diff --git a/clang/lib/Parse/ParseTentative.cpp b/clang/lib/Parse/ParseTentative.cpp
--- a/clang/lib/Parse/ParseTentative.cpp
+++ b/clang/lib/Parse/ParseTentative.cpp
@@ -593,7 +593,8 @@
                  (Tok.is(tok::greatergreater) ||
                   (Tok.is(tok::ellipsis) &&
                    NextToken().isOneOf(tok::greater, tok::greatergreater,
-                                       tok::comma)))))) {
+                                       tok::comma)))) ||
+                (getLangOpts().CUDA && Tok.is(tok::greatergreatergreater)))) {
       TPR = TPResult::True;
       isAmbiguous = true;
 
diff --git a/clang/test/Parser/cuda-kernel-call-c++11.cu b/clang/test/Parser/cuda-kernel-call-c++11.cu
--- a/clang/test/Parser/cuda-kernel-call-c++11.cu
+++ b/clang/test/Parser/cuda-kernel-call-c++11.cu
@@ -3,6 +3,8 @@
 template<typename T=int> struct S {};
 template<typename> void f();
 
+template<typename T, typename... V> struct S<T(V...)> {};
+
 
 void foo(void) {
   // In C++11 mode, all of these are expected to parse correctly, and the CUDA
@@ -21,4 +23,6 @@
 
   (void)(&f<S<S<int>>>==0);
   (void)(&f<S<S<>>>==0);
+
+  S<S<S<void()>>> s6;
 }