[PATCH 35/38] [noalias] D9403: llvm.noalias - Clang CodeGen for local restrict-qualified pointers

[jeroen.dobbelaere]

Summary

This is part of the series started by D68484.

Rebase of D9403

[erichkeane]

clang/lib/CodeGen/CGDecl.cpp

1878

I suspect we'd want to do this as a twine so that it only allocates 1x?

[jeroen.dobbelaere]

clang/lib/CodeGen/CGDecl.cpp

1878

Yes, see D68521. (I try to not modify Hal's original patches in the 'rebase' version)

[jeroen.dobbelaere]

Rebased

[jeroen.dobbelaere]

For review convenience, all changes related to the original local restrict patches have now been incorporated in the full restrict patch series.

clang/lib/CodeGen/CGDecl.cpp

 #include "clang/Basic/CodeGenOptions.h"
 #include "clang/Basic/SourceManager.h"
 #include "clang/Basic/TargetInfo.h"
 #include "clang/CodeGen/CGFunctionInfo.h"
 #include "llvm/Analysis/ValueTracking.h"
 #include "llvm/IR/DataLayout.h"
 #include "llvm/IR/GlobalVariable.h"
 #include "llvm/IR/Intrinsics.h"
+#include "llvm/IR/MDBuilder.h"
 #include "llvm/IR/Type.h"
 
 using namespace clang;
 using namespace CodeGen;
 
 void CodeGenFunction::EmitDecl(const Decl &D) {
   switch (D.getKind()) {
   case Decl::BuiltinTemplate:
static llvm::Constant *replaceUndef(CodeGenModule &CGM, IsPattern isPattern,
   return llvm::ConstantVector::get(Values);
 }
 
 /// EmitAutoVarDecl - Emit code and set up an entry in LocalDeclMap for a
 /// variable declaration with auto, register, or no storage class specifier.
 /// These turn into simple stack objects, or GlobalValues depending on target.
 void CodeGenFunction::EmitAutoVarDecl(const VarDecl &D) {
   AutoVarEmission emission = EmitAutoVarAlloca(D);
+  EmitAutoVarNoAlias(emission);
   EmitAutoVarInit(emission);
   EmitAutoVarCleanups(emission);
 }
 
 /// Emit a lifetime.begin marker if some criteria are satisfied.
 /// \return a pointer to the temporary size Value if a marker was emitted, null
 /// otherwise
 llvm::Value *CodeGenFunction::EmitLifetimeStart(uint64_t Size,
void CodeGenFunction::EmitAutoVarInit(const AutoVarEmission &emission) {
   }
 
   llvm::Type *BP = CGM.Int8Ty->getPointerTo(Loc.getAddressSpace());
   emitStoresForConstant(
       CGM, D, (Loc.getType() == BP) ? Loc : Builder.CreateBitCast(Loc, BP),
       type.isVolatileQualified(), Builder, constant);
 }
 
-/// Emit an expression as an initializer for an object (variable, field, etc.)
+// For all local restrict-qualified local variables, we create a noalias
+// metadata scope. This scope is used to identify each restrict-qualified
+// variable and the other memory accesses within the scope where its aliasing
+// assumptions apply. The scope metadata is stored in the NoAliasAddrMap map
+// where the pointer to the local variable is the key in the map.
+void CodeGenFunction::EmitAutoVarNoAlias(const AutoVarEmission &emission) {
+  assert(emission.Variable && "emission was not valid!");
+
+  // Don't emit noalias intrinsics unless we're optimizing.
+  if (CGM.getCodeGenOpts().OptimizationLevel == 0)
+    return;
+
+  const VarDecl &D = *emission.Variable;
+  QualType type = D.getType();
+
+  // Emit a noalias intrinsic for restrict-qualified variables.
+  if (!type.isRestrictQualified())
+    return;
+
+  llvm::MDBuilder MDB(CurFn->getContext());
+  if (!NoAliasDomain)
+    NoAliasDomain = MDB.createAnonymousAliasScopeDomain(CurFn->getName());
+
+  std::string Name = CurFn->getName();
+  Name += ": ";
+  Name += D.getName();
+
+  llvm::MDNode *Scope =
+    MDB.createAnonymousAliasScope(NoAliasDomain, Name);
+  addNoAliasScope(Scope);
+
+  SmallVector<llvm::Metadata *, 8> ScopeListEntries(1, Scope);
+  llvm::MDNode *ScopeList =
+    llvm::MDNode::get(CurFn->getContext(), ScopeListEntries);
+
+  // Check whether this is a byref variable that's potentially
+  // captured and moved by its own initializer.  If so, we'll need to
+  // emit the initializer first, then copy into the variable.
+  const Expr *Init = D.getInit();
+  bool capturedByInit = emission.IsEscapingByRef && isCapturedBy(D, Init);
+
+  Address Loc =
+    capturedByInit ? emission.Addr : emission.getObjectAddress(*this);
+  NoAliasAddrMap[Loc.getPointer()] = ScopeList;
+}
+
+// Emit an expression as an initializer for an object (variable, field, etc.)
 /// at the given location.  The expression is not necessarily the normal
 /// initializer for the object, and the address is not necessarily
 /// its normal location.
 ///
 /// \param init the initializing expression
 /// \param D the object to act as if we're initializing
 /// \param loc the address to initialize; its type is a pointer
 ///   to the LLVM mapping of the object's type

clang/lib/CodeGen/CGExpr.cpp

if (Ty->isVectorType()) {
       if (Addr.getElementType() != SrcTy) {
         Addr = Builder.CreateElementBitCast(Addr, SrcTy, "storetmp");
       }
     }
   }
 
   Value = EmitToMemory(Value, Ty);
 
+  // If this is an assignment to a restrict-qualified local variable, then we
+  // have pointer aliasing assumptions that can be applied to the pointer value
+  // being stored.
+  auto NAI = NoAliasAddrMap.find(Addr.getPointer());
+  if (NAI != NoAliasAddrMap.end())
+    Value = Builder.CreateNoAliasPointer(Value, NAI->second);
+
   LValue AtomicLValue =
       LValue::MakeAddr(Addr, Ty, getContext(), BaseInfo, TBAAInfo);
   if (Ty->isAtomicType() ||
       (!isInit && LValueIsSuitableForInlineAtomic(AtomicLValue))) {
     EmitAtomicStore(RValue::get(Value), AtomicLValue, isInit);
     return;
   }
 

clang/lib/CodeGen/CGStmt.cpp

bool CodeGenFunction::EmitSimpleStmt(const Stmt *S) {
   case Stmt::DefaultStmtClass:  EmitDefaultStmt(cast<DefaultStmt>(*S));   break;
   case Stmt::CaseStmtClass:     EmitCaseStmt(cast<CaseStmt>(*S));         break;
   case Stmt::SEHLeaveStmtClass: EmitSEHLeaveStmt(cast<SEHLeaveStmt>(*S)); break;
   }
 
   return true;
 }
 
+bool CodeGenFunction::hasLocalRestrictVars(const CompoundStmt &S) {
+  // We may have restrict-qualified variables, but if we're not optimizing, we
+  // don't do anything special with them.
+  if (CGM.getCodeGenOpts().OptimizationLevel == 0)
+    return false;
+
+  for (const auto *C : S.body())
+    if (const auto *DS = dyn_cast<DeclStmt>(C))
+      for (const auto *I : DS->decls())
+        if (const auto *VD = dyn_cast<VarDecl>(I))
+          if (VD->getType().isRestrictQualified())
+            return true;
+
+  return false;
+}
+
 /// EmitCompoundStmt - Emit a compound statement {..} node.  If GetLast is true,
 /// this captures the expression result of the last sub-statement and returns it
 /// (for use by the statement expression extension).
 Address CodeGenFunction::EmitCompoundStmt(const CompoundStmt &S, bool GetLast,
                                           AggValueSlot AggSlot) {
   PrettyStackTraceLoc CrashInfo(getContext().getSourceManager(),S.getLBracLoc(),
                              "LLVM IR generation of compound statement ('{}')");
 
   // Keep track of the current cleanup stack depth, including debug scopes.
-  LexicalScope Scope(*this, S.getSourceRange());
+  LexicalScope Scope(*this, S.getSourceRange(), hasLocalRestrictVars(S));
 
   return EmitCompoundStmtWithoutScope(S, GetLast, AggSlot);
 }
 
 Address
 CodeGenFunction::EmitCompoundStmtWithoutScope(const CompoundStmt &S,
                                               bool GetLast,
                                               AggValueSlot AggSlot) {
void CodeGenFunction::LexicalScope::rescopeLabels() {
   }
 
   // Reparent the labels if the new scope also has cleanups.
   if (innermostScope != EHScopeStack::stable_end() && ParentScope) {
     ParentScope->Labels.append(Labels.begin(), Labels.end());
   }
 }
 
+// For all of the instructions generated for this lexical scope that access
+// memory, add the noalias metadata associated with any block-local
+// restrict-qualified pointers from this scope.
+void CodeGenFunction::LexicalNoAliasInfo::addNoAliasMD() {
+  if (MemoryInsts.empty() || NoAliasScopes.empty())
+    return;
+
+  llvm::MDNode *NewScopeList =
+    llvm::MDNode::get(MemoryInsts[0]->getParent()->getContext(),
+                      NoAliasScopes);
+
+  for (auto &I : MemoryInsts)
+    I->setMetadata(
+          llvm::LLVMContext::MD_noalias,
+          llvm::MDNode::concatenate(I->getMetadata(
+                                      llvm::LLVMContext::MD_noalias),
+                                      NewScopeList));
+
+  MemoryInsts.clear();
+}
 
 void CodeGenFunction::EmitLabelStmt(const LabelStmt &S) {
   EmitLabel(S.getDecl());
   EmitStmt(S.getSubStmt());
 }
 
 void CodeGenFunction::EmitAttributedStmt(const AttributedStmt &S) {
   EmitStmt(S.getSubStmt(), S.getAttrs());

clang/lib/CodeGen/CodeGenFunction.h

 #include "clang/Basic/CapturedStmt.h"
 #include "clang/Basic/CodeGenOptions.h"
 #include "clang/Basic/OpenMPKinds.h"
 #include "clang/Basic/TargetInfo.h"
 #include "llvm/ADT/ArrayRef.h"
 #include "llvm/ADT/DenseMap.h"
 #include "llvm/ADT/MapVector.h"
 #include "llvm/ADT/SmallVector.h"
+#include "llvm/ADT/TinyPtrVector.h"
 #include "llvm/IR/ValueHandle.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Transforms/Utils/SanitizerStats.h"
 
 namespace llvm {
 class BasicBlock;
 class LLVMContext;
 class MDNode;
typedef llvm::function_ref<std::pair<llvm::Value *, llvm::Value *>(
       CodeGenFunction &, const OMPExecutableDirective &S, Address LB,
       Address UB)>
       CodeGenDispatchBoundsTy;
 
   /// CGBuilder insert helper. This function is called after an
   /// instruction is created using Builder.
   void InsertHelper(llvm::Instruction *I, const llvm::Twine &Name,
                     llvm::BasicBlock *BB,
-                    llvm::BasicBlock::iterator InsertPt) const;
+                    llvm::BasicBlock::iterator InsertPt);
 
   /// CurFuncDecl - Holds the Decl for the current outermost
   /// non-closure context.
   const Decl *CurFuncDecl;
   /// CurCodeDecl - This is the inner-most code context, which includes blocks.
   const Decl *CurCodeDecl;
   const CGFunctionInfo *CurFnInfo;
   QualType FnRetTy;
void ForceCleanup(std::initializer_list<llvm::Value**> ValuesToReload = {}) {
       CGF.CurrentCleanupScopeDepth = OldCleanupScopeDepth;
     }
   };
 
   // Cleanup stack depth of the RunCleanupsScope that was pushed most recently.
   EHScopeStack::stable_iterator CurrentCleanupScopeDepth =
       EHScopeStack::stable_end();
 
-  class LexicalScope : public RunCleanupsScope {
+  bool hasLocalRestrictVars(const CompoundStmt &S);
+
+  // The noalias scopes used to tag pointer values assigned to block-local
+  // restrict-qualified variables, and the memory-accessing instructions within
+  // this lexical scope to which the associated pointer-aliasing assumptions
+  // might apply. One of these will exist for each lexical scope.
+  struct LexicalNoAliasInfo {
+    bool RecordMemoryInsts;
+    llvm::TinyPtrVector<llvm::Instruction *> MemoryInsts;
+    llvm::TinyPtrVector<llvm::Metadata *> NoAliasScopes;
+
+    LexicalNoAliasInfo(bool RecordMemoryInsts = false)
+      : RecordMemoryInsts(RecordMemoryInsts) {}
+
+    void recordMemoryInsts() {
+      RecordMemoryInsts = true;
+    }
+
+    void recordMemoryInstruction(llvm::Instruction *I) {
+      if (RecordMemoryInsts)
+        MemoryInsts.push_back(I);
+    }
+
+    void addNoAliasScope(llvm::MDNode *Scope) {
+      assert(RecordMemoryInsts &&
+             "Adding noalias scope but not recording memory accesses!");
+      NoAliasScopes.push_back(Scope);
+    }
+
+    void addNoAliasMD();
+  };
+
+  LexicalNoAliasInfo FnNoAliasInfo;
+
+  class LexicalScope : public RunCleanupsScope, public LexicalNoAliasInfo {
     SourceRange Range;
     SmallVector<const LabelDecl*, 4> Labels;
     LexicalScope *ParentScope;
 
     LexicalScope(const LexicalScope &) = delete;
     void operator=(const LexicalScope &) = delete;
 
   public:
     /// Enter a new cleanup scope.
-    explicit LexicalScope(CodeGenFunction &CGF, SourceRange Range)
-      : RunCleanupsScope(CGF), Range(Range), ParentScope(CGF.CurLexicalScope) {
+    explicit LexicalScope(CodeGenFunction &CGF, SourceRange Range,
+                          bool RecordMemoryInsts = false)
+      : RunCleanupsScope(CGF), LexicalNoAliasInfo(RecordMemoryInsts),
+        Range(Range), ParentScope(CGF.CurLexicalScope) {
       CGF.CurLexicalScope = this;
       if (CGDebugInfo *DI = CGF.getDebugInfo())
         DI->EmitLexicalBlockStart(CGF.Builder, Range.getBegin());
     }
 
     void addLabel(const LabelDecl *label) {
       assert(PerformCleanup && "adding label to dead scope?");
       Labels.push_back(label);
     }
 
+    // If we have block-local restrict-qualified pointers, we need to keep
+    // track of the memory-accessing instructions in the blocks where such
+    // pointers are declared (including lexical scopes that are children of
+    // those blocks) so that we can later add the appropriate metadata. Record
+    // this instruction and so the same in any parent scopes.
+    void recordMemoryInstruction(llvm::Instruction *I) {
+      LexicalNoAliasInfo::recordMemoryInstruction(I);
+      if (ParentScope)
+        ParentScope->recordMemoryInstruction(I);
+      else
+        CGF.FnNoAliasInfo.recordMemoryInstruction(I);
+    }
+
     /// Exit this cleanup scope, emitting any accumulated
     /// cleanups.
     ~LexicalScope() {
       if (CGDebugInfo *DI = CGF.getDebugInfo())
         DI->EmitLexicalBlockEnd(CGF.Builder, Range.getEnd());
 
       // If we should perform a cleanup, force them now.  Note that
       // this ends the cleanup scope before rescoping any labels.
       if (PerformCleanup) {
         ApplyDebugLocation DL(CGF, Range.getEnd());
         ForceCleanup();
       }
     }
 
     /// Force the emission of cleanups now, instead of waiting
     /// until this object is destroyed.
     void ForceCleanup() {
+      addNoAliasMD();
+
       CGF.CurLexicalScope = ParentScope;
       RunCleanupsScope::ForceCleanup();
 
       if (!Labels.empty())
         rescopeLabels();
     }
 
     bool hasLabels() const {
       return !Labels.empty();
     }
 
     void rescopeLabels();
   };
 
   typedef llvm::DenseMap<const Decl *, Address> DeclMapTy;
 
+  // Record this instruction for the purpose of later adding noalias metadata,
+  // is applicible, in order to support block-local restrict-qualified
+  // pointers.
+  void recordMemoryInstruction(llvm::Instruction *I) {
+    if (CurLexicalScope)
+      CurLexicalScope->recordMemoryInstruction(I);
+    else
+      FnNoAliasInfo.recordMemoryInstruction(I);
+  }
+
+  void addNoAliasScope(llvm::MDNode *Scope) {
+    if (CurLexicalScope)
+      CurLexicalScope->addNoAliasScope(Scope);
+    else
+      FnNoAliasInfo.addNoAliasScope(Scope);
+  }
+
   /// The class used to assign some variables some temporarily addresses.
   class OMPMapVars {
     DeclMapTy SavedLocals;
     DeclMapTy SavedTempAddresses;
     OMPMapVars(const OMPMapVars &) = delete;
     void operator=(const OMPMapVars &) = delete;
 
   public:
private:
   /// True if we need emit the life-time markers.
   const bool ShouldEmitLifetimeMarkers;
 
   /// Add OpenCL kernel arg metadata and the kernel attribute metadata to
   /// the function metadata.
   void EmitOpenCLKernelMetadata(const FunctionDecl *FD,
                                 llvm::Function *Fn);
 
+  /// The noalias domain metadata for this function.
+  llvm::MDNode *NoAliasDomain;
+  /// A map between the addresses of local restrict-qualified variables and
+  /// their noalias scope.
+  llvm::DenseMap<llvm::Value *, llvm::MDNode*> NoAliasAddrMap;
+
 public:
   CodeGenFunction(CodeGenModule &cgm, bool suppressNewContext=false);
   ~CodeGenFunction();
 
   CodeGenTypes &getTypes() const { return CGM.getTypes(); }
   ASTContext &getContext() const { return CGM.getContext(); }
   CGDebugInfo *getDebugInfo() {
     if (DisableDebugInfo)

   /// dimension of an array. It registers the association of its (1-dimensional)
   /// QualTypes and size expression's debug node, so that CGDebugInfo can
   /// reference this node when creating the DISubrange object to describe the
   /// array types.
   void EmitAndRegisterVariableArrayDimensions(CGDebugInfo *DI,
                                               const VarDecl &D,
                                               bool EmitDebugInfo);
 
+  void EmitAutoVarNoAlias(const AutoVarEmission &emission);
+
   void EmitStaticVarDecl(const VarDecl &D,
                          llvm::GlobalValue::LinkageTypes Linkage);
 
   class ParamValue {
     llvm::Value *Value;
     unsigned Alignment;
     ParamValue(llvm::Value *V, unsigned A) : Value(V), Alignment(A) {}
   public:

clang/lib/CodeGen/CodeGenFunction.cpp

 }
 
 CodeGenFunction::CodeGenFunction(CodeGenModule &cgm, bool suppressNewContext)
     : CodeGenTypeCache(cgm), CGM(cgm), Target(cgm.getTarget()),
       Builder(cgm, cgm.getModule().getContext(), llvm::ConstantFolder(),
               CGBuilderInserterTy(this)),
       SanOpts(CGM.getLangOpts().Sanitize), DebugInfo(CGM.getModuleDebugInfo()),
       PGO(cgm), ShouldEmitLifetimeMarkers(shouldEmitLifetimeMarkers(
-                    CGM.getCodeGenOpts(), CGM.getLangOpts())) {
+                    CGM.getCodeGenOpts(), CGM.getLangOpts())),
+      NoAliasDomain(nullptr) {
   if (!suppressNewContext)
     CGM.getCXXABI().getMangleContext().startNewFunction();
 
   llvm::FastMathFlags FMF;
   if (CGM.getLangOpts().FastMath)
     FMF.setFast();
   if (CGM.getLangOpts().FiniteMathOnly) {
     FMF.setNoNaNs();
#undef SANITIZER
   // target-features/target-cpu?
   if (CurFuncDecl)
     if (const auto *VecWidth = CurFuncDecl->getAttr<MinVectorWidthAttr>())
       LargestVectorWidth = VecWidth->getVectorWidth();
 }
 
 void CodeGenFunction::EmitFunctionBody(const Stmt *Body) {
   incrementProfileCounter(Body);
-  if (const CompoundStmt *S = dyn_cast<CompoundStmt>(Body))
+  if (const CompoundStmt *S = dyn_cast<CompoundStmt>(Body)) {
+    // Block-local restrict-qualified pointers have the property of implying
+    // exclusivity of access within their block, even with respect to accesses
+    // in their block prior to the point of declaraction of the
+    // restrict-qualified pointer. We don't want to incur the expense
+    // associated with recording memory-accessing instructions when we won't
+    // have any block-local restrict-qualified pointers, so we check for any
+    // relevant declaractions first.
+    if (hasLocalRestrictVars(*S))
+      FnNoAliasInfo.recordMemoryInsts();
+
     EmitCompoundStmtWithoutScope(*S);
-  else
+
+    // Now that we're done with the block, add noalias metadata if we had any
+    // block-local restrict-qualified pointers.
+    FnNoAliasInfo.addNoAliasMD();
+  } else {
     EmitStmt(Body);
   }
+}
 
 /// When instrumenting to collect profile data, the counts for some blocks
 /// such as switch cases need to not include the fall-through counts, so
 /// emit a branch around the instrumentation code. When not instrumenting,
 /// this just calls EmitBlock().
 void CodeGenFunction::EmitBlockWithFallThrough(llvm::BasicBlock *BB,
                                                const Stmt *S) {
   llvm::BasicBlock *SkipCountBB = nullptr;

 
 CodeGenFunction::SanitizerScope::~SanitizerScope() {
   CGF->IsSanitizerScope = false;
 }
 
 void CodeGenFunction::InsertHelper(llvm::Instruction *I,
                                    const llvm::Twine &Name,
                                    llvm::BasicBlock *BB,
-                                   llvm::BasicBlock::iterator InsertPt) const {
+                                   llvm::BasicBlock::iterator InsertPt) {
   LoopStack.InsertHelper(I);
   if (IsSanitizerScope)
     CGM.getSanitizerMetadata()->disableSanitizerForInstruction(I);
+
+  // When we have block-local restrict-qualified pointers, we need to record
+  // all memory-accessing instructions (i.e. any kind of instruction for which
+  // AA::getModRefInfo might return something other than NoModRef) so that they
+  // can be tagged with noalias metadata with noalias scopes corresponding to
+  // the applicable restrict-qualified pointers.
+  if (I->mayReadOrWriteMemory())
+    recordMemoryInstruction(I);
 }
 
 void CGBuilderInserter::InsertHelper(
     llvm::Instruction *I, const llvm::Twine &Name, llvm::BasicBlock *BB,
     llvm::BasicBlock::iterator InsertPt) const {
   llvm::IRBuilderDefaultInserter::InsertHelper(I, Name, BB, InsertPt);
   if (CGF)
     CGF->InsertHelper(I, Name, BB, InsertPt);

clang/test/CodeGen/noalias.c

+// RUN: %clang_cc1 -triple x86_64-apple-darwin -O1 -disable-llvm-optzns %s -emit-llvm -o - | FileCheck %s
+
+int r;
+void ex1(int *);
+
+int *a;
+int *foo() {
+  int * restrict x = a;
+  return x;
+
+// CHECK-LABEL: define i32* @foo()
+// CHECK: [[x_addr_foo1:%[a-z0-9_.]+]] = alloca i32*
+// CHECK: [[x_foo1:%[a-z0-9_.]+]] = load i32*, i32** @a{{.*}}, !noalias [[TAG_foo1:!.*]]
+// CHECK: [[x_a_foo1:%[a-z0-9_.]+]] = call i32* @llvm.noalias.p0i32(i32* [[x_foo1]], metadata [[TAG_foo1]])
+// CHECK: store i32* [[x_a_foo1]], i32** [[x_addr_foo1]]{{.*}}, !noalias [[TAG_foo1]]
+}
+
+int *a2;
+int *foo1(int b) {
+  int * restrict x;
+
+// CHECK-LABEL: define i32* @foo1(i32 %b)
+// CHECK: [[x_addr_foo2:%[a-z0-9_.]+]] = alloca i32*
+// CHECK: [[x2_addr_foo2:%[a-z0-9_.]+]] = alloca i32*
+
+  if (b) {
+    x = a;
+    r += *x;
+    ex1(x);
+
+// CHECK: [[x_foo2:%[a-z0-9_.]+]] = load i32*, i32** @a{{.*}}, !noalias [[x_x2_tag_foo2:!.*]]
+// CHECK: [[x_a_foo2:%[a-z0-9_.]+]] = call i32* @llvm.noalias.p0i32(i32* [[x_foo2]], metadata [[x_tag_foo2:!.*]])
+// CHECK: store i32* [[x_a_foo2]], i32** [[x_addr_foo2]]{{.*}}, !noalias [[x_x2_tag_foo2]]
+// CHECK: call void @ex1
+    ++x;
+    *x = r;
+    ex1(x);
+
+// CHECK:  [[old_x_foo2:%[a-z0-9_.]+]] = load i32*, i32** [[x_addr_foo2]]{{.*}}, !noalias [[x_x2_tag_foo2]]
+// CHECK:  [[x_foo2:%[a-z0-9_.]+]] = getelementptr inbounds i32, i32* [[old_x_foo2]], i32 1
+// CHECK:  [[x_a_foo2:%[a-z0-9_.]+]] = call i32* @llvm.noalias.p0i32(i32* [[x_foo2]], metadata [[x_tag_foo2]])
+// CHECK:  store i32* [[x_a_foo2]], i32** [[x_addr_foo2]]{{.*}}, !noalias [[x_x2_tag_foo2]]
+// CHECK: call void @ex1
+
+    x += b;
+    *x = r;
+    ex1(x);
+
+// CHECK:  [[old_x_foo2:%[a-z0-9_.]+]] = load i32*, i32** [[x_addr_foo2]]{{.*}}, !noalias [[x_x2_tag_foo2]]
+// CHECK:  [[x_foo2:%[a-z0-9_.]+]] = getelementptr inbounds i32, i32* [[old_x_foo2]], i64
+// CHECK:  [[x_a_foo2:%[a-z0-9_.]+]] = call i32* @llvm.noalias.p0i32(i32* [[x_foo2]], metadata [[x_tag_foo2]])
+// CHECK:  store i32* [[x_a_foo2]], i32** [[x_addr_foo2]]{{.*}}, !noalias [[x_x2_tag_foo2]]
+// CHECK: call void @ex1
+
+    int * restrict x2 = a2;
+    *x2 = r;
+    ex1(x2);
+
+// CHECK: [[x2_foo2:%[a-z0-9_.]+]] = load i32*, i32** @a2{{.*}}, !noalias [[x_x2_tag_foo2]]
+// CHECK: [[x2_a_foo2:%[a-z0-9_.]+]] = call i32* @llvm.noalias.p0i32(i32* [[x2_foo2]], metadata [[x2_tag_foo2:!.*]])
+// CHECK: store i32* [[x2_a_foo2]], i32** [[x2_addr_foo2]]{{.*}}, !noalias [[x_x2_tag_foo2]]
+// CHECK: call void @ex1
+  } else {
+    x = a2;
+    r += *x;
+
+// CHECK: [[x_foo2:%[a-z0-9_.]+]] = load i32*, i32** @a2{{.*}}, !noalias [[x_tag_foo2]]
+// CHECK: [[x_a_foo2:%[a-z0-9_.]+]] = call i32* @llvm.noalias.p0i32(i32* [[x_foo2]], metadata [[x_tag_foo2]])
+// CHECK: store i32* [[x_a_foo2]], i32** [[x_addr_foo2]]{{.*}}, !noalias [[x_tag_foo2]]
+  }
+
+  return x;
+}
+
+int *bar() {
+  int * x = a;
+  return x;
+
+// CHECK-LABEL: define i32* @bar()
+// CHECK-NOT: noalias
+// CHECK: ret i32*
+}
+

clang/test/OpenMP/taskloop_firstprivate_codegen.cpp

 
 // CHECK: define internal i32 [[TASK_ENTRY]](i32 %0, [[KMP_TASK_MAIN_TY]]* noalias %1)
 
 // CHECK: [[PRIV_VAR_ADDR:%.+]] = alloca [[S_DOUBLE_TY]]*,
 // CHECK: [[PRIV_T_VAR_ADDR:%.+]] = alloca i32*,
 // CHECK: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_DOUBLE_TY]]]*,
 // CHECK: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
 // CHECK: [[PRIV_SIVAR_ADDR:%.+]] = alloca i32*,
-// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
+// CHECK: [[PRIV_NAFP:%.+]] = call void (i8*, ...)* @llvm.noalias.p0f_isVoidp0i8varargf(void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*),
+// CHECK: store void (i8*, ...)* [[PRIV_NAFP]], void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
 // CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
 
 // CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, [[S_DOUBLE_TY]]** [[PRIV_VAR_ADDR]], i32** [[PRIV_T_VAR_ADDR]], [2 x [[S_DOUBLE_TY]]]** [[PRIV_S_ARR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], i32** [[PRIV_SIVAR_ADDR]])
 
 // CHECK: [[PRIV_VAR:%.+]] = load [[S_DOUBLE_TY]]*, [[S_DOUBLE_TY]]** [[PRIV_VAR_ADDR]],
 // CHECK: [[PRIV_T_VAR:%.+]] = load i32*, i32** [[PRIV_T_VAR_ADDR]],
 // CHECK: [[PRIV_S_ARR:%.+]] = load [2 x [[S_DOUBLE_TY]]]*, [2 x [[S_DOUBLE_TY]]]** [[PRIV_S_ARR_ADDR]],
 // CHECK: [[PRIV_VEC:%.+]] = load [2 x i32]*, [2 x i32]** [[PRIV_VEC_ADDR]],

 // CHECK: ret void
 
 // CHECK: define internal i32 [[TASK_ENTRY]](i32 %0, [[KMP_TASK_TMAIN_TY]]* noalias %1)
 // CHECK: alloca i32*,
 // CHECK-DAG: [[PRIV_T_VAR_ADDR:%.+]] = alloca i32*,
 // CHECK-DAG: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
 // CHECK-DAG: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_INT_TY]]]*,
 // CHECK-DAG: [[PRIV_VAR_ADDR:%.+]] = alloca [[S_INT_TY]]*,
-// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
+// CHECK: [[PRIV_NAFP:%.+]] = call void (i8*, ...)* @llvm.noalias.p0f_isVoidp0i8varargf(void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*),
+// CHECK: store void (i8*, ...)* [[PRIV_NAFP]], void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
 // CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
 // CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, i32** [[PRIV_T_VAR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], [2 x [[S_INT_TY]]]** [[PRIV_S_ARR_ADDR]], [[S_INT_TY]]** [[PRIV_VAR_ADDR]])
 // CHECK: [[PRIV_T_VAR:%.+]] = load i32*, i32** [[PRIV_T_VAR_ADDR]],
 // CHECK: [[PRIV_VEC:%.+]] = load [2 x i32]*, [2 x i32]** [[PRIV_VEC_ADDR]],
 // CHECK: [[PRIV_S_ARR:%.+]] = load [2 x [[S_INT_TY]]]*, [2 x [[S_INT_TY]]]** [[PRIV_S_ARR_ADDR]],
 // CHECK: [[PRIV_VAR:%.+]] = load [[S_INT_TY]]*, [[S_INT_TY]]** [[PRIV_VAR_ADDR]],
 
 // Privates actually are used.

clang/test/OpenMP/taskloop_lastprivate_codegen.cpp

 
 // CHECK: define internal i32 [[TASK_ENTRY]](i32 %0, [[KMP_TASK_MAIN_TY]]* noalias %1)
 
 // CHECK: [[PRIV_VAR_ADDR:%.+]] = alloca [[S_DOUBLE_TY]]*,
 // CHECK: [[PRIV_T_VAR_ADDR:%.+]] = alloca i32*,
 // CHECK: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_DOUBLE_TY]]]*,
 // CHECK: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
 // CHECK: [[PRIV_SIVAR_ADDR:%.+]] = alloca i32*,
-// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
+// CHECK: [[PRIV_NAFP:%.+]] = call void (i8*, ...)* @llvm.noalias.p0f_isVoidp0i8varargf(void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*),
+// CHECK: store void (i8*, ...)* [[PRIV_NAFP]], void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
 // CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
 
 // CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, [[S_DOUBLE_TY]]** [[PRIV_VAR_ADDR]], i32** [[PRIV_T_VAR_ADDR]], [2 x [[S_DOUBLE_TY]]]** [[PRIV_S_ARR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], i32** [[PRIV_SIVAR_ADDR]])
 
 // CHECK: [[PRIV_VAR:%.+]] = load [[S_DOUBLE_TY]]*, [[S_DOUBLE_TY]]** [[PRIV_VAR_ADDR]],
 // CHECK: [[PRIV_T_VAR:%.+]] = load i32*, i32** [[PRIV_T_VAR_ADDR]],
 // CHECK: [[PRIV_S_ARR:%.+]] = load [2 x [[S_DOUBLE_TY]]]*, [2 x [[S_DOUBLE_TY]]]** [[PRIV_S_ARR_ADDR]],
 // CHECK: [[PRIV_VEC:%.+]] = load [2 x i32]*, [2 x i32]** [[PRIV_VEC_ADDR]],

 // CHECK: ret void
 
 // CHECK: define internal i32 [[TASK_ENTRY]](i32 %0, [[KMP_TASK_TMAIN_TY]]* noalias %1)
 // CHECK: alloca i32*,
 // CHECK-DAG: [[PRIV_T_VAR_ADDR:%.+]] = alloca i32*,
 // CHECK-DAG: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
 // CHECK-DAG: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_INT_TY]]]*,
 // CHECK-DAG: [[PRIV_VAR_ADDR:%.+]] = alloca [[S_INT_TY]]*,
-// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
+// CHECK: [[PRIV_NAFP:%.+]] = call void (i8*, ...)* @llvm.noalias.p0f_isVoidp0i8varargf(void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*),
+// CHECK: store void (i8*, ...)* [[PRIV_NAFP]], void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
 // CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
 // CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, i32** [[PRIV_T_VAR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], [2 x [[S_INT_TY]]]** [[PRIV_S_ARR_ADDR]], [[S_INT_TY]]** [[PRIV_VAR_ADDR]])
 // CHECK: [[PRIV_T_VAR:%.+]] = load i32*, i32** [[PRIV_T_VAR_ADDR]],
 // CHECK: [[PRIV_VEC:%.+]] = load [2 x i32]*, [2 x i32]** [[PRIV_VEC_ADDR]],
 // CHECK: [[PRIV_S_ARR:%.+]] = load [2 x [[S_INT_TY]]]*, [2 x [[S_INT_TY]]]** [[PRIV_S_ARR_ADDR]],
 // CHECK: [[PRIV_VAR:%.+]] = load [[S_INT_TY]]*, [[S_INT_TY]]** [[PRIV_VAR_ADDR]],
 
 // Privates actually are used.

clang/test/OpenMP/taskloop_private_codegen.cpp

 
 // CHECK: define internal i32 [[TASK_ENTRY]](i32 %0, [[KMP_TASK_MAIN_TY]]* noalias %1)
 
 // CHECK: [[PRIV_VAR_ADDR:%.+]] = alloca [[S_DOUBLE_TY]]*,
 // CHECK: [[PRIV_T_VAR_ADDR:%.+]] = alloca i32*,
 // CHECK: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_DOUBLE_TY]]]*,
 // CHECK: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
 // CHECK: [[PRIV_SIVAR_ADDR:%.+]] = alloca i32*,
-// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
+// CHECK: [[PRIV_NAFP:%.+]] = call void (i8*, ...)* @llvm.noalias.p0f_isVoidp0i8varargf(void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*),
+// CHECK: store void (i8*, ...)* [[PRIV_NAFP]], void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
 // CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
 // CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, [[S_DOUBLE_TY]]** [[PRIV_VAR_ADDR]], i32** [[PRIV_T_VAR_ADDR]], [2 x [[S_DOUBLE_TY]]]** [[PRIV_S_ARR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], i32** [[PRIV_SIVAR_ADDR]])
 // CHECK: [[PRIV_VAR:%.+]] = load [[S_DOUBLE_TY]]*, [[S_DOUBLE_TY]]** [[PRIV_VAR_ADDR]],
 // CHECK: [[PRIV_T_VAR:%.+]] = load i32*, i32** [[PRIV_T_VAR_ADDR]],
 // CHECK: [[PRIV_S_ARR:%.+]] = load [2 x [[S_DOUBLE_TY]]]*, [2 x [[S_DOUBLE_TY]]]** [[PRIV_S_ARR_ADDR]],
 // CHECK: [[PRIV_VEC:%.+]] = load [2 x i32]*, [2 x i32]** [[PRIV_VEC_ADDR]],
 // CHECK: [[PRIV_SIVAR:%.+]] = load i32*, i32** [[PRIV_SIVAR_ADDR]],
 

 
 // CHECK: define internal i32 [[TASK_ENTRY]](i32 %0, [[KMP_TASK_TMAIN_TY]]* noalias %1)
 
 // CHECK: alloca i32*,
 // CHECK-DAG: [[PRIV_T_VAR_ADDR:%.+]] = alloca i32*,
 // CHECK-DAG: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
 // CHECK-DAG: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_INT_TY]]]*,
 // CHECK-DAG: [[PRIV_VAR_ADDR:%.+]] = alloca [[S_INT_TY]]*,
-// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
+// CHECK: [[PRIV_NAFP:%.+]] = call void (i8*, ...)* @llvm.noalias.p0f_isVoidp0i8varargf(void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*),
+// CHECK: store void (i8*, ...)* [[PRIV_NAFP]], void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
 // CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
 // CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, i32** [[PRIV_T_VAR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], [2 x [[S_INT_TY]]]** [[PRIV_S_ARR_ADDR]], [[S_INT_TY]]** [[PRIV_VAR_ADDR]])
 // CHECK: [[PRIV_T_VAR:%.+]] = load i32*, i32** [[PRIV_T_VAR_ADDR]],
 // CHECK: [[PRIV_VEC:%.+]] = load [2 x i32]*, [2 x i32]** [[PRIV_VEC_ADDR]],
 // CHECK: [[PRIV_S_ARR:%.+]] = load [2 x [[S_INT_TY]]]*, [2 x [[S_INT_TY]]]** [[PRIV_S_ARR_ADDR]],
 // CHECK: [[PRIV_VAR:%.+]] = load [[S_INT_TY]]*, [[S_INT_TY]]** [[PRIV_VAR_ADDR]],
 
 // Privates actually are used.

clang/test/OpenMP/taskloop_simd_firstprivate_codegen.cpp

 
 // CHECK: define internal i32 [[TASK_ENTRY]](i32 %0, [[KMP_TASK_MAIN_TY]]* noalias %1)
 
 // CHECK: [[PRIV_VAR_ADDR:%.+]] = alloca [[S_DOUBLE_TY]]*,
 // CHECK: [[PRIV_T_VAR_ADDR:%.+]] = alloca i32*,
 // CHECK: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_DOUBLE_TY]]]*,
 // CHECK: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
 // CHECK: [[PRIV_SIVAR_ADDR:%.+]] = alloca i32*,
-// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
+// CHECK: [[PRIV_NAFP:%.+]] = call void (i8*, ...)* @llvm.noalias.p0f_isVoidp0i8varargf(void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*),
+// CHECK: store void (i8*, ...)* [[PRIV_NAFP]], void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
 // CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
 
 // CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, [[S_DOUBLE_TY]]** [[PRIV_VAR_ADDR]], i32** [[PRIV_T_VAR_ADDR]], [2 x [[S_DOUBLE_TY]]]** [[PRIV_S_ARR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], i32** [[PRIV_SIVAR_ADDR]])
 
 // CHECK: [[PRIV_VAR:%.+]] = load [[S_DOUBLE_TY]]*, [[S_DOUBLE_TY]]** [[PRIV_VAR_ADDR]],
 // CHECK: [[PRIV_T_VAR:%.+]] = load i32*, i32** [[PRIV_T_VAR_ADDR]],
 // CHECK: [[PRIV_S_ARR:%.+]] = load [2 x [[S_DOUBLE_TY]]]*, [2 x [[S_DOUBLE_TY]]]** [[PRIV_S_ARR_ADDR]],
 // CHECK: [[PRIV_VEC:%.+]] = load [2 x i32]*, [2 x i32]** [[PRIV_VEC_ADDR]],

 // CHECK: ret void
 
 // CHECK: define internal i32 [[TASK_ENTRY]](i32 %0, [[KMP_TASK_TMAIN_TY]]* noalias %1)
 // CHECK: alloca i32*,
 // CHECK-DAG: [[PRIV_T_VAR_ADDR:%.+]] = alloca i32*,
 // CHECK-DAG: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
 // CHECK-DAG: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_INT_TY]]]*,
 // CHECK-DAG: [[PRIV_VAR_ADDR:%.+]] = alloca [[S_INT_TY]]*,
-// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
+// CHECK: [[PRIV_NAFP:%.+]] = call void (i8*, ...)* @llvm.noalias.p0f_isVoidp0i8varargf(void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*),
+// CHECK: store void (i8*, ...)* [[PRIV_NAFP]], void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
 // CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
 // CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, i32** [[PRIV_T_VAR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], [2 x [[S_INT_TY]]]** [[PRIV_S_ARR_ADDR]], [[S_INT_TY]]** [[PRIV_VAR_ADDR]])
 // CHECK: [[PRIV_T_VAR:%.+]] = load i32*, i32** [[PRIV_T_VAR_ADDR]],
 // CHECK: [[PRIV_VEC:%.+]] = load [2 x i32]*, [2 x i32]** [[PRIV_VEC_ADDR]],
 // CHECK: [[PRIV_S_ARR:%.+]] = load [2 x [[S_INT_TY]]]*, [2 x [[S_INT_TY]]]** [[PRIV_S_ARR_ADDR]],
 // CHECK: [[PRIV_VAR:%.+]] = load [[S_INT_TY]]*, [[S_INT_TY]]** [[PRIV_VAR_ADDR]],
 
 // Privates actually are used.

clang/test/OpenMP/taskloop_simd_lastprivate_codegen.cpp

 
 // CHECK: define internal i32 [[TASK_ENTRY]](i32 %0, [[KMP_TASK_MAIN_TY]]* noalias %1)
 
 // CHECK: [[PRIV_VAR_ADDR:%.+]] = alloca [[S_DOUBLE_TY]]*,
 // CHECK: [[PRIV_T_VAR_ADDR:%.+]] = alloca i32*,
 // CHECK: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_DOUBLE_TY]]]*,
 // CHECK: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
 // CHECK: [[PRIV_SIVAR_ADDR:%.+]] = alloca i32*,
-// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
+// CHECK: [[PRIV_NAFP:%.+]] = call void (i8*, ...)* @llvm.noalias.p0f_isVoidp0i8varargf(void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*),
+// CHECK: store void (i8*, ...)* [[PRIV_NAFP]], void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
 // CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
 
 // CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, [[S_DOUBLE_TY]]** [[PRIV_VAR_ADDR]], i32** [[PRIV_T_VAR_ADDR]], [2 x [[S_DOUBLE_TY]]]** [[PRIV_S_ARR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], i32** [[PRIV_SIVAR_ADDR]])
 
 // CHECK: [[PRIV_VAR:%.+]] = load [[S_DOUBLE_TY]]*, [[S_DOUBLE_TY]]** [[PRIV_VAR_ADDR]],
 // CHECK: [[PRIV_T_VAR:%.+]] = load i32*, i32** [[PRIV_T_VAR_ADDR]],
 // CHECK: [[PRIV_S_ARR:%.+]] = load [2 x [[S_DOUBLE_TY]]]*, [2 x [[S_DOUBLE_TY]]]** [[PRIV_S_ARR_ADDR]],
 // CHECK: [[PRIV_VEC:%.+]] = load [2 x i32]*, [2 x i32]** [[PRIV_VEC_ADDR]],

 // CHECK: ret void
 
 // CHECK: define internal i32 [[TASK_ENTRY]](i32 %0, [[KMP_TASK_TMAIN_TY]]* noalias %1)
 // CHECK: alloca i32*,
 // CHECK-DAG: [[PRIV_T_VAR_ADDR:%.+]] = alloca i32*,
 // CHECK-DAG: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
 // CHECK-DAG: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_INT_TY]]]*,
 // CHECK-DAG: [[PRIV_VAR_ADDR:%.+]] = alloca [[S_INT_TY]]*,
-// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
+// CHECK: [[PRIV_NAFP:%.+]] = call void (i8*, ...)* @llvm.noalias.p0f_isVoidp0i8varargf(void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*),
+// CHECK: store void (i8*, ...)* [[PRIV_NAFP]], void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
 // CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
 // CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, i32** [[PRIV_T_VAR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], [2 x [[S_INT_TY]]]** [[PRIV_S_ARR_ADDR]], [[S_INT_TY]]** [[PRIV_VAR_ADDR]])
 // CHECK: [[PRIV_T_VAR:%.+]] = load i32*, i32** [[PRIV_T_VAR_ADDR]],
 // CHECK: [[PRIV_VEC:%.+]] = load [2 x i32]*, [2 x i32]** [[PRIV_VEC_ADDR]],
 // CHECK: [[PRIV_S_ARR:%.+]] = load [2 x [[S_INT_TY]]]*, [2 x [[S_INT_TY]]]** [[PRIV_S_ARR_ADDR]],
 // CHECK: [[PRIV_VAR:%.+]] = load [[S_INT_TY]]*, [[S_INT_TY]]** [[PRIV_VAR_ADDR]],
 
 // Privates actually are used.

clang/test/OpenMP/taskloop_simd_private_codegen.cpp

 
 // CHECK: define internal i32 [[TASK_ENTRY]](i32 %0, [[KMP_TASK_MAIN_TY]]* noalias %1)
 
 // CHECK: [[PRIV_VAR_ADDR:%.+]] = alloca [[S_DOUBLE_TY]]*,
 // CHECK: [[PRIV_T_VAR_ADDR:%.+]] = alloca i32*,
 // CHECK: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_DOUBLE_TY]]]*,
 // CHECK: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
 // CHECK: [[PRIV_SIVAR_ADDR:%.+]] = alloca i32*,
-// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
+// CHECK: [[PRIV_NAFP:%.+]] = call void (i8*, ...)* @llvm.noalias.p0f_isVoidp0i8varargf(void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*),
+// CHECK: store void (i8*, ...)* [[PRIV_NAFP]], void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
 // CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
 // CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, [[S_DOUBLE_TY]]** [[PRIV_VAR_ADDR]], i32** [[PRIV_T_VAR_ADDR]], [2 x [[S_DOUBLE_TY]]]** [[PRIV_S_ARR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], i32** [[PRIV_SIVAR_ADDR]])
 // CHECK: [[PRIV_VAR:%.+]] = load [[S_DOUBLE_TY]]*, [[S_DOUBLE_TY]]** [[PRIV_VAR_ADDR]],
 // CHECK: [[PRIV_T_VAR:%.+]] = load i32*, i32** [[PRIV_T_VAR_ADDR]],
 // CHECK: [[PRIV_S_ARR:%.+]] = load [2 x [[S_DOUBLE_TY]]]*, [2 x [[S_DOUBLE_TY]]]** [[PRIV_S_ARR_ADDR]],
 // CHECK: [[PRIV_VEC:%.+]] = load [2 x i32]*, [2 x i32]** [[PRIV_VEC_ADDR]],
 // CHECK: [[PRIV_SIVAR:%.+]] = load i32*, i32** [[PRIV_SIVAR_ADDR]],
 

 
 // CHECK: define internal i32 [[TASK_ENTRY]](i32 %0, [[KMP_TASK_TMAIN_TY]]* noalias %1)
 
 // CHECK: alloca i32*,
 // CHECK-DAG: [[PRIV_T_VAR_ADDR:%.+]] = alloca i32*,
 // CHECK-DAG: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
 // CHECK-DAG: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_INT_TY]]]*,
 // CHECK-DAG: [[PRIV_VAR_ADDR:%.+]] = alloca [[S_INT_TY]]*,
-// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
+// CHECK: [[PRIV_NAFP:%.+]] = call void (i8*, ...)* @llvm.noalias.p0f_isVoidp0i8varargf(void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*),
+// CHECK: store void (i8*, ...)* [[PRIV_NAFP]], void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
 // CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
 // CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, i32** [[PRIV_T_VAR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], [2 x [[S_INT_TY]]]** [[PRIV_S_ARR_ADDR]], [[S_INT_TY]]** [[PRIV_VAR_ADDR]])
 // CHECK: [[PRIV_T_VAR:%.+]] = load i32*, i32** [[PRIV_T_VAR_ADDR]],
 // CHECK: [[PRIV_VEC:%.+]] = load [2 x i32]*, [2 x i32]** [[PRIV_VEC_ADDR]],
 // CHECK: [[PRIV_S_ARR:%.+]] = load [2 x [[S_INT_TY]]]*, [2 x [[S_INT_TY]]]** [[PRIV_S_ARR_ADDR]],
 // CHECK: [[PRIV_VAR:%.+]] = load [[S_INT_TY]]*, [[S_INT_TY]]** [[PRIV_VAR_ADDR]],
 
 // Privates actually are used.