IDF13 Intel wants you to know that Moore's Law is not dead. And to prove it, CEO Brian Krzanich rolled out his company's next generation of process shrinkage at the Intel Developer Forum in San Francisco.
"I'm here to introduce the first 14-nanometer PC," Krzanich said during his Tuesday keynote. The Ultrabook he displayed to his audience was based on Intel's 14nm "Broadwell" microarchitecture, and was "fully operational" – and to prove it, Krzanich demoed the laptop playing ZeptoLab's Cut the Rope.
More ReadingThe huge flaw in Moore’s Law? It's NOT a law after allIntel touts tardy Broadwell Core CPUs for laptops, PCsToshiba plans chippery with mere 0.5V power slurp by 2017Intel admits: Broadwell Core M chip looking a bit thin, no fans found at allSamsung, GlobalFoundries ink exclusive, multi-year 14nm FinFET deal
"This is it, folks," he said. "Fourteen nanometers is here, it's working, and will be shipping by the end of this year." According to Krzanich, 14nm Broadwell systems will provide a 30 per cent improvement in power consumption over today's comparable 22nm "Haswell" chips – but power saving may be even greater.
"We're not done yet," he said. "That's as far as we've been able to test it so far."
The Broadwell chip playing Cut the Rope in Krzanich's demo will be joined by an Atom-based 14nm chip, he said, around the end of 2014.
Intel president Renée James, who shared the keynote stage with Krzanich, was adamant about the health of the Intel cofounder's guiding legislation. "Moore's Law has been declared dead at least once a decade since I've been at Intel," she said, "and as you know – you heard from Brian – we have 14 nanometer working and we can see beyond that. I assure you it's alive and well."
According to James, that "alive and well" status will allow Intel make it down to 7nm – although her presentation didn't include any projections beyond that node.
As anyone who has been following the chip-baking industry knows, getting down to 7nm without the advent of commercially usable extreme ultraviolet (EUV) lithography will be a daunting task – Intel CTO Justin Rattner admitted as much to The Reg just this May.
But EUV is proving to be an elusive technology, as GlobalFoundries CEO Ajit Manocha told SEMICON 2013 this July. "We all know that EUV is late," he said. "We desperately need EUV, and EUV is still not ready."
Another chip-process researcher, speaking at that same conference, has gone so far as to have given up on EUV. "I'm not working on EUV at all," said Laurent Miller, CEO of Leti, the nanotechnologies arm of the French research-and-technology organization CEA. "Absolutely not, because I don't believe in it."
Exactly what inspires James to have such faith in the continuance of Moore's Law, she didn't say. Krzanich, in fact, put the kibosh on one alternative technology – graphene transistors – in response to a question about that candidate in a first-ever keynote-audience Q&A.
"Graphene is totally exciting," he said. "We absolutely have research going on in graphene." However, he noted that cost, reliability, and repeatability make manufacturing graphene chips problematic. "I can tell you that in the next several generations you're not going to see a lot of graphene parts, but there's absolutely a lot of research going on."
Will Moore's Law – which, as James recounted correctly, has repeatly been declared dead for reasons of both physics and finance – rise from its deathbed one more time? Who knows – but as Intel Fellow Shekhar Borkar once told us, "The engineers, they'll find out a way to do it."
If Borkar's confidence is well-founded, perhaps 10 years from now during Kzanich's IDF23 keynote, he'll proudly tell his crowd, "I'm here to introduce the first graphene transitor–based PC." ®
Although Krzanich and James' tag-team keynote was 90 minutes of hoopla, futurism, medical miracles, and starry-eyed optimism, the discussion of such a meat-and-potatoes topic as transitor scaling was inevitable. As Krzanich said, "You can't have an Intel presentation without talking about Moore's Law."