fix nvrtc deadlock with `cuda version != 10.1`: https://github.com/xmrig/xmrig-nvidia/issues/260

implementation is derived from the reverence implementation in xmrig

Use only the half AES matrix and compute the other half in place.
This PR increases the possible occupancy.

- move source code to `src`
- categorize files and move to group folder
- change upper case class files to lower case
- change C++ header to `*.hpp`