[CUDA] Make NVVM builtins available with CUDA-11/PTX6.5

Differential Revision: https://reviews.llvm.org/D79449

clang/include/clang/Basic/BuiltinsNVPTX.def

@@ -20,7 +20,9 @@
 #pragma push_macro("SM_70")
 #pragma push_macro("SM_72")
 #pragma push_macro("SM_75")
-#define SM_75 "sm_75"
+#pragma push_macro("SM_80")
+#define SM_80 "sm_80"
+#define SM_75 "sm_75|" SM_80
 #define SM_72 "sm_72|" SM_75
 #define SM_70 "sm_70|" SM_72
 
@@ -31,7 +33,9 @@
 #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
@@ -721,7 +725,9 @@ TARGET_BUILTIN(__imma_m8n8k32_st_c_i32, "vi*iC*UiIi", "", AND(SM_75,PTX63))
 #pragma pop_macro("SM_70")
 #pragma pop_macro("SM_72")
 #pragma pop_macro("SM_75")
+#pragma pop_macro("SM_80")
 #pragma pop_macro("PTX60")
 #pragma pop_macro("PTX61")
 #pragma pop_macro("PTX63")
 #pragma pop_macro("PTX64")
+#pragma pop_macro("PTX65")

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