Reading the CUDA documentation, there are several
instances where it points out support for 32-Bit is either
depreciated or being depreciated. So although a lot of the
CUDA programming will probably work just fine in 32-bit,
you may eventually stumble into something that might not be
supported.
CUDA in general I think is trying to shift completely away
from utilizing the 32-bit architecture.
I'm not going to pretend to understand and spend the
rest of my day trying to explain why it is the way it is.
All I can tell you is, I compiled a 64-bit DLL and mIRC
wouldn't accept it.
I see what you're saying though, I could just create a new
64-bit process that could utilize the CUDA features.
