10/26/2011

Is multicore a viable choice for medical devices?

Will even relatively simple devices
eventually require multicore?
Multicore processors, and the software required to run on them, can increase the complexity of any embedded system. Some industries, notably networking, have long embraced this added complexity. The medical device market isn't one of them.

It's easy to see why, as this same complexity could potentially hinder or prolong the process of securing FDA approval for a medical device. Getting approval is already hard enough and long enough; any new technology that might further extend the ordeal is rightly looked upon with skepticism.

And yet, multicore is the way of the future for medical devices, save for relatively simple products. We've seen this trend in other markets, including automotive, and the medical device market will, in all likelihood, follow suit.

Should medical developers be concerned? Yes, but not too much. As my colleague Justin Moon argues, the techniques needed to validate multi-core medical systems are, in fact, the same proven techniques that developers already apply to single-core systems. These techniques include testing, statistical analysis, fault tree analysis, and design verification. Meanwhile, the tools and OS technology needed to create, analyze, and optimize multicore-capable applications are, in many cases, quite mature.

And, of course, let's not forget a key benefit of multicore: significantly increased performance (through concurrency) without an attendant increase in power consumption and heat dissipation.

But enough from me. To get the argument straight from the horse's mouth, read Justin's article, Smart OS strategy makes multicore viable for medical devices, which EE Times published earlier this month.

Testing, statistical analysis, and design validation complement one another to validate a software system, whether it is running on one or multiple cores. (Click image to magnify.)
 

No comments: