As far as using nvcc
, one needs to use the corresponding gcc
(currently max. 5.4 I believe) in conjunction. This of course somewhat prevents one from u
Currently up to C++14 is supported in device code (Introduced in CUDA 9)
--std {c++03|c++11|c++14}
Options for Specifying Behavior of Compiler/Linker
However, if your host is only using C++17, it should be possible to use separate compilation and link them with library. Separate Compilation and Linking of CUDA C++ Device Code
Update: formatting and more info