CSIRO hooks up gaming brains to crunch numbers

Mike Bantick
Wednesday, 25 November 2009 07:02

Your IT - Home IT

Apart from providing high resolution graphics as a way for gamers to frag each other, the Graphics Processing Units (GPU) attached to every video-card can provide computing power for scientists wanting to unlock the secrets of the human genome.

The hardware that goes into your average family desktop today can be somewhat powerful.  This is usually so of a typical PC gamer, with an emphasis on the video display for high resolution battles.

Though it is important for your explosions to look good, it hardly betters mankind.  Researchers at the CSIRO labs in Canberra Australia are now utilising the power of the PC Video-Card brain, the Graphics Processing Unit (GPU) to crunch data in some of sciences more mathematically intense endeavours.

The new GPU cluster will complement the supercomputing resources available to CSIRO researchers such as the recently installed NCI facility at the Australian National University.

The cluster will allow CSIRO scientists to explore what may well be the next generation approach to supercomputing, the use of GPU technology for parallel processing.

The CSIRO GPU cluster will be launched today in Canberra.  The first of its kind in Australia, the cluster is about the size of six large refrigerators and contains 61,440 computer cores.

CSIRO Computational and Simulation Science leader Dr John Taylor said the computer cluster combines Central Processing Units (CPUs) like those in PCs with more powerful Graphics Processing Units (GPUs) to make it more efficient.

“GPUs have been around a while, hidden in your computer game console but now we’re seeing them in scientific computing,” Dr Taylor said.

They were initially designed to render 3D scenes in computer games.  GPUs speed up data processing by allowing a computer to massively multi-task through parallel processing.

Per unit of processing power, a GPU cluster is typically less expensive and more energy efficient than a CPU-based supercomputer.

GPUs are not just useful for image data; they can tackle big science challenges processing petabytes of data and more, very quickly.  Speeds of 30 to 70 times faster than CPUs are common.

“It’s pleasing to see the first installation of a GPU cluster in Australia,” CSIRO Information Sciences Group Executive Dr Alex Zelinsky said.

“This cluster will be part of our family of high-end computers in CSIRO and important to our e-Research Strategy.”

“It will enable CSIRO to, in a cost effective way, be globally competitive in addressing computational challenges for ‘big science’.”

CONTINUED on PAGE 2