https://gcc.gnu.org/bugzilla/show_bug.cgi?id=115740

--- Comment #15 from Jonathan Wakely <redi at gcc dot gnu.org> ---
https://llvm.org/docs/CompileCudaWithLLVM.html#detecting-clang-vs-nvcc-from-code
suggests that __CUDA_ARCH__ is the right macro (thanks to zhao)

Reply via email to