According to an article published today on European Union Information site Cordis Europa, the healthcare sector is projected to be the latest beneficiary of EU-funded efforts to drive innovation. Stick with it, because it may well be good stuff, albeit a bit errr abstract. It’s certainly not your average EU communique… well let’s hope not.
The DESYRE consortium is an EU-backed initiative to the tune of €2.8M. To be honest I’d pay them that if they could explain it in plain English, but for the purpose of pandering to the boffins out there we’ll plug on. So DESYRE is working on what it calls “systems which are reliable but depend on unreliable components”, if that makes sense. It doesn’t to me, but as long as the consortium with experts from Greece, Italy, the Netherlands, Switzerland and the United Kingdom understand it, we’ll be ok.
Speaking to participants at the recent DATE 2012 conference in Dresden, Germany, DESYRE project leader Ioannis Sourdis from the Department of Computer Engineering at Chalmers University of Technology in Sweden said devices being used by the medical world today, such as pacemakers and other implantable medical devices, rely on three critical components: reliability, small size and longevity.
Experts estimate that fault rates will increase as technology develops. The DESYRE team is therefore creating new design techniques for future ‘Systems-on-Chips’ to give reliability a boost but to also cut power and performance overheads that are associated with fault tolerance.
Still not clear?
‘We focus on the design of future highly reliable Systems-on-Chips that consume far less power than other designs for high reliability systems,’ Professor Sourdis explained. ‘This approach allows by design devices that combine high reliability with small batteries and state-of-the-art longevity. It is perfect for safety-critical applications such as in implantable medical devices, for example pacemakers or deep brain stimulators that treat Parkinson’s disease.’
Am I going mad or is this the most confusing thing you’ve ever read too?
Most studies that put the spotlight on reliable systems usually focus on fail-safe mechanisms that use a number of redundancy schemes. In this case, sensitive sub-systems are seen as ‘fail-safe’. In order to assess faults in the sub-system, more energy is used, which in turn cuts the performance of chips. The end result is lost time and wasted energy.
The DESYRE project partners are splitting the System-on-Chip into two distinct areas. The first is extremely resistant to faults, while the second contains fault-prone processing ones. The researchers say the cores on the fault-prone area are interchangeable, and that the task of one core can be transferred to any of the other cores in case of a diagnosed malfunction. The fault-free part of the chip, meanwhile, observes the operation of the fault-prone part by executing ‘sanity checks’ of the processing cores. They are also responsible for guaranteeing that every core handles an assigned sub-task without any errors.
‘It sounds perhaps counterintuitive to design a highly reliable System-on-Chip on the basis of components that may fail, and yet this is exactly what we propose to do,’ says Gerard Rauwerda, chief technology officer of Recore Systems B.V. of the Netherlands, one of DESYRE’s industrial partners. ‘The beauty of the DESYRE approach is that the system continues to do its job reliably, even if one or more cores fail, extending chip longevity.’
This innovative, fault-tolerance device will help cut energy use by at least 10% to 20% and lessen penalties on performance, according to the team.
‘People that need implantable medical devices will also benefit from this, as it pays off in a longer battery life and a postponed device replacement without any compromise to reliability,’ Professor Sourdis says.
If only he’d said that at the start.