“Nvidia pitches its Tesla hardware as a magical solution for the world’s toughest computing problems. Just move your code that runs well across many processors over to the Tesla boards, and Shazam!. You enjoy sometimes 400 per cent improvements in overall performance. Despite such mind-blowing increases in horsepower, Tesla continues to occupy a space that one could characterize as ultra-niche. Only the brave few have navigated Nvidia’s CUDA programming apparatus to tweak their code for the general purpose graphics processors inside of the Tesla systems. That ultra-niche, however, may grow into a niche over the coming year thanks to the introduction of more powerful Tesla systems.”
The latest Mac OS X version, snow leopard, has build-in support for GPU utilization. This nVidia card, although it is interesting only for a niche, could be a predecessor of more mainstream co-processor like hardware that will be present in mainstream hardware.
Technically you can take advantage of the GPU with OpenGL 2 as it stands today, meaning most popular operating systems.
OpenCL itself is interesting and if, according to wikipedia, apple really does take it to khronos then it would hopefully be available everywhere the vendors have OpenGL implementation already.
In reality, this has nothing to do with Mac OS X, although Apple seems to be doing something productive by attempting to wrangle a common API/Lib for GPGPU work. Having CUDA, Brook+, and whatever else is out there seems to be aggravating at best from my experience writting gpgpu stuff. OpenGL is the only cross platform api at the moment, and even then their are quirks depending on the hardware vendor.