Intel looks beyond silicon for processors past 2017

David Flynn
25 October 2009, 9:45 PM


Intel CEO Paul Otellini says that silicon will last for three more generations of processors, when it will be replaced by a new and “very cool” base material.


Silicon has been the foundation of the processor ever since the processor was invented – and before that, stretching back to the early days of the discrete transistor in 1954.

That’s over 50 years as the magic ingredient of modern electronics and the not-so-secret sauce of the digital era.

But silicon’s days are numbered, at least when it comes to microprocessors, says Intel.

Speaking at San Francisco’s Web 2.0 Summit last week, Intel CEO Paul Otellini said that silicon was in its last decade as the base material of the CPU.

Otellini forecast that Intel would produce “three more generations” of silicon processors before shifting to a new semiconductor material.

Given that Intel’s ‘tick-tock’ model sees a new microarchitecture every two years – and starting at the current  45nm ‘Nehalem’ silicon microachitecture, which will be followed by 32nm (‘Sandy Bridge’) in 2011, then 22nm (Haswell’) in 2013 and 16nm (codename unknown) in 2015 – then Otellini’s talking about the first wave of non-silicon processors kicking off by 2017.

Otellini said that chips based on these new materials are already up and running in Intel’s labs, but he held back on revealing what materials and technologies these are, saying only that  “It’s very cool.”

Intel has long been directing large amounts of its already-substantial R&D budget – which is estimated at US$5 billion per year – towards new ‘post-silicon’ materials and the association manufacturing techniques.

These include indium antimonide, a  ‘compound semiconductor’ which Intel reports as clocking at 1.5x the speed of silicon transistors while drawing one-tenth of the power; optical ‘circuits’ which could lessen the reliance on relatively slow physical circuitry such as copper; as well as carbon nanotubes and semiconductor ‘nanowires’.

Intel is investigating what it terms ‘3D transistors’, which allow current to be controlled on three sides instead of passing through just one gate, to effectively triple the processing power.

Mind you, there’s still plenty of juice left in the current silicon architecture.

The first 32nm Sandy Bridge chips of 2011 are expected to hit 4GHz with four to eight cores (no more dual-core processors) with the CPU and GPU on a single die, making this Intel’s first mainstream ‘SoC’ (System On a Chip) platform.

Advanced design and temperature monitoring will enable a new ‘Dynamic Turbo’ which allows the CPU to exceed the total thermal ceiling by 20-30% for brief periods of a few minutes.

And the 22nm Haswell platform is expected to have upwards of eight cores and possibly even include an on-die evolution of Intel’s multi-core x86 Larrabee graphics.


Post your comment



Comments

RSS feed Email alert

Aubrey (New user):

My money is on Illudium Phosdex as the secret new material. We have approximately three and a half centuries until supplies run out and there is a final showdown between galactic civilisations on Planet X.

Calculon is another possibility.

If Intel could manage to get hold of enough Thiotimoline, they would get a processor so fast it would be able to carry out instructions before they were issued.

26 October 2009, 11:54 AM (3 years ago)report abuse Send to a friend reply

Me In Oz (User):

Quoting Aubrey:
three and a half centuries until supplies run out

No probs Aubrey!
Apparently Linux will have taken over the universe. Which will mean that you can still run Ubuntu 2450.xx with P3 and 512 M RAM .... ;)





26 October 2009, 12:34 PM (3 years ago)report abuse Send to a friend reply

Aubrey (New user):

Quoting Me In Oz:
you can still run Ubuntu 2450.xx with P3 and 512 M RAM .... ;)

I do hope so, but by then I will have certainly upgraded to a P4 to run my Matter Transfer Device. Of course, Ubuntu will have long run out of stupid animal-based names for their releases. 2450.04 is to be "Desperate Dandelion". But it will still be brown.


26 October 2009, 3:41 PM (3 years ago)report abuse Send to a friend reply

Me In Oz (User):

Quoting Aubrey:
2450.04 is to be "Desperate Dandelion".

.... or "Fundamentally Fungi", the plant that will rule the world ;)




26 October 2009, 3:57 PM (3 years ago)report abuse Send to a friend reply

Dale B. Ritter, B.A. (New user):

Intel could be a future innovator if this keeps up. Their 3D chips may benefit from new physics modeling techniques with the picoyoctoscale resolution for all particles, fields, and waves that chip design research needs to challenge the pico/femtoscale horizon. Infodensity is the key to valid research, which can be exact in terms of electron picoyoctostructure when interactive topological function mapping is strictly applied.

Recent advancements in quantum science have produced the picoyoctometric, 3D, interactive video atomic model imaging function, in terms of chronons and spacons for exact, quantized, relativistic animation. This format returns clear numerical data for a full spectrum of variables. The atom's RQT (relative quantum topological) data point imaging function is built by combination of the relativistic Einstein-Lorenz transform functions for time, mass, and energy with the workon quantized electromagnetic wave equations for frequency and wavelength.

The atom labeled psi (Z) pulsates at the frequency {Nhu=e/h} by cycles of {e=m(c^2)} transformation of nuclear surface mass to forcons with joule values, followed by nuclear force absorption. This radiation process is limited only by spacetime boundaries of {Gravity-Time}, where gravity is the force binding space to psi, forming the GT integral atomic wavefunction. The expression is defined as the series expansion differential of nuclear output rates with quantum symmetry numbers assigned along the progression to give topology to the solutions.

Next, the correlation function for the manifold of internal heat capacity energy particle 3D functions is extracted by rearranging the total internal momentum function to the photon gain rule and integrating it for GT limits. This produces a series of 26 topological waveparticle functions of the five classes; {+Positron, Workon, Thermon, -Electromagneton, Magnemedon}, each the 3D data image of a type of energy intermedon of the 5/2 kT J internal energy cloud, accounting for all of them.

Those 26 energy data values intersect the sizes of the fundamental physical constants: h, h-bar, delta, nuclear magneton, beta magneton, k (series). They quantize atomic dynamics by acting as fulcrum particles. The result is the picoyoctometric, 3D, interactive video atomic model data point imaging function, responsive to keyboard input of virtual photon gain events by relativistic, quantized shifts of electron, force, and energy field states and positions.

Images of the h-bar magnetic energy waveparticle of ~175 picoyoctometers are available online at http://www.symmecon.com with the complete RQT atomic modeling manual titled The Crystalon Door, copyright TXu1-266-788. TCD conforms to the unopposed motion of disclosure in U.S. District (NM) Court of 04/02/2001 titled The Solution to the Equation of Schrodinger.







26 October 2009, 4:10 PM (3 years ago)report abuse Send to a friend reply

DandamanV (New user):

I'm all for it! Bring in the new age!

26 October 2009, 7:13 PM (3 years ago)report abuse Send to a friend reply

anonymous user Anonymous user