Index: cfe/trunk/lib/CodeGen/CGCUDANV.cpp
===================================================================
--- cfe/trunk/lib/CodeGen/CGCUDANV.cpp
+++ cfe/trunk/lib/CodeGen/CGCUDANV.cpp
@@ -132,6 +132,8 @@
   llvm::Function *makeModuleCtorFunction() override;
   /// Creates module destructor function
   llvm::Function *makeModuleDtorFunction() override;
+  /// Construct and return the stub name of a kernel.
+  std::string getDeviceStubName(llvm::StringRef Name) const override;
 };
 
 }
@@ -217,10 +219,20 @@
 
 void CGNVCUDARuntime::emitDeviceStub(CodeGenFunction &CGF,
                                      FunctionArgList &Args) {
-  assert(getDeviceSideName(CGF.CurFuncDecl) == CGF.CurFn->getName() ||
-         getDeviceSideName(CGF.CurFuncDecl) + ".stub" == CGF.CurFn->getName() ||
-         CGF.CGM.getContext().getTargetInfo().getCXXABI() !=
-             CGF.CGM.getContext().getAuxTargetInfo()->getCXXABI());
+  // Ensure either we have different ABIs between host and device compilations,
+  // says host compilation following MSVC ABI but device compilation follows
+  // Itanium C++ ABI or, if they follow the same ABI, kernel names after
+  // mangling should be the same after name stubbing. The later checking is
+  // very important as the device kernel name being mangled in host-compilation
+  // is used to resolve the device binaries to be executed. Inconsistent naming
+  // result in undefined behavior. Even though we cannot check that naming
+  // directly between host- and device-compilations, the host- and
+  // device-mangling in host compilation could help catching certain ones.
+  assert((CGF.CGM.getContext().getAuxTargetInfo() &&
+          (CGF.CGM.getContext().getAuxTargetInfo()->getCXXABI() !=
+           CGF.CGM.getContext().getTargetInfo().getCXXABI())) ||
+         getDeviceStubName(getDeviceSideName(CGF.CurFuncDecl)) ==
+             CGF.CurFn->getName());
 
   EmittedKernels.push_back({CGF.CurFn, CGF.CurFuncDecl});
   if (CudaFeatureEnabled(CGM.getTarget().getSDKVersion(),
@@ -780,6 +792,12 @@
   return ModuleDtorFunc;
 }
 
+std::string CGNVCUDARuntime::getDeviceStubName(llvm::StringRef Name) const {
+  if (!CGM.getLangOpts().HIP)
+    return Name;
+  return std::move((Name + ".stub").str());
+}
+
 CGCUDARuntime *CodeGen::CreateNVCUDARuntime(CodeGenModule &CGM) {
   return new CGNVCUDARuntime(CGM);
 }
Index: cfe/trunk/lib/CodeGen/CGCUDARuntime.h
===================================================================
--- cfe/trunk/lib/CodeGen/CGCUDARuntime.h
+++ cfe/trunk/lib/CodeGen/CGCUDARuntime.h
@@ -15,6 +15,8 @@
 #ifndef LLVM_CLANG_LIB_CODEGEN_CGCUDARUNTIME_H
 #define LLVM_CLANG_LIB_CODEGEN_CGCUDARUNTIME_H
 
+#include "llvm/ADT/StringRef.h"
+
 namespace llvm {
 class Function;
 class GlobalVariable;
@@ -63,6 +65,9 @@
   /// Returns a module cleanup function or nullptr if it's not needed.
   /// Must be called after ModuleCtorFunction
   virtual llvm::Function *makeModuleDtorFunction() = 0;
+
+  /// Construct and return the stub name of a kernel.
+  virtual std::string getDeviceStubName(llvm::StringRef Name) const = 0;
 };
 
 /// Creates an instance of a CUDA runtime class.
Index: cfe/trunk/lib/CodeGen/CodeGenModule.cpp
===================================================================
--- cfe/trunk/lib/CodeGen/CodeGenModule.cpp
+++ cfe/trunk/lib/CodeGen/CodeGenModule.cpp
@@ -1088,13 +1088,11 @@
   const auto *ND = cast<NamedDecl>(GD.getDecl());
   std::string MangledName = getMangledNameImpl(*this, GD, ND);
 
-  // Postfix kernel stub names with .stub to differentiate them from kernel
-  // names in device binaries. This is to facilitate the debugger to find
-  // the correct symbols for kernels in the device binary.
+  // Adjust kernel stub mangling as we may need to be able to differentiate
+  // them from the kernel itself (e.g., for HIP).
   if (auto *FD = dyn_cast<FunctionDecl>(GD.getDecl()))
-    if (getLangOpts().HIP && !getLangOpts().CUDAIsDevice &&
-        FD->hasAttr<CUDAGlobalAttr>())
-      MangledName = MangledName + ".stub";
+    if (!getLangOpts().CUDAIsDevice && FD->hasAttr<CUDAGlobalAttr>())
+      MangledName = getCUDARuntime().getDeviceStubName(MangledName);
 
   auto Result = Manglings.insert(std::make_pair(MangledName, GD));
   return MangledDeclNames[CanonicalGD] = Result.first->first();