General-Purpose computation on GPUs (aka GPGPU) is big news in the scientific research market. This article for PC Plus magazine looks at whether the average Nvidia or AMD GPU can give your PC a significant speed boost.
GPUs are ideal number-crunchers – they’re designed to work with ’streams’ of data, applying pre-programmed operations to each part. GPUs are at their best working with large datasets that require the same computation.
Calgary-based company OpenGeoSolutions uses Nvidia’s Tesla hardware to improve its seismic modelling via a technique called ‘Spectral Decomposition’. The process involves analysing low-level electromagnetic frequencies (caused by variances in rock mass) to build a stratigraphic view of the earth’s geology.
On a typical CPU-based cluster, building sub-surface images took anywhere from 2 hours to several days.
With a Tesla system, OpenGeoSolutions reported a performance increase that was “totally unprecedented”.
That’s all great, you might say. But I’m unlikely to be solving shallow water equations or prospecting for oil beneath the Alaskan ice. What sort of impact does this have on a desktop PC? Beyond the obvious gaming applications, what’s in it for me?
Right now, not much. If you’ve got an average graphics card like an Nvidia GeForce 9600 GT, your GPU (which features 64 separate stream processing cores) can already handle real-time physics effects. Nvidia ported Ageia’s PhysX code libraries to its 8-Series GPUs after acquiring the company back in February 2008.
More recently, we’ve seen the potential for faster media encoding with the release of Badaboom. Ripping a DVD or converting a video file would typically monopolise a CPU-only system. Built with Nvidia’s CUDA language, Badaboom allocates this data-intensive workload to an Nvidia GPU, so the CPU can still be used for day-to-day tasks.
The full text of this article appears in PC Plus magazine, issue 279. Or you can read it online here: Why your next CPU could be a GPU.