General-Purpose Graphics Processing Unit is what the abbreviation GPGPU stands for. It first got some attention with the launch of ATI’s R600 GPU and to follow up, NVIDIA launched the CUDA architecture, which is compatible with the GeForce 8 series of GPUs. The basic idea of GPGPU simply is to use the GPU for other things than just rendering graphics. Thanks to their highly parallel designs, they are very good at these kinds of calculations and can handle high workloads. Both ATI and NVIDIA have realized this and developed technology allowing the GPUs to perform new and exciting tasks.
Information has now been posted that suggests that NVIDIA is working on the first GPGPU for Macs. It’s not entirely clear what a Mac-compatible GPGPU is, but since many of Apple’s workstations are used for digital audio and video editing these are two of the hottest tasks for NVIDIA to target. It doesn’t say when a Mac-compatible GPGPU would arrive, NVIDIA is suppose to work at full capacity.
Back in June 2007, NVIDIA launched the Tesla graphics card, which was the first hybrid graphics card, designed for both graphics and advanced GPGPU-related tasks. The GPGPU market will most likely continue to grow over the coming years, and there is no doubt that you can achieve quite a lot through the extreme force that are today’s graphics cards.
“In science applications, calculations have seen speed boosts from a 45 times to as much as 415 times in processing MRI scans for hospitals. Increases such as this can mean the difference between using a single system and a whole computer cluster to do the same work, the company says.”
