Index: lib/CodeGen/CGDeclCXX.cpp
===================================================================
--- lib/CodeGen/CGDeclCXX.cpp
+++ lib/CodeGen/CGDeclCXX.cpp
@@ -14,6 +14,7 @@
 #include "CGCXXABI.h"
 #include "CGObjCRuntime.h"
 #include "CGOpenMPRuntime.h"
+#include "TargetInfo.h"
 #include "clang/Basic/CodeGenOptions.h"
 #include "llvm/ADT/StringExtras.h"
 #include "llvm/IR/Intrinsics.h"
@@ -118,9 +119,21 @@
     CXXDestructorDecl *Dtor = Record->getDestructor();
 
     Func = CGM.getAddrAndTypeOfCXXStructor(GlobalDecl(Dtor, Dtor_Complete));
-    Argument = llvm::ConstantExpr::getBitCast(
-        Addr.getPointer(), CGF.getTypes().ConvertType(Type)->getPointerTo());
-
+    if (CGF.getContext().getLangOpts().OpenCL) {
+      auto DestAS =
+          CGM.getTargetCodeGenInfo().getAddrSpaceOfCxaAtexitPtrParam();
+      auto DestTy = CGF.getTypes().ConvertType(Type)->getPointerTo(
+          CGM.getContext().getTargetAddressSpace(DestAS));
+      auto SrcAS = D.getType().getQualifiers().getAddressSpace();
+      if (DestAS == SrcAS)
+        Argument = llvm::ConstantExpr::getBitCast(Addr.getPointer(), DestTy);
+      else
+        Argument = CGM.getTargetCodeGenInfo().performAddrSpaceCast(
+            CGM, Addr.getPointer(), SrcAS, LangAS::opencl_global, DestTy);
+    } else {
+      Argument = llvm::ConstantExpr::getBitCast(
+          Addr.getPointer(), CGF.getTypes().ConvertType(Type)->getPointerTo());
+    }
   // Otherwise, the standard logic requires a helper function.
   } else {
     Func = CodeGenFunction(CGM)
Index: lib/CodeGen/CodeGenModule.cpp
===================================================================
--- lib/CodeGen/CodeGenModule.cpp
+++ lib/CodeGen/CodeGenModule.cpp
@@ -3577,8 +3577,12 @@
 llvm::Constant *
 CodeGenModule::CreateRuntimeVariable(llvm::Type *Ty,
                                      StringRef Name) {
-  auto *Ret =
-      GetOrCreateLLVMGlobal(Name, llvm::PointerType::getUnqual(Ty), nullptr);
+  auto PtrTy =
+      getContext().getLangOpts().OpenCL
+          ? llvm::PointerType::get(
+                Ty, getContext().getTargetAddressSpace(LangAS::opencl_global))
+          : llvm::PointerType::getUnqual(Ty);
+  auto *Ret = GetOrCreateLLVMGlobal(Name, PtrTy, nullptr);
   setDSOLocal(cast<llvm::GlobalValue>(Ret->stripPointerCasts()));
   return Ret;
 }
Index: lib/CodeGen/ItaniumCXXABI.cpp
===================================================================
--- lib/CodeGen/ItaniumCXXABI.cpp
+++ lib/CodeGen/ItaniumCXXABI.cpp
@@ -2284,8 +2284,19 @@
   llvm::Type *dtorTy =
     llvm::FunctionType::get(CGF.VoidTy, CGF.Int8PtrTy, false)->getPointerTo();
 
+  // Preserve address space of addr.
+  auto AddrAS = addr ? addr->getType()->getPointerAddressSpace() : 0;
+  auto AddrInt8PtrTy =
+      AddrAS ? CGF.Int8Ty->getPointerTo(AddrAS) : CGF.Int8PtrTy;
+
+  // Create a variable that binds the atexit to this shared object.
+  llvm::Constant *handle =
+      CGF.CGM.CreateRuntimeVariable(CGF.Int8Ty, "__dso_handle");
+  auto *GV = cast<llvm::GlobalValue>(handle->stripPointerCasts());
+  GV->setVisibility(llvm::GlobalValue::HiddenVisibility);
+
   // extern "C" int __cxa_atexit(void (*f)(void *), void *p, void *d);
-  llvm::Type *paramTys[] = { dtorTy, CGF.Int8PtrTy, CGF.Int8PtrTy };
+  llvm::Type *paramTys[] = {dtorTy, AddrInt8PtrTy, handle->getType()};
   llvm::FunctionType *atexitTy =
     llvm::FunctionType::get(CGF.IntTy, paramTys, false);
 
@@ -2294,12 +2305,6 @@
   if (llvm::Function *fn = dyn_cast<llvm::Function>(atexit.getCallee()))
     fn->setDoesNotThrow();
 
-  // Create a variable that binds the atexit to this shared object.
-  llvm::Constant *handle =
-      CGF.CGM.CreateRuntimeVariable(CGF.Int8Ty, "__dso_handle");
-  auto *GV = cast<llvm::GlobalValue>(handle->stripPointerCasts());
-  GV->setVisibility(llvm::GlobalValue::HiddenVisibility);
-
   if (!addr)
     // addr is null when we are trying to register a dtor annotated with
     // __attribute__((destructor)) in a constructor function. Using null here is
@@ -2309,7 +2314,7 @@
 
   llvm::Value *args[] = {llvm::ConstantExpr::getBitCast(
                              cast<llvm::Constant>(dtor.getCallee()), dtorTy),
-                         llvm::ConstantExpr::getBitCast(addr, CGF.Int8PtrTy),
+                         llvm::ConstantExpr::getBitCast(addr, AddrInt8PtrTy),
                          handle};
   CGF.EmitNounwindRuntimeCall(atexit, args);
 }
Index: lib/CodeGen/TargetInfo.h
===================================================================
--- lib/CodeGen/TargetInfo.h
+++ lib/CodeGen/TargetInfo.h
@@ -267,6 +267,11 @@
                                                LangAS SrcAddr, LangAS DestAddr,
                                                llvm::Type *DestTy) const;
 
+  /// Get address space of pointer parameter for __cxa_atexit.
+  virtual LangAS getAddrSpaceOfCxaAtexitPtrParam() const {
+    return LangAS::Default;
+  }
+
   /// Get the syncscope used in LLVM IR.
   virtual llvm::SyncScope::ID getLLVMSyncScopeID(const LangOptions &LangOpts,
                                                  SyncScope Scope,
Index: test/CodeGenOpenCLCXX/atexit.cl
===================================================================
--- /dev/null
+++ test/CodeGenOpenCLCXX/atexit.cl
@@ -0,0 +1,11 @@
+//RUN: %clang_cc1 %s -triple spir -cl-std=c++ -emit-llvm -O0 -o - | FileCheck %s
+
+struct S {
+  ~S(){};
+};
+S s;
+
+//CHECK-LABEL: define internal void @__cxx_global_var_init()
+//CHECK: call i32 @__cxa_atexit(void (i8*)* bitcast (void (%struct.S addrspace(4)*)* @_ZNU3AS41SD1Ev to void (i8*)*), i8* addrspacecast (i8 addrspace(1)* getelementptr inbounds (%struct.S, %struct.S addrspace(1)* @s, i32 0, i32 0) to i8*), i8 addrspace(1)* @__dso_handle)
+
+//CHECK: declare i32 @__cxa_atexit(void (i8*)*, i8*, i8 addrspace(1)*)