I thought about this briefly, myself, while in computer architecture optimization classes. As the GPU is basically a tailored CPU used to offload graphics processing from the main CPU, why can’t you offload more things onto it?’
And the answer is: you can. Folding@Home is a distributed computing project that is developed by Stanford University, and has been around awhile. While I don’t currently use it, I have in the past. I support the World Community Grid project, currently, because it gets me free gigs on Easynews, and it works with the Boinc client for my linux machines. But, Folding@Home always seemed to be the most efficient at what it does. No frills, no fancy screensavers, little overhead. It just folds and folds and folds protein.
Now, it can stake claim to unused GPU cycles on that roaring video card you have. And you only use a fraction of those while not going for that next rank in Battlefield 2. Desktop computing can even consider to have an idle 3d processor, for the most part.
Unfortunately, they only have this working on ATI cards. They couldn’t get it working on the Nvidia flavors. This leaves me out in the cold, at least for now. The chips are just a bit too specialized, and not in the “general” category of GPU’s anymore.
Andy Keane, general manager of visualization applications at Nvidia, said in response to the ATI/Stanford announcement that general processing graphics processing units (GPGPUs) so far have been “fundamentally flawed” in a sense that there has not been a lot of “commercial exploitation with GPUs as a processor.”
He mentioned that Nvidia wants to change this situation and considers the GPGPU market as “exciting” and something that “the company has been looking at for years.” He stated that he had no personal knowledge of the development of a Folding@Home client for the Nvidia platform, but stressed that the company has a “long-standing relationship with Stanford.”
The merger excites the gamer in me, as the possibilities of CPU-GPU sharing, cooperation, and even 