Merge llvm, clang, lld and lldb trunk r291274, and resolve conflicts.

10 files changed, 460 insertions, 287 deletions

diff --git a/contrib/llvm/lib/Transforms/IPO/FunctionImport.cpp b/contrib/llvm/lib/Transforms/IPO/FunctionImport.cpp
index 6dd95f8dcd55..6b32f6c31f72 100644
--- a/contrib/llvm/lib/Transforms/IPO/FunctionImport.cpp
+++ b/contrib/llvm/lib/Transforms/IPO/FunctionImport.cpp
@@ -36,7 +36,10 @@
 
 using namespace llvm;
 
-STATISTIC(NumImported, "Number of functions imported");
+STATISTIC(NumImportedFunctions, "Number of functions imported");
+STATISTIC(NumImportedModules, "Number of modules imported from");
+STATISTIC(NumDeadSymbols, "Number of dead stripped symbols in index");
+STATISTIC(NumLiveSymbols, "Number of live symbols in index");
 
 /// Limit on instruction count of imported functions.
 static cl::opt<unsigned> ImportInstrLimit(
@@ -69,6 +72,9 @@ static cl::opt<float> ImportColdMultiplier(
 static cl::opt<bool> PrintImports("print-imports", cl::init(false), cl::Hidden,
                                   cl::desc("Print imported functions"));
 
+static cl::opt<bool> ComputeDead("compute-dead", cl::init(true), cl::Hidden,
+                                 cl::desc("Compute dead symbols"));
+
 // Temporary allows the function import pass to disable always linking
 // referenced discardable symbols.
 static cl::opt<bool>
@@ -105,78 +111,6 @@ static std::unique_ptr<Module> loadFile(const std::string &FileName,
 
 namespace {
 
-// Return true if the Summary describes a GlobalValue that can be externally
-// referenced, i.e. it does not need renaming (linkage is not local) or renaming
-// is possible (does not have a section for instance).
-static bool canBeExternallyReferenced(const GlobalValueSummary &Summary) {
-  if (!Summary.needsRenaming())
-    return true;
-
-  if (Summary.noRename())
-    // Can't externally reference a global that needs renaming if has a section
-    // or is referenced from inline assembly, for example.
-    return false;
-
-  return true;
-}
-
-// Return true if \p GUID describes a GlobalValue that can be externally
-// referenced, i.e. it does not need renaming (linkage is not local) or
-// renaming is possible (does not have a section for instance).
-static bool canBeExternallyReferenced(const ModuleSummaryIndex &Index,
-                                      GlobalValue::GUID GUID) {
-  auto Summaries = Index.findGlobalValueSummaryList(GUID);
-  if (Summaries == Index.end())
-    return true;
-  if (Summaries->second.size() != 1)
-    // If there are multiple globals with this GUID, then we know it is
-    // not a local symbol, and it is necessarily externally referenced.
-    return true;
-
-  // We don't need to check for the module path, because if it can't be
-  // externally referenced and we call it, it is necessarilly in the same
-  // module
-  return canBeExternallyReferenced(**Summaries->second.begin());
-}
-
-// Return true if the global described by \p Summary can be imported in another
-// module.
-static bool eligibleForImport(const ModuleSummaryIndex &Index,
-                              const GlobalValueSummary &Summary) {
-  if (!canBeExternallyReferenced(Summary))
-    // Can't import a global that needs renaming if has a section for instance.
-    // FIXME: we may be able to import it by copying it without promotion.
-    return false;
-
-  // Don't import functions that are not viable to inline.
-  if (Summary.isNotViableToInline())
-    return false;
-
-  // Check references (and potential calls) in the same module. If the current
-  // value references a global that can't be externally referenced it is not
-  // eligible for import. First check the flag set when we have possible
-  // opaque references (e.g. inline asm calls), then check the call and
-  // reference sets.
-  if (Summary.hasInlineAsmMaybeReferencingInternal())
-    return false;
-  bool AllRefsCanBeExternallyReferenced =
-      llvm::all_of(Summary.refs(), [&](const ValueInfo &VI) {
-        return canBeExternallyReferenced(Index, VI.getGUID());
-      });
-  if (!AllRefsCanBeExternallyReferenced)
-    return false;
-
-  if (auto *FuncSummary = dyn_cast<FunctionSummary>(&Summary)) {
-    bool AllCallsCanBeExternallyReferenced = llvm::all_of(
-        FuncSummary->calls(), [&](const FunctionSummary::EdgeTy &Edge) {
-          return canBeExternallyReferenced(Index, Edge.first.getGUID());
-        });
-    if (!AllCallsCanBeExternallyReferenced)
-      return false;
-  }
-  return true;
-}
-
 /// Given a list of possible callee implementation for a call site, select one
 /// that fits the \p Threshold.
 ///
@@ -214,7 +148,7 @@ selectCallee(const ModuleSummaryIndex &Index,
         if (Summary->instCount() > Threshold)
           return false;
 
-        if (!eligibleForImport(Index, *Summary))
+        if (Summary->notEligibleToImport())
           return false;
 
         return true;
@@ -346,7 +280,8 @@ static void computeImportForFunction(
 static void ComputeImportForModule(
     const GVSummaryMapTy &DefinedGVSummaries, const ModuleSummaryIndex &Index,
     FunctionImporter::ImportMapTy &ImportList,
-    StringMap<FunctionImporter::ExportSetTy> *ExportLists = nullptr) {
+    StringMap<FunctionImporter::ExportSetTy> *ExportLists = nullptr,
+    const DenseSet<GlobalValue::GUID> *DeadSymbols = nullptr) {
   // Worklist contains the list of function imported in this module, for which
   // we will analyse the callees and may import further down the callgraph.
   SmallVector<EdgeInfo, 128> Worklist;
@@ -354,6 +289,10 @@ static void ComputeImportForModule(
   // Populate the worklist with the import for the functions in the current
   // module
   for (auto &GVSummary : DefinedGVSummaries) {
+    if (DeadSymbols && DeadSymbols->count(GVSummary.first)) {
+      DEBUG(dbgs() << "Ignores Dead GUID: " << GVSummary.first << "\n");
+      continue;
+    }
     auto *Summary = GVSummary.second;
     if (auto *AS = dyn_cast<AliasSummary>(Summary))
       Summary = &AS->getAliasee();
@@ -393,14 +332,15 @@ void llvm::ComputeCrossModuleImport(
     const ModuleSummaryIndex &Index,
     const StringMap<GVSummaryMapTy> &ModuleToDefinedGVSummaries,
     StringMap<FunctionImporter::ImportMapTy> &ImportLists,
-    StringMap<FunctionImporter::ExportSetTy> &ExportLists) {
+    StringMap<FunctionImporter::ExportSetTy> &ExportLists,
+    const DenseSet<GlobalValue::GUID> *DeadSymbols) {
   // For each module that has function defined, compute the import/export lists.
   for (auto &DefinedGVSummaries : ModuleToDefinedGVSummaries) {
     auto &ImportList = ImportLists[DefinedGVSummaries.first()];
     DEBUG(dbgs() << "Computing import for Module '"
                  << DefinedGVSummaries.first() << "'\n");
     ComputeImportForModule(DefinedGVSummaries.second, Index, ImportList,
-                           &ExportLists);
+                           &ExportLists, DeadSymbols);
   }
 
   // When computing imports we added all GUIDs referenced by anything
@@ -462,6 +402,86 @@ void llvm::ComputeCrossModuleImportForModule(
 #endif
 }
 
+DenseSet<GlobalValue::GUID> llvm::computeDeadSymbols(
+    const ModuleSummaryIndex &Index,
+    const DenseSet<GlobalValue::GUID> &GUIDPreservedSymbols) {
+  if (!ComputeDead)
+    return DenseSet<GlobalValue::GUID>();
+  if (GUIDPreservedSymbols.empty())
+    // Don't do anything when nothing is live, this is friendly with tests.
+    return DenseSet<GlobalValue::GUID>();
+  DenseSet<GlobalValue::GUID> LiveSymbols = GUIDPreservedSymbols;
+  SmallVector<GlobalValue::GUID, 128> Worklist;
+  Worklist.reserve(LiveSymbols.size() * 2);
+  for (auto GUID : LiveSymbols) {
+    DEBUG(dbgs() << "Live root: " << GUID << "\n");
+    Worklist.push_back(GUID);
+  }
+  // Add values flagged in the index as live roots to the worklist.
+  for (const auto &Entry : Index) {
+    bool IsLiveRoot = llvm::any_of(
+        Entry.second,
+        [&](const std::unique_ptr<llvm::GlobalValueSummary> &Summary) {
+          return Summary->liveRoot();
+        });
+    if (!IsLiveRoot)
+      continue;
+    DEBUG(dbgs() << "Live root (summary): " << Entry.first << "\n");
+    Worklist.push_back(Entry.first);
+  }
+
+  while (!Worklist.empty()) {
+    auto GUID = Worklist.pop_back_val();
+    auto It = Index.findGlobalValueSummaryList(GUID);
+    if (It == Index.end()) {
+      DEBUG(dbgs() << "Not in index: " << GUID << "\n");
+      continue;
+    }
+
+    // FIXME: we should only make the prevailing copy live here
+    for (auto &Summary : It->second) {
+      for (auto Ref : Summary->refs()) {
+        auto RefGUID = Ref.getGUID();
+        if (LiveSymbols.insert(RefGUID).second) {
+          DEBUG(dbgs() << "Marking live (ref): " << RefGUID << "\n");
+          Worklist.push_back(RefGUID);
+        }
+      }
+      if (auto *FS = dyn_cast<FunctionSummary>(Summary.get())) {
+        for (auto Call : FS->calls()) {
+          auto CallGUID = Call.first.getGUID();
+          if (LiveSymbols.insert(CallGUID).second) {
+            DEBUG(dbgs() << "Marking live (call): " << CallGUID << "\n");
+            Worklist.push_back(CallGUID);
+          }
+        }
+      }
+      if (auto *AS = dyn_cast<AliasSummary>(Summary.get())) {
+        auto AliaseeGUID = AS->getAliasee().getOriginalName();
+        if (LiveSymbols.insert(AliaseeGUID).second) {
+          DEBUG(dbgs() << "Marking live (alias): " << AliaseeGUID << "\n");
+          Worklist.push_back(AliaseeGUID);
+        }
+      }
+    }
+  }
+  DenseSet<GlobalValue::GUID> DeadSymbols;
+  DeadSymbols.reserve(
+      std::min(Index.size(), Index.size() - LiveSymbols.size()));
+  for (auto &Entry : Index) {
+    auto GUID = Entry.first;
+    if (!LiveSymbols.count(GUID)) {
+      DEBUG(dbgs() << "Marking dead: " << GUID << "\n");
+      DeadSymbols.insert(GUID);
+    }
+  }
+  DEBUG(dbgs() << LiveSymbols.size() << " symbols Live, and "
+               << DeadSymbols.size() << " symbols Dead \n");
+  NumDeadSymbols += DeadSymbols.size();
+  NumLiveSymbols += LiveSymbols.size();
+  return DeadSymbols;
+}
+
 /// Compute the set of summaries needed for a ThinLTO backend compilation of
 /// \p ModulePath.
 void llvm::gatherImportedSummariesForModule(
@@ -625,7 +645,6 @@ Expected<bool> FunctionImporter::importFunctions(
     // now, before linking it (otherwise this will be a noop).
     if (Error Err = SrcModule->materializeMetadata())
       return std::move(Err);
-    UpgradeDebugInfo(*SrcModule);
 
     auto &ImportGUIDs = FunctionsToImportPerModule->second;
     // Find the globals to import
@@ -698,6 +717,10 @@ Expected<bool> FunctionImporter::importFunctions(
       }
     }
 
+    // Upgrade debug info after we're done materializing all the globals and we
+    // have loaded all the required metadata!
+    UpgradeDebugInfo(*SrcModule);
+
     // Link in the specified functions.
     if (renameModuleForThinLTO(*SrcModule, Index, &GlobalsToImport))
       return true;
@@ -717,9 +740,10 @@ Expected<bool> FunctionImporter::importFunctions(
       report_fatal_error("Function Import: link error");
 
     ImportedCount += GlobalsToImport.size();
+    NumImportedModules++;
   }
 
-  NumImported += ImportedCount;
+  NumImportedFunctions += ImportedCount;
 
   DEBUG(dbgs() << "Imported " << ImportedCount << " functions for Module "
                << DestModule.getModuleIdentifier() << "\n");
diff --git a/contrib/llvm/lib/Transforms/IPO/LowerTypeTests.cpp b/contrib/llvm/lib/Transforms/IPO/LowerTypeTests.cpp
index 2948878cffc4..f4742aaf748f 100644
--- a/contrib/llvm/lib/Transforms/IPO/LowerTypeTests.cpp
+++ b/contrib/llvm/lib/Transforms/IPO/LowerTypeTests.cpp
@@ -27,9 +27,12 @@
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/Intrinsics.h"
 #include "llvm/IR/Module.h"
+#include "llvm/IR/ModuleSummaryIndexYAML.h"
 #include "llvm/IR/Operator.h"
 #include "llvm/Pass.h"
 #include "llvm/Support/Debug.h"
+#include "llvm/Support/Error.h"
+#include "llvm/Support/FileSystem.h"
 #include "llvm/Support/TrailingObjects.h"
 #include "llvm/Support/raw_ostream.h"
 #include "llvm/Transforms/IPO.h"
@@ -52,6 +55,20 @@ static cl::opt<bool> AvoidReuse(
     cl::desc("Try to avoid reuse of byte array addresses using aliases"),
     cl::Hidden, cl::init(true));
 
+static cl::opt<std::string> ClSummaryAction(
+    "lowertypetests-summary-action",
+    cl::desc("What to do with the summary when running this pass"), cl::Hidden);
+
+static cl::opt<std::string> ClReadSummary(
+    "lowertypetests-read-summary",
+    cl::desc("Read summary from given YAML file before running pass"),
+    cl::Hidden);
+
+static cl::opt<std::string> ClWriteSummary(
+    "lowertypetests-write-summary",
+    cl::desc("Write summary to given YAML file after running pass"),
+    cl::Hidden);
+
 bool BitSetInfo::containsGlobalOffset(uint64_t Offset) const {
   if (Offset < ByteOffset)
     return false;
@@ -66,38 +83,6 @@ bool BitSetInfo::containsGlobalOffset(uint64_t Offset) const {
   return Bits.count(BitOffset);
 }
 
-bool BitSetInfo::containsValue(
-    const DataLayout &DL,
-    const DenseMap<GlobalObject *, uint64_t> &GlobalLayout, Value *V,
-    uint64_t COffset) const {
-  if (auto GV = dyn_cast<GlobalObject>(V)) {
-    auto I = GlobalLayout.find(GV);
-    if (I == GlobalLayout.end())
-      return false;
-    return containsGlobalOffset(I->second + COffset);
-  }
-
-  if (auto GEP = dyn_cast<GEPOperator>(V)) {
-    APInt APOffset(DL.getPointerSizeInBits(0), 0);
-    bool Result = GEP->accumulateConstantOffset(DL, APOffset);
-    if (!Result)
-      return false;
-    COffset += APOffset.getZExtValue();
-    return containsValue(DL, GlobalLayout, GEP->getPointerOperand(), COffset);
-  }
-
-  if (auto Op = dyn_cast<Operator>(V)) {
-    if (Op->getOpcode() == Instruction::BitCast)
-      return containsValue(DL, GlobalLayout, Op->getOperand(0), COffset);
-
-    if (Op->getOpcode() == Instruction::Select)
-      return containsValue(DL, GlobalLayout, Op->getOperand(1), COffset) &&
-             containsValue(DL, GlobalLayout, Op->getOperand(2), COffset);
-  }
-
-  return false;
-}
-
 void BitSetInfo::print(raw_ostream &OS) const {
   OS << "offset " << ByteOffset << " size " << BitSize << " align "
      << (1 << AlignLog2);
@@ -204,7 +189,7 @@ struct ByteArrayInfo {
   std::set<uint64_t> Bits;
   uint64_t BitSize;
   GlobalVariable *ByteArray;
-  Constant *Mask;
+  GlobalVariable *MaskGlobal;
 };
 
 /// A POD-like structure that we use to store a global reference together with
@@ -241,6 +226,9 @@ public:
 class LowerTypeTestsModule {
   Module &M;
 
+  // This is for testing purposes only.
+  std::unique_ptr<ModuleSummaryIndex> OwnedSummary;
+
   bool LinkerSubsectionsViaSymbols;
   Triple::ArchType Arch;
   Triple::OSType OS;
@@ -248,6 +236,7 @@ class LowerTypeTestsModule {
 
   IntegerType *Int1Ty = Type::getInt1Ty(M.getContext());
   IntegerType *Int8Ty = Type::getInt8Ty(M.getContext());
+  PointerType *Int8PtrTy = Type::getInt8PtrTy(M.getContext());
   IntegerType *Int32Ty = Type::getInt32Ty(M.getContext());
   PointerType *Int32PtrTy = PointerType::getUnqual(Int32Ty);
   IntegerType *Int64Ty = Type::getInt64Ty(M.getContext());
@@ -259,6 +248,37 @@ class LowerTypeTestsModule {
   // Mapping from type identifiers to the call sites that test them.
   DenseMap<Metadata *, std::vector<CallInst *>> TypeTestCallSites;
 
+  /// This structure describes how to lower type tests for a particular type
+  /// identifier. It is either built directly from the global analysis (during
+  /// regular LTO or the regular LTO phase of ThinLTO), or indirectly using type
+  /// identifier summaries and external symbol references (in ThinLTO backends).
+  struct TypeIdLowering {
+    TypeTestResolution::Kind TheKind;
+
+    /// All except Unsat: the start address within the combined global.
+    Constant *OffsetedGlobal;
+
+    /// ByteArray, Inline, AllOnes: log2 of the required global alignment
+    /// relative to the start address.
+    Constant *AlignLog2;
+
+    /// ByteArray, Inline, AllOnes: size of the memory region covering members
+    /// of this type identifier as a multiple of 2^AlignLog2.
+    Constant *Size;
+
+    /// ByteArray, Inline, AllOnes: range of the size expressed as a bit width.
+    unsigned SizeBitWidth;
+
+    /// ByteArray: the byte array to test the address against.
+    Constant *TheByteArray;
+
+    /// ByteArray: the bit mask to apply to bytes loaded from the byte array.
+    Constant *BitMask;
+
+    /// Inline: the bit mask to test the address against.
+    Constant *InlineBits;
+  };
+
   std::vector<ByteArrayInfo> ByteArrayInfos;
 
   Function *WeakInitializerFn = nullptr;
@@ -268,15 +288,13 @@ class LowerTypeTestsModule {
               const DenseMap<GlobalTypeMember *, uint64_t> &GlobalLayout);
   ByteArrayInfo *createByteArray(BitSetInfo &BSI);
   void allocateByteArrays();
-  Value *createBitSetTest(IRBuilder<> &B, BitSetInfo &BSI, ByteArrayInfo *&BAI,
+  Value *createBitSetTest(IRBuilder<> &B, const TypeIdLowering &TIL,
                           Value *BitOffset);
   void lowerTypeTestCalls(
       ArrayRef<Metadata *> TypeIds, Constant *CombinedGlobalAddr,
       const DenseMap<GlobalTypeMember *, uint64_t> &GlobalLayout);
-  Value *
-  lowerBitSetCall(CallInst *CI, BitSetInfo &BSI, ByteArrayInfo *&BAI,
-                  Constant *CombinedGlobal,
-                  const DenseMap<GlobalObject *, uint64_t> &GlobalLayout);
+  Value *lowerTypeTestCall(Metadata *TypeId, CallInst *CI,
+                           const TypeIdLowering &TIL);
   void buildBitSetsFromGlobalVariables(ArrayRef<Metadata *> TypeIds,
                                        ArrayRef<GlobalTypeMember *> Globals);
   unsigned getJumpTableEntrySize();
@@ -302,6 +320,7 @@ class LowerTypeTestsModule {
 
 public:
   LowerTypeTestsModule(Module &M);
+  ~LowerTypeTestsModule();
   bool lower();
 };
 
@@ -380,7 +399,7 @@ ByteArrayInfo *LowerTypeTestsModule::createByteArray(BitSetInfo &BSI) {
   BAI->Bits = BSI.Bits;
   BAI->BitSize = BSI.BitSize;
   BAI->ByteArray = ByteArrayGlobal;
-  BAI->Mask = ConstantExpr::getPtrToInt(MaskGlobal, Int8Ty);
+  BAI->MaskGlobal = MaskGlobal;
   return BAI;
 }
 
@@ -399,8 +418,9 @@ void LowerTypeTestsModule::allocateByteArrays() {
     uint8_t Mask;
     BAB.allocate(BAI->Bits, BAI->BitSize, ByteArrayOffsets[I], Mask);
 
-    BAI->Mask->replaceAllUsesWith(ConstantInt::get(Int8Ty, Mask));
-    cast<GlobalVariable>(BAI->Mask->getOperand(0))->eraseFromParent();
+    BAI->MaskGlobal->replaceAllUsesWith(
+        ConstantExpr::getIntToPtr(ConstantInt::get(Int8Ty, Mask), Int8PtrTy));
+    BAI->MaskGlobal->eraseFromParent();
   }
 
   Constant *ByteArrayConst = ConstantDataArray::get(M.getContext(), BAB.Bytes);
@@ -435,101 +455,121 @@ void LowerTypeTestsModule::allocateByteArrays() {
   ByteArraySizeBytes = BAB.Bytes.size();
 }
 
-/// Build a test that bit BitOffset is set in BSI, where
-/// BitSetGlobal is a global containing the bits in BSI.
-Value *LowerTypeTestsModule::createBitSetTest(IRBuilder<> &B, BitSetInfo &BSI,
-                                              ByteArrayInfo *&BAI,
+/// Build a test that bit BitOffset is set in the type identifier that was
+/// lowered to TIL, which must be either an Inline or a ByteArray.
+Value *LowerTypeTestsModule::createBitSetTest(IRBuilder<> &B,
+                                              const TypeIdLowering &TIL,
                                               Value *BitOffset) {
-  if (BSI.BitSize <= 64) {
+  if (TIL.TheKind == TypeTestResolution::Inline) {
     // If the bit set is sufficiently small, we can avoid a load by bit testing
     // a constant.
-    IntegerType *BitsTy;
-    if (BSI.BitSize <= 32)
-      BitsTy = Int32Ty;
-    else
-      BitsTy = Int64Ty;
-
-    uint64_t Bits = 0;
-    for (auto Bit : BSI.Bits)
-      Bits |= uint64_t(1) << Bit;
-    Constant *BitsConst = ConstantInt::get(BitsTy, Bits);
-    return createMaskedBitTest(B, BitsConst, BitOffset);
+    return createMaskedBitTest(B, TIL.InlineBits, BitOffset);
   } else {
-    if (!BAI) {
-      ++NumByteArraysCreated;
-      BAI = createByteArray(BSI);
-    }
-
-    Constant *ByteArray = BAI->ByteArray;
-    Type *Ty = BAI->ByteArray->getValueType();
+    Constant *ByteArray = TIL.TheByteArray;
     if (!LinkerSubsectionsViaSymbols && AvoidReuse) {
       // Each use of the byte array uses a different alias. This makes the
       // backend less likely to reuse previously computed byte array addresses,
       // improving the security of the CFI mechanism based on this pass.
-      ByteArray = GlobalAlias::create(BAI->ByteArray->getValueType(), 0,
-                                      GlobalValue::PrivateLinkage, "bits_use",
-                                      ByteArray, &M);
+      ByteArray = GlobalAlias::create(Int8Ty, 0, GlobalValue::PrivateLinkage,
+                                      "bits_use", ByteArray, &M);
     }
 
-    Value *ByteAddr = B.CreateGEP(Ty, ByteArray, BitOffset);
+    Value *ByteAddr = B.CreateGEP(Int8Ty, ByteArray, BitOffset);
     Value *Byte = B.CreateLoad(ByteAddr);
 
-    Value *ByteAndMask = B.CreateAnd(Byte, BAI->Mask);
+    Value *ByteAndMask =
+        B.CreateAnd(Byte, ConstantExpr::getPtrToInt(TIL.BitMask, Int8Ty));
     return B.CreateICmpNE(ByteAndMask, ConstantInt::get(Int8Ty, 0));
   }
 }
 
+static bool isKnownTypeIdMember(Metadata *TypeId, const DataLayout &DL,
+                                Value *V, uint64_t COffset) {
+  if (auto GV = dyn_cast<GlobalObject>(V)) {
+    SmallVector<MDNode *, 2> Types;
+    GV->getMetadata(LLVMContext::MD_type, Types);
+    for (MDNode *Type : Types) {
+      if (Type->getOperand(1) != TypeId)
+        continue;
+      uint64_t Offset =
+          cast<ConstantInt>(
+              cast<ConstantAsMetadata>(Type->getOperand(0))->getValue())
+              ->getZExtValue();
+      if (COffset == Offset)
+        return true;
+    }
+    return false;
+  }
+
+  if (auto GEP = dyn_cast<GEPOperator>(V)) {
+    APInt APOffset(DL.getPointerSizeInBits(0), 0);
+    bool Result = GEP->accumulateConstantOffset(DL, APOffset);
+    if (!Result)
+      return false;
+    COffset += APOffset.getZExtValue();
+    return isKnownTypeIdMember(TypeId, DL, GEP->getPointerOperand(), COffset);
+  }
+
+  if (auto Op = dyn_cast<Operator>(V)) {
+    if (Op->getOpcode() == Instruction::BitCast)
+      return isKnownTypeIdMember(TypeId, DL, Op->getOperand(0), COffset);
+
+    if (Op->getOpcode() == Instruction::Select)
+      return isKnownTypeIdMember(TypeId, DL, Op->getOperand(1), COffset) &&
+             isKnownTypeIdMember(TypeId, DL, Op->getOperand(2), COffset);
+  }
+
+  return false;
+}
+
 /// Lower a llvm.type.test call to its implementation. Returns the value to
 /// replace the call with.
-Value *LowerTypeTestsModule::lowerBitSetCall(
-    CallInst *CI, BitSetInfo &BSI, ByteArrayInfo *&BAI,
-    Constant *CombinedGlobalIntAddr,
-    const DenseMap<GlobalObject *, uint64_t> &GlobalLayout) {
+Value *LowerTypeTestsModule::lowerTypeTestCall(Metadata *TypeId, CallInst *CI,
+                                               const TypeIdLowering &TIL) {
+  if (TIL.TheKind == TypeTestResolution::Unsat)
+    return ConstantInt::getFalse(M.getContext());
+
   Value *Ptr = CI->getArgOperand(0);
   const DataLayout &DL = M.getDataLayout();
-
-  if (BSI.containsValue(DL, GlobalLayout, Ptr))
+  if (isKnownTypeIdMember(TypeId, DL, Ptr, 0))
     return ConstantInt::getTrue(M.getContext());
 
-  Constant *OffsetedGlobalAsInt = ConstantExpr::getAdd(
-      CombinedGlobalIntAddr, ConstantInt::get(IntPtrTy, BSI.ByteOffset));
-
   BasicBlock *InitialBB = CI->getParent();
 
   IRBuilder<> B(CI);
 
   Value *PtrAsInt = B.CreatePtrToInt(Ptr, IntPtrTy);
 
-  if (BSI.isSingleOffset())
+  Constant *OffsetedGlobalAsInt =
+      ConstantExpr::getPtrToInt(TIL.OffsetedGlobal, IntPtrTy);
+  if (TIL.TheKind == TypeTestResolution::Single)
     return B.CreateICmpEQ(PtrAsInt, OffsetedGlobalAsInt);
 
   Value *PtrOffset = B.CreateSub(PtrAsInt, OffsetedGlobalAsInt);
 
-  Value *BitOffset;
-  if (BSI.AlignLog2 == 0) {
-    BitOffset = PtrOffset;
-  } else {
-    // We need to check that the offset both falls within our range and is
-    // suitably aligned. We can check both properties at the same time by
-    // performing a right rotate by log2(alignment) followed by an integer
-    // comparison against the bitset size. The rotate will move the lower
-    // order bits that need to be zero into the higher order bits of the
-    // result, causing the comparison to fail if they are nonzero. The rotate
-    // also conveniently gives us a bit offset to use during the load from
-    // the bitset.
-    Value *OffsetSHR =
-        B.CreateLShr(PtrOffset, ConstantInt::get(IntPtrTy, BSI.AlignLog2));
-    Value *OffsetSHL = B.CreateShl(
-        PtrOffset,
-        ConstantInt::get(IntPtrTy, DL.getPointerSizeInBits(0) - BSI.AlignLog2));
-    BitOffset = B.CreateOr(OffsetSHR, OffsetSHL);
-  }
-
-  Constant *BitSizeConst = ConstantInt::get(IntPtrTy, BSI.BitSize);
+  // We need to check that the offset both falls within our range and is
+  // suitably aligned. We can check both properties at the same time by
+  // performing a right rotate by log2(alignment) followed by an integer
+  // comparison against the bitset size. The rotate will move the lower
+  // order bits that need to be zero into the higher order bits of the
+  // result, causing the comparison to fail if they are nonzero. The rotate
+  // also conveniently gives us a bit offset to use during the load from
+  // the bitset.
+  Value *OffsetSHR =
+      B.CreateLShr(PtrOffset, ConstantExpr::getZExt(TIL.AlignLog2, IntPtrTy));
+  Value *OffsetSHL = B.CreateShl(
+      PtrOffset, ConstantExpr::getZExt(
+                     ConstantExpr::getSub(
+                         ConstantInt::get(Int8Ty, DL.getPointerSizeInBits(0)),
+                         TIL.AlignLog2),
+                     IntPtrTy));
+  Value *BitOffset = B.CreateOr(OffsetSHR, OffsetSHL);
+
+  Constant *BitSizeConst = ConstantExpr::getZExt(TIL.Size, IntPtrTy);
   Value *OffsetInRange = B.CreateICmpULT(BitOffset, BitSizeConst);
 
   // If the bit set is all ones, testing against it is unnecessary.
-  if (BSI.isAllOnes())
+  if (TIL.TheKind == TypeTestResolution::AllOnes)
     return OffsetInRange;
 
   TerminatorInst *Term = SplitBlockAndInsertIfThen(OffsetInRange, CI, false);
@@ -537,7 +577,7 @@ Value *LowerTypeTestsModule::lowerBitSetCall(
 
   // Now that we know that the offset is in range and aligned, load the
   // appropriate bit from the bitset.
-  Value *Bit = createBitSetTest(ThenB, BSI, BAI, BitOffset);
+  Value *Bit = createBitSetTest(ThenB, TIL, BitOffset);
 
   // The value we want is 0 if we came directly from the initial block
   // (having failed the range or alignment checks), or the loaded bit if
@@ -622,11 +662,7 @@ void LowerTypeTestsModule::buildBitSetsFromGlobalVariables(
 void LowerTypeTestsModule::lowerTypeTestCalls(
     ArrayRef<Metadata *> TypeIds, Constant *CombinedGlobalAddr,
     const DenseMap<GlobalTypeMember *, uint64_t> &GlobalLayout) {
-  Constant *CombinedGlobalIntAddr =
-      ConstantExpr::getPtrToInt(CombinedGlobalAddr, IntPtrTy);
-  DenseMap<GlobalObject *, uint64_t> GlobalObjLayout;
-  for (auto &P : GlobalLayout)
-    GlobalObjLayout[P.first->getGlobal()] = P.second;
+  CombinedGlobalAddr = ConstantExpr::getBitCast(CombinedGlobalAddr, Int8PtrTy);
 
   // For each type identifier in this disjoint set...
   for (Metadata *TypeId : TypeIds) {
@@ -640,13 +676,43 @@ void LowerTypeTestsModule::lowerTypeTestCalls(
       BSI.print(dbgs());
     });
 
-    ByteArrayInfo *BAI = nullptr;
+    TypeIdLowering TIL;
+    TIL.OffsetedGlobal = ConstantExpr::getGetElementPtr(
+        Int8Ty, CombinedGlobalAddr, ConstantInt::get(IntPtrTy, BSI.ByteOffset)),
+    TIL.AlignLog2 = ConstantInt::get(Int8Ty, BSI.AlignLog2);
+    if (BSI.isAllOnes()) {
+      TIL.TheKind = (BSI.BitSize == 1) ? TypeTestResolution::Single
+                                       : TypeTestResolution::AllOnes;
+      TIL.SizeBitWidth = (BSI.BitSize <= 256) ? 8 : 32;
+      TIL.Size = ConstantInt::get((BSI.BitSize <= 256) ? Int8Ty : Int32Ty,
+                                  BSI.BitSize);
+    } else if (BSI.BitSize <= 64) {
+      TIL.TheKind = TypeTestResolution::Inline;
+      TIL.SizeBitWidth = (BSI.BitSize <= 32) ? 5 : 6;
+      TIL.Size = ConstantInt::get(Int8Ty, BSI.BitSize);
+      uint64_t InlineBits = 0;
+      for (auto Bit : BSI.Bits)
+        InlineBits |= uint64_t(1) << Bit;
+      if (InlineBits == 0)
+        TIL.TheKind = TypeTestResolution::Unsat;
+      else
+        TIL.InlineBits = ConstantInt::get(
+            (BSI.BitSize <= 32) ? Int32Ty : Int64Ty, InlineBits);
+    } else {
+      TIL.TheKind = TypeTestResolution::ByteArray;
+      TIL.SizeBitWidth = (BSI.BitSize <= 256) ? 8 : 32;
+      TIL.Size = ConstantInt::get((BSI.BitSize <= 256) ? Int8Ty : Int32Ty,
+                                  BSI.BitSize);
+      ++NumByteArraysCreated;
+      ByteArrayInfo *BAI = createByteArray(BSI);
+      TIL.TheByteArray = BAI->ByteArray;
+      TIL.BitMask = BAI->MaskGlobal;
+    }
 
     // Lower each call to llvm.type.test for this type identifier.
     for (CallInst *CI : TypeTestCallSites[TypeId]) {
       ++NumTypeTestCallsLowered;
-      Value *Lowered =
-          lowerBitSetCall(CI, BSI, BAI, CombinedGlobalIntAddr, GlobalObjLayout);
+      Value *Lowered = lowerTypeTestCall(TypeId, CI, TIL);
       CI->replaceAllUsesWith(Lowered);
       CI->eraseFromParent();
     }
@@ -1080,6 +1146,22 @@ void LowerTypeTestsModule::buildBitSetsFromDisjointSet(
 
 /// Lower all type tests in this module.
 LowerTypeTestsModule::LowerTypeTestsModule(Module &M) : M(M) {
+  // Handle the command-line summary arguments. This code is for testing
+  // purposes only, so we handle errors directly.
+  if (!ClSummaryAction.empty()) {
+    OwnedSummary = make_unique<ModuleSummaryIndex>();
+    if (!ClReadSummary.empty()) {
+      ExitOnError ExitOnErr("-lowertypetests-read-summary: " + ClReadSummary +
+                            ": ");
+      auto ReadSummaryFile =
+          ExitOnErr(errorOrToExpected(MemoryBuffer::getFile(ClReadSummary)));
+
+      yaml::Input In(ReadSummaryFile->getBuffer());
+      In >> *OwnedSummary;
+      ExitOnErr(errorCodeToError(In.error()));
+    }
+  }
+
   Triple TargetTriple(M.getTargetTriple());
   LinkerSubsectionsViaSymbols = TargetTriple.isMacOSX();
   Arch = TargetTriple.getArch();
@@ -1087,6 +1169,20 @@ LowerTypeTestsModule::LowerTypeTestsModule(Module &M) : M(M) {
   ObjectFormat = TargetTriple.getObjectFormat();
 }
 
+LowerTypeTestsModule::~LowerTypeTestsModule() {
+  if (ClSummaryAction.empty() || ClWriteSummary.empty())
+    return;
+
+  ExitOnError ExitOnErr("-lowertypetests-write-summary: " + ClWriteSummary +
+                        ": ");
+  std::error_code EC;
+  raw_fd_ostream OS(ClWriteSummary, EC, sys::fs::F_Text);
+  ExitOnErr(errorCodeToError(EC));
+
+  yaml::Output Out(OS);
+  Out << *OwnedSummary;
+}
+
 bool LowerTypeTestsModule::lower() {
   Function *TypeTestFunc =
       M.getFunction(Intrinsic::getName(Intrinsic::type_test));
diff --git a/contrib/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp b/contrib/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
index f863d192fc2f..b29ed3c87451 100644
--- a/contrib/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ b/contrib/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -1637,6 +1637,20 @@ Instruction *InstCombiner::visitCallInst(CallInst &CI) {
 
     break;
   }
+  case Intrinsic::cos:
+  case Intrinsic::amdgcn_cos: {
+    Value *SrcSrc;
+    Value *Src = II->getArgOperand(0);
+    if (match(Src, m_FNeg(m_Value(SrcSrc))) ||
+        match(Src, m_Intrinsic<Intrinsic::fabs>(m_Value(SrcSrc)))) {
+      // cos(-x) -> cos(x)
+      // cos(fabs(x)) -> cos(x)
+      II->setArgOperand(0, SrcSrc);
+      return II;
+    }
+
+    break;
+  }
   case Intrinsic::ppc_altivec_lvx:
   case Intrinsic::ppc_altivec_lvxl:
     // Turn PPC lvx -> load if the pointer is known aligned.
diff --git a/contrib/llvm/lib/Transforms/Instrumentation/AddressSanitizer.cpp b/contrib/llvm/lib/Transforms/Instrumentation/AddressSanitizer.cpp
index 6a7cb0e45c63..1d5528398776 100644
--- a/contrib/llvm/lib/Transforms/Instrumentation/AddressSanitizer.cpp
+++ b/contrib/llvm/lib/Transforms/Instrumentation/AddressSanitizer.cpp
@@ -514,7 +514,8 @@ struct AddressSanitizer : public FunctionPass {
   void instrumentAddress(Instruction *OrigIns, Instruction *InsertBefore,
                          Value *Addr, uint32_t TypeSize, bool IsWrite,
                          Value *SizeArgument, bool UseCalls, uint32_t Exp);
-  void instrumentUnusualSizeOrAlignment(Instruction *I, Value *Addr,
+  void instrumentUnusualSizeOrAlignment(Instruction *I,
+                                        Instruction *InsertBefore, Value *Addr,
                                         uint32_t TypeSize, bool IsWrite,
                                         Value *SizeArgument, bool UseCalls,
                                         uint32_t Exp);
@@ -1056,20 +1057,18 @@ Value *AddressSanitizer::isInterestingMemoryAccess(Instruction *I,
           return nullptr;
         *IsWrite = false;
       }
-      // Only instrument if the mask is constant for now.
-      if (isa<ConstantVector>(CI->getOperand(2 + OpOffset))) {
-        auto BasePtr = CI->getOperand(0 + OpOffset);
-        auto Ty = cast<PointerType>(BasePtr->getType())->getElementType();
-        *TypeSize = DL.getTypeStoreSizeInBits(Ty);
-        if (auto AlignmentConstant =
-                dyn_cast<ConstantInt>(CI->getOperand(1 + OpOffset)))
-          *Alignment = (unsigned)AlignmentConstant->getZExtValue();
-        else
-          *Alignment = 1; // No alignment guarantees. We probably got Undef
-        if (MaybeMask)
-          *MaybeMask = CI->getOperand(2 + OpOffset);
-        PtrOperand = BasePtr;
-      }
+
+      auto BasePtr = CI->getOperand(0 + OpOffset);
+      auto Ty = cast<PointerType>(BasePtr->getType())->getElementType();
+      *TypeSize = DL.getTypeStoreSizeInBits(Ty);
+      if (auto AlignmentConstant =
+              dyn_cast<ConstantInt>(CI->getOperand(1 + OpOffset)))
+        *Alignment = (unsigned)AlignmentConstant->getZExtValue();
+      else
+        *Alignment = 1; // No alignment guarantees. We probably got Undef
+      if (MaybeMask)
+        *MaybeMask = CI->getOperand(2 + OpOffset);
+      PtrOperand = BasePtr;
     }
   }
 
@@ -1130,24 +1129,25 @@ void AddressSanitizer::instrumentPointerComparisonOrSubtraction(
 }
 
 static void doInstrumentAddress(AddressSanitizer *Pass, Instruction *I,
-                                Value *Addr, unsigned Alignment,
-                                unsigned Granularity, uint32_t TypeSize,
-                                bool IsWrite, Value *SizeArgument,
-                                bool UseCalls, uint32_t Exp) {
+                                Instruction *InsertBefore, Value *Addr,
+                                unsigned Alignment, unsigned Granularity,
+                                uint32_t TypeSize, bool IsWrite,
+                                Value *SizeArgument, bool UseCalls,
+                                uint32_t Exp) {
   // Instrument a 1-, 2-, 4-, 8-, or 16- byte access with one check
   // if the data is properly aligned.
   if ((TypeSize == 8 || TypeSize == 16 || TypeSize == 32 || TypeSize == 64 ||
        TypeSize == 128) &&
       (Alignment >= Granularity || Alignment == 0 || Alignment >= TypeSize / 8))
-    return Pass->instrumentAddress(I, I, Addr, TypeSize, IsWrite, nullptr,
-                                   UseCalls, Exp);
-  Pass->instrumentUnusualSizeOrAlignment(I, Addr, TypeSize, IsWrite, nullptr,
-                                         UseCalls, Exp);
+    return Pass->instrumentAddress(I, InsertBefore, Addr, TypeSize, IsWrite,
+                                   nullptr, UseCalls, Exp);
+  Pass->instrumentUnusualSizeOrAlignment(I, InsertBefore, Addr, TypeSize,
+                                         IsWrite, nullptr, UseCalls, Exp);
 }
 
 static void instrumentMaskedLoadOrStore(AddressSanitizer *Pass,
                                         const DataLayout &DL, Type *IntptrTy,
-                                        ConstantVector *Mask, Instruction *I,
+                                        Value *Mask, Instruction *I,
                                         Value *Addr, unsigned Alignment,
                                         unsigned Granularity, uint32_t TypeSize,
                                         bool IsWrite, Value *SizeArgument,
@@ -1157,15 +1157,30 @@ static void instrumentMaskedLoadOrStore(AddressSanitizer *Pass,
   unsigned Num = VTy->getVectorNumElements();
   auto Zero = ConstantInt::get(IntptrTy, 0);
   for (unsigned Idx = 0; Idx < Num; ++Idx) {
-    // dyn_cast as we might get UndefValue
-    auto Masked = dyn_cast<ConstantInt>(Mask->getOperand(Idx));
-    if (Masked && Masked->isAllOnesValue()) {
+    Value *InstrumentedAddress = nullptr;
+    Instruction *InsertBefore = I;
+    if (auto *Vector = dyn_cast<ConstantVector>(Mask)) {
+      // dyn_cast as we might get UndefValue
+      if (auto *Masked = dyn_cast<ConstantInt>(Vector->getOperand(Idx))) {
+        if (Masked->isNullValue())
+          // Mask is constant false, so no instrumentation needed.
+          continue;
+        // If we have a true or undef value, fall through to doInstrumentAddress
+        // with InsertBefore == I
+      }
+    } else {
       IRBuilder<> IRB(I);
-      auto InstrumentedAddress =
-          IRB.CreateGEP(Addr, {Zero, ConstantInt::get(IntptrTy, Idx)});
-      doInstrumentAddress(Pass, I, InstrumentedAddress, Alignment, Granularity,
-                          ElemTypeSize, IsWrite, SizeArgument, UseCalls, Exp);
+      Value *MaskElem = IRB.CreateExtractElement(Mask, Idx);
+      TerminatorInst *ThenTerm = SplitBlockAndInsertIfThen(MaskElem, I, false);
+      InsertBefore = ThenTerm;
     }
+
+    IRBuilder<> IRB(InsertBefore);
+    InstrumentedAddress =
+        IRB.CreateGEP(Addr, {Zero, ConstantInt::get(IntptrTy, Idx)});
+    doInstrumentAddress(Pass, I, InsertBefore, InstrumentedAddress, Alignment,
+                        Granularity, ElemTypeSize, IsWrite, SizeArgument,
+                        UseCalls, Exp);
   }
 }
 
@@ -1220,12 +1235,11 @@ void AddressSanitizer::instrumentMop(ObjectSizeOffsetVisitor &ObjSizeVis,
 
   unsigned Granularity = 1 << Mapping.Scale;
   if (MaybeMask) {
-    auto Mask = cast<ConstantVector>(MaybeMask);
-    instrumentMaskedLoadOrStore(this, DL, IntptrTy, Mask, I, Addr, Alignment,
-                                Granularity, TypeSize, IsWrite, nullptr,
-                                UseCalls, Exp);
+    instrumentMaskedLoadOrStore(this, DL, IntptrTy, MaybeMask, I, Addr,
+                                Alignment, Granularity, TypeSize, IsWrite,
+                                nullptr, UseCalls, Exp);
   } else {
-    doInstrumentAddress(this, I, Addr, Alignment, Granularity, TypeSize,
+    doInstrumentAddress(this, I, I, Addr, Alignment, Granularity, TypeSize,
                         IsWrite, nullptr, UseCalls, Exp);
   }
 }
@@ -1342,9 +1356,9 @@ void AddressSanitizer::instrumentAddress(Instruction *OrigIns,
 // and the last bytes. We call __asan_report_*_n(addr, real_size) to be able
 // to report the actual access size.
 void AddressSanitizer::instrumentUnusualSizeOrAlignment(
-    Instruction *I, Value *Addr, uint32_t TypeSize, bool IsWrite,
-    Value *SizeArgument, bool UseCalls, uint32_t Exp) {
-  IRBuilder<> IRB(I);
+    Instruction *I, Instruction *InsertBefore, Value *Addr, uint32_t TypeSize,
+    bool IsWrite, Value *SizeArgument, bool UseCalls, uint32_t Exp) {
+  IRBuilder<> IRB(InsertBefore);
   Value *Size = ConstantInt::get(IntptrTy, TypeSize / 8);
   Value *AddrLong = IRB.CreatePointerCast(Addr, IntptrTy);
   if (UseCalls) {
@@ -1358,8 +1372,8 @@ void AddressSanitizer::instrumentUnusualSizeOrAlignment(
     Value *LastByte = IRB.CreateIntToPtr(
         IRB.CreateAdd(AddrLong, ConstantInt::get(IntptrTy, TypeSize / 8 - 1)),
         Addr->getType());
-    instrumentAddress(I, I, Addr, 8, IsWrite, Size, false, Exp);
-    instrumentAddress(I, I, LastByte, 8, IsWrite, Size, false, Exp);
+    instrumentAddress(I, InsertBefore, Addr, 8, IsWrite, Size, false, Exp);
+    instrumentAddress(I, InsertBefore, LastByte, 8, IsWrite, Size, false, Exp);
   }
 }
 
diff --git a/contrib/llvm/lib/Transforms/Scalar/GVN.cpp b/contrib/llvm/lib/Transforms/Scalar/GVN.cpp
index 9485bfd7c296..0137378b828b 100644
--- a/contrib/llvm/lib/Transforms/Scalar/GVN.cpp
+++ b/contrib/llvm/lib/Transforms/Scalar/GVN.cpp
@@ -1572,6 +1572,13 @@ bool GVN::PerformLoadPRE(LoadInst *LI, AvailValInBlkVect &ValuesPerBlock,
 
   // Assign value numbers to the new instructions.
   for (Instruction *I : NewInsts) {
+    // Instructions that have been inserted in predecessor(s) to materialize
+    // the load address do not retain their original debug locations. Doing
+    // so could lead to confusing (but correct) source attributions.
+    // FIXME: How do we retain source locations without causing poor debugging
+    // behavior?
+    I->setDebugLoc(DebugLoc());
+
     // FIXME: We really _ought_ to insert these value numbers into their
     // parent's availability map.  However, in doing so, we risk getting into
     // ordering issues.  If a block hasn't been processed yet, we would be
@@ -1601,8 +1608,11 @@ bool GVN::PerformLoadPRE(LoadInst *LI, AvailValInBlkVect &ValuesPerBlock,
     if (auto *RangeMD = LI->getMetadata(LLVMContext::MD_range))
       NewLoad->setMetadata(LLVMContext::MD_range, RangeMD);
 
-    // Transfer DebugLoc.
-    NewLoad->setDebugLoc(LI->getDebugLoc());
+    // We do not propagate the old load's debug location, because the new
+    // load now lives in a different BB, and we want to avoid a jumpy line
+    // table.
+    // FIXME: How do we retain source locations without causing poor debugging
+    // behavior?
 
     // Add the newly created load.
     ValuesPerBlock.push_back(AvailableValueInBlock::get(UnavailablePred,
diff --git a/contrib/llvm/lib/Transforms/Scalar/LICM.cpp b/contrib/llvm/lib/Transforms/Scalar/LICM.cpp
index 1cc5c8f0da84..6ef9d0561322 100644
--- a/contrib/llvm/lib/Transforms/Scalar/LICM.cpp
+++ b/contrib/llvm/lib/Transforms/Scalar/LICM.cpp
@@ -408,6 +408,7 @@ bool llvm::hoistRegion(DomTreeNode *N, AliasAnalysis *AA, LoopInfo *LI,
           CurAST->deleteValue(&I);
           I.eraseFromParent();
         }
+        Changed = true;
         continue;
       }
 
@@ -766,6 +767,14 @@ static bool hoist(Instruction &I, const DominatorTree *DT, const Loop *CurLoop,
   // Move the new node to the Preheader, before its terminator.
   I.moveBefore(Preheader->getTerminator());
 
+  // Do not retain debug locations when we are moving instructions to different
+  // basic blocks, because we want to avoid jumpy line tables. Calls, however,
+  // need to retain their debug locs because they may be inlined.
+  // FIXME: How do we retain source locations without causing poor debugging
+  // behavior?
+  if (!isa<CallInst>(I))
+    I.setDebugLoc(DebugLoc());
+
   if (isa<LoadInst>(I))
     ++NumMovedLoads;
   else if (isa<CallInst>(I))
@@ -911,14 +920,23 @@ bool llvm::promoteLoopAccessesToScalars(
   //
   // If at least one store is guaranteed to execute, both properties are
   // satisfied, and promotion is legal.
+  //
   // This, however, is not a necessary condition. Even if no store/load is
-  // guaranteed to execute, we can still establish these properties:
-  // (p1) by proving that hoisting the load into the preheader is
-  // safe (i.e. proving dereferenceability on all paths through the loop). We
+  // guaranteed to execute, we can still establish these properties.
+  // We can establish (p1) by proving that hoisting the load into the preheader
+  // is safe (i.e. proving dereferenceability on all paths through the loop). We
   // can use any access within the alias set to prove dereferenceability,
   // since they're all must alias.
-  // (p2) by proving the memory is thread-local, so the memory model
+  // 
+  // There are two ways establish (p2): 
+  // a) Prove the location is thread-local. In this case the memory model
   // requirement does not apply, and stores are safe to insert.
+  // b) Prove a store dominates every exit block. In this case, if an exit
+  // blocks is reached, the original dynamic path would have taken us through
+  // the store, so inserting a store into the exit block is safe. Note that this
+  // is different from the store being guaranteed to execute. For instance,
+  // if an exception is thrown on the first iteration of the loop, the original
+  // store is never executed, but the exit blocks are not executed either.
 
   bool DereferenceableInPH = false;
   bool SafeToInsertStore = false;
@@ -1000,6 +1018,17 @@ bool llvm::promoteLoopAccessesToScalars(
           }
         }
 
+        // If a store dominates all exit blocks, it is safe to sink.
+        // As explained above, if an exit block was executed, a dominating
+        // store must have been been executed at least once, so we are not
+        // introducing stores on paths that did not have them.
+        // Note that this only looks at explicit exit blocks. If we ever
+        // start sinking stores into unwind edges (see above), this will break.
+        if (!SafeToInsertStore)
+          SafeToInsertStore = llvm::all_of(ExitBlocks, [&](BasicBlock *Exit) {
+            return DT->dominates(Store->getParent(), Exit);
+          });
+
         // If the store is not guaranteed to execute, we may still get
         // deref info through it.
         if (!DereferenceableInPH) {
diff --git a/contrib/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp b/contrib/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp
index fd167db11789..2743574ecca6 100644
--- a/contrib/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp
+++ b/contrib/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp
@@ -997,7 +997,7 @@ bool LoopIdiomRecognize::runOnNoncountableLoop() {
 /// Check if the given conditional branch is based on the comparison between
 /// a variable and zero, and if the variable is non-zero, the control yields to
 /// the loop entry. If the branch matches the behavior, the variable involved
-/// in the comparion is returned. This function will be called to see if the
+/// in the comparison is returned. This function will be called to see if the
 /// precondition and postcondition of the loop are in desirable form.
 static Value *matchCondition(BranchInst *BI, BasicBlock *LoopEntry) {
   if (!BI || !BI->isConditional())
diff --git a/contrib/llvm/lib/Transforms/Scalar/LoopSink.cpp b/contrib/llvm/lib/Transforms/Scalar/LoopSink.cpp
index 90309d7ebba6..f64354497771 100644
--- a/contrib/llvm/lib/Transforms/Scalar/LoopSink.cpp
+++ b/contrib/llvm/lib/Transforms/Scalar/LoopSink.cpp
@@ -283,8 +283,7 @@ static bool sinkLoopInvariantInstructions(Loop &L, AAResults &AA, LoopInfo &LI,
   // sinked.
   for (auto II = Preheader->rbegin(), E = Preheader->rend(); II != E;) {
     Instruction *I = &*II++;
-    if (!L.hasLoopInvariantOperands(I) ||
-        !canSinkOrHoistInst(*I, &AA, &DT, &L, &CurAST, nullptr))
+    if (!canSinkOrHoistInst(*I, &AA, &DT, &L, &CurAST, nullptr))
       continue;
     if (sinkInstruction(L, *I, ColdLoopBBs, LoopBlockNumber, LI, DT, BFI))
       Changed = true;
diff --git a/contrib/llvm/lib/Transforms/Utils/FunctionImportUtils.cpp b/contrib/llvm/lib/Transforms/Utils/FunctionImportUtils.cpp
index 440e36767edf..678d02e05d42 100644
--- a/contrib/llvm/lib/Transforms/Utils/FunctionImportUtils.cpp
+++ b/contrib/llvm/lib/Transforms/Utils/FunctionImportUtils.cpp
@@ -56,12 +56,9 @@ bool FunctionImportGlobalProcessing::shouldPromoteLocalToGlobal(
   if (!isPerformingImport() && !isModuleExporting())
     return false;
 
-  // If we are exporting, we need to see whether this value is marked
-  // as NoRename in the summary. If we are importing, we may not have
-  // a summary in the distributed backend case (only summaries for values
-  // importes as defs, not references, are included in the index passed
-  // to the distributed backends).
   if (isPerformingImport()) {
+    assert((!GlobalsToImport->count(SGV) || !isNonRenamableLocal(*SGV)) &&
+           "Attempting to promote non-renamable local");
     // We don't know for sure yet if we are importing this value (as either
     // a reference or a def), since we are simply walking all values in the
     // module. But by necessity if we end up importing it and it is local,
@@ -77,13 +74,28 @@ bool FunctionImportGlobalProcessing::shouldPromoteLocalToGlobal(
   assert(Summaries->second.size() == 1 && "Local has more than one summary");
   auto Linkage = Summaries->second.front()->linkage();
   if (!GlobalValue::isLocalLinkage(Linkage)) {
-    assert(!Summaries->second.front()->noRename());
+    assert(!isNonRenamableLocal(*SGV) &&
+           "Attempting to promote non-renamable local");
     return true;
   }
 
   return false;
 }
 
+#ifndef NDEBUG
+bool FunctionImportGlobalProcessing::isNonRenamableLocal(
+    const GlobalValue &GV) const {
+  if (!GV.hasLocalLinkage())
+    return false;
+  // This needs to stay in sync with the logic in buildModuleSummaryIndex.
+  if (GV.hasSection())
+    return true;
+  if (Used.count(const_cast<GlobalValue *>(&GV)))
+    return true;
+  return false;
+}
+#endif
+
 std::string FunctionImportGlobalProcessing::getName(const GlobalValue *SGV,
                                                     bool DoPromote) {
   // For locals that must be promoted to global scope, ensure that
diff --git a/contrib/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/contrib/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 8cde0c4cd607..31daba2248aa 100644
--- a/contrib/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/contrib/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -6785,22 +6785,19 @@ LoopVectorizationCostModel::expectedCost(unsigned VF) {
   return Cost;
 }
 
-/// \brief Check whether the address computation for a non-consecutive memory
-/// access looks like an unlikely candidate for being merged into the indexing
-/// mode.
+/// \brief Gets Address Access SCEV after verifying that the access pattern
+/// is loop invariant except the induction variable dependence.
 ///
-/// We look for a GEP which has one index that is an induction variable and all
-/// other indices are loop invariant. If the stride of this access is also
-/// within a small bound we decide that this address computation can likely be
-/// merged into the addressing mode.
-/// In all other cases, we identify the address computation as complex.
-static bool isLikelyComplexAddressComputation(Value *Ptr,
-                                              LoopVectorizationLegality *Legal,
-                                              ScalarEvolution *SE,
-                                              const Loop *TheLoop) {
+/// This SCEV can be sent to the Target in order to estimate the address
+/// calculation cost.
+static const SCEV *getAddressAccessSCEV(
+              Value *Ptr,
+              LoopVectorizationLegality *Legal,
+              ScalarEvolution *SE,
+              const Loop *TheLoop) {
   auto *Gep = dyn_cast<GetElementPtrInst>(Ptr);
   if (!Gep)
-    return true;
+    return nullptr;
 
   // We are looking for a gep with all loop invariant indices except for one
   // which should be an induction variable.
@@ -6809,33 +6806,11 @@ static bool isLikelyComplexAddressComputation(Value *Ptr,
     Value *Opd = Gep->getOperand(i);
     if (!SE->isLoopInvariant(SE->getSCEV(Opd), TheLoop) &&
         !Legal->isInductionVariable(Opd))
-      return true;
+      return nullptr;
   }
 
-  // Now we know we have a GEP ptr, %inv, %ind, %inv. Make sure that the step
-  // can likely be merged into the address computation.
-  unsigned MaxMergeDistance = 64;
-
-  const SCEVAddRecExpr *AddRec = dyn_cast<SCEVAddRecExpr>(SE->getSCEV(Ptr));
-  if (!AddRec)
-    return true;
-
-  // Check the step is constant.
-  const SCEV *Step = AddRec->getStepRecurrence(*SE);
-  // Calculate the pointer stride and check if it is consecutive.
-  const auto *C = dyn_cast<SCEVConstant>(Step);
-  if (!C)
-    return true;
-
-  const APInt &APStepVal = C->getAPInt();
-
-  // Huge step value - give up.
-  if (APStepVal.getBitWidth() > 64)
-    return true;
-
-  int64_t StepVal = APStepVal.getSExtValue();
-
-  return StepVal > MaxMergeDistance;
+  // Now we know we have a GEP ptr, %inv, %ind, %inv. return the Ptr SCEV.
+  return SE->getSCEV(Ptr);
 }
 
 static bool isStrideMul(Instruction *I, LoopVectorizationLegality *Legal) {
@@ -7063,12 +7038,12 @@ unsigned LoopVectorizationCostModel::getInstructionCost(Instruction *I,
       unsigned Cost = 0;
       Type *PtrTy = ToVectorTy(Ptr->getType(), VF);
 
-      // True if the memory instruction's address computation is complex.
-      bool IsComplexComputation =
-          isLikelyComplexAddressComputation(Ptr, Legal, SE, TheLoop);
+      // Figure out whether the access is strided and get the stride value
+      // if it's known in compile time
+      const SCEV *PtrSCEV = getAddressAccessSCEV(Ptr, Legal, SE, TheLoop); 
 
       // Get the cost of the scalar memory instruction and address computation.
-      Cost += VF * TTI.getAddressComputationCost(PtrTy, IsComplexComputation);
+      Cost += VF * TTI.getAddressComputationCost(PtrTy, SE, PtrSCEV);
       Cost += VF *
               TTI.getMemoryOpCost(I->getOpcode(), ValTy->getScalarType(),
                                   Alignment, AS);