLlvmPtrType(mod.getContext()));
           }
         } else {
-          typeDesc = getTypeDescriptor(mod, rewriter, loc,
-                                       fir::unwrapIfDerived(boxTy));
+          typeDesc = getTypeDescriptor(
+              mod, rewriter, loc, fir::unwrapIfDerived(boxTy), this->options);
         }
       }
       if (typeDesc)
@@ -3021,22 +3037,10 @@ struct TypeDescOpConversion : public fir::FIROpConversion<fir::TypeDescOp> {
     assert(mlir::isa<fir::RecordType>(inTy) && "expecting fir.type");
     auto recordType = mlir::dyn_cast<fir::RecordType>(inTy);
     auto module = typeDescOp.getOperation()->getParentOfType<mlir::ModuleOp>();
-    std::string typeDescName =
-        this->options.typeDescriptorsRenamedForAssembly
-            ? fir::NameUniquer::getTypeDescriptorAssemblyName(
-                  recordType.getName())
-            : fir::NameUniquer::getTypeDescriptorName(recordType.getName());
-    auto llvmPtrTy = ::getLlvmPtrType(typeDescOp.getContext());
-    if (auto global = module.lookupSymbol<mlir::LLVM::GlobalOp>(typeDescName)) {
-      rewriter.replaceOpWithNewOp<mlir::LLVM::AddressOfOp>(
-          typeDescOp, llvmPtrTy, global.getSymName());
-      return mlir::success();
-    } else if (auto global = module.lookupSymbol<fir::GlobalOp>(typeDescName)) {
-      rewriter.replaceOpWithNewOp<mlir::LLVM::AddressOfOp>(
-          typeDescOp, llvmPtrTy, global.getSymName());
-      return mlir::success();
-    }
-    return mlir::failure();
+    mlir::Value typeDesc = getTypeDescriptor(
+        module, rewriter, typeDescOp.getLoc(), recordType, this->options);
+    rewriter.replaceOp(typeDescOp, typeDesc);
+    return mlir::success();
   }
 };
 

flang/lib/Optimizer/Passes/CommandLineOpts.cpp

@@ -39,6 +39,12 @@ cl::opt<bool> ignoreMissingTypeDescriptors(
              "translating FIR to LLVM"),
     cl::init(false), cl::Hidden);
 
+cl::opt<bool> skipExternalRttiDefinition(
+    "skip-external-rtti-definition", llvm::cl::init(false),
+    llvm::cl::desc("do not define rtti static objects for types belonging to "
+                   "other compilation units"),
+    cl::Hidden);
+
 OptimizationLevel defaultOptLevel{OptimizationLevel::O0};
 
 codegenoptions::DebugInfoKind noDebugInfo{codegenoptions::NoDebugInfo};