diff --git a/clang/include/clang/Basic/BuiltinsNVPTX.def b/clang/include/clang/Basic/BuiltinsNVPTX.def
--- a/clang/include/clang/Basic/BuiltinsNVPTX.def
+++ b/clang/include/clang/Basic/BuiltinsNVPTX.def
@@ -31,7 +31,9 @@
 #pragma push_macro("PTX61")
 #pragma push_macro("PTX63")
 #pragma push_macro("PTX64")
-#define PTX64 "ptx64"
+#pragma push_macro("PTX65")
+#define PTX65 "ptx65"
+#define PTX64 "ptx64|" PTX65
 #define PTX63 "ptx63|" PTX64
 #define PTX61 "ptx61|" PTX63
 #define PTX60 "ptx60|" PTX61
@@ -725,3 +727,4 @@
 #pragma pop_macro("PTX61")
 #pragma pop_macro("PTX63")
 #pragma pop_macro("PTX64")
+#pragma pop_macro("PTX65")
diff --git a/clang/test/CodeGen/builtins-nvptx-ptx60.cu b/clang/test/CodeGen/builtins-nvptx-ptx60.cu
--- a/clang/test/CodeGen/builtins-nvptx-ptx60.cu
+++ b/clang/test/CodeGen/builtins-nvptx-ptx60.cu
@@ -2,6 +2,10 @@
 // RUN:            -fcuda-is-device -target-feature +ptx60 \
 // RUN:            -S -emit-llvm -o - -x cuda %s \
 // RUN:   | FileCheck -check-prefix=CHECK %s
+// RUN: %clang_cc1 -triple nvptx64-unknown-unknown -target-cpu sm_80 \
+// RUN:            -fcuda-is-device -target-feature +ptx65 \
+// RUN:            -S -emit-llvm -o - -x cuda %s \
+// RUN:   | FileCheck -check-prefix=CHECK %s
 // RUN: %clang_cc1 -triple nvptx-unknown-unknown -target-cpu sm_60 \
 // RUN:   -fcuda-is-device -S -o /dev/null -x cuda -verify %s