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
diff --git a/llvm/lib/ExecutionEngine/Orc/CMakeLists.txt b/llvm/lib/ExecutionEngine/Orc/CMakeLists.txt
index 2c1a772..94d84b6 100644
--- a/llvm/lib/ExecutionEngine/Orc/CMakeLists.txt
+++ b/llvm/lib/ExecutionEngine/Orc/CMakeLists.txt
@@ -21,7 +21,8 @@
   RPCUtils.cpp
   RTDyldObjectLinkingLayer.cpp
   ThreadSafeModule.cpp
-
+  Speculation.cpp
+  SpeculateAnalyses.cpp
   ADDITIONAL_HEADER_DIRS
   ${LLVM_MAIN_INCLUDE_DIR}/llvm/ExecutionEngine/Orc
 
@@ -31,6 +32,7 @@
 
 target_link_libraries(LLVMOrcJIT
   PRIVATE
+  LLVMAnalysis
   LLVMBitReader
   LLVMBitWriter
   )
diff --git a/llvm/lib/ExecutionEngine/Orc/CompileOnDemandLayer.cpp b/llvm/lib/ExecutionEngine/Orc/CompileOnDemandLayer.cpp
index efb98e0..a91dd4e 100644
--- a/llvm/lib/ExecutionEngine/Orc/CompileOnDemandLayer.cpp
+++ b/llvm/lib/ExecutionEngine/Orc/CompileOnDemandLayer.cpp
@@ -118,6 +118,9 @@
   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 @@
 
   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 &
diff --git a/llvm/lib/ExecutionEngine/Orc/LazyReexports.cpp b/llvm/lib/ExecutionEngine/Orc/LazyReexports.cpp
index fc82058..11ba2e5 100644
--- a/llvm/lib/ExecutionEngine/Orc/LazyReexports.cpp
+++ b/llvm/lib/ExecutionEngine/Orc/LazyReexports.cpp
@@ -50,7 +50,6 @@
     SourceJD = I->second.first;
     SymbolName = I->second.second;
   }
-
   auto LookupResult =
       ES.lookup(JITDylibSearchList({{SourceJD, true}}), SymbolName);
 
@@ -121,7 +120,8 @@
 
 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 @@
           [&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 @@
 
   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 @@
         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();
diff --git a/llvm/lib/ExecutionEngine/Orc/SpeculateAnalyses.cpp b/llvm/lib/ExecutionEngine/Orc/SpeculateAnalyses.cpp
new file mode 100644
index 0000000..9d8c2f3
--- /dev/null
+++ b/llvm/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
diff --git a/llvm/lib/ExecutionEngine/Orc/Speculation.cpp b/llvm/lib/ExecutionEngine/Orc/Speculation.cpp
new file mode 100644
index 0000000..5ab5831
--- /dev/null
+++ b/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