Speculative Compilation

[ORC] Remove Speculator Variants for Different Program Representations

[ORC] Block Freq Analysis

Speculative Compilation with Naive Block Frequency

Add Applications to OrcSpeculation

ORC v2 with Block Freq Query & Example

Deleted BenchMark Programs

Signed-off-by: preejackie <praveenvelliengiri@gmail.com>

ORCv2 comments resolved

[ORCV2] NFC

ORCv2 NFC

[ORCv2] Speculative compilation - CFGWalkQuery

ORCv2 Adapting IRSpeculationLayer to new locking scheme

llvm-svn: 367756

examples/CMakeLists.txt

@@ -5,6 +5,7 @@ add_subdirectory(HowToUseLLJIT)
 add_subdirectory(LLJITExamples)
 add_subdirectory(Kaleidoscope)
 add_subdirectory(ModuleMaker)
+add_subdirectory(SpeculativeJIT)
 
 if(LLVM_ENABLE_EH AND (NOT WIN32) AND (NOT "${LLVM_NATIVE_ARCH}" STREQUAL "ARM"))
     add_subdirectory(ExceptionDemo)

examples/SpeculativeJIT/CMakeLists.txt

@@ -0,0 +1,14 @@
+set(LLVM_LINK_COMPONENTS
+  Core
+  IRReader
+  OrcJIT
+  ExecutionEngine
+  Support
+  nativecodegen
+  Analysis
+  Passes
+  )
+
+add_llvm_example(SpeculativeJIT
+  SpeculativeJIT.cpp
+  )

examples/SpeculativeJIT/SpeculativeJIT.cpp

@@ -0,0 +1,197 @@
+#include "llvm/ExecutionEngine/Orc/CompileOnDemandLayer.h"
+#include "llvm/ExecutionEngine/Orc/CompileUtils.h"
+#include "llvm/ExecutionEngine/Orc/Core.h"
+#include "llvm/ExecutionEngine/Orc/ExecutionUtils.h"
+#include "llvm/ExecutionEngine/Orc/IRCompileLayer.h"
+#include "llvm/ExecutionEngine/Orc/IndirectionUtils.h"
+#include "llvm/ExecutionEngine/Orc/JITTargetMachineBuilder.h"
+#include "llvm/ExecutionEngine/Orc/RTDyldObjectLinkingLayer.h"
+#include "llvm/ExecutionEngine/Orc/SpeculateAnalyses.h"
+#include "llvm/ExecutionEngine/Orc/Speculation.h"
+#include "llvm/ExecutionEngine/SectionMemoryManager.h"
+#include "llvm/IRReader/IRReader.h"
+#include "llvm/Support/CommandLine.h"
+#include "llvm/Support/Debug.h"
+#include "llvm/Support/InitLLVM.h"
+#include "llvm/Support/SourceMgr.h"
+#include "llvm/Support/TargetSelect.h"
+#include "llvm/Support/ThreadPool.h"
+
+#include <list>
+#include <string>
+
+using namespace llvm;
+using namespace llvm::orc;
+
+static cl::list<std::string> InputFiles(cl::Positional, cl::OneOrMore,
+                                        cl::desc("input files"));
+
+static cl::list<std::string> InputArgv("args", cl::Positional,
+                                       cl::desc("<program arguments>..."),
+                                       cl::ZeroOrMore, cl::PositionalEatsArgs);
+
+static cl::opt<unsigned> NumThreads("num-threads", cl::Optional,
+                                    cl::desc("Number of compile threads"),
+                                    cl::init(4));
+
+ExitOnError ExitOnErr;
+
+// Add Layers
+class SpeculativeJIT {
+public:
+  static Expected<std::unique_ptr<SpeculativeJIT>> Create() {
+    auto JTMB = orc::JITTargetMachineBuilder::detectHost();
+    if (!JTMB)
+      return JTMB.takeError();
+
+    auto DL = JTMB->getDefaultDataLayoutForTarget();
+    if (!DL)
+      return DL.takeError();
+
+    auto ES = llvm::make_unique<ExecutionSession>();
+
+    auto LCTMgr = createLocalLazyCallThroughManager(
+        JTMB->getTargetTriple(), *ES,
+        pointerToJITTargetAddress(explodeOnLazyCompileFailure));
+    if (!LCTMgr)
+      return LCTMgr.takeError();
+
+    auto ISMBuilder =
+        createLocalIndirectStubsManagerBuilder(JTMB->getTargetTriple());
+    if (!ISMBuilder)
+      return make_error<StringError>("No indirect stubs manager for target",
+                                     inconvertibleErrorCode());
+
+    auto ProcessSymbolsSearchGenerator =
+        DynamicLibrarySearchGenerator::GetForCurrentProcess(
+            DL->getGlobalPrefix());
+    if (!ProcessSymbolsSearchGenerator)
+      return ProcessSymbolsSearchGenerator.takeError();
+
+    std::unique_ptr<SpeculativeJIT> SJ(new SpeculativeJIT(
+        std::move(ES), std::move(*DL), std::move(*JTMB), std::move(*LCTMgr),
+        std::move(ISMBuilder), std::move(*ProcessSymbolsSearchGenerator)));
+    return std::move(SJ);
+  }
+
+  ExecutionSession &getES() { return *ES; }
+
+  Error addModule(JITDylib &JD, ThreadSafeModule TSM) {
+    return CODLayer.add(JD, std::move(TSM));
+  }
+
+  Expected<JITEvaluatedSymbol> lookup(StringRef UnmangledName) {
+    return ES->lookup({&ES->getMainJITDylib()}, Mangle(UnmangledName));
+  }
+
+  ~SpeculativeJIT() { CompileThreads.wait(); }
+
+private:
+  using IndirectStubsManagerBuilderFunction =
+      std::function<std::unique_ptr<IndirectStubsManager>()>;
+
+  static void explodeOnLazyCompileFailure() {
+    errs() << "Lazy compilation failed, Symbol Implmentation not found!\n";
+    exit(1);
+  }
+
+  SpeculativeJIT(std::unique_ptr<ExecutionSession> ES, DataLayout DL,
+                 orc::JITTargetMachineBuilder JTMB,
+                 std::unique_ptr<LazyCallThroughManager> LCTMgr,
+                 IndirectStubsManagerBuilderFunction ISMBuilder,
+                 DynamicLibrarySearchGenerator ProcessSymbolsGenerator)
+      : ES(std::move(ES)), DL(std::move(DL)), LCTMgr(std::move(LCTMgr)),
+        CompileLayer(*this->ES, ObjLayer,
+                     ConcurrentIRCompiler(std::move(JTMB))),
+        S(Imps, *this->ES),
+        SpeculateLayer(*this->ES, CompileLayer, S, BlockFreqQuery()),
+        CODLayer(*this->ES, SpeculateLayer, *this->LCTMgr,
+                 std::move(ISMBuilder)) {
+    this->ES->getMainJITDylib().setGenerator(
+        std::move(ProcessSymbolsGenerator));
+    this->CODLayer.setImplMap(&Imps);
+    this->ES->setDispatchMaterialization(
+
+        [this](JITDylib &JD, std::unique_ptr<MaterializationUnit> MU) {
+          // FIXME: Switch to move capture once we have c  14.
+          auto SharedMU = std::shared_ptr<MaterializationUnit>(std::move(MU));
+          auto Work = [SharedMU, &JD]() { SharedMU->doMaterialize(JD); };
+          CompileThreads.async(std::move(Work));
+        });
+    JITEvaluatedSymbol SpeculatorSymbol(JITTargetAddress(&S),
+                                        JITSymbolFlags::Exported);
+    ExitOnErr(this->ES->getMainJITDylib().define(
+        absoluteSymbols({{Mangle("__orc_speculator"), SpeculatorSymbol}})));
+    LocalCXXRuntimeOverrides CXXRuntimeoverrides;
+    ExitOnErr(CXXRuntimeoverrides.enable(this->ES->getMainJITDylib(), Mangle));
+  }
+
+  static std::unique_ptr<SectionMemoryManager> createMemMgr() {
+    return llvm::make_unique<SectionMemoryManager>();
+  }
+
+  std::unique_ptr<ExecutionSession> ES;
+  DataLayout DL;
+  MangleAndInterner Mangle{*ES, DL};
+  ThreadPool CompileThreads{NumThreads};
+
+  Triple TT;
+  std::unique_ptr<LazyCallThroughManager> LCTMgr;
+  IRCompileLayer CompileLayer;
+  ImplSymbolMap Imps;
+  Speculator S;
+  RTDyldObjectLinkingLayer ObjLayer{*ES, createMemMgr};
+  IRSpeculationLayer SpeculateLayer;
+  CompileOnDemandLayer CODLayer;
+};
+
+int main(int argc, char *argv[]) {
+  // Initialize LLVM.
+  InitLLVM X(argc, argv);
+
+  InitializeNativeTarget();
+  InitializeNativeTargetAsmPrinter();
+
+  cl::ParseCommandLineOptions(argc, argv, "SpeculativeJIT");
+  ExitOnErr.setBanner(std::string(argv[0]) + ": ");
+
+  if (NumThreads < 1) {
+    errs() << "Speculative compilation requires one or more dedicated compile "
+              "threads\n";
+    return 1;
+  }
+
+  // Create a JIT instance.
+  auto SJ = ExitOnErr(SpeculativeJIT::Create());
+
+  // Load the IR inputs.
+  for (const auto &InputFile : InputFiles) {
+    SMDiagnostic Err;
+    auto Ctx = llvm::make_unique<LLVMContext>();
+    auto M = parseIRFile(InputFile, Err, *Ctx);
+    if (!M) {
+      Err.print(argv[0], errs());
+      return 1;
+    }
+
+    ExitOnErr(SJ->addModule(SJ->getES().getMainJITDylib(),
+                            ThreadSafeModule(std::move(M), std::move(Ctx))));
+  }
+
+  // Build an argv array for the JIT'd main.
+  std::vector<const char *> ArgV;
+  ArgV.push_back(argv[0]);
+  for (const auto &InputArg : InputArgv)
+    ArgV.push_back(InputArg.data());
+  ArgV.push_back(nullptr);
+
+  // Look up the JIT'd main, cast it to a function pointer, then call it.
+
+  auto MainSym = ExitOnErr(SJ->lookup("main"));
+  int (*Main)(int, const char *[]) =
+      (int (*)(int, const char *[]))MainSym.getAddress();
+
+  Main(ArgV.size() - 1, ArgV.data());
+
+  return 0;
+}

include/llvm/ExecutionEngine/Orc/CompileOnDemandLayer.h

@@ -26,6 +26,7 @@
 #include "llvm/ExecutionEngine/Orc/LazyReexports.h"
 #include "llvm/ExecutionEngine/Orc/Legacy.h"
 #include "llvm/ExecutionEngine/Orc/OrcError.h"
+#include "llvm/ExecutionEngine/Orc/Speculation.h"
 #include "llvm/ExecutionEngine/RuntimeDyld.h"
 #include "llvm/IR/Attributes.h"
 #include "llvm/IR/Constant.h"
@@ -91,6 +92,8 @@ public:
   /// Sets the partition function.
   void setPartitionFunction(PartitionFunction Partition);
 
+  /// Sets the ImplSymbolMap
+  void setImplMap(ImplSymbolMap *Imp);
   /// Emits the given module. This should not be called by clients: it will be
   /// called by the JIT when a definition added via the add method is requested.
   void emit(MaterializationResponsibility R, ThreadSafeModule TSM) override;
@@ -128,6 +131,7 @@ private:
   PerDylibResourcesMap DylibResources;
   PartitionFunction Partition = compileRequested;
   SymbolLinkagePromoter PromoteSymbols;
+  ImplSymbolMap *AliaseeImpls = nullptr;
 };
 
 /// Compile-on-demand layer.

include/llvm/ExecutionEngine/Orc/LazyReexports.h

@@ -18,6 +18,7 @@
 
 #include "llvm/ExecutionEngine/Orc/Core.h"
 #include "llvm/ExecutionEngine/Orc/IndirectionUtils.h"
+#include "llvm/ExecutionEngine/Orc/Speculation.h"
 
 namespace llvm {
 
@@ -159,7 +160,7 @@ public:
                                    IndirectStubsManager &ISManager,
                                    JITDylib &SourceJD,
                                    SymbolAliasMap CallableAliases,
-                                   VModuleKey K);
+                                   ImplSymbolMap *SrcJDLoc, VModuleKey K);
 
   StringRef getName() const override;
 
@@ -174,6 +175,7 @@ private:
   SymbolAliasMap CallableAliases;
   std::shared_ptr<LazyCallThroughManager::NotifyResolvedFunction>
       NotifyResolved;
+  ImplSymbolMap *AliaseeTable;
 };
 
 /// Define lazy-reexports based on the given SymbolAliasMap. Each lazy re-export
@@ -182,9 +184,10 @@ private:
 inline std::unique_ptr<LazyReexportsMaterializationUnit>
 lazyReexports(LazyCallThroughManager &LCTManager,
               IndirectStubsManager &ISManager, JITDylib &SourceJD,
-              SymbolAliasMap CallableAliases, VModuleKey K = VModuleKey()) {
+              SymbolAliasMap CallableAliases, ImplSymbolMap *SrcJDLoc = nullptr,
+              VModuleKey K = VModuleKey()) {
   return llvm::make_unique<LazyReexportsMaterializationUnit>(
-      LCTManager, ISManager, SourceJD, std::move(CallableAliases),
+      LCTManager, ISManager, SourceJD, std::move(CallableAliases), SrcJDLoc,
       std::move(K));
 }
 

include/llvm/ExecutionEngine/Orc/SpeculateAnalyses.h

@@ -0,0 +1,72 @@
+//===-- SpeculateAnalyses.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
+//
+//===----------------------------------------------------------------------===//
+// \file
+/// Contains the Analyses and Result Interpretation to select likely functions
+/// to Speculatively compile before they are called. [Experimentation]
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_EXECUTIONENGINE_ORC_SPECULATEANALYSES_H
+#define LLVM_EXECUTIONENGINE_ORC_SPECULATEANALYSES_H
+
+#include "llvm/ExecutionEngine/Orc/Core.h"
+#include "llvm/ExecutionEngine/Orc/Speculation.h"
+
+#include <vector>
+
+namespace {
+using namespace llvm;
+std::vector<const BasicBlock *> findBBwithCalls(const Function &F,
+                                                bool IndirectCall = false) {
+  std::vector<const BasicBlock *> BBs;
+
+  auto findCallInst = [&IndirectCall](const Instruction &I) {
+    if (auto Call = dyn_cast<CallBase>(&I)) {
+      if (Call->isIndirectCall())
+        return IndirectCall;
+      else
+        return true;
+    } else
+      return false;
+  };
+  for (auto &BB : F)
+    if (findCallInst(*BB.getTerminator()) ||
+        llvm::any_of(BB.instructionsWithoutDebug(), findCallInst))
+      BBs.emplace_back(&BB);
+
+  return BBs;
+}
+} // namespace
+
+namespace llvm {
+
+namespace orc {
+
+// Direct calls in high frequency basic blocks are extracted.
+class BlockFreqQuery {
+private:
+  void findCalles(const BasicBlock *, DenseSet<StringRef> &);
+  size_t numBBToGet(size_t);
+
+public:
+  using ResultTy = Optional<DenseMap<StringRef, DenseSet<StringRef>>>;
+
+  // Find likely next executables based on IR Block Frequency
+  ResultTy operator()(Function &F, FunctionAnalysisManager &FAM);
+};
+
+// Walk the CFG by exploting BranchProbabilityInfo
+class CFGWalkQuery {
+public:
+  using ResultTy = Optional<DenseMap<StringRef, DenseSet<StringRef>>>;
+  ResultTy operator()(Function &F, FunctionAnalysisManager &FAM);
+};
+
+} // namespace orc
+} // namespace llvm
+
+#endif // LLVM_EXECUTIONENGINE_ORC_SPECULATEANALYSES_H

include/llvm/ExecutionEngine/Orc/Speculation.h

@@ -0,0 +1,208 @@
+//===-- Speculation.h - Speculative Compilation --*- 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
+//
+//===----------------------------------------------------------------------===//
+//
+// Contains the definition to support speculative compilation when laziness is
+// enabled.
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_EXECUTIONENGINE_ORC_SPECULATION_H
+#define LLVM_EXECUTIONENGINE_ORC_SPECULATION_H
+
+#include "llvm/ADT/ArrayRef.h"
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/Optional.h"
+#include "llvm/ExecutionEngine/Orc/Core.h"
+#include "llvm/ExecutionEngine/Orc/IRCompileLayer.h"
+#include "llvm/IR/PassManager.h"
+#include "llvm/Passes/PassBuilder.h"
+
+#include <mutex>
+#include <type_traits>
+#include <utility>
+#include <vector>
+
+namespace llvm {
+namespace orc {
+
+class Speculator;
+
+// Track the Impls (JITDylib,Symbols) of Symbols while lazy call through
+// trampolines are created. Operations are guarded by locks tp ensure that Imap
+// stays in consistent state after read/write
+
+class ImplSymbolMap {
+  friend class Speculator;
+
+public:
+  using AliaseeDetails = std::pair<SymbolStringPtr, JITDylib *>;
+  using Alias = SymbolStringPtr;
+  using ImapTy = DenseMap<Alias, AliaseeDetails>;
+  void trackImpls(SymbolAliasMap ImplMaps, JITDylib *SrcJD);
+
+private:
+  // FIX ME: find a right way to distinguish the pre-compile Symbols, and update
+  // the callsite
+  Optional<AliaseeDetails> getImplFor(const SymbolStringPtr &StubSymbol) {
+    std::lock_guard<std::mutex> Lockit(ConcurrentAccess);
+    auto Position = Maps.find(StubSymbol);
+    if (Position != Maps.end())
+      return Position->getSecond();
+    else
+      return None;
+  }
+
+  std::mutex ConcurrentAccess;
+  ImapTy Maps;
+};
+
+// Defines Speculator Concept,
+class Speculator {
+public:
+  using TargetFAddr = JITTargetAddress;
+  using FunctionCandidatesMap = DenseMap<SymbolStringPtr, SymbolNameSet>;
+  using StubAddrLikelies = DenseMap<TargetFAddr, SymbolNameSet>;
+
+private:
+  void registerSymbolsWithAddr(TargetFAddr ImplAddr,
+                               SymbolNameSet likelySymbols) {
+    std::lock_guard<std::mutex> Lockit(ConcurrentAccess);
+    GlobalSpecMap.insert({ImplAddr, std::move(likelySymbols)});
+  }
+
+  void launchCompile(JITTargetAddress FAddr) {
+    SymbolNameSet CandidateSet;
+    // Copy CandidateSet is necessary, to avoid unsynchronized access to
+    // the datastructure.
+    {
+      std::lock_guard<std::mutex> Lockit(ConcurrentAccess);
+      auto It = GlobalSpecMap.find(FAddr);
+      // Kill this when jump on first call instrumentation is in place;
+      auto Iv = AlreadyExecuted.insert(FAddr);
+      if (It == GlobalSpecMap.end() || Iv.second == false)
+        return;
+      else
+        CandidateSet = It->getSecond();
+    }
+
+    // Try to distinguish pre-compiled symbols!
+    for (auto &Callee : CandidateSet) {
+      auto ImplSymbol = AliaseeImplTable.getImplFor(Callee);
+      if (!ImplSymbol.hasValue())
+        continue;
+      const auto &ImplSymbolName = ImplSymbol.getPointer()->first;
+      auto *ImplJD = ImplSymbol.getPointer()->second;
+      ES.lookup(JITDylibSearchList({{ImplJD, true}}),
+                SymbolNameSet({ImplSymbolName}), SymbolState::Ready,
+                [this](Expected<SymbolMap> Result) {
+                  if (auto Err = Result.takeError())
+                    ES.reportError(std::move(Err));
+                },
+                NoDependenciesToRegister);
+    }
+  }
+
+public:
+  Speculator(ImplSymbolMap &Impl, ExecutionSession &ref)
+      : AliaseeImplTable(Impl), ES(ref), GlobalSpecMap(0) {}
+  Speculator(const Speculator &) = delete;
+  Speculator(Speculator &&) = delete;
+  Speculator &operator=(const Speculator &) = delete;
+  Speculator &operator=(Speculator &&) = delete;
+  ~Speculator() {}
+
+  // Speculatively compile likely functions for the given Stub Address.
+  // destination of __orc_speculate_for jump
+  void speculateFor(TargetFAddr StubAddr) { launchCompile(StubAddr); }
+
+  // FIXME : Register with Stub Address, after JITLink Fix.
+  void registerSymbols(FunctionCandidatesMap Candidates, JITDylib *JD) {
+    for (auto &SymPair : Candidates) {
+      auto Target = SymPair.first;
+      auto Likely = SymPair.second;
+
+      auto OnReadyFixUp = [Likely, Target,
+                           this](Expected<SymbolMap> ReadySymbol) {
+        if (ReadySymbol) {
+          auto RAddr = (*ReadySymbol)[Target].getAddress();
+          registerSymbolsWithAddr(RAddr, std::move(Likely));
+        } else
+          this->getES().reportError(ReadySymbol.takeError());
+      };
+      // Include non-exported symbols also.
+      ES.lookup(JITDylibSearchList({{JD, true}}), SymbolNameSet({Target}),
+                SymbolState::Ready, OnReadyFixUp, NoDependenciesToRegister);
+    }
+  }
+
+  ExecutionSession &getES() { return ES; }
+
+private:
+  std::mutex ConcurrentAccess;
+  ImplSymbolMap &AliaseeImplTable;
+  ExecutionSession &ES;
+  DenseSet<TargetFAddr> AlreadyExecuted;
+  StubAddrLikelies GlobalSpecMap;
+};
+// replace DenseMap with Pair
+class IRSpeculationLayer : public IRLayer {
+public:
+  using IRlikiesStrRef = Optional<DenseMap<StringRef, DenseSet<StringRef>>>;
+  using ResultEval =
+      std::function<IRlikiesStrRef(Function &, FunctionAnalysisManager &)>;
+  using TargetAndLikelies = DenseMap<SymbolStringPtr, SymbolNameSet>;
+
+  IRSpeculationLayer(ExecutionSession &ES, IRCompileLayer &BaseLayer,
+                     Speculator &Spec, ResultEval Interpreter)
+      : IRLayer(ES), NextLayer(BaseLayer), S(Spec), QueryAnalysis(Interpreter) {
+    PB.registerFunctionAnalyses(FAM);
+  }
+
+  template <
+      typename AnalysisTy,
+      typename std::enable_if<
+          std::is_base_of<AnalysisInfoMixin<AnalysisTy>, AnalysisTy>::value,
+          bool>::type = true>
+  void registerAnalysis() {
+    FAM.registerPass([]() { return AnalysisTy(); });
+  }
+
+  void emit(MaterializationResponsibility R, ThreadSafeModule TSM);
+
+private:
+  TargetAndLikelies
+  internToJITSymbols(DenseMap<StringRef, DenseSet<StringRef>> IRNames) {
+    assert(!IRNames.empty() && "No IRNames received to Intern?");
+    TargetAndLikelies InternedNames;
+    DenseSet<SymbolStringPtr> TargetJITNames;
+    ExecutionSession &Es = getExecutionSession();
+    for (auto &NamePair : IRNames) {
+      for (auto &TargetNames : NamePair.second)
+        TargetJITNames.insert(Es.intern(TargetNames));
+
+      InternedNames.insert(
+          {Es.intern(NamePair.first), std::move(TargetJITNames)});
+    }
+    return InternedNames;
+  }
+
+  IRCompileLayer &NextLayer;
+  Speculator &S;
+  PassBuilder PB;
+  FunctionAnalysisManager FAM;
+  ResultEval QueryAnalysis;
+};
+
+// Runtime Function Interface
+extern "C" {
+void __orc_speculate_for(Speculator *, uint64_t stub_id);
+}
+
+} // namespace orc
+} // namespace llvm
+
+#endif // LLVM_EXECUTIONENGINE_ORC_SPECULATION_H

lib/ExecutionEngine/Orc/CMakeLists.txt

@@ -21,7 +21,8 @@ add_llvm_library(LLVMOrcJIT
   RPCUtils.cpp
   RTDyldObjectLinkingLayer.cpp
   ThreadSafeModule.cpp
-
+  Speculation.cpp
+  SpeculateAnalyses.cpp
   ADDITIONAL_HEADER_DIRS
   ${LLVM_MAIN_INCLUDE_DIR}/llvm/ExecutionEngine/Orc
 
@@ -31,6 +32,7 @@ add_llvm_library(LLVMOrcJIT
 
 target_link_libraries(LLVMOrcJIT
   PRIVATE
+  LLVMAnalysis
   LLVMBitReader
   LLVMBitWriter
   )

lib/ExecutionEngine/Orc/CompileOnDemandLayer.cpp

@@ -118,6 +118,9 @@ void CompileOnDemandLayer::setPartitionFunction(PartitionFunction Partition) {
   this->Partition = std::move(Partition);
 }
 
+void CompileOnDemandLayer::setImplMap(ImplSymbolMap *Imp) {
+  this->AliaseeImpls = Imp;
+}
 void CompileOnDemandLayer::emit(MaterializationResponsibility R,
                                 ThreadSafeModule TSM) {
   assert(TSM && "Null module");
@@ -161,7 +164,7 @@ void CompileOnDemandLayer::emit(MaterializationResponsibility R,
 
   R.replace(reexports(PDR.getImplDylib(), std::move(NonCallables), true));
   R.replace(lazyReexports(LCTMgr, PDR.getISManager(), PDR.getImplDylib(),
-                          std::move(Callables)));
+                          std::move(Callables), AliaseeImpls));
 }
 
 CompileOnDemandLayer::PerDylibResources &

lib/ExecutionEngine/Orc/LazyReexports.cpp

@@ -50,7 +50,6 @@ LazyCallThroughManager::callThroughToSymbol(JITTargetAddress TrampolineAddr) {
     SourceJD = I->second.first;
     SymbolName = I->second.second;
   }
-
   auto LookupResult =
       ES.lookup(JITDylibSearchList({{SourceJD, true}}), SymbolName);
 
@@ -121,7 +120,8 @@ createLocalLazyCallThroughManager(const Triple &T, ExecutionSession &ES,
 
 LazyReexportsMaterializationUnit::LazyReexportsMaterializationUnit(
     LazyCallThroughManager &LCTManager, IndirectStubsManager &ISManager,
-    JITDylib &SourceJD, SymbolAliasMap CallableAliases, VModuleKey K)
+    JITDylib &SourceJD, SymbolAliasMap CallableAliases, ImplSymbolMap *SrcJDLoc,
+    VModuleKey K)
     : MaterializationUnit(extractFlags(CallableAliases), std::move(K)),
       LCTManager(LCTManager), ISManager(ISManager), SourceJD(SourceJD),
       CallableAliases(std::move(CallableAliases)),
@@ -129,7 +129,8 @@ LazyReexportsMaterializationUnit::LazyReexportsMaterializationUnit(
           [&ISManager](JITDylib &JD, const SymbolStringPtr &SymbolName,
                        JITTargetAddress ResolvedAddr) {
             return ISManager.updatePointer(*SymbolName, ResolvedAddr);
-          })) {}
+          })),
+      AliaseeTable(SrcJDLoc) {}
 
 StringRef LazyReexportsMaterializationUnit::getName() const {
   return "<Lazy Reexports>";
@@ -149,7 +150,7 @@ void LazyReexportsMaterializationUnit::materialize(
 
   if (!CallableAliases.empty())
     R.replace(lazyReexports(LCTManager, ISManager, SourceJD,
-                            std::move(CallableAliases)));
+                            std::move(CallableAliases), AliaseeTable));
 
   IndirectStubsManager::StubInitsMap StubInits;
   for (auto &Alias : RequestedAliases) {
@@ -168,6 +169,9 @@ void LazyReexportsMaterializationUnit::materialize(
         std::make_pair(*CallThroughTrampoline, Alias.second.AliasFlags);
   }
 
+  if (AliaseeTable != nullptr && !RequestedAliases.empty())
+    AliaseeTable->trackImpls(RequestedAliases, &SourceJD);
+
   if (auto Err = ISManager.createStubs(StubInits)) {
     SourceJD.getExecutionSession().reportError(std::move(Err));
     R.failMaterialization();

lib/ExecutionEngine/Orc/SpeculateAnalyses.cpp

@@ -0,0 +1,87 @@
+//===-- SpeculateAnalyses.cpp  --*- 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
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/ExecutionEngine/Orc/SpeculateAnalyses.h"
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/STLExtras.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/Analysis/BlockFrequencyInfo.h"
+
+// Implementations of Queries shouldn't need to lock the resources
+// such as LLVMContext, each argument (function) has a non-shared LLVMContext
+namespace llvm {
+namespace orc {
+
+// Collect direct calls only
+void BlockFreqQuery::findCalles(const BasicBlock *BB,
+                                DenseSet<StringRef> &CallesNames) {
+  assert(BB != nullptr && "Traversing Null BB to find calls?");
+
+  auto getCalledFunction = [&CallesNames](const CallBase *Call) {
+    auto CalledValue = Call->getCalledOperand()->stripPointerCasts();
+    if (auto DirectCall = dyn_cast<Function>(CalledValue))
+      CallesNames.insert(DirectCall->getName());
+  };
+  for (auto &I : BB->instructionsWithoutDebug())
+    if (auto CI = dyn_cast<CallInst>(&I))
+      getCalledFunction(CI);
+
+  if (auto II = dyn_cast<InvokeInst>(BB->getTerminator()))
+    getCalledFunction(II);
+}
+
+// blind calculation
+size_t BlockFreqQuery::numBBToGet(size_t numBB) {
+  // small CFG
+  if (numBB < 4)
+    return numBB;
+  // mid-size CFG
+  else if (numBB < 20)
+    return (numBB / 2);
+  else
+    return (numBB / 2) + (numBB / 4);
+}
+
+BlockFreqQuery::ResultTy BlockFreqQuery::
+operator()(Function &F, FunctionAnalysisManager &FAM) {
+  DenseMap<StringRef, DenseSet<StringRef>> CallerAndCalles;
+  DenseSet<StringRef> Calles;
+  SmallVector<std::pair<const BasicBlock *, uint64_t>, 8> BBFreqs;
+
+  auto IBBs = findBBwithCalls(F);
+
+  if (IBBs.empty())
+    return None;
+
+  auto &BFI = FAM.getResult<BlockFrequencyAnalysis>(F);
+
+  for (const auto I : IBBs)
+    BBFreqs.push_back({I, BFI.getBlockFreq(I).getFrequency()});
+
+  assert(IBBs.size() == BBFreqs.size() && "BB Count Mismatch");
+
+  llvm::sort(BBFreqs.begin(), BBFreqs.end(),
+             [](decltype(BBFreqs)::const_reference BBF,
+                decltype(BBFreqs)::const_reference BBS) {
+               return BBF.second > BBS.second ? true : false;
+             });
+
+  // ignoring number of direct calls in a BB
+  auto Topk = numBBToGet(BBFreqs.size());
+
+  for (size_t i = 0; i < Topk; i++)
+    findCalles(BBFreqs[i].first, Calles);
+
+  assert(!Calles.empty() && "Running Analysis on Function with no calls?");
+
+  CallerAndCalles.insert({F.getName(), std::move(Calles)});
+
+  return CallerAndCalles;
+}
+} // namespace orc
+} // namespace llvm

lib/ExecutionEngine/Orc/Speculation.cpp

@@ -0,0 +1,97 @@
+//===---------- speculation.cpp - Utilities for Speculation ----------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/ExecutionEngine/Orc/Speculation.h"
+
+#include "llvm/IR/BasicBlock.h"
+#include "llvm/IR/Function.h"
+#include "llvm/IR/IRBuilder.h"
+#include "llvm/IR/Instruction.h"
+#include "llvm/IR/Instructions.h"
+#include "llvm/IR/LLVMContext.h"
+#include "llvm/IR/Module.h"
+#include "llvm/IR/Type.h"
+#include "llvm/IR/Verifier.h"
+
+#include <vector>
+
+namespace llvm {
+
+namespace orc {
+
+// ImplSymbolMap methods
+void ImplSymbolMap::trackImpls(SymbolAliasMap ImplMaps, JITDylib *SrcJD) {
+  assert(SrcJD && "Tracking on Null Source .impl dylib");
+  std::lock_guard<std::mutex> Lockit(ConcurrentAccess);
+  for (auto &I : ImplMaps) {
+    auto It = Maps.insert({I.first, {I.second.Aliasee, SrcJD}});
+    // check rationale when independent dylibs have same symbol name?
+    assert(It.second && "ImplSymbols are already tracked for this Symbol?");
+    (void)(It);
+  }
+}
+
+// If two modules, share the same LLVMContext, different threads must
+// not access those modules concurrently, doing so leave the
+// LLVMContext in in-consistent state.
+// But here since each TSM has a unique Context associated with it,
+// on locking is necessary!
+void IRSpeculationLayer::emit(MaterializationResponsibility R,
+                              ThreadSafeModule TSM) {
+
+  assert(TSM && "Speculation Layer received Null Module ?");
+  assert(TSM.getContext().getContext() != nullptr &&
+         "Module with null LLVMContext?");
+
+  // Instrumentation of runtime calls
+  auto &InContext = *TSM.getContext().getContext();
+  auto SpeculatorVTy = StructType::create(InContext, "Class.Speculator");
+  auto RuntimeCallTy = FunctionType::get(
+      Type::getVoidTy(InContext),
+      {SpeculatorVTy->getPointerTo(), Type::getInt64Ty(InContext)}, false);
+  auto RuntimeCall =
+      Function::Create(RuntimeCallTy, Function::LinkageTypes::ExternalLinkage,
+                       "__orc_speculate_for", TSM.getModuleUnlocked());
+  auto SpeclAddr = new GlobalVariable(
+      *TSM.getModuleUnlocked(), SpeculatorVTy, false,
+      GlobalValue::LinkageTypes::ExternalLinkage, nullptr, "__orc_speculator");
+
+  IRBuilder<> Mutator(InContext);
+
+  // QueryAnalysis allowed to transform the IR source, one such example is
+  // Simplify CFG helps the static branch prediction heuristics!
+  for (auto &Fn : TSM.getModuleUnlocked()->getFunctionList()) {
+    if (!Fn.isDeclaration()) {
+      auto IRNames = QueryAnalysis(Fn, FAM);
+      // Instrument and register if Query has result
+      if (IRNames.hasValue()) {
+        Mutator.SetInsertPoint(&(Fn.getEntryBlock().front()));
+        auto ImplAddrToUint =
+            Mutator.CreatePtrToInt(&Fn, Type::getInt64Ty(InContext));
+        Mutator.CreateCall(RuntimeCallTy, RuntimeCall,
+                           {SpeclAddr, ImplAddrToUint});
+        S.registerSymbols(internToJITSymbols(IRNames.getValue()),
+                          &R.getTargetJITDylib());
+      }
+    }
+  }
+  // No locking needed read only operation.
+  assert(!(verifyModule(*TSM.getModuleUnlocked())) &&
+         "Speculation Instrumentation breaks IR?");
+
+  NextLayer.emit(std::move(R), std::move(TSM));
+}
+
+// Runtime Function Implementation
+extern "C" void __orc_speculate_for(Speculator *Ptr, uint64_t StubId) {
+  assert(Ptr && " Null Address Received in orc_speculate_for ");
+  Ptr->speculateFor(StubId);
+}
+
+} // namespace orc
+} // namespace llvm