The GPU code seems to be relatively isolated to memory operations in gpuops.cu. Not altogether sure but a quick review suggests such mapping is supported by OpenCL. So one could rewrite that module and the whole thing would work without CUDA. Of course, in terms of compilers it is going to be a while before users can move away from nvcc for nvidia graphics card support.

However, as with the parent I'd really like to see a generic OpenCL vectorization kernel module. Strong suspicion that this work was directly or indirectly underwritten by Nvidia so I guess someone (Intel?) needs to step up and fund similar academic projects.