BREAKTHROUGH: Feisty startup slashes chip power by 50% 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 …
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.
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.
I'd imagine intel has considered these things but feels it's better to bet on their current dominant products position in the industry rather than betting on which new bit of silicon makes it into the most popular next-gen mobile devices. Startups have less to lose. Then again Intel may be working on just this but they did not feel the need to flood the news around looking for business alliances because they have the leverage to pull it off by themselves.
I think they are a little muddled in the use of the word soc. Everything is evolving towards soc's be it a basic chip or and intel behemoth.
I'm not convinced that the current and future Arm derived SoC aren't an order of magnitude more complex than where these guys are aiming.
And if they do mean to include complex Arms then the same argument applies to Atoms and Brazos too.
"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?
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
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.
The Register 
Biting the hand that feeds IT
Copyright. All rights reserved © 1998–2024
