If you're having trouble with template functions in CUDA, look at MXCudaMath.cu.
Exp(), Ln(), and ^ operator (like Pow()), but these have not been thoroughly tested so use with caution.
Note: The GPU code has not been set up in Linux yet, although there;s no reason it shouldn't work if you want to set it up yourself. I'm waiting on OpenSuse 13.1 to be released next week to update my setup. Once it's out I'll switch to getting the Linux side caught up.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
This release contains:
Note: The GPU code has not been set up in Linux yet, although there;s no reason it shouldn't work if you want to set it up yourself. I'm waiting on OpenSuse 13.1 to be released next week to update my setup. Once it's out I'll switch to getting the Linux side caught up.