Index: clang/lib/Sema/SemaOverload.cpp
===================================================================
--- clang/lib/Sema/SemaOverload.cpp
+++ clang/lib/Sema/SemaOverload.cpp
@@ -9821,8 +9821,10 @@
         llvm::any_of(Candidates, [&](OverloadCandidate *Cand) {
           // Check viable function only.
           return Cand->Viable && Cand->Function &&
-                 S.IdentifyCUDAPreference(Caller, Cand->Function) ==
-                     Sema::CFP_SameSide;
+                 (S.IdentifyCUDAPreference(Caller, Cand->Function) ==
+                      Sema::CFP_SameSide ||
+                  S.IdentifyCUDAPreference(Caller, Cand->Function) ==
+                      Sema::CFP_HostDevice);
         });
     if (ContainsSameSideCandidate) {
       auto IsWrongSideCandidate = [&](OverloadCandidate *Cand) {
Index: clang/test/SemaCUDA/function-overload.cu
===================================================================
--- clang/test/SemaCUDA/function-overload.cu
+++ clang/test/SemaCUDA/function-overload.cu
@@ -331,9 +331,6 @@
 // If we have a mix of HD and H-only or D-only candidates in the overload set,
 // normal C++ overload resolution rules apply first.
 template <typename T> TemplateReturnTy template_vs_hd_function(T arg)
-#ifdef __CUDA_ARCH__
-//expected-note@-2 {{declared here}}
-#endif
 {
   return TemplateReturnTy();
 }
@@ -342,11 +339,13 @@
 }
 
 __host__ __device__ void test_host_device_calls_hd_template() {
-  HostDeviceReturnTy ret1 = template_vs_hd_function(1.0f);
-  TemplateReturnTy ret2 = template_vs_hd_function(1);
 #ifdef __CUDA_ARCH__
-  // expected-error@-2 {{reference to __host__ function 'template_vs_hd_function<int>' in __host__ __device__ function}}
+  typedef HostDeviceReturnTy ExpectedReturnTy;
+#else
+  typedef TemplateReturnTy ExpectedReturnTy;
 #endif
+  HostDeviceReturnTy ret1 = template_vs_hd_function(1.0f);
+  ExpectedReturnTy ret2 = template_vs_hd_function(1);
 }
 
 __host__ void test_host_calls_hd_template() {