In an attempt to illustrate the low power requirements of its latest Linux-based supercomputer, a company called SiCortex put together a demonstration showing the massive number-cruncher performing billions of calculations per-second while a team of between eight to ten bicyclists pedaled to keep it going. The NextFest presentation was a ploy to showcase the small power consumption of the new machine, and to point out that energy conservation for both system power and cooling are major issues facing manufacturers and end-users. As the custom Trek bikes churned out 260-watts of power each, Dr. John Mucci -- the company's CEO -- said, "Ten years ago, this analysis was impossible on even the biggest computers, and now it's being done on a bicycle powered machine," then added, "Ten years from now, we'll probably be doing it right down at the docks as they unload the ships." Which sounds kind of weird, but isn't.

[Via I4U]

Scientists have been on the hunt for years attempting to model the human brain, but typically any research in this area was strictly used for medical purposes. Steve Furber of the University of Manchester is the head honcho of the Spinnaker (short for spiking neural network architecture) project, which seeks to better understand the complex interactions of brain cells in hopes of creating more "fault-tolerant computers." Furber states that although we lose one neuron per second during our adult life (just think, you've already lost a couple dozen reading this post), yet our brains don't suffer any catastrophic meltdowns or periods of underperformance because of it. Rather, the brain has an impeccable ability to disregard malfunctions and find alternate ways to function without throwing a theoretical BSOD. The Spinnaker computer consists of silicon chips containing 20 microprocessors, 19 of which will behave as neurons while the remaining processor records the activities. Each chip will replicate about 20,000 human neurons, and unlike normal processors, Furber's approach will eliminate the "clocks" that typically synchronize the processes, providing a much more accurate representation of how biological neurons somehow keep on ticking (so to speak). The Spinnaker project is hoping to reach a functioning system containing 50 chips and a thousand processors within two years, and although we don't claim to be experts on the subject, it sounds like they should take a peek at how those self-healing chips are coming along, eh?

[Thanks, Ian]