CodeGen: Fix address space of global variable

Certain targets (e.g. amdgcn) require global variable to stay in global or constant address space. In C or C++ global variables are emitted in the default (generic) address space. This patch introduces virtual functions TargetCodeGenInfo::getGlobalVarAddressSpace and TargetInfo::getConstantAddressSpace to handle this in a general approach. It only affects IR generated for amdgcn target. Differential Revision: https://reviews.llvm.org/D33842 llvm-svn: 307470
2026-01-28 01:04:49 +08:00 · 2017-07-08 13:24:52 +00:00
parent affab3047e
commit cbf647cc3a
13 changed files with 276 additions and 142 deletions
--- a/clang/include/clang/Basic/TargetInfo.h
+++ b/clang/include/clang/Basic/TargetInfo.h
@@ -23,6 +23,7 @@
 #include "clang/Basic/VersionTuple.h"
 #include "llvm/ADT/APInt.h"
 #include "llvm/ADT/IntrusiveRefCntPtr.h"
+#include "llvm/ADT/Optional.h"
 #include "llvm/ADT/SmallSet.h"
 #include "llvm/ADT/StringMap.h"
 #include "llvm/ADT/StringRef.h"
@@ -954,6 +955,14 @@ public:
    return *AddrSpaceMap;
  }

+  /// \brief Return an AST address space which can be used opportunistically
+  /// for constant global memory. It must be possible to convert pointers into
+  /// this address space to LangAS::Default. If no such address space exists,
+  /// this may return None, and such optimizations will be disabled.
+  virtual llvm::Optional<unsigned> getConstantAddressSpace() const {
+    return LangAS::Default;
+  }
+
  /// \brief Retrieve the name of the platform as it is used in the
  /// availability attribute.
  StringRef getPlatformName() const { return PlatformName; }
--- a/clang/lib/Basic/Targets.cpp
+++ b/clang/lib/Basic/Targets.cpp
@@ -2404,6 +2404,10 @@ public:
    return LangAS::opencl_constant;
  }

+  llvm::Optional<unsigned> getConstantAddressSpace() const override {
+    return LangAS::FirstTargetAddressSpace + AS.Constant;
+  }
+
  /// \returns Target specific vtbl ptr address space.
  unsigned getVtblPtrAddressSpace() const override { return AS.Constant; }

--- a/clang/lib/CodeGen/CGBlocks.cpp
+++ b/clang/lib/CodeGen/CGBlocks.cpp
@@ -736,9 +736,9 @@ llvm::Value *CodeGenFunction::EmitBlockLiteral(const CGBlockInfo &blockInfo) {
  llvm::Constant *isa =
      (!CGM.getContext().getLangOpts().OpenCL)
          ? CGM.getNSConcreteStackBlock()
-          : CGM.getNullPointer(cast<llvm::PointerType>(
-                                   CGM.getNSConcreteStackBlock()->getType()),
-                               QualType(getContext().VoidPtrTy));
+          : CGM.getNullPointer(VoidPtrPtrTy,
+                               CGM.getContext().getPointerType(
+                                   QualType(CGM.getContext().VoidPtrTy)));
  isa = llvm::ConstantExpr::getBitCast(isa, VoidPtrTy);

  // Build the block descriptor.
@@ -1141,12 +1141,11 @@ static llvm::Constant *buildGlobalBlock(CodeGenModule &CGM,
  auto fields = builder.beginStruct();

  // isa
-  fields.add(
-      (!CGM.getContext().getLangOpts().OpenCL)
-          ? CGM.getNSConcreteGlobalBlock()
-          : CGM.getNullPointer(cast<llvm::PointerType>(
-                                   CGM.getNSConcreteGlobalBlock()->getType()),
-                               QualType(CGM.getContext().VoidPtrTy)));
+  fields.add((!CGM.getContext().getLangOpts().OpenCL)
+                 ? CGM.getNSConcreteGlobalBlock()
+                 : CGM.getNullPointer(CGM.VoidPtrPtrTy,
+                                      CGM.getContext().getPointerType(QualType(
+                                          CGM.getContext().VoidPtrTy))));

  // __flags
  BlockFlags flags = BLOCK_IS_GLOBAL | BLOCK_HAS_SIGNATURE;
--- a/clang/lib/CodeGen/CGDecl.cpp
+++ b/clang/lib/CodeGen/CGDecl.cpp
@@ -221,8 +221,8 @@ llvm::Constant *CodeGenModule::getOrCreateStaticVarDecl(
    Name = getStaticDeclName(*this, D);

  llvm::Type *LTy = getTypes().ConvertTypeForMem(Ty);
-  unsigned AddrSpace =
-      GetGlobalVarAddressSpace(&D, getContext().getTargetAddressSpace(Ty));
+  unsigned AS = GetGlobalVarAddressSpace(&D);
+  unsigned TargetAS = getContext().getTargetAddressSpace(AS);

  // Local address space cannot have an initializer.
  llvm::Constant *Init = nullptr;
@@ -231,12 +231,9 @@ llvm::Constant *CodeGenModule::getOrCreateStaticVarDecl(
  else
    Init = llvm::UndefValue::get(LTy);

-  llvm::GlobalVariable *GV =
-    new llvm::GlobalVariable(getModule(), LTy,
-                             Ty.isConstant(getContext()), Linkage,
-                             Init, Name, nullptr,
-                             llvm::GlobalVariable::NotThreadLocal,
-                             AddrSpace);
+  llvm::GlobalVariable *GV = new llvm::GlobalVariable(
+      getModule(), LTy, Ty.isConstant(getContext()), Linkage, Init, Name,
+      nullptr, llvm::GlobalVariable::NotThreadLocal, TargetAS);
  GV->setAlignment(getContext().getDeclAlign(&D).getQuantity());
  setGlobalVisibility(GV, &D);

@@ -254,11 +251,12 @@ llvm::Constant *CodeGenModule::getOrCreateStaticVarDecl(
  }

  // Make sure the result is of the correct type.
-  unsigned ExpectedAddrSpace = getContext().getTargetAddressSpace(Ty);
+  unsigned ExpectedAS = Ty.getAddressSpace();
  llvm::Constant *Addr = GV;
-  if (AddrSpace != ExpectedAddrSpace) {
-    llvm::PointerType *PTy = llvm::PointerType::get(LTy, ExpectedAddrSpace);
-    Addr = llvm::ConstantExpr::getAddrSpaceCast(GV, PTy);
+  if (AS != ExpectedAS) {
+    Addr = getTargetCodeGenInfo().performAddrSpaceCast(
+        *this, GV, AS, ExpectedAS,
+        LTy->getPointerTo(getContext().getTargetAddressSpace(ExpectedAS)));
  }

  setStaticLocalDeclAddress(&D, Addr);
--- a/clang/lib/CodeGen/CGExpr.cpp
+++ b/clang/lib/CodeGen/CGExpr.cpp
@@ -338,9 +338,10 @@ pushTemporaryCleanup(CodeGenFunction &CGF, const MaterializeTemporaryExpr *M,
  }
 }

-static Address
-createReferenceTemporary(CodeGenFunction &CGF,
-                         const MaterializeTemporaryExpr *M, const Expr *Inner) {
+static Address createReferenceTemporary(CodeGenFunction &CGF,
+                                        const MaterializeTemporaryExpr *M,
+                                        const Expr *Inner) {
+  auto &TCG = CGF.getTargetHooks();
  switch (M->getStorageDuration()) {
  case SD_FullExpression:
  case SD_Automatic: {
@@ -353,13 +354,24 @@ createReferenceTemporary(CodeGenFunction &CGF,
        (Ty->isArrayType() || Ty->isRecordType()) &&
        CGF.CGM.isTypeConstant(Ty, true))
      if (llvm::Constant *Init = CGF.CGM.EmitConstantExpr(Inner, Ty, &CGF)) {
-        auto *GV = new llvm::GlobalVariable(
-            CGF.CGM.getModule(), Init->getType(), /*isConstant=*/true,
-            llvm::GlobalValue::PrivateLinkage, Init, ".ref.tmp");
-        CharUnits alignment = CGF.getContext().getTypeAlignInChars(Ty);
-        GV->setAlignment(alignment.getQuantity());
-        // FIXME: Should we put the new global into a COMDAT?
-        return Address(GV, alignment);
+        if (auto AddrSpace = CGF.getTarget().getConstantAddressSpace()) {
+          auto AS = AddrSpace.getValue();
+          auto *GV = new llvm::GlobalVariable(
+              CGF.CGM.getModule(), Init->getType(), /*isConstant=*/true,
+              llvm::GlobalValue::PrivateLinkage, Init, ".ref.tmp", nullptr,
+              llvm::GlobalValue::NotThreadLocal,
+              CGF.getContext().getTargetAddressSpace(AS));
+          CharUnits alignment = CGF.getContext().getTypeAlignInChars(Ty);
+          GV->setAlignment(alignment.getQuantity());
+          llvm::Constant *C = GV;
+          if (AS != LangAS::Default)
+            C = TCG.performAddrSpaceCast(
+                CGF.CGM, GV, AS, LangAS::Default,
+                GV->getValueType()->getPointerTo(
+                    CGF.getContext().getTargetAddressSpace(LangAS::Default)));
+          // FIXME: Should we put the new global into a COMDAT?
+          return Address(C, alignment);
+        }
      }
    return CGF.CreateMemTemp(Ty, "ref.tmp");
  }
@@ -440,9 +452,11 @@ EmitMaterializeTemporaryExpr(const MaterializeTemporaryExpr *M) {

  // Create and initialize the reference temporary.
  Address Object = createReferenceTemporary(*this, M, E);
-  if (auto *Var = dyn_cast<llvm::GlobalVariable>(Object.getPointer())) {
+  if (auto *Var = dyn_cast<llvm::GlobalVariable>(
+          Object.getPointer()->stripPointerCasts())) {
    Object = Address(llvm::ConstantExpr::getBitCast(
-        Var, ConvertTypeForMem(E->getType())->getPointerTo()),
+                         cast<llvm::Constant>(Object.getPointer()),
+                         ConvertTypeForMem(E->getType())->getPointerTo()),
                     Object.getAlignment());
    // If the temporary is a global and has a constant initializer or is a
    // constant temporary that we promoted to a global, we may have already
--- a/clang/lib/CodeGen/CodeGenFunction.h
+++ b/clang/lib/CodeGen/CodeGenFunction.h
@@ -1479,6 +1479,9 @@ public:

  const TargetInfo &getTarget() const { return Target; }
  llvm::LLVMContext &getLLVMContext() { return CGM.getLLVMContext(); }
+  const TargetCodeGenInfo &getTargetHooks() const {
+    return CGM.getTargetCodeGenInfo();
+  }

  //===--------------------------------------------------------------------===//
  //                                  Cleanups
@@ -3820,10 +3823,6 @@ public:
 private:
  QualType getVarArgType(const Expr *Arg);

-  const TargetCodeGenInfo &getTargetHooks() const {
-    return CGM.getTargetCodeGenInfo();
-  }
-
  void EmitDeclMetadata();

  BlockByrefHelpers *buildByrefHelpers(llvm::StructType &byrefType,
--- a/clang/lib/CodeGen/CodeGenModule.cpp
+++ b/clang/lib/CodeGen/CodeGenModule.cpp
@@ -2367,11 +2367,13 @@ CodeGenModule::GetOrCreateLLVMGlobal(StringRef MangledName,
      return llvm::ConstantExpr::getBitCast(Entry, Ty);
  }

-  unsigned AddrSpace = GetGlobalVarAddressSpace(D, Ty->getAddressSpace());
+  auto AddrSpace = GetGlobalVarAddressSpace(D);
+  auto TargetAddrSpace = getContext().getTargetAddressSpace(AddrSpace);
+
  auto *GV = new llvm::GlobalVariable(
      getModule(), Ty->getElementType(), false,
      llvm::GlobalValue::ExternalLinkage, nullptr, MangledName, nullptr,
-      llvm::GlobalVariable::NotThreadLocal, AddrSpace);
+      llvm::GlobalVariable::NotThreadLocal, TargetAddrSpace);

  // If we already created a global with the same mangled name (but different
  // type) before, take its name and remove it from its parent.
@@ -2428,8 +2430,14 @@ CodeGenModule::GetOrCreateLLVMGlobal(StringRef MangledName,
      GV->setSection(".cp.rodata");
  }

-  if (AddrSpace != Ty->getAddressSpace())
-    return llvm::ConstantExpr::getAddrSpaceCast(GV, Ty);
+  auto ExpectedAS =
+      D ? D->getType().getAddressSpace()
+        : (LangOpts.OpenCL ? LangAS::opencl_global : LangAS::Default);
+  auto ExpectedTargetAS = getContext().getTargetAddressSpace(ExpectedAS);
+  assert(ExpectedTargetAS == Ty->getPointerAddressSpace());
+  if (AddrSpace != ExpectedAS)
+    return getTargetCodeGenInfo().performAddrSpaceCast(*this, GV, AddrSpace,
+                                                       ExpectedAS, Ty);

  return GV;
 }
@@ -2563,18 +2571,27 @@ CharUnits CodeGenModule::GetTargetTypeStoreSize(llvm::Type *Ty) const {
      getDataLayout().getTypeStoreSizeInBits(Ty));
 }

-unsigned CodeGenModule::GetGlobalVarAddressSpace(const VarDecl *D,
-                                                 unsigned AddrSpace) {
-  if (D && LangOpts.CUDA && LangOpts.CUDAIsDevice) {
-    if (D->hasAttr<CUDAConstantAttr>())
-      AddrSpace = getContext().getTargetAddressSpace(LangAS::cuda_constant);
-    else if (D->hasAttr<CUDASharedAttr>())
-      AddrSpace = getContext().getTargetAddressSpace(LangAS::cuda_shared);
-    else
-      AddrSpace = getContext().getTargetAddressSpace(LangAS::cuda_device);
+unsigned CodeGenModule::GetGlobalVarAddressSpace(const VarDecl *D) {
+  unsigned AddrSpace;
+  if (LangOpts.OpenCL) {
+    AddrSpace = D ? D->getType().getAddressSpace() : LangAS::opencl_global;
+    assert(AddrSpace == LangAS::opencl_global ||
+           AddrSpace == LangAS::opencl_constant ||
+           AddrSpace == LangAS::opencl_local ||
+           AddrSpace >= LangAS::FirstTargetAddressSpace);
+    return AddrSpace;
  }

-  return AddrSpace;
+  if (LangOpts.CUDA && LangOpts.CUDAIsDevice) {
+    if (D && D->hasAttr<CUDAConstantAttr>())
+      return LangAS::cuda_constant;
+    else if (D && D->hasAttr<CUDASharedAttr>())
+      return LangAS::cuda_shared;
+    else
+      return LangAS::cuda_device;
+  }
+
+  return getTargetCodeGenInfo().getGlobalVarAddressSpace(*this, D);
 }

 template<typename SomeDecl>
@@ -2727,10 +2744,9 @@ void CodeGenModule::EmitGlobalVarDefinition(const VarDecl *D,
  // "extern int x[];") and then a definition of a different type (e.g.
  // "int x[10];"). This also happens when an initializer has a different type
  // from the type of the global (this happens with unions).
-  if (!GV ||
-      GV->getType()->getElementType() != InitType ||
+  if (!GV || GV->getType()->getElementType() != InitType ||
      GV->getType()->getAddressSpace() !=
-       GetGlobalVarAddressSpace(D, getContext().getTargetAddressSpace(ASTTy))) {
+          getContext().getTargetAddressSpace(GetGlobalVarAddressSpace(D))) {

    // Move the old entry aside so that we'll create a new one.
    Entry->setName(StringRef());
@@ -3739,20 +3755,26 @@ ConstantAddress CodeGenModule::GetAddrOfGlobalTemporary(
      Linkage = llvm::GlobalVariable::InternalLinkage;
    }
  }
-  unsigned AddrSpace = GetGlobalVarAddressSpace(
-      VD, getContext().getTargetAddressSpace(MaterializedType));
+  unsigned AddrSpace =
+      VD ? GetGlobalVarAddressSpace(VD) : MaterializedType.getAddressSpace();
+  auto TargetAS = getContext().getTargetAddressSpace(AddrSpace);
  auto *GV = new llvm::GlobalVariable(
      getModule(), Type, Constant, Linkage, InitialValue, Name.c_str(),
-      /*InsertBefore=*/nullptr, llvm::GlobalVariable::NotThreadLocal,
-      AddrSpace);
+      /*InsertBefore=*/nullptr, llvm::GlobalVariable::NotThreadLocal, TargetAS);
  setGlobalVisibility(GV, VD);
  GV->setAlignment(Align.getQuantity());
  if (supportsCOMDAT() && GV->isWeakForLinker())
    GV->setComdat(TheModule.getOrInsertComdat(GV->getName()));
  if (VD->getTLSKind())
    setTLSMode(GV, *VD);
-  MaterializedGlobalTemporaryMap[E] = GV;
-  return ConstantAddress(GV, Align);
+  llvm::Constant *CV = GV;
+  if (AddrSpace != LangAS::Default)
+    CV = getTargetCodeGenInfo().performAddrSpaceCast(
+        *this, GV, AddrSpace, LangAS::Default,
+        Type->getPointerTo(
+            getContext().getTargetAddressSpace(LangAS::Default)));
+  MaterializedGlobalTemporaryMap[E] = CV;
+  return ConstantAddress(CV, Align);
 }

 /// EmitObjCPropertyImplementations - Emit information for synthesized
--- a/clang/lib/CodeGen/CodeGenModule.h
+++ b/clang/lib/CodeGen/CodeGenModule.h
@@ -710,11 +710,15 @@ public:
                                     SourceLocation Loc = SourceLocation(),
                                     bool TLS = false);

-  /// Return the address space of the underlying global variable for D, as
+  /// Return the AST address space of the underlying global variable for D, as
  /// determined by its declaration. Normally this is the same as the address
  /// space of D's type, but in CUDA, address spaces are associated with
-  /// declarations, not types.
-  unsigned GetGlobalVarAddressSpace(const VarDecl *D, unsigned AddrSpace);
+  /// declarations, not types. If D is nullptr, return the default address
+  /// space for global variable.
+  ///
+  /// For languages without explicit address spaces, if D has default address
+  /// space, target-specific global or constant address space may be returned.
+  unsigned GetGlobalVarAddressSpace(const VarDecl *D);

  /// Return the llvm::Constant for the address of the given global variable.
  /// If Ty is non-null and if the global doesn't exist, then it will be created
--- a/clang/lib/CodeGen/TargetInfo.cpp
+++ b/clang/lib/CodeGen/TargetInfo.cpp
@@ -416,14 +416,33 @@ llvm::Constant *TargetCodeGenInfo::getNullPointer(const CodeGen::CodeGenModule &
  return llvm::ConstantPointerNull::get(T);
 }

+unsigned TargetCodeGenInfo::getGlobalVarAddressSpace(CodeGenModule &CGM,
+                                                     const VarDecl *D) const {
+  assert(!CGM.getLangOpts().OpenCL &&
+         !(CGM.getLangOpts().CUDA && CGM.getLangOpts().CUDAIsDevice) &&
+         "Address space agnostic languages only");
+  return D ? D->getType().getAddressSpace() : LangAS::Default;
+}
+
 llvm::Value *TargetCodeGenInfo::performAddrSpaceCast(
    CodeGen::CodeGenFunction &CGF, llvm::Value *Src, unsigned SrcAddr,
    unsigned DestAddr, llvm::Type *DestTy, bool isNonNull) const {
  // Since target may map different address spaces in AST to the same address
  // space, an address space conversion may end up as a bitcast.
+  if (auto *C = dyn_cast<llvm::Constant>(Src))
+    return performAddrSpaceCast(CGF.CGM, C, SrcAddr, DestAddr, DestTy);
  return CGF.Builder.CreatePointerBitCastOrAddrSpaceCast(Src, DestTy);
 }

+llvm::Constant *
+TargetCodeGenInfo::performAddrSpaceCast(CodeGenModule &CGM, llvm::Constant *Src,
+                                        unsigned SrcAddr, unsigned DestAddr,
+                                        llvm::Type *DestTy) const {
+  // Since target may map different address spaces in AST to the same address
+  // space, an address space conversion may end up as a bitcast.
+  return llvm::ConstantExpr::getPointerCast(Src, DestTy);
+}
+
 static bool isEmptyRecord(ASTContext &Context, QualType T, bool AllowArrays);

 /// isEmptyField - Return true iff a the field is "empty", that is it
@@ -7325,6 +7344,8 @@ public:
    return LangAS::FirstTargetAddressSpace +
           getABIInfo().getDataLayout().getAllocaAddrSpace();
  }
+  unsigned getGlobalVarAddressSpace(CodeGenModule &CGM,
+                                    const VarDecl *D) const override;
 };
 }

@@ -7408,6 +7429,31 @@ llvm::Constant *AMDGPUTargetCodeGenInfo::getNullPointer(
      llvm::ConstantPointerNull::get(NPT), PT);
 }

+unsigned
+AMDGPUTargetCodeGenInfo::getGlobalVarAddressSpace(CodeGenModule &CGM,
+                                                  const VarDecl *D) const {
+  assert(!CGM.getLangOpts().OpenCL &&
+         !(CGM.getLangOpts().CUDA && CGM.getLangOpts().CUDAIsDevice) &&
+         "Address space agnostic languages only");
+  unsigned DefaultGlobalAS =
+      LangAS::FirstTargetAddressSpace +
+      CGM.getContext().getTargetAddressSpace(LangAS::opencl_global);
+  if (!D)
+    return DefaultGlobalAS;
+
+  unsigned AddrSpace = D->getType().getAddressSpace();
+  assert(AddrSpace == LangAS::Default ||
+         AddrSpace >= LangAS::FirstTargetAddressSpace);
+  if (AddrSpace != LangAS::Default)
+    return AddrSpace;
+
+  if (CGM.isTypeConstant(D->getType(), false)) {
+    if (auto ConstAS = CGM.getTarget().getConstantAddressSpace())
+      return ConstAS.getValue();
+  }
+  return DefaultGlobalAS;
+}
+
 //===----------------------------------------------------------------------===//
 // SPARC v8 ABI Implementation.
 // Based on the SPARC Compliance Definition version 2.4.1.
--- a/clang/lib/CodeGen/TargetInfo.h
+++ b/clang/lib/CodeGen/TargetInfo.h
@@ -229,6 +229,13 @@ public:
  virtual llvm::Constant *getNullPointer(const CodeGen::CodeGenModule &CGM,
      llvm::PointerType *T, QualType QT) const;

+  /// Get target favored AST address space of a global variable for languages
+  /// other than OpenCL and CUDA.
+  /// If \p D is nullptr, returns the default target favored address space
+  /// for global variable.
+  virtual unsigned getGlobalVarAddressSpace(CodeGenModule &CGM,
+                                            const VarDecl *D) const;
+
  /// Get the AST address space for alloca.
  virtual unsigned getASTAllocaAddressSpace() const { return LangAS::Default; }

@@ -243,6 +250,15 @@ public:
                                            unsigned DestAddr,
                                            llvm::Type *DestTy,
                                            bool IsNonNull = false) const;
+
+  /// Perform address space cast of a constant expression of pointer type.
+  /// \param V is the LLVM constant to be casted to another address space.
+  /// \param SrcAddr is the language address space of \p V.
+  /// \param DestAddr is the targeted language address space.
+  /// \param DestTy is the destination LLVM pointer type.
+  virtual llvm::Constant *
+  performAddrSpaceCast(CodeGenModule &CGM, llvm::Constant *V, unsigned SrcAddr,
+                       unsigned DestAddr, llvm::Type *DestTy) const;
 };

 } // namespace CodeGen
--- a/clang/test/CodeGen/address-space.c
+++ b/clang/test/CodeGen/address-space.c
@@ -24,11 +24,13 @@ int test2(int i) { return ban[i]; }
 __attribute__((address_space(2))) int *A, *B;

 // CHECK-LABEL: define void @test3()
-// GIZ: load i32 addrspace(2)*, i32 addrspace(2)** @B
-// PIZ: load i32 addrspace(2)*, i32 addrspace(2)* addrspace(4)* @B
+// X86: load i32 addrspace(2)*, i32 addrspace(2)** @B
+// AMDGIZ: load i32 addrspace(2)*, i32 addrspace(2)** addrspacecast (i32 addrspace(2)* addrspace(1)* @B to i32 addrspace(2)**)
+// PIZ: load i32 addrspace(2)*, i32 addrspace(2)* addrspace(4)* addrspacecast (i32 addrspace(2)* addrspace(1)* @B to i32 addrspace(2)* addrspace(4)*)
 // CHECK: load i32, i32 addrspace(2)*
-// GIZ: load i32 addrspace(2)*, i32 addrspace(2)** @A
-// PIZ: load i32 addrspace(2)*, i32 addrspace(2)* addrspace(4)* @A
+// X86: load i32 addrspace(2)*, i32 addrspace(2)** @A
+// AMDGIZ: load i32 addrspace(2)*, i32 addrspace(2)** addrspacecast (i32 addrspace(2)* addrspace(1)* @A to i32 addrspace(2)**)
+// PIZ: load i32 addrspace(2)*, i32 addrspace(2)* addrspace(4)* addrspacecast (i32 addrspace(2)* addrspace(1)* @A to i32 addrspace(2)* addrspace(4)*)
 // CHECK: store i32 {{.*}}, i32 addrspace(2)*
 void test3() {
  *A = *B;
--- a/clang/test/CodeGen/default-address-space.c
+++ b/clang/test/CodeGen/default-address-space.c
@@ -1,24 +1,24 @@
 // RUN: %clang_cc1 -triple amdgcn -emit-llvm < %s | FileCheck -check-prefixes=PIZ,COM %s
 // RUN: %clang_cc1 -triple amdgcn---amdgiz -emit-llvm < %s | FileCheck -check-prefixes=CHECK,COM %s

-// PIZ-DAG: @foo = common addrspace(4) global i32 0
-// CHECK-DAG: @foo = common global i32 0
+// PIZ-DAG: @foo = common addrspace(1) global i32 0
+// CHECK-DAG: @foo = common addrspace(1) global i32 0
 int foo;

-// PIZ-DAG: @ban = common addrspace(4) global [10 x i32] zeroinitializer
-// CHECK-DAG: @ban = common global [10 x i32] zeroinitializer
+// PIZ-DAG: @ban = common addrspace(1) global [10 x i32] zeroinitializer
+// CHECK-DAG: @ban = common addrspace(1) global [10 x i32] zeroinitializer
 int ban[10];

-// PIZ-DAG: @A = common addrspace(4) global i32 addrspace(4)* null
-// PIZ-DAG: @B = common addrspace(4) global i32 addrspace(4)* null
-// CHECK-DAG: @A = common global i32* null
-// CHECK-DAG: @B = common global i32* null
+// PIZ-DAG: @A = common addrspace(1) global i32 addrspace(4)* null
+// PIZ-DAG: @B = common addrspace(1) global i32 addrspace(4)* null
+// CHECK-DAG: @A = common addrspace(1) global i32* null
+// CHECK-DAG: @B = common addrspace(1) global i32* null
 int *A;
 int *B;

 // COM-LABEL: define i32 @test1()
-// PIZ: load i32, i32 addrspace(4)* @foo
-// CHECK: load i32, i32* @foo
+// PIZ: load i32, i32 addrspace(4)* addrspacecast{{[^@]+}} @foo
+// CHECK: load i32, i32* addrspacecast{{[^@]+}} @foo
 int test1() { return foo; }

 // COM-LABEL: define i32 @test2(i32 %i)
@@ -30,13 +30,13 @@ int test1() { return foo; }
 int test2(int i) { return ban[i]; }

 // COM-LABEL: define void @test3()
-// PIZ: load i32 addrspace(4)*, i32 addrspace(4)* addrspace(4)* @B
+// PIZ: load i32 addrspace(4)*, i32 addrspace(4)* addrspace(4)* addrspacecast{{[^@]+}} @B
 // PIZ: load i32, i32 addrspace(4)*
-// PIZ: load i32 addrspace(4)*, i32 addrspace(4)* addrspace(4)* @A
+// PIZ: load i32 addrspace(4)*, i32 addrspace(4)* addrspace(4)* addrspacecast{{[^@]+}} @A
 // PIZ: store i32 {{.*}}, i32 addrspace(4)*
-// CHECK: load i32*, i32** @B
+// CHECK: load i32*, i32** addrspacecast{{.*}} @B
 // CHECK: load i32, i32*
-// CHECK: load i32*, i32** @A
+// CHECK: load i32*, i32** addrspacecast{{.*}} @A
 // CHECK: store i32 {{.*}}, i32*
 void test3() {
  *A = *B;
--- a/clang/test/CodeGenCXX/cxx0x-initializer-stdinitializerlist.cpp
+++ b/clang/test/CodeGenCXX/cxx0x-initializer-stdinitializerlist.cpp
@@ -1,4 +1,5 @@
-// RUN: %clang_cc1 -std=c++11 -triple x86_64-none-linux-gnu -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -std=c++11 -triple x86_64-none-linux-gnu -emit-llvm -o - %s | FileCheck -check-prefixes=X86,CHECK %s
+// RUN: %clang_cc1 -std=c++11 -triple amdgcn-amd-amdhsa-amdgiz -DNO_TLS -emit-llvm -o - %s | FileCheck -check-prefixes=AMD,CHECK %s

 namespace std {
  typedef decltype(sizeof(int)) size_t;
@@ -46,54 +47,72 @@ struct wantslist1 {
  wantslist1(std::initializer_list<destroyme1>);
  ~wantslist1();
 };
-
-// CHECK: @_ZGR15globalInitList1_ = internal constant [3 x i32] [i32 1, i32 2, i32 3]
-// CHECK: @globalInitList1 = global %{{[^ ]+}} { i32* getelementptr inbounds ([3 x i32], [3 x i32]* @_ZGR15globalInitList1_, i32 0, i32 0), i{{32|64}} 3 }
+// X86: @_ZGR15globalInitList1_ = internal constant [3 x i32] [i32 1, i32 2, i32 3]
+// X86: @globalInitList1 = global %{{[^ ]+}} { i32* getelementptr inbounds ([3 x i32], [3 x i32]* @_ZGR15globalInitList1_, i32 0, i32 0), i{{32|64}} 3 }
+// AMD: @_ZGR15globalInitList1_ = internal addrspace(1) constant [3 x i32] [i32 1, i32 2, i32 3]
+// AMD: @globalInitList1 = addrspace(1) global %{{[^ ]+}} { i32* addrspacecast (i32 addrspace(1)* getelementptr inbounds ([3 x i32], [3 x i32] addrspace(1)* @_ZGR15globalInitList1_, i32 0, i32 0) to i32*), i{{32|64}} 3 }
 std::initializer_list<int> globalInitList1 = {1, 2, 3};

+#ifndef NO_TLS
 namespace thread_local_global_array {
-  // FIXME: We should be able to constant-evaluate this even though the
-  // initializer is not a constant expression (pointers to thread_local
-  // objects aren't really a problem).
-  //
-  // CHECK: @_ZN25thread_local_global_array1xE = thread_local global
-  // CHECK: @_ZGRN25thread_local_global_array1xE_ = internal thread_local constant [4 x i32] [i32 1, i32 2, i32 3, i32 4]
-  std::initializer_list<int> thread_local x = { 1, 2, 3, 4 };
+// FIXME: We should be able to constant-evaluate this even though the
+// initializer is not a constant expression (pointers to thread_local
+// objects aren't really a problem).
+//
+// X86: @_ZN25thread_local_global_array1xE = thread_local global
+// X86: @_ZGRN25thread_local_global_array1xE_ = internal thread_local constant [4 x i32] [i32 1, i32 2, i32 3, i32 4]
+std::initializer_list<int> thread_local x = {1, 2, 3, 4};
 }
+#endif

-// CHECK: @globalInitList2 = global %{{[^ ]+}} zeroinitializer
-// CHECK: @_ZGR15globalInitList2_ = internal global [2 x %[[WITHARG:[^ ]*]]] zeroinitializer
+// X86: @globalInitList2 = global %{{[^ ]+}} zeroinitializer
+// X86: @_ZGR15globalInitList2_ = internal global [2 x %[[WITHARG:[^ ]*]]] zeroinitializer
+// AMD: @globalInitList2 = addrspace(1) global %{{[^ ]+}} zeroinitializer
+// AMD: @_ZGR15globalInitList2_ = internal addrspace(1) global [2 x %[[WITHARG:[^ ]*]]] zeroinitializer

-// CHECK: @_ZN15partly_constant1kE = global i32 0, align 4
-// CHECK: @_ZN15partly_constant2ilE = global {{.*}} null, align 8
-// CHECK: @[[PARTLY_CONSTANT_OUTER:_ZGRN15partly_constant2ilE.*]] = internal global {{.*}} zeroinitializer, align 8
-// CHECK: @[[PARTLY_CONSTANT_INNER:_ZGRN15partly_constant2ilE.*]] = internal global [3 x {{.*}}] zeroinitializer, align 8
-// CHECK: @[[PARTLY_CONSTANT_FIRST:_ZGRN15partly_constant2ilE.*]] = internal constant [3 x i32] [i32 1, i32 2, i32 3], align 4
-// CHECK: @[[PARTLY_CONSTANT_SECOND:_ZGRN15partly_constant2ilE.*]] = internal global [2 x i32] zeroinitializer, align 4
-// CHECK: @[[PARTLY_CONSTANT_THIRD:_ZGRN15partly_constant2ilE.*]] = internal constant [4 x i32] [i32 5, i32 6, i32 7, i32 8], align 4
+// X86: @_ZN15partly_constant1kE = global i32 0, align 4
+// X86: @_ZN15partly_constant2ilE = global {{.*}} null, align 8
+// X86: @[[PARTLY_CONSTANT_OUTER:_ZGRN15partly_constant2ilE.*]] = internal global {{.*}} zeroinitializer, align 8
+// X86: @[[PARTLY_CONSTANT_INNER:_ZGRN15partly_constant2ilE.*]] = internal global [3 x {{.*}}] zeroinitializer, align 8
+// X86: @[[PARTLY_CONSTANT_FIRST:_ZGRN15partly_constant2ilE.*]] = internal constant [3 x i32] [i32 1, i32 2, i32 3], align 4
+// X86: @[[PARTLY_CONSTANT_SECOND:_ZGRN15partly_constant2ilE.*]] = internal global [2 x i32] zeroinitializer, align 4
+// X86: @[[PARTLY_CONSTANT_THIRD:_ZGRN15partly_constant2ilE.*]] = internal constant [4 x i32] [i32 5, i32 6, i32 7, i32 8], align 4
+// AMD: @_ZN15partly_constant1kE = addrspace(1) global i32 0, align 4
+// AMD: @_ZN15partly_constant2ilE = addrspace(2) global {{.*}} null, align 8
+// AMD: @[[PARTLY_CONSTANT_OUTER:_ZGRN15partly_constant2ilE.*]] = internal addrspace(2) global {{.*}} zeroinitializer, align 8
+// AMD: @[[PARTLY_CONSTANT_INNER:_ZGRN15partly_constant2ilE.*]] = internal addrspace(2) global [3 x {{.*}}] zeroinitializer, align 8
+// AMD: @[[PARTLY_CONSTANT_FIRST:_ZGRN15partly_constant2ilE.*]] = internal addrspace(2) constant [3 x i32] [i32 1, i32 2, i32 3], align 4
+// AMD: @[[PARTLY_CONSTANT_SECOND:_ZGRN15partly_constant2ilE.*]] = internal addrspace(2) global [2 x i32] zeroinitializer, align 4
+// AMD: @[[PARTLY_CONSTANT_THIRD:_ZGRN15partly_constant2ilE.*]] = internal addrspace(2) constant [4 x i32] [i32 5, i32 6, i32 7, i32 8], align 4

-// CHECK: @[[REFTMP1:.*]] = private constant [2 x i32] [i32 42, i32 43], align 4
-// CHECK: @[[REFTMP2:.*]] = private constant [3 x %{{.*}}] [%{{.*}} { i32 1 }, %{{.*}} { i32 2 }, %{{.*}} { i32 3 }], align 4
+// X86: @[[REFTMP1:.*]] = private constant [2 x i32] [i32 42, i32 43], align 4
+// X86: @[[REFTMP2:.*]] = private constant [3 x %{{.*}}] [%{{.*}} { i32 1 }, %{{.*}} { i32 2 }, %{{.*}} { i32 3 }], align 4
+// AMD: @[[REFTMP1:.*]] = private addrspace(2) constant [2 x i32] [i32 42, i32 43], align 4
+// AMD: @[[REFTMP2:.*]] = private addrspace(2) constant [3 x %{{.*}}] [%{{.*}} { i32 1 }, %{{.*}} { i32 2 }, %{{.*}} { i32 3 }], align 4

 // CHECK: appending global

-
 // thread_local initializer:
-// CHECK-LABEL: define internal void
-// CHECK: store i32* getelementptr inbounds ([4 x i32], [4 x i32]* @_ZGRN25thread_local_global_array1xE_, i64 0, i64 0),
-// CHECK:       i32** getelementptr inbounds ({{.*}}, {{.*}}* @_ZN25thread_local_global_array1xE, i32 0, i32 0), align 8
-// CHECK: store i64 4, i64* getelementptr inbounds ({{.*}}, {{.*}}* @_ZN25thread_local_global_array1xE, i32 0, i32 1), align 8
+// X86-LABEL: define internal void @__cxx_global_var_init
+// X86: store i32* getelementptr inbounds ([4 x i32], [4 x i32]* @_ZGRN25thread_local_global_array1xE_, i64 0, i64 0),
+// X86:       i32** getelementptr inbounds ({{.*}}, {{.*}}* @_ZN25thread_local_global_array1xE, i32 0, i32 0), align 8
+// X86: store i64 4, i64* getelementptr inbounds ({{.*}}, {{.*}}* @_ZN25thread_local_global_array1xE, i32 0, i32 1), align 8

-
-// CHECK-LABEL: define internal void
-// CHECK: call void @_ZN8witharg1C1ERK10destroyme1(%[[WITHARG]]* getelementptr inbounds ([2 x %[[WITHARG]]], [2 x %[[WITHARG]]]* @_ZGR15globalInitList2_, i{{32|64}} 0, i{{32|64}} 0
-// CHECK: call void @_ZN8witharg1C1ERK10destroyme1(%[[WITHARG]]* getelementptr inbounds ([2 x %[[WITHARG]]], [2 x %[[WITHARG]]]* @_ZGR15globalInitList2_, i{{32|64}} 0, i{{32|64}} 1
-// CHECK: __cxa_atexit
-// CHECK: store %[[WITHARG]]* getelementptr inbounds ([2 x %[[WITHARG]]], [2 x %[[WITHARG]]]* @_ZGR15globalInitList2_, i64 0, i64 0),
-// CHECK:       %[[WITHARG]]** getelementptr inbounds (%{{.*}}, %{{.*}}* @globalInitList2, i32 0, i32 0), align 8
-// CHECK: store i64 2, i64* getelementptr inbounds (%{{.*}}, %{{.*}}* @globalInitList2, i32 0, i32 1), align 8
-// CHECK: call void @_ZN10destroyme1D1Ev
+// CHECK-LABEL: define internal void @__cxx_global_var_init
+// X86: call void @_ZN8witharg1C1ERK10destroyme1(%[[WITHARG]]* getelementptr inbounds ([2 x %[[WITHARG]]], [2 x %[[WITHARG]]]* @_ZGR15globalInitList2_, i{{32|64}} 0, i{{32|64}} 0
+// X86: call void @_ZN8witharg1C1ERK10destroyme1(%[[WITHARG]]* getelementptr inbounds ([2 x %[[WITHARG]]], [2 x %[[WITHARG]]]* @_ZGR15globalInitList2_, i{{32|64}} 0, i{{32|64}} 1
+// AMD: call void @_ZN8witharg1C1ERK10destroyme1(%[[WITHARG]]* getelementptr inbounds ([2 x %[[WITHARG]]], [2 x %[[WITHARG]]]* addrspacecast ({{[^@]+}} @_ZGR15globalInitList2_ {{[^)]+}}), i{{32|64}} 0, i{{32|64}} 0
+// AMD: call void @_ZN8witharg1C1ERK10destroyme1(%[[WITHARG]]* getelementptr inbounds ([2 x %[[WITHARG]]], [2 x %[[WITHARG]]]* addrspacecast ({{[^@]+}} @_ZGR15globalInitList2_ {{[^)]+}}), i{{32|64}} 0, i{{32|64}} 1
+// CHECK: call i32 @__cxa_atexit
+// X86: store %[[WITHARG]]* getelementptr inbounds ([2 x %[[WITHARG]]], [2 x %[[WITHARG]]]* @_ZGR15globalInitList2_, i64 0, i64 0),
+// X86:       %[[WITHARG]]** getelementptr inbounds (%{{.*}}, %{{.*}}* @globalInitList2, i32 0, i32 0), align 8
+// X86: store i64 2, i64* getelementptr inbounds (%{{.*}}, %{{.*}}* @globalInitList2, i32 0, i32 1), align 8
+// AMD: store %[[WITHARG]]* getelementptr inbounds ([2 x %[[WITHARG]]], [2 x %[[WITHARG]]]* addrspacecast ({{[^@]+}} @_ZGR15globalInitList2_ {{[^)]+}}), i64 0, i64 0),
+// AMD:       %[[WITHARG]]** getelementptr inbounds (%{{.*}}, %{{.*}}* addrspacecast ({{[^@]+}} @globalInitList2 {{[^)]+}}), i32 0, i32 0), align 8
+// AMD: store i64 2, i64* getelementptr inbounds (%{{.*}}, %{{.*}}* addrspacecast ({{[^@]+}} @globalInitList2 {{[^)]+}}), i32 0, i32 1), align 8
 // CHECK: call void @_ZN10destroyme1D1Ev
+// CHECK-NEXT: call void @_ZN10destroyme1D1Ev
+// CHECK-NEXT: ret void
 std::initializer_list<witharg1> globalInitList2 = {
  witharg1(destroyme1()), witharg1(destroyme1())
 };
@@ -101,7 +120,9 @@ std::initializer_list<witharg1> globalInitList2 = {
 void fn1(int i) {
  // CHECK-LABEL: define void @_Z3fn1i
  // temporary array
-  // CHECK: [[array:%[^ ]+]] = alloca [3 x i32]
+  // X86: [[array:%[^ ]+]] = alloca [3 x i32]
+  // AMD: [[alloca:%[^ ]+]] = alloca [3 x i32], align 4, addrspace(5)
+  // AMD: [[array:%[^ ]+]] = addrspacecast [3 x i32] addrspace(5)* [[alloca]] to [3 x i32]*
  // CHECK: getelementptr inbounds [3 x i32], [3 x i32]* [[array]], i{{32|64}} 0
  // CHECK-NEXT: store i32 1, i32*
  // CHECK-NEXT: getelementptr
@@ -175,7 +196,6 @@ void fn6() {
  destroyme2 dm2;
  // CHECK: call void @_ZN10destroyme2D1Ev
 }
-
 void fn7() {
  // CHECK-LABEL: define void @_Z3fn7v
  // temps should be destroyed before dm2
@@ -366,37 +386,36 @@ namespace partly_constant {
  std::initializer_list<std::initializer_list<int>> &&il = { { 1, 2, 3 }, { 4, k }, { 5, 6, 7, 8 } };
  // First init list.
  // CHECK-NOT: @[[PARTLY_CONSTANT_FIRST]],
-  // CHECK: store i32* getelementptr inbounds ({{.*}}, {{.*}}* @[[PARTLY_CONSTANT_FIRST]], i64 0, i64 0),
-  // CHECK:       i32** getelementptr inbounds ({{.*}}, {{.*}}* @[[PARTLY_CONSTANT_INNER]], i64 0, i64 0, i32 0)
-  // CHECK: store i64 3, i64* getelementptr inbounds ({{.*}}, {{.*}}* @[[PARTLY_CONSTANT_INNER]], i64 0, i64 0, i32 1)
+  // CHECK: store i32* getelementptr inbounds ({{.*}}, {{.*}}* {{.*}}@[[PARTLY_CONSTANT_FIRST]]{{.*}}, i64 0, i64 0),
+  // CHECK:       i32** getelementptr inbounds ({{.*}}, {{.*}}* {{.*}}@[[PARTLY_CONSTANT_INNER]]{{.*}}, i64 0, i64 0, i32 0)
+  // CHECK: store i64 3, i64* getelementptr inbounds ({{.*}}, {{.*}}* {{.*}}@[[PARTLY_CONSTANT_INNER]]{{.*}}, i64 0, i64 0, i32 1)
  // CHECK-NOT: @[[PARTLY_CONSTANT_FIRST]],
  //
  // Second init list array (non-constant).
-  // CHECK: store i32 4, i32* getelementptr inbounds ({{.*}}, {{.*}}* @[[PARTLY_CONSTANT_SECOND]], i64 0, i64 0)
-  // CHECK: load i32, i32* @_ZN15partly_constant1kE
-  // CHECK: store i32 {{.*}}, i32* getelementptr inbounds ({{.*}}, {{.*}}* @[[PARTLY_CONSTANT_SECOND]], i64 0, i64 1)
+  // CHECK: store i32 4, i32* getelementptr inbounds ({{.*}}, {{.*}}* {{.*}}@[[PARTLY_CONSTANT_SECOND]]{{.*}}, i64 0, i64 0)
+  // CHECK: load i32, i32* {{.*}}@_ZN15partly_constant1kE
+  // CHECK: store i32 {{.*}}, i32* getelementptr inbounds ({{.*}}, {{.*}}* {{.*}}@[[PARTLY_CONSTANT_SECOND]]{{.*}}, i64 0, i64 1)
  //
  // Second init list.
-  // CHECK: store i32* getelementptr inbounds ({{.*}}, {{.*}}* @[[PARTLY_CONSTANT_SECOND]], i64 0, i64 0),
-  // CHECK:       i32** getelementptr inbounds ({{.*}}, {{.*}}* @[[PARTLY_CONSTANT_INNER]], i64 0, i64 1, i32 0)
-  // CHECK: store i64 2, i64* getelementptr inbounds ({{.*}}, {{.*}}* @[[PARTLY_CONSTANT_INNER]], i64 0, i64 1, i32 1)
+  // CHECK: store i32* getelementptr inbounds ({{.*}}, {{.*}}* {{.*}}@[[PARTLY_CONSTANT_SECOND]]{{.*}}, i64 0, i64 0),
+  // CHECK:       i32** getelementptr inbounds ({{.*}}, {{.*}}* {{.*}}@[[PARTLY_CONSTANT_INNER]]{{.*}}, i64 0, i64 1, i32 0)
+  // CHECK: store i64 2, i64* getelementptr inbounds ({{.*}}, {{.*}}* {{.*}}@[[PARTLY_CONSTANT_INNER]]{{.*}}, i64 0, i64 1, i32 1)
  //
  // Third init list.
  // CHECK-NOT: @[[PARTLY_CONSTANT_THIRD]],
-  // CHECK: store i32* getelementptr inbounds ({{.*}}, {{.*}}* @[[PARTLY_CONSTANT_THIRD]], i64 0, i64 0),
-  // CHECK:       i32** getelementptr inbounds ({{.*}}, {{.*}}* @[[PARTLY_CONSTANT_INNER]], i64 0, i64 2, i32 0)
-  // CHECK: store i64 4, i64* getelementptr inbounds ({{.*}}, {{.*}}* @_ZGRN15partly_constant2ilE4_, i64 0, i64 2, i32 1)
+  // CHECK: store i32* getelementptr inbounds ({{.*}}, {{.*}}* {{.*}}@[[PARTLY_CONSTANT_THIRD]]{{.*}}, i64 0, i64 0),
+  // CHECK:       i32** getelementptr inbounds ({{.*}}, {{.*}}* {{.*}}@[[PARTLY_CONSTANT_INNER]]{{.*}}, i64 0, i64 2, i32 0)
+  // CHECK: store i64 4, i64* getelementptr inbounds ({{.*}}, {{.*}}* {{.*}}@_ZGRN15partly_constant2ilE4_{{.*}}, i64 0, i64 2, i32 1)
  // CHECK-NOT: @[[PARTLY_CONSTANT_THIRD]],
  //
  // Outer init list.
-  // CHECK: store {{.*}}* getelementptr inbounds ({{.*}}, {{.*}}* @[[PARTLY_CONSTANT_INNER]], i64 0, i64 0),
-  // CHECK:       {{.*}}** getelementptr inbounds ({{.*}}, {{.*}}* @[[PARTLY_CONSTANT_OUTER]], i32 0, i32 0)
-  // CHECK: store i64 3, i64* getelementptr inbounds ({{.*}}, {{.*}}* @[[PARTLY_CONSTANT_OUTER]], i32 0, i32 1)
+  // CHECK: store {{.*}}* getelementptr inbounds ({{.*}}, {{.*}}* {{.*}}@[[PARTLY_CONSTANT_INNER]]{{.*}}, i64 0, i64 0),
+  // CHECK:       {{.*}}** getelementptr inbounds ({{.*}}, {{.*}}* {{.*}}@[[PARTLY_CONSTANT_OUTER]]{{.*}}, i32 0, i32 0)
+  // CHECK: store i64 3, i64* getelementptr inbounds ({{.*}}, {{.*}}* {{.*}}@[[PARTLY_CONSTANT_OUTER]]{{.*}}, i32 0, i32 1)
  //
  // 'il' reference.
-  // CHECK: store {{.*}}* @[[PARTLY_CONSTANT_OUTER]], {{.*}}** @_ZN15partly_constant2ilE, align 8
+  // CHECK: store {{.*}}* {{.*}}@[[PARTLY_CONSTANT_OUTER]]{{.*}}, {{.*}}** {{.*}}@_ZN15partly_constant2ilE{{.*}}, align 8
 }
-
 namespace nested {
  struct A { A(); ~A(); };
  struct B { const A &a; ~B(); };
@@ -463,7 +482,7 @@ namespace PR20445 {
  template<int x> void f() { new MyClass({42, 43}); }
  template void f<0>();
  // CHECK-LABEL: define {{.*}} @_ZN7PR204451fILi0EEEvv(
-  // CHECK: store i32* getelementptr inbounds ([2 x i32], [2 x i32]* @[[REFTMP1]], i64 0, i64 0)
+  // CHECK: store i32* getelementptr inbounds ([2 x i32], [2 x i32]* {{.*}}@[[REFTMP1]]{{.*}}, i64 0, i64 0)
  // CHECK: call void @_ZN7PR204456vectorC1ESt16initializer_listIiE(
  // CHECK: call void @_ZN7PR204457MyClassC1ERKNS_6vectorE(
 }
@@ -476,9 +495,9 @@ namespace ConstExpr {
  };
  void f(std::initializer_list<C>);
  void g() {
-// CHECK-LABEL: _ZN9ConstExpr1gEv
-// CHECK: store %"class.ConstExpr::C"* getelementptr inbounds ([3 x %"class.ConstExpr::C"], [3 x %"class.ConstExpr::C"]* @[[REFTMP2]], i64 0, i64 0)
-// CHECK: call void @_ZN9ConstExpr1fESt16initializer_listINS_1CEE
+    // CHECK-LABEL: _ZN9ConstExpr1gEv
+    // CHECK: store %"class.ConstExpr::C"* getelementptr inbounds ([3 x %"class.ConstExpr::C"], [3 x %"class.ConstExpr::C"]* {{.*}}@[[REFTMP2]]{{.*}}, i64 0, i64 0)
+    // CHECK: call void @_ZN9ConstExpr1fESt16initializer_listINS_1CEE
    f({C(1), C(2), C(3)});
  }
 }
@@ -498,11 +517,13 @@ namespace B19773010 {
  void f1() {
    // CHECK-LABEL: @_ZN9B197730102f1Ev
    testcase a{{"", ENUM_CONSTANT}};
-    // CHECK: store %"struct.B19773010::pair"* getelementptr inbounds ([1 x %"struct.B19773010::pair"], [1 x %"struct.B19773010::pair"]* bitcast ([1 x { i8*, i32 }]* @.ref.tmp{{.*}} to [1 x %"struct.B19773010::pair"]*), i64 0, i64 0), %"struct.B19773010::pair"** %{{.*}}, align 8
+    // X86: store %"struct.B19773010::pair"* getelementptr inbounds ([1 x %"struct.B19773010::pair"], [1 x %"struct.B19773010::pair"]* bitcast ([1 x { i8*, i32 }]* @.ref.tmp{{.*}} to [1 x %"struct.B19773010::pair"]*), i64 0, i64 0), %"struct.B19773010::pair"** %{{.*}}, align 8
+    // AMD: store %"struct.B19773010::pair"* getelementptr inbounds ([1 x %"struct.B19773010::pair"], [1 x %"struct.B19773010::pair"]* addrspacecast{{.*}} bitcast ([1 x { i8*, i32 }] addrspace(2)* @.ref.tmp{{.*}} to [1 x %"struct.B19773010::pair"] addrspace(2)*){{.*}}, i64 0, i64 0), %"struct.B19773010::pair"** %{{.*}}, align 8
  }
  void f2() {
    // CHECK-LABEL: @_ZN9B197730102f2Ev
-    // CHECK: store %"struct.B19773010::pair"* getelementptr inbounds ([1 x %"struct.B19773010::pair"], [1 x %"struct.B19773010::pair"]* bitcast ([1 x { i8*, i32 }]* @_ZGRZN9B197730102f2EvE1p_ to [1 x %"struct.B19773010::pair"]*), i64 0, i64 0), %"struct.B19773010::pair"** getelementptr inbounds ([2 x %"class.std::initializer_list.10"], [2 x %"class.std::initializer_list.10"]* @_ZZN9B197730102f2EvE1p, i64 0, i64 1, i32 0), align 16
+    // X86: store %"struct.B19773010::pair"* getelementptr inbounds ([1 x %"struct.B19773010::pair"], [1 x %"struct.B19773010::pair"]* bitcast ([1 x { i8*, i32 }]* @_ZGRZN9B197730102f2EvE1p_ to [1 x %"struct.B19773010::pair"]*), i64 0, i64 0), %"struct.B19773010::pair"** getelementptr inbounds ([2 x %"class.std::initializer_list.10"], [2 x %"class.std::initializer_list.10"]* @_ZZN9B197730102f2EvE1p, i64 0, i64 1, i32 0), align 16
+    // AMD: store %"struct.B19773010::pair"* getelementptr inbounds ([1 x %"struct.B19773010::pair"], [1 x %"struct.B19773010::pair"]* addrspacecast{{.*}} bitcast ([1 x { i8*, i32 }] addrspace(1)* @_ZGRZN9B197730102f2EvE1p_ to [1 x %"struct.B19773010::pair"] addrspace(1)*){{.*}}, i64 0, i64 0), %"struct.B19773010::pair"** getelementptr inbounds ([2 x %"class.std::initializer_list.10"], [2 x %"class.std::initializer_list.10"]* addrspacecast{{.*}}@_ZZN9B197730102f2EvE1p{{.*}}, i64 0, i64 1, i32 0), align 8
    static std::initializer_list<pair<const char *, E>> a, p[2] =
        {a, {{"", ENUM_CONSTANT}}};
  }