[NVPTX] Support the OpenCL generic addrspace feature by default (llvm#137940)

As best as I can see, all NVPTX architectures support the generic
address space.

I note there's a FIXME in the target's address space map about 'generic'
still having to be added to the target but we haven't observed any
issues with it downstream. The generic address space is mapped to the
same target address space as default/private (0), but this isn't
necessarily a problem for users.

Author: frasercrmck

clang/lib/Basic/Targets/NVPTX.h

@@ -170,6 +170,8 @@ class LLVM_LIBRARY_VISIBILITY NVPTXTargetInfo : public TargetInfo {
     Opts["cl_khr_global_int32_extended_atomics"] = true;
     Opts["cl_khr_local_int32_base_atomics"] = true;
     Opts["cl_khr_local_int32_extended_atomics"] = true;
+
+    Opts["__opencl_c_generic_address_space"] = true;
   }
 
   const llvm::omp::GV &getGridValue() const override {

clang/test/Misc/nvptx.languageOptsOpenCL.cl

@@ -132,3 +132,11 @@
 #pragma OPENCL EXTENSION cl_khr_subgroups: enable
 // expected-warning@-1{{unsupported OpenCL extension 'cl_khr_subgroups' - ignoring}}
 
+#if (__OPENCL_C_VERSION__ >= 300)
+#ifndef __opencl_c_generic_address_space
+#error "Missing __opencl_c_generic_address_space define"
+#else
+#error "Incorrect __opencl_c_generic_address_space define"
+#endif
+#pragma OPENCL EXTENSION __opencl_c_generic_address_space: enable
+#endif