The Register® — Biting the hand that feeds IT

Feeds

BREAKTHROUGH: Feisty startup slashes chip power by 50%

SuVolta to Intel: 'The future is the $10 chip, not the $200 chip'

An impressively staffed startup by the name of SuVolta has teamed up with Japanese heavyweight Fujitsu Semiconductor to create a new chip-baking technique that promises low-power, inexpensive chips created in a highly scalable process and manufactured using equipment that's already ready in chip foundries.

Yes, that description is a bit of a mouthful – but that's the breadth of promise offered by SuVolta's "deeply depleted channel" (DDC) CMOS transistor tech, as presented on Wednesday by a Fujitsu researcher at the 2011 International Electron Devices Meeting (IEDM) currently underway in Washington DC.

If DDC works as advertised – and from the deep-dive details and test results provided to The Reg by SuVolta's director of device and modeling Lucian Shifren, we have no reason to think that it shouldn't – it could revolutionize how low-power system-on-chip (SoC) silicon is created.

What DDC involves, and what provides its promise, is a new way of creating transistors based on standard bulk planar CMOS manufacturing techniques, and not on more-expensive and specialized transistor manufacturing processes that have cropped up in the past decade or so to allow chip designers to keep pace with that tough taskmaster, Moore's Law.

Shifren emphasized that although DDC could be applied to any level of chippery, SuVolta is currently more concerned with foundry-created, low-power chips, and not the hefty x86 CPUs baked by Intel in their custom fabs. SoCs are where the market is headed, he told us.

"CPUs and GPUs are not actually driving the semiconductor market anymore," Shifren said. "What's driving it are SoCs, and especially those adapted to mobile forms."

The company that's currently driving semiconductor technology, however, is Intel. But Chipzilla has traditionally focused its research on larger, more powerful chips based on the aging IA architecture – although it would dearly love to break into the lucrative mobile market, dominated by non-IA ARM chippery.

"If you look at the industry as a whole right now, who really defines the technology and the technology roadmap?" Shifren asked, rhetorically. "It's Intel." He also gave historical props to IBM, but averred that in recent years Intel has been leading the way.

As an example, Shifren offered Intel's variation of 3D FinFET transistor technology, what Chipzilla calls Tri-Gate. "Have a look at how after Intel made its announcement of FinFET, everybody and their mother came out and said they were going to be working on FinFET," he said.

According to Shifren, however, neither FinFET nor another transistor structure known as fully depleted silicon-on-insulator (FD-SOI), which has been around for nearly a decade, are the best choices for the low-power, low-cost SoC market – although others may disagree when Shifren says "I believe FD-SOI is dead."

SuVolta IEDM presentation slide

SuVolta's DDC transistor shares many advantages of cheap-as-dirt, versatile bulk planar CMOS (click to enlarge)

Not only are both of those techniques expensive when compared with good ol' traditional non-depleted planar bulk CMOS, Shifren says, but they don't scale well for creating a range of chips running at different voltages.

(A bit of background: you'll notice that the term "depleted" is being bandied about a bit. Simply put, a depleted transistor is one in which stray current is minimized in such a way as to prevent power leakage, and to allow the transistor to be activated at a lower voltage. For a fuller explanation, check out an earlier Reg article about Intel's tri-gate transistors.)

Shifren told us that voltage reduction has been given short shrift in the drive to keep up with Moore's Law. "If you look at Moore's Law, and how Moore's Law has been evolving over the last couple of years," he said, "advances in patterning and moving to double patterning, immersion masks, and things like that, the industry has been able to keep along with Moore's Law – as long as you're talking about dimensional scaling.

"But if you have a look at the voltages," he continued, "they haven't scaled nearly as quickly. They actually haven't scaled at all in the last couple of years."

He recited the history of processor voltage scaling, starting a five volts, then down to the low fours, then 3.5V, 2.5V, 1.8V. Then curve of the decreases began to flatten out, now hovering around 1V to 0.7V. Moore's Law, on the other hand, has kept chugging along, doubling transistor density every 18 to 24 months.

SuVolta's breakthrough is that it has managed to slash that voltage requirement essentially in half, a level of improvement that should please any fan of Moore's Law–scale improvements. The company's DDC transistors, used in a proof-of-concept SRAM chip manufactured by Fujitsu, require a mere 0.425V.

Next page: Three layers, no waiting

Yes and no

If Intel tweaks existing equipment and it is low cost, then others can easily license it and do the same. Others might also find ways to further refine it. If Intel finds an entirely new method that is cost prohibitive for the others, then licensing it is not likely. This gives Intel a competitive advantage. They will do anything to keep it which has been proven by their practices.

4
0

Intel didn't invent the Tri-gate/Fin-FET/3D Transistor

AMD were talking about it first[1]. Intel only started claiming credit for an identical technology advancement (Tri-Gate) a good 4+ years later and - like AMD - are yet to come to market with a product using 3D transistors.

It's interesting how everyone is giving the credit to Intel for something that was clearly developed (or at the very least, theorised) elsewhere. I'm sure it's not the first - or last time - that will happen.

And much of the advances Intel make in their manufacturing process are only necessary because of the crap design of their IA architecture. Whether this startup is right or wrong, it's beyond doubt that Intel have made many mistakes in the past and still live with the cost of most of them today.

1. http://www.xbitlabs.com/news/other/display/20030918140333.html

3
0

Subtle & sneaky

It's kind of weird, you'd have thought Intel, with it''s *huge* investment in chip fabs, would be looking for exactly this type of approach (clever tweaks of the *existing* tools and processes it uses) to give those improvements.

Instead the start-up using what appears to be a *deeper* understanding of what is going on has achieved this leverage.

I'd guess someone has been caning their HPC hardware to run the sims that worked out the theory in detail.

Thumbs up for this, with the proviso that it has to be translated into *products* first.

3
0

Intel are the incumbents

and it is in their interests to support the status quo - protects the license revenue as Lance says and maximises the returns on investments already made. It is up to new entrants to be disruptive (and take more of the risks); this is not just complacency on Intel's part - their resources are huge but not infinite and they cannot do everything. Intel's business practices often limit the reach of their technical prowess (marketing trumps engineering) - look at ARM's continued dominance of the low-power space (Intel was an ARM licensee but dropped out and gave that business away) and also Intel's marketing boys hobbling the Atom chip.

Marketing also dictates a "black and white" approach - something has to win and all the alternatives must lose so Intel try to pick the winner (e.g. FinFET) and have to back it. From that point, everything else has to be inferior or the powerpoint slides don't stack up.

Microsoft is a direct and obvious comparison - although Intel has far greater research chops than they do; MS will defend the PC (and Windows and .Net) to the death and are frantically playing catch-up with on mulitple fronts (Metro UI, Bing, Win on ARM, ...).

Power consumption is a big issue and this new lot will do well from noticing that. I hope.

1
0
Anonymous Coward

Intel leading?

"If you look at the industry as a whole right now, who really defines the technology and the technology roadmap?" Shifren asked, rhetorically. "It's Intel."

...in what universe?

Shifren seems to be mixing his apples and his oranges here. His process is intended for SoC fabrication, so why is he comparing it with power hungry PC chip processes? Saying that Intel leads the tech road map is a very general statement and wholly untrue when it comes to chips in the low power SoC category. They have been trying for years to come up with anything that could go head to head with an ARM and failed thus far, so how is it that they define the tech road map?

1
0

More from The Register

MYSTERY Nokia Lumia with gazillion-pixel camera 'spotted'
With 20Mp sensor - NOW will you try Windows Phone 8?
The iWatch is coming! The iWatch is coming!
Reports: Apple's wrister to have 1.5-inch OLED, test units being built
US boffin builds 32-way Raspberry Pi cluster
Beowulf cluster built for the price of a single PC
 breaking news
Dell's PC-on-a-stick landing in July: report
Wyse up, suckers, could this be a new set-side-stick?
Review: HP Pavilion 14 Chromebook
All roads lead to Chrome?
Borked your iDevice? Pay EVEN MORE to have it fixed by Applecare
Or scream at their hapless techies on their forums
Review: Sony Xperia SP
The new mid-range marvel? Oh yes.
Euro PC shipments plummet into bottomless pit of DOOOOM
11th quarter of decline, 20pc drop on last year - Gartner