Low power vs high performance at 22 nm & below - Embedded.com

Low power vs high performance at 22 nm & below

Intel’s recent move to new 22 nanometer CMOS processtechnology in its Atom CPU road map has upset a delicate balancemaintained over the last ten years or so among circuit designers, processorarchitects, and embedded system hardware and software developers.

Whatis upsetting the balance and may force a rethink of every aspect of embeddedsystems design is Intel’s shift away from a well understood planar structure toa vertical 3D FinFET. The company claimsthat going vertical allows significantly higher performance at lower power thanmost planar techniques. If Intel is successful, it will be hard for ARM and itslicensees and other CPU architectures to avoid making the jump as well.

In the past, as semiconductor manufacturers went to smaller nanometergeometries with traditional planar CMOS designs, developers at all levels -circuit and logic design, processor architecture, and software development -have been able to adjust.

Working within the planar CMOS structure, theyfound ways to not only take advantage of the improvements in density,performance and power, but also deal with the problems of leakage, noise,reliability, EMI and ESD that nanometer scaling caused. Some of the articlesthat have run on Embedded.com and in ESD Magazine on these topic are included inthe most recent issue of the Tech Focus newsletter. Of these, my Editor’s Top Picks are:

Power aware verificationof ARM-based designs
Building a highperformance, ultra low power 32-bit MCU
Meeting the Low PowerImperative at 28nm

Several questions occur to me. If such achange is necessary, are the tough issues relating to reliability andperformance with vertical FinFET structures well understood? And will many ofthe techniques developers have developed in planar CMOS designs still apply? Orwill everything have to be rethought? Is such a vertical move at the processlevel necessary across all embedded CPU designs? Or is it something forced onIntel by the nature of its X86 architecture?

I would like to hear from you, proand con, in the form of blogs and opinion commentary and as design articlesabout how you are dealing with the changes.

Embedded.com Site Editor Bernard Cole is also site leader of iApplianceweb and a partner in the TechRite Associates editorial services consultancy. He welcomes your feedback. Call him at 602-288-7257 or send an email to .

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.