Move the "findUsedStructTypes" functionality outside of the Module class.

The "findUsedStructTypes" method is very expensive to run. It needs to be
optimized so that LTO can run faster. Splitting this method out of the Module
class will help this occur. For instance, it can keep a list of seen objects so
that it doesn't process them over and over again.

llvm-svn: 161228

Author: isanbard

llvm/include/llvm/Module.h

@@ -301,11 +301,6 @@ class Module {
   typedef DenseMap<StructType*, unsigned, DenseMapInfo<StructType*> >
                    NumeredTypesMapTy;
 
-  /// findUsedStructTypes - Walk the entire module and find all of the
-  /// struct types that are in use, returning them in a vector.
-  void findUsedStructTypes(std::vector<StructType*> &StructTypes,
-                           bool OnlyNamed = false) const;
-  
   /// getTypeByName - Return the type with the specified name, or null if there
   /// is none by that name.
   StructType *getTypeByName(StringRef Name) const;

llvm/include/llvm/TypeFinder.h

@@ -0,0 +1,78 @@
+//===-- llvm/TypeFinder.h - Class for finding used struct types -*- C++ -*-===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+//
+// This file contains the declaration of the TypeFinder class. 
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_TYPEFINDER_H
+#define LLVM_TYPEFINDER_H
+
+#include "llvm/ADT/DenseSet.h"
+#include <vector>
+
+namespace llvm {
+
+class MDNode;
+class Module;
+class StructType;
+class Type;
+class Value;
+
+/// TypeFinder - Walk over a module, identifying all of the types that are
+/// used by the module.
+class TypeFinder {
+  // To avoid walking constant expressions multiple times and other IR
+  // objects, we keep several helper maps.
+  DenseSet<const Value*> VisitedConstants;
+  DenseSet<Type*> VisitedTypes;
+
+  std::vector<StructType*> StructTypes;
+  bool OnlyNamed;
+
+public:
+  TypeFinder() : OnlyNamed(false) {}
+
+  void run(const Module &M, bool onlyNamed);
+  void clear();
+
+  typedef std::vector<StructType*>::iterator iterator;
+  typedef std::vector<StructType*>::const_iterator const_iterator;
+
+  iterator begin() { return StructTypes.begin(); }
+  iterator end() { return StructTypes.end(); }
+
+  const_iterator begin() const { return StructTypes.begin(); }
+  const_iterator end() const { return StructTypes.end(); }
+
+  bool empty() const { return StructTypes.empty(); }
+  size_t size() const { return StructTypes.size(); }
+  iterator erase(iterator I, iterator E) { return StructTypes.erase(I, E); }
+
+  StructType *&operator[](unsigned Idx) { return StructTypes[Idx]; }
+
+private:
+  /// incorporateType - This method adds the type to the list of used
+  /// structures if it's not in there already.
+  void incorporateType(Type *Ty);
+
+  /// incorporateValue - This method is used to walk operand lists finding types
+  /// hiding in constant expressions and other operands that won't be walked in
+  /// other ways.  GlobalValues, basic blocks, instructions, and inst operands
+  /// are all explicitly enumerated.
+  void incorporateValue(const Value *V);
+
+  /// incorporateMDNode - This method is used to walk the operands of an MDNode
+  /// to find types hiding within.
+  void incorporateMDNode(const MDNode *V);
+};
+
+} // end llvm namespace
+
+#endif

llvm/lib/Linker/LinkModules.cpp

@@ -16,6 +16,7 @@
 #include "llvm/DerivedTypes.h"
 #include "llvm/Instructions.h"
 #include "llvm/Module.h"
+#include "llvm/TypeFinder.h"
 #include "llvm/ADT/DenseSet.h"
 #include "llvm/ADT/Optional.h"
 #include "llvm/ADT/SetVector.h"
@@ -595,13 +596,13 @@ void ModuleLinker::computeTypeMapping() {
   // At this point, the destination module may have a type "%foo = { i32 }" for
   // example.  When the source module got loaded into the same LLVMContext, if
   // it had the same type, it would have been renamed to "%foo.42 = { i32 }".
-  std::vector<StructType*> SrcStructTypes;
-  SrcM->findUsedStructTypes(SrcStructTypes, true);
+  TypeFinder SrcStructTypes;
+  SrcStructTypes.run(*SrcM, true);
   SmallPtrSet<StructType*, 32> SrcStructTypesSet(SrcStructTypes.begin(),
                                                  SrcStructTypes.end());
 
-  std::vector<StructType*> DstStructTypes;
-  DstM->findUsedStructTypes(DstStructTypes, true);
+  TypeFinder DstStructTypes;
+  DstStructTypes.run(*DstM, true);
   SmallPtrSet<StructType*, 32> DstStructTypesSet(DstStructTypes.begin(),
                                                  DstStructTypes.end());
 

llvm/lib/Transforms/IPO/StripSymbols.cpp

@@ -27,6 +27,7 @@
 #include "llvm/Instructions.h"
 #include "llvm/Module.h"
 #include "llvm/Pass.h"
+#include "llvm/TypeFinder.h"
 #include "llvm/ValueSymbolTable.h"
 #include "llvm/Transforms/Utils/Local.h"
 #include "llvm/ADT/DenseMap.h"
@@ -175,8 +176,8 @@ static void StripSymtab(ValueSymbolTable &ST, bool PreserveDbgInfo) {
 
 // Strip any named types of their names.
 static void StripTypeNames(Module &M, bool PreserveDbgInfo) {
-  std::vector<StructType*> StructTypes;
-  M.findUsedStructTypes(StructTypes);
+  TypeFinder StructTypes;
+  StructTypes.run(M, false);
 
   for (unsigned i = 0, e = StructTypes.size(); i != e; ++i) {
     StructType *STy = StructTypes[i];

llvm/lib/VMCore/AsmWriter.cpp

@@ -26,6 +26,7 @@
 #include "llvm/IntrinsicInst.h"
 #include "llvm/Operator.h"
 #include "llvm/Module.h"
+#include "llvm/TypeFinder.h"
 #include "llvm/ValueSymbolTable.h"
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/SmallString.h"
@@ -145,7 +146,7 @@ class TypePrinting {
 public:
 
   /// NamedTypes - The named types that are used by the current module.
-  std::vector<StructType*> NamedTypes;
+  TypeFinder NamedTypes;
 
   /// NumberedTypes - The numbered types, along with their value.
   DenseMap<StructType*, unsigned> NumberedTypes;
@@ -164,7 +165,7 @@ class TypePrinting {
 
 
 void TypePrinting::incorporateTypes(const Module &M) {
-  M.findUsedStructTypes(NamedTypes);
+  NamedTypes.run(M, false);
 
   // The list of struct types we got back includes all the struct types, split
   // the unnamed ones out to a numbering and remove the anonymous structs.

llvm/lib/VMCore/CMakeLists.txt

@@ -31,6 +31,7 @@ add_llvm_library(LLVMCore
   PassRegistry.cpp
   PrintModulePass.cpp
   Type.cpp
+  TypeFinder.cpp
   Use.cpp
   User.cpp
   Value.cpp

llvm/lib/VMCore/Module.cpp

@@ -467,143 +467,3 @@ void Module::removeLibrary(StringRef Lib) {
       return;
     }
 }
-
-//===----------------------------------------------------------------------===//
-// Type finding functionality.
-//===----------------------------------------------------------------------===//
-
-namespace {
-  /// TypeFinder - Walk over a module, identifying all of the types that are
-  /// used by the module.
-  class TypeFinder {
-    // To avoid walking constant expressions multiple times and other IR
-    // objects, we keep several helper maps.
-    DenseSet<const Value*> VisitedConstants;
-    DenseSet<Type*> VisitedTypes;
-
-    std::vector<StructType*> &StructTypes;
-    bool OnlyNamed;
-  public:
-    TypeFinder(std::vector<StructType*> &structTypes, bool onlyNamed)
-      : StructTypes(structTypes), OnlyNamed(onlyNamed) {}
-
-    void run(const Module &M) {
-      // Get types from global variables.
-      for (Module::const_global_iterator I = M.global_begin(),
-           E = M.global_end(); I != E; ++I) {
-        incorporateType(I->getType());
-        if (I->hasInitializer())
-          incorporateValue(I->getInitializer());
-      }
-
-      // Get types from aliases.
-      for (Module::const_alias_iterator I = M.alias_begin(),
-           E = M.alias_end(); I != E; ++I) {
-        incorporateType(I->getType());
-        if (const Value *Aliasee = I->getAliasee())
-          incorporateValue(Aliasee);
-      }
-
-      // Get types from functions.
-      SmallVector<std::pair<unsigned, MDNode*>, 4> MDForInst;
-      for (Module::const_iterator FI = M.begin(), E = M.end(); FI != E; ++FI) {
-        incorporateType(FI->getType());
-
-        // First incorporate the arguments.
-        for (Function::const_arg_iterator AI = FI->arg_begin(),
-               AE = FI->arg_end(); AI != AE; ++AI)
-          incorporateValue(AI);
-
-        for (Function::const_iterator BB = FI->begin(), E = FI->end();
-             BB != E;++BB)
-          for (BasicBlock::const_iterator II = BB->begin(),
-               E = BB->end(); II != E; ++II) {
-            const Instruction &I = *II;
-            // Incorporate the type of the instruction.
-            incorporateType(I.getType());
-
-            // Incorporate non-instruction operand types. (We are incorporating
-            // all instructions with this loop.)
-            for (User::const_op_iterator OI = I.op_begin(), OE = I.op_end();
-                 OI != OE; ++OI)
-              if (!isa<Instruction>(OI))
-                incorporateValue(*OI);
-
-            // Incorporate types hiding in metadata.
-            I.getAllMetadataOtherThanDebugLoc(MDForInst);
-            for (unsigned i = 0, e = MDForInst.size(); i != e; ++i)
-              incorporateMDNode(MDForInst[i].second);
-            MDForInst.clear();
-          }
-      }
-
-      for (Module::const_named_metadata_iterator I = M.named_metadata_begin(),
-           E = M.named_metadata_end(); I != E; ++I) {
-        const NamedMDNode *NMD = I;
-        for (unsigned i = 0, e = NMD->getNumOperands(); i != e; ++i)
-          incorporateMDNode(NMD->getOperand(i));
-      }
-    }
-
-  private:
-    void incorporateType(Type *Ty) {
-      // Check to see if we're already visited this type.
-      if (!VisitedTypes.insert(Ty).second)
-        return;
-
-      // If this is a structure or opaque type, add a name for the type.
-      if (StructType *STy = dyn_cast<StructType>(Ty))
-        if (!OnlyNamed || STy->hasName())
-          StructTypes.push_back(STy);
-
-      // Recursively walk all contained types.
-      for (Type::subtype_iterator I = Ty->subtype_begin(),
-           E = Ty->subtype_end(); I != E; ++I)
-        incorporateType(*I);
-    }
-
-    /// incorporateValue - This method is used to walk operand lists finding
-    /// types hiding in constant expressions and other operands that won't be
-    /// walked in other ways.  GlobalValues, basic blocks, instructions, and
-    /// inst operands are all explicitly enumerated.
-    void incorporateValue(const Value *V) {
-      if (const MDNode *M = dyn_cast<MDNode>(V))
-        return incorporateMDNode(M);
-      if (!isa<Constant>(V) || isa<GlobalValue>(V)) return;
-
-      // Already visited?
-      if (!VisitedConstants.insert(V).second)
-        return;
-
-      // Check this type.
-      incorporateType(V->getType());
-
-      // If this is an instruction, we incorporate it separately.
-      if (isa<Instruction>(V))
-        return;
-
-      // Look in operands for types.
-      const User *U = cast<User>(V);
-      for (Constant::const_op_iterator I = U->op_begin(),
-           E = U->op_end(); I != E;++I)
-        incorporateValue(*I);
-    }
-
-    void incorporateMDNode(const MDNode *V) {
-
-      // Already visited?
-      if (!VisitedConstants.insert(V).second)
-        return;
-
-      // Look in operands for types.
-      for (unsigned i = 0, e = V->getNumOperands(); i != e; ++i)
-        if (Value *Op = V->getOperand(i))
-          incorporateValue(Op);
-    }
-  };
-} // end anonymous namespace
-
-void Module::findUsedStructTypes(std::vector<StructType*> &StructTypes,
-                                 bool OnlyNamed) const {
-  TypeFinder(StructTypes, OnlyNamed).run(*this);
-}