[OpenCL] Add missing C++ legacy atomics with generic

[svenvh]

Summary

https://reviews.llvm.org/D62335 added some C++ for OpenCL specific
builtins to opencl-c.h, but these were not mirrored to the TableGen
builtin functions yet.

The TableGen builtins machinery does not have dedicated version
handling for C++ for OpenCL at the moment: all builtin versioning is
tied to LangOpts.OpenCLVersion (i.e., the OpenCL C version). As a
workaround, to add builtins that are only available in C++ for OpenCL,
we define a function extension guarded by the __cplusplus macro.

Fixes PR50041.

[Anastasia]

LGTM!

I realized that as they haven't been added to the OpenCL 3 yet it means they remain as Clang extension. I am going to document this. We could allow their uses in OpenCL C too as an extension though. There were other requests to make them available in OpenCL C too.

clang/lib/Sema/OpenCLBuiltins.td

 def FuncExtKhrLocalInt32BaseAtomics      : FunctionExtension<"cl_khr_local_int32_base_atomics">;
 def FuncExtKhrLocalInt32ExtendedAtomics  : FunctionExtension<"cl_khr_local_int32_extended_atomics">;
 def FuncExtKhrInt64BaseAtomics           : FunctionExtension<"cl_khr_int64_base_atomics">;
 def FuncExtKhrInt64ExtendedAtomics       : FunctionExtension<"cl_khr_int64_extended_atomics">;
 def FuncExtKhrMipmapImage                : FunctionExtension<"cl_khr_mipmap_image">;
 def FuncExtKhrMipmapImageWrites          : FunctionExtension<"cl_khr_mipmap_image_writes">;
 def FuncExtKhrGlMsaaSharing              : FunctionExtension<"cl_khr_gl_msaa_sharing">;
 
+// Not a real extension, but a workaround to add C++ for OpenCL specific builtins.
+def FuncExtOpenCLCxx                     : FunctionExtension<"__cplusplus">;
+
 // Multiple extensions
 def FuncExtKhrMipmapWritesAndWrite3d     : FunctionExtension<"cl_khr_mipmap_image_writes cl_khr_3d_image_writes">;
 
 // Arm extensions.
 def ArmIntegerDotProductInt8                   : FunctionExtension<"cl_arm_integer_dot_product_int8">;
 def ArmIntegerDotProductAccumulateInt8         : FunctionExtension<"cl_arm_integer_dot_product_accumulate_int8">;
 def ArmIntegerDotProductAccumulateInt16        : FunctionExtension<"cl_arm_integer_dot_product_accumulate_int16">;
 def ArmIntegerDotProductAccumulateSaturateInt8 : FunctionExtension<"cl_arm_integer_dot_product_accumulate_saturate_int8">;
foreach Type = [Int, UInt] in {
     foreach name = ["atomic_inc", "atomic_dec"] in {
       def : Builtin<name, [Type, PointerType<VolatileType<Type>, AS>]>;
     }
     foreach name = ["atomic_cmpxchg"] in {
       def : Builtin<name, [Type, PointerType<VolatileType<Type>, AS>, Type, Type]>;
     }
   }
 }
+
+let Extension = FuncExtOpenCLCxx in {
+  foreach Type = [Int, UInt] in {
+    foreach name = ["atomic_add", "atomic_sub", "atomic_xchg",
+                    "atomic_min", "atomic_max", "atomic_and",
+                    "atomic_or", "atomic_xor"] in {
+      def : Builtin<name, [Type, PointerType<VolatileType<Type>, GenericAS>, Type]>;
+    }
+  }
+}
+
 // OpenCL v2.0 s6.13.11 - Atomic Functions.
 let MinVersion = CL20 in {
   def : Builtin<"atomic_work_item_fence", [Void, MemFenceFlags, MemoryOrder, MemoryScope]>;
 
   foreach TypePair = [[AtomicInt, Int], [AtomicUInt, UInt],
                       [AtomicLong, Long], [AtomicULong, ULong],
                       [AtomicFloat, Float], [AtomicDouble, Double]] in {
     def : Builtin<"atomic_init",

clang/test/SemaOpenCL/fdeclare-opencl-builtins.cl

void test_atomic_fetch(volatile __generic atomic_int *a_int,
   ip = atomic_fetch_add(a_intptr, ptrdiff);
   uip = atomic_fetch_add(a_uintptr, ptrdiff);
 
   ip = atomic_fetch_or(a_intptr, ip);
   uip = atomic_fetch_or(a_uintptr, uip);
 }
 #endif
 
+// Test old atomic overloaded with generic address space in C++ for OpenCL.
+#if __OPENCL_C_VERSION__ >= 200
+void test_legacy_atomics_cpp(__generic volatile unsigned int *a) {
+  atomic_add(a, 1);
+#if !defined(__cplusplus)
+  // expected-error@-2{{no matching function for call to 'atomic_add'}}
+  // expected-note@-3 4 {{candidate function not viable}}
+#endif
+}
+#endif
+
 kernel void basic_conversion() {
   float f;
   char2 c2;
   long2 l2;
   float4 f4;
   int4 i4;
 
 #ifdef NO_FP64