[ThinLTO] Internalize readonly globals

This patch allows internalising globals if all accesses to them
(from live functions) are from non-volatile load instructions

Differential revision: https://reviews.llvm.org/D49362

llvm-svn: 346584

llvm/include/llvm/IR/ModuleSummaryIndex.h

@@ -163,13 +163,13 @@ using GlobalValueSummaryMapTy =
 /// Struct that holds a reference to a particular GUID in a global value
 /// summary.
 struct ValueInfo {
-  PointerIntPair<const GlobalValueSummaryMapTy::value_type *, 1, bool>
-      RefAndFlag;
+  PointerIntPair<const GlobalValueSummaryMapTy::value_type *, 2, int>
+      RefAndFlags;
 
   ValueInfo() = default;
   ValueInfo(bool HaveGVs, const GlobalValueSummaryMapTy::value_type *R) {
-    RefAndFlag.setPointer(R);
-    RefAndFlag.setInt(HaveGVs);
+    RefAndFlags.setPointer(R);
+    RefAndFlags.setInt(HaveGVs);
   }
 
   operator bool() const { return getRef(); }
@@ -189,10 +189,12 @@ struct ValueInfo {
                      : getRef()->second.U.Name;
   }
 
-  bool haveGVs() const { return RefAndFlag.getInt(); }
+  bool haveGVs() const { return RefAndFlags.getInt() & 0x1; }
+  bool isReadOnly() const { return RefAndFlags.getInt() & 0x2; }
+  void setReadOnly() { RefAndFlags.setInt(RefAndFlags.getInt() | 0x2); }
 
   const GlobalValueSummaryMapTy::value_type *getRef() const {
-    return RefAndFlag.getPointer();
+    return RefAndFlags.getPointer();
   }
 
   bool isDSOLocal() const;
@@ -543,6 +545,8 @@ class FunctionSummary : public GlobalValueSummary {
           std::move(TypeTestAssumeConstVCalls),
           std::move(TypeCheckedLoadConstVCalls)});
   }
+  // Gets the number of immutable refs in RefEdgeList
+  unsigned immutableRefCount() const;
 
   /// Check if this is a function summary.
   static bool classof(const GlobalValueSummary *GVS) {
@@ -652,19 +656,30 @@ template <> struct DenseMapInfo<FunctionSummary::ConstVCall> {
 /// Global variable summary information to aid decisions and
 /// implementation of importing.
 ///
-/// Currently this doesn't add anything to the base \p GlobalValueSummary,
-/// but is a placeholder as additional info may be added to the summary
-/// for variables.
+/// Global variable summary has extra flag, telling if it is
+/// modified during the program run or not. This affects ThinLTO
+/// internalization
 class GlobalVarSummary : public GlobalValueSummary {
-
 public:
-  GlobalVarSummary(GVFlags Flags, std::vector<ValueInfo> Refs)
-      : GlobalValueSummary(GlobalVarKind, Flags, std::move(Refs)) {}
+  struct GVarFlags {
+    GVarFlags(bool ReadOnly = false) : ReadOnly(ReadOnly) {}
+
+    unsigned ReadOnly : 1;
+  } VarFlags;
+
+  GlobalVarSummary(GVFlags Flags, GVarFlags VarFlags,
+                   std::vector<ValueInfo> Refs)
+      : GlobalValueSummary(GlobalVarKind, Flags, std::move(Refs)),
+        VarFlags(VarFlags) {}
 
   /// Check if this is a global variable summary.
   static bool classof(const GlobalValueSummary *GVS) {
     return GVS->getSummaryKind() == GlobalVarKind;
   }
+
+  GVarFlags varflags() const { return VarFlags; }
+  void setReadOnly(bool RO) { VarFlags.ReadOnly = RO; }
+  bool isReadOnly() const { return VarFlags.ReadOnly; }
 };
 
 struct TypeTestResolution {
@@ -1135,6 +1150,9 @@ class ModuleSummaryIndex {
 
   /// Print out strongly connected components for debugging.
   void dumpSCCs(raw_ostream &OS);
+
+  /// Analyze index and detect unmodified globals
+  void propagateConstants(const DenseSet<GlobalValue::GUID> &PreservedSymbols);
 };
 
 /// GraphTraits definition to build SCC for the index
@@ -1184,6 +1202,14 @@ struct GraphTraits<ModuleSummaryIndex *> : public GraphTraits<ValueInfo> {
   }
 };
 
+static inline bool canImportGlobalVar(GlobalValueSummary *S) {
+  assert(isa<GlobalVarSummary>(S->getBaseObject()));
+
+  // We don't import GV with references, because it can result
+  // in promotion of local variables in the source module.
+  return !GlobalValue::isInterposableLinkage(S->linkage()) &&
+         !S->notEligibleToImport() && S->refs().empty();
+}
 } // end namespace llvm
 
 #endif // LLVM_IR_MODULESUMMARYINDEX_H

llvm/include/llvm/Transforms/IPO/FunctionImport.h

@@ -176,6 +176,14 @@ void computeDeadSymbols(
     const DenseSet<GlobalValue::GUID> &GUIDPreservedSymbols,
     function_ref<PrevailingType(GlobalValue::GUID)> isPrevailing);
 
+/// Compute dead symbols and run constant propagation in combined index
+/// after that.
+void computeDeadSymbolsWithConstProp(
+    ModuleSummaryIndex &Index,
+    const DenseSet<GlobalValue::GUID> &GUIDPreservedSymbols,
+    function_ref<PrevailingType(GlobalValue::GUID)> isPrevailing,
+    bool ImportEnabled);
+
 /// Converts value \p GV to declaration, or replaces with a declaration if
 /// it is an alias. Returns true if converted, false if replaced.
 bool convertToDeclaration(GlobalValue &GV);

llvm/include/llvm/Transforms/Utils/FunctionImportUtils.h

@@ -113,7 +113,6 @@ class FunctionImportGlobalProcessing {
 bool renameModuleForThinLTO(
     Module &M, const ModuleSummaryIndex &Index,
     SetVector<GlobalValue *> *GlobalsToImport = nullptr);
-
 } // End llvm namespace
 
 #endif

llvm/lib/Analysis/ModuleSummaryAnalysis.cpp

@@ -220,10 +220,19 @@ static void addIntrinsicToSummary(
   }
 }
 
-static void computeFunctionSummary(
-    ModuleSummaryIndex &Index, const Module &M, const Function &F,
-    BlockFrequencyInfo *BFI, ProfileSummaryInfo *PSI, DominatorTree &DT,
-    bool HasLocalsInUsedOrAsm, DenseSet<GlobalValue::GUID> &CantBePromoted) {
+static bool isNonVolatileLoad(const Instruction *I) {
+  if (const auto *LI = dyn_cast<LoadInst>(I))
+    return !LI->isVolatile();
+
+  return false;
+}
+
+static void computeFunctionSummary(ModuleSummaryIndex &Index, const Module &M,
+                                   const Function &F, BlockFrequencyInfo *BFI,
+                                   ProfileSummaryInfo *PSI, DominatorTree &DT,
+                                   bool HasLocalsInUsedOrAsm,
+                                   DenseSet<GlobalValue::GUID> &CantBePromoted,
+                                   bool IsThinLTO) {
   // Summary not currently supported for anonymous functions, they should
   // have been named.
   assert(F.hasName());
@@ -244,13 +253,21 @@ static void computeFunctionSummary(
   // Add personality function, prefix data and prologue data to function's ref
   // list.
   findRefEdges(Index, &F, RefEdges, Visited);
+  std::vector<const Instruction *> NonVolatileLoads;
 
   bool HasInlineAsmMaybeReferencingInternal = false;
   for (const BasicBlock &BB : F)
     for (const Instruction &I : BB) {
       if (isa<DbgInfoIntrinsic>(I))
         continue;
       ++NumInsts;
+      if (isNonVolatileLoad(&I)) {
+        // Postpone processing of non-volatile load instructions
+        // See comments below
+        Visited.insert(&I);
+        NonVolatileLoads.push_back(&I);
+        continue;
+      }
       findRefEdges(Index, &I, RefEdges, Visited);
       auto CS = ImmutableCallSite(&I);
       if (!CS)
@@ -340,6 +357,24 @@ static void computeFunctionSummary(
       }
     }
 
+  // By now we processed all instructions in a function, except
+  // non-volatile loads. All new refs we add in a loop below
+  // are obviously constant. All constant refs are grouped in the
+  // end of RefEdges vector, so we can use a single integer value
+  // to identify them.
+  unsigned RefCnt = RefEdges.size();
+  for (const Instruction *I : NonVolatileLoads) {
+    Visited.erase(I);
+    findRefEdges(Index, I, RefEdges, Visited);
+  }
+  std::vector<ValueInfo> Refs = RefEdges.takeVector();
+  // Regular LTO module doesn't participate in ThinLTO import,
+  // so no reference from it can be readonly, since this would
+  // require importing variable as local copy
+  if (IsThinLTO)
+    for (; RefCnt < Refs.size(); ++RefCnt)
+      Refs[RefCnt].setReadOnly();
+
   // Explicit add hot edges to enforce importing for designated GUIDs for
   // sample PGO, to enable the same inlines as the profiled optimized binary.
   for (auto &I : F.getImportGUIDs())
@@ -363,9 +398,9 @@ static void computeFunctionSummary(
           // Don't try to import functions with noinline attribute.
           F.getAttributes().hasFnAttribute(Attribute::NoInline)};
   auto FuncSummary = llvm::make_unique<FunctionSummary>(
-      Flags, NumInsts, FunFlags, RefEdges.takeVector(),
-      CallGraphEdges.takeVector(), TypeTests.takeVector(),
-      TypeTestAssumeVCalls.takeVector(), TypeCheckedLoadVCalls.takeVector(),
+      Flags, NumInsts, FunFlags, std::move(Refs), CallGraphEdges.takeVector(),
+      TypeTests.takeVector(), TypeTestAssumeVCalls.takeVector(),
+      TypeCheckedLoadVCalls.takeVector(),
       TypeTestAssumeConstVCalls.takeVector(),
       TypeCheckedLoadConstVCalls.takeVector());
   if (NonRenamableLocal)
@@ -382,8 +417,13 @@ computeVariableSummary(ModuleSummaryIndex &Index, const GlobalVariable &V,
   bool NonRenamableLocal = isNonRenamableLocal(V);
   GlobalValueSummary::GVFlags Flags(V.getLinkage(), NonRenamableLocal,
                                     /* Live = */ false, V.isDSOLocal());
-  auto GVarSummary =
-      llvm::make_unique<GlobalVarSummary>(Flags, RefEdges.takeVector());
+
+  // Don't mark variables we won't be able to internalize as read-only.
+  GlobalVarSummary::GVarFlags VarFlags(
+      !V.hasComdat() && !V.hasAppendingLinkage() && !V.isInterposable() &&
+      !V.hasAvailableExternallyLinkage() && !V.hasDLLExportStorageClass());
+  auto GVarSummary = llvm::make_unique<GlobalVarSummary>(Flags, VarFlags,
+                                                         RefEdges.takeVector());
   if (NonRenamableLocal)
     CantBePromoted.insert(V.getGUID());
   if (HasBlockAddress)
@@ -487,13 +527,19 @@ ModuleSummaryIndex llvm::buildModuleSummaryIndex(
             Index.addGlobalValueSummary(*GV, std::move(Summary));
           } else {
             std::unique_ptr<GlobalVarSummary> Summary =
-                llvm::make_unique<GlobalVarSummary>(GVFlags,
-                                                    ArrayRef<ValueInfo>{});
+                llvm::make_unique<GlobalVarSummary>(
+                    GVFlags, GlobalVarSummary::GVarFlags(),
+                    ArrayRef<ValueInfo>{});
             Index.addGlobalValueSummary(*GV, std::move(Summary));
           }
         });
   }
 
+  bool IsThinLTO = true;
+  if (auto *MD =
+          mdconst::extract_or_null<ConstantInt>(M.getModuleFlag("ThinLTO")))
+    IsThinLTO = MD->getZExtValue();
+
   // Compute summaries for all functions defined in module, and save in the
   // index.
   for (auto &F : M) {
@@ -514,7 +560,7 @@ ModuleSummaryIndex llvm::buildModuleSummaryIndex(
 
     computeFunctionSummary(Index, M, F, BFI, PSI, DT,
                            !LocalsUsed.empty() || HasLocalInlineAsmSymbol,
-                           CantBePromoted);
+                           CantBePromoted, IsThinLTO);
   }
 
   // Compute summaries for all variables defined in module, and save in the
@@ -545,11 +591,6 @@ ModuleSummaryIndex llvm::buildModuleSummaryIndex(
   setLiveRoot(Index, "llvm.global_dtors");
   setLiveRoot(Index, "llvm.global.annotations");
 
-  bool IsThinLTO = true;
-  if (auto *MD =
-          mdconst::extract_or_null<ConstantInt>(M.getModuleFlag("ThinLTO")))
-    IsThinLTO = MD->getZExtValue();
-
   for (auto &GlobalList : Index) {
     // Ignore entries for references that are undefined in the current module.
     if (GlobalList.second.SummaryList.empty())

llvm/lib/AsmParser/LLParser.cpp

@@ -7642,7 +7642,8 @@ bool LLParser::ParseVariableSummary(std::string Name, GlobalValue::GUID GUID,
   if (ParseToken(lltok::rparen, "expected ')' here"))
     return true;
 
-  auto GS = llvm::make_unique<GlobalVarSummary>(GVFlags, std::move(Refs));
+  auto GS = llvm::make_unique<GlobalVarSummary>(
+      GVFlags, GlobalVarSummary::GVarFlags(), std::move(Refs));
 
   GS->setModulePath(ModulePath);