I am attempting to parallelize simulation code I am using for my thesis with CUDA/Thrust. CUDA/Thrust require use of the nvcc compiler. The C++ code the simulation is written in is kept in an XCode project, and my research group uses XCode feature to track changes and interface with other code, so working outside of it would be hugely inconvenient.
Unfortunately, though I have successfully installed CUDA 6.0, including the nvcc compiler, I cannot find how to make XCode choose nvcc rather than the default compiler. It does not seem to be an option (see screenshot).
I evidently lack the reputation to post an image, but here is a link to it in Dropbox. https://dl.dropboxusercontent.com/u/10738291/XCode%20Screen%20Shot.png If you don't want to look, it just shows that the only compiler option under 'Build Options' is LLVM.
The getting started guide (http://docs.nvidia.com/cuda/cuda-getting-started-guide-for-mac-os-x/#compiler-verification) says only what compiler options to invoke when already using nvcc, but not how to force use of nvcc.
Any idea how I can get XCode to use nvcc instead?