[CodeGen] Port GlobalMerge to new pass manager (llvm#77474)

llvm/include/llvm/CodeGen/CodeGenPassBuilder.h

@@ -30,6 +30,7 @@
 #include "llvm/CodeGen/ExpandMemCmp.h"
 #include "llvm/CodeGen/ExpandReductions.h"
 #include "llvm/CodeGen/GCMetadata.h"
+#include "llvm/CodeGen/GlobalMerge.h"
 #include "llvm/CodeGen/IndirectBrExpand.h"
 #include "llvm/CodeGen/InterleavedAccess.h"
 #include "llvm/CodeGen/InterleavedLoadCombine.h"
@@ -280,6 +281,9 @@ template <typename DerivedT> class CodeGenPassBuilder {
                                    inconvertibleErrorCode());
   }
 
+  /// Target can override this to add GlobalMergePass before all IR passes.
+  void addGlobalMergePass(AddIRPass &) const {}
+
   /// Add passes that optimize instruction level parallelism for out-of-order
   /// targets. These passes are run while the machine code is still in SSA
   /// form, so they can use MachineTraceMetrics to control their heuristics.
@@ -593,6 +597,7 @@ CodeGenPassBuilder<Derived>::getPassNameFromLegacyName(StringRef Name) const {
 
 template <typename Derived>
 void CodeGenPassBuilder<Derived>::addISelPasses(AddIRPass &addPass) const {
+  derived().addGlobalMergePass(addPass);
   if (TM.useEmulatedTLS())
     addPass(LowerEmuTLSPass());
 

llvm/include/llvm/CodeGen/GlobalMerge.h

@@ -0,0 +1,50 @@
+//===- llvm/CodeGen/GlobalMerge.h -------------------------------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_CODEGEN_GLOBALMERGE_H
+#define LLVM_CODEGEN_GLOBALMERGE_H
+
+#include "llvm/IR/PassManager.h"
+
+namespace llvm {
+
+class TargetMachine;
+
+struct GlobalMergeOptions {
+  // FIXME: Infer the maximum possible offset depending on the actual users
+  // (these max offsets are different for the users inside Thumb or ARM
+  // functions), see the code that passes in the offset in the ARM backend
+  // for more information.
+  unsigned MaxOffset = 0;
+  bool GroupByUse = true;
+  bool IgnoreSingleUse = true;
+  bool MergeConst = false;
+  /// Whether we should merge global variables that have external linkage.
+  bool MergeExternal = true;
+  /// Whether we should try to optimize for size only.
+  /// Currently, this applies a dead simple heuristic: only consider globals
+  /// used in minsize functions for merging.
+  /// FIXME: This could learn about optsize, and be used in the cost model.
+  bool SizeOnly = false;
+};
+
+// FIXME: This pass must run before AsmPrinterPass::doInitialization!
+class GlobalMergePass : public PassInfoMixin<GlobalMergePass> {
+  const TargetMachine *TM;
+  GlobalMergeOptions Options;
+
+public:
+  GlobalMergePass(const TargetMachine *TM, GlobalMergeOptions Options)
+      : TM(TM), Options(Options) {}
+
+  PreservedAnalyses run(Module &M, ModuleAnalysisManager &MAM);
+};
+
+} // namespace llvm
+
+#endif // LLVM_CODEGEN_GLOBALMERGE_H

llvm/include/llvm/CodeGen/MachinePassRegistry.def

@@ -23,9 +23,10 @@ MODULE_ANALYSIS("pass-instrumentation", PassInstrumentationAnalysis, (PIC))
 #ifndef MODULE_PASS
 #define MODULE_PASS(NAME, PASS_NAME, CONSTRUCTOR)
 #endif
-MODULE_PASS("pre-isel-intrinsic-lowering", PreISelIntrinsicLoweringPass, ())
+MODULE_PASS("global-merge", GlobalMergePass, (TM, GlobalMergeOptions()))
 MODULE_PASS("jmc-instrumenter", JMCInstrumenterPass, ())
 MODULE_PASS("lower-emutls", LowerEmuTLSPass, ())
+MODULE_PASS("pre-isel-intrinsic-lowering", PreISelIntrinsicLoweringPass, ())
 MODULE_PASS("shadow-stack-gc-lowering", ShadowStackGCLoweringPass, ())
 #undef MODULE_PASS
 

llvm/lib/CodeGen/GlobalMerge.cpp

@@ -60,6 +60,7 @@
 //
 // ===---------------------------------------------------------------------===//
 
+#include "llvm/CodeGen/GlobalMerge.h"
 #include "llvm/ADT/BitVector.h"
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/SetVector.h"
@@ -137,88 +138,99 @@ STATISTIC(NumMerged, "Number of globals merged");
 
 namespace {
 
-  class GlobalMerge : public FunctionPass {
-    const TargetMachine *TM = nullptr;
-
-    // FIXME: Infer the maximum possible offset depending on the actual users
-    // (these max offsets are different for the users inside Thumb or ARM
-    // functions), see the code that passes in the offset in the ARM backend
-    // for more information.
-    unsigned MaxOffset;
-
-    /// Whether we should try to optimize for size only.
-    /// Currently, this applies a dead simple heuristic: only consider globals
-    /// used in minsize functions for merging.
-    /// FIXME: This could learn about optsize, and be used in the cost model.
-    bool OnlyOptimizeForSize = false;
-
-    /// Whether we should merge global variables that have external linkage.
-    bool MergeExternalGlobals = false;
+class GlobalMergeImpl {
+  const TargetMachine *TM = nullptr;
+  GlobalMergeOptions Opt;
+  bool IsMachO = false;
+
+private:
+  bool doMerge(SmallVectorImpl<GlobalVariable *> &Globals, Module &M,
+               bool isConst, unsigned AddrSpace) const;
+
+  /// Merge everything in \p Globals for which the corresponding bit
+  /// in \p GlobalSet is set.
+  bool doMerge(const SmallVectorImpl<GlobalVariable *> &Globals,
+               const BitVector &GlobalSet, Module &M, bool isConst,
+               unsigned AddrSpace) const;
+
+  /// Check if the given variable has been identified as must keep
+  /// \pre setMustKeepGlobalVariables must have been called on the Module that
+  ///      contains GV
+  bool isMustKeepGlobalVariable(const GlobalVariable *GV) const {
+    return MustKeepGlobalVariables.count(GV);
+  }
 
-    bool IsMachO = false;
+  /// Collect every variables marked as "used" or used in a landing pad
+  /// instruction for this Module.
+  void setMustKeepGlobalVariables(Module &M);
 
-    bool doMerge(SmallVectorImpl<GlobalVariable*> &Globals,
-                 Module &M, bool isConst, unsigned AddrSpace) const;
+  /// Collect every variables marked as "used"
+  void collectUsedGlobalVariables(Module &M, StringRef Name);
 
-    /// Merge everything in \p Globals for which the corresponding bit
-    /// in \p GlobalSet is set.
-    bool doMerge(const SmallVectorImpl<GlobalVariable *> &Globals,
-                 const BitVector &GlobalSet, Module &M, bool isConst,
-                 unsigned AddrSpace) const;
+  /// Keep track of the GlobalVariable that must not be merged away
+  SmallSetVector<const GlobalVariable *, 16> MustKeepGlobalVariables;
 
-    /// Check if the given variable has been identified as must keep
-    /// \pre setMustKeepGlobalVariables must have been called on the Module that
-    ///      contains GV
-    bool isMustKeepGlobalVariable(const GlobalVariable *GV) const {
-      return MustKeepGlobalVariables.count(GV);
-    }
+public:
+  GlobalMergeImpl(const TargetMachine *TM, GlobalMergeOptions Opt)
+      : TM(TM), Opt(Opt) {}
+  bool run(Module &M);
+};
 
-    /// Collect every variables marked as "used" or used in a landing pad
-    /// instruction for this Module.
-    void setMustKeepGlobalVariables(Module &M);
+class GlobalMerge : public FunctionPass {
+  const TargetMachine *TM = nullptr;
+  GlobalMergeOptions Opt;
 
-    /// Collect every variables marked as "used"
-    void collectUsedGlobalVariables(Module &M, StringRef Name);
+public:
+  static char ID; // Pass identification, replacement for typeid.
 
-    /// Keep track of the GlobalVariable that must not be merged away
-    SmallSetVector<const GlobalVariable *, 16> MustKeepGlobalVariables;
+  explicit GlobalMerge() : FunctionPass(ID) {
+    Opt.MaxOffset = GlobalMergeMaxOffset;
+    initializeGlobalMergePass(*PassRegistry::getPassRegistry());
+  }
 
-  public:
-    static char ID;             // Pass identification, replacement for typeid.
+  explicit GlobalMerge(const TargetMachine *TM, unsigned MaximalOffset,
+                       bool OnlyOptimizeForSize, bool MergeExternalGlobals)
+      : FunctionPass(ID), TM(TM) {
+    Opt.MaxOffset = MaximalOffset;
+    Opt.SizeOnly = OnlyOptimizeForSize;
+    Opt.MergeExternal = MergeExternalGlobals;
+    initializeGlobalMergePass(*PassRegistry::getPassRegistry());
+  }
 
-    explicit GlobalMerge()
-        : FunctionPass(ID), MaxOffset(GlobalMergeMaxOffset) {
-      initializeGlobalMergePass(*PassRegistry::getPassRegistry());
-    }
+  bool doInitialization(Module &M) override {
+    GlobalMergeImpl P(TM, Opt);
+    return P.run(M);
+  }
+  bool runOnFunction(Function &F) override { return false; }
 
-    explicit GlobalMerge(const TargetMachine *TM, unsigned MaximalOffset,
-                         bool OnlyOptimizeForSize, bool MergeExternalGlobals)
-        : FunctionPass(ID), TM(TM), MaxOffset(MaximalOffset),
-          OnlyOptimizeForSize(OnlyOptimizeForSize),
-          MergeExternalGlobals(MergeExternalGlobals) {
-      initializeGlobalMergePass(*PassRegistry::getPassRegistry());
-    }
+  StringRef getPassName() const override { return "Merge internal globals"; }
 
-    bool doInitialization(Module &M) override;
-    bool runOnFunction(Function &F) override;
-    bool doFinalization(Module &M) override;
+  void getAnalysisUsage(AnalysisUsage &AU) const override {
+    AU.setPreservesCFG();
+    FunctionPass::getAnalysisUsage(AU);
+  }
+};
 
-    StringRef getPassName() const override { return "Merge internal globals"; }
+} // end anonymous namespace
 
-    void getAnalysisUsage(AnalysisUsage &AU) const override {
-      AU.setPreservesCFG();
-      FunctionPass::getAnalysisUsage(AU);
-    }
-  };
+PreservedAnalyses GlobalMergePass::run(Module &M, ModuleAnalysisManager &) {
+  GlobalMergeImpl P(TM, Options);
+  bool Changed = P.run(M);
+  if (!Changed)
+    return PreservedAnalyses::all();
 
-} // end anonymous namespace
+  PreservedAnalyses PA;
+  PA.preserveSet<CFGAnalyses>();
+  return PA;
+}
 
 char GlobalMerge::ID = 0;
 
 INITIALIZE_PASS(GlobalMerge, DEBUG_TYPE, "Merge global variables", false, false)
 
-bool GlobalMerge::doMerge(SmallVectorImpl<GlobalVariable*> &Globals,
-                          Module &M, bool isConst, unsigned AddrSpace) const {
+bool GlobalMergeImpl::doMerge(SmallVectorImpl<GlobalVariable *> &Globals,
+                              Module &M, bool isConst,
+                              unsigned AddrSpace) const {
   auto &DL = M.getDataLayout();
   // FIXME: Find better heuristics
   llvm::stable_sort(
@@ -333,7 +345,7 @@ bool GlobalMerge::doMerge(SmallVectorImpl<GlobalVariable*> &Globals,
         Function *ParentFn = I->getParent()->getParent();
 
         // If we're only optimizing for size, ignore non-minsize functions.
-        if (OnlyOptimizeForSize && !ParentFn->hasMinSize())
+        if (Opt.SizeOnly && !ParentFn->hasMinSize())
           continue;
 
         size_t UGSIdx = GlobalUsesByFunction[ParentFn];
@@ -434,9 +446,9 @@ bool GlobalMerge::doMerge(SmallVectorImpl<GlobalVariable*> &Globals,
   return Changed;
 }
 
-bool GlobalMerge::doMerge(const SmallVectorImpl<GlobalVariable *> &Globals,
-                          const BitVector &GlobalSet, Module &M, bool isConst,
-                          unsigned AddrSpace) const {
+bool GlobalMergeImpl::doMerge(const SmallVectorImpl<GlobalVariable *> &Globals,
+                              const BitVector &GlobalSet, Module &M,
+                              bool isConst, unsigned AddrSpace) const {
   assert(Globals.size() > 1);
 
   Type *Int32Ty = Type::getInt32Ty(M.getContext());
@@ -467,7 +479,7 @@ bool GlobalMerge::doMerge(const SmallVectorImpl<GlobalVariable *> &Globals,
       unsigned Padding = alignTo(MergedSize, Alignment) - MergedSize;
       MergedSize += Padding;
       MergedSize += DL.getTypeAllocSize(Ty);
-      if (MergedSize > MaxOffset) {
+      if (MergedSize > Opt.MaxOffset) {
         break;
       }
       if (Padding) {
@@ -563,7 +575,7 @@ bool GlobalMerge::doMerge(const SmallVectorImpl<GlobalVariable *> &Globals,
   return Changed;
 }
 
-void GlobalMerge::collectUsedGlobalVariables(Module &M, StringRef Name) {
+void GlobalMergeImpl::collectUsedGlobalVariables(Module &M, StringRef Name) {
   // Extract global variables from llvm.used array
   const GlobalVariable *GV = M.getGlobalVariable(Name);
   if (!GV || !GV->hasInitializer()) return;
@@ -577,7 +589,7 @@ void GlobalMerge::collectUsedGlobalVariables(Module &M, StringRef Name) {
       MustKeepGlobalVariables.insert(G);
 }
 
-void GlobalMerge::setMustKeepGlobalVariables(Module &M) {
+void GlobalMergeImpl::setMustKeepGlobalVariables(Module &M) {
   collectUsedGlobalVariables(M, "llvm.used");
   collectUsedGlobalVariables(M, "llvm.compiler.used");
 
@@ -604,7 +616,7 @@ void GlobalMerge::setMustKeepGlobalVariables(Module &M) {
   }
 }
 
-bool GlobalMerge::doInitialization(Module &M) {
+bool GlobalMergeImpl::run(Module &M) {
   if (!EnableGlobalMerge)
     return false;
 
@@ -632,7 +644,7 @@ bool GlobalMerge::doInitialization(Module &M) {
     if (TM && !TM->shouldAssumeDSOLocal(M, &GV))
       continue;
 
-    if (!(MergeExternalGlobals && GV.hasExternalLinkage()) &&
+    if (!(Opt.MergeExternal && GV.hasExternalLinkage()) &&
         !GV.hasInternalLinkage())
       continue;
 
@@ -659,7 +671,7 @@ bool GlobalMerge::doInitialization(Module &M) {
       continue;
 
     Type *Ty = GV.getValueType();
-    if (DL.getTypeAllocSize(Ty) < MaxOffset) {
+    if (DL.getTypeAllocSize(Ty) < Opt.MaxOffset) {
       if (TM &&
           TargetLoweringObjectFile::getKindForGlobal(&GV, *TM).isBSS())
         BSSGlobals[{AddressSpace, Section}].push_back(&GV);
@@ -686,15 +698,6 @@ bool GlobalMerge::doInitialization(Module &M) {
   return Changed;
 }
 
-bool GlobalMerge::runOnFunction(Function &F) {
-  return false;
-}
-
-bool GlobalMerge::doFinalization(Module &M) {
-  MustKeepGlobalVariables.clear();
-  return false;
-}
-
 Pass *llvm::createGlobalMergePass(const TargetMachine *TM, unsigned Offset,
                                   bool OnlyOptimizeForSize,
                                   bool MergeExternalByDefault) {

llvm/lib/Passes/PassBuilder.cpp

@@ -81,6 +81,7 @@
 #include "llvm/CodeGen/ExpandLargeFpConvert.h"
 #include "llvm/CodeGen/ExpandMemCmp.h"
 #include "llvm/CodeGen/GCMetadata.h"
+#include "llvm/CodeGen/GlobalMerge.h"
 #include "llvm/CodeGen/HardwareLoops.h"
 #include "llvm/CodeGen/IndirectBrExpand.h"
 #include "llvm/CodeGen/InterleavedAccess.h"
@@ -1082,6 +1083,32 @@ Expected<bool> parseWinEHPrepareOptions(StringRef Params) {
                                "WinEHPreparePass");
 }
 
+Expected<GlobalMergeOptions> parseGlobalMergeOptions(StringRef Params) {
+  GlobalMergeOptions Result;
+  while (!Params.empty()) {
+    StringRef ParamName;
+    std::tie(ParamName, Params) = Params.split(';');
+
+    bool Enable = !ParamName.consume_front("no-");
+    if (ParamName == "group-by-use")
+      Result.GroupByUse = Enable;
+    else if (ParamName == "ignore-single-use")
+      Result.IgnoreSingleUse = Enable;
+    else if (ParamName == "merge-const")
+      Result.MergeConst = Enable;
+    else if (ParamName == "merge-external")
+      Result.MergeExternal = Enable;
+    else if (ParamName.consume_front("max-offset=")) {
+      if (ParamName.getAsInteger(0, Result.MaxOffset))
+        return make_error<StringError>(
+            formatv("invalid GlobalMergePass parameter '{0}' ", ParamName)
+                .str(),
+            inconvertibleErrorCode());
+    }
+  }
+  return Result;
+}
+
 } // namespace
 
 /// Tests whether a pass name starts with a valid prefix for a default pipeline