IBM's breakthrough chip technology lights the path to exascale computing

Dec 01, 2010
IBM has unveiled a new chip technology, called CMOS Integrated Silicon Nanophotonics chip technology, which enables a 10X improvement in integration density and produces smaller, faster and more power-efficient chips than is possible with conventional technologies. Image courtesy of IBM Research

(PhysOrg.com) -- IBM scientists today unveiled a new chip technology that integrates electrical and optical devices on the same piece of silicon, enabling computer chips to communicate using pulses of light (instead of electrical signals), resulting in smaller, faster and more power-efficient chips than is possible with conventional technologies.

The new technology, called CMOS Integrated Nanophotonics, is the result of a decade of development at IBM's global Research laboratories. The patented technology will change and improve the way communicate – by integrating optical devices and functions directly onto a silicon chip, enabling over 10X improvement in integration density than is feasible with current manufacturing techniques.

IBM anticipates that Silicon Nanophotonics will dramatically increase the speed and performance between chips, and further the company's ambitious Exascale computing program, which is aimed at developing a supercomputer that can perform one million trillion calculations—or an Exaflop—in a single second. An Exascale supercomputer will be approximately one thousand times faster than the fastest machine today.

“The development of the Silicon Nanophotonics technology brings the vision of on-chip optical interconnections much closer to reality,” said Dr. T.C. Chen, vice president, Science and Technology, IBM Research. “With embedded into the processor chips, the prospect of building power-efficient computer systems with performance at the Exaflop level is one step closer to reality.”

In addition to combining electrical and on a single chip, the new IBM technology can be produced on the front-end of a standard CMOS manufacturing line and requires no new or special tooling. With this approach, silicon transistors can share the same silicon layer with silicon nanophotonics devices. To make this approach possible, IBM researchers have developed a suite of integrated ultra-compact active and passive silicon nanophotonics devices that are all scaled down to the diffraction limit – the smallest size that dielectric optics can afford.

“Our CMOS Integrated Nanophotonics breakthrough promises unprecedented increases in silicon chip function and performance via ubiquitous low-power optical communications between racks, modules, chips or even within a single chip itself,” said Dr. Yurii A. Vlasov, Manager of the Silicon Nanophotonics Department at IBM Research. “The next step in this advancement is to establishing manufacturability of this process in a commercial foundry using IBM deeply scaled CMOS processes.”

By adding just a few more processing modules to a standard CMOS fabrication flow, the technology enables a variety of silicon components, such as: modulators, germanium photodetectors and ultra-compact wavelength-division multiplexers to be integrated with high-performance analog and digital CMOS circuitry. As a result, single-chip optical communications transceivers can now be manufactured in a standard CMOS foundry, rather than assembled from multiple parts made with expensive compound semiconductor technology.

The density of optical and electrical integration demonstrated by IBM's new technology is unprecedented – a single transceiver channel with all accompanying optical and electrical circuitry occupies only 0.5mm2 – 10 times smaller than previously announced by others. The technology is amenable for building single-chip transceivers with area as small as 4x4mm2 that can receive and transmit over Terabits per second that is over a trillion bits per second.

Explore further: A bump circuit with flexible tuning ability that uses 500 times less power

More information: The details and results of this research effort will be reported in a presentation delivered by Dr. Yurii Vlasov at the major international semiconductor industry conference SEMICON held in Tokyo on the December 1, 2010. The talk is entitled “CMOS Integrated Silicon Nanophotonics: Enabling Technology for Exascale Computational Systems” co-authored by William Green, Solomon Assefa, Alexander Rylyakov, Clint Schow, Folkert Horst, and Yurii Vlasov of IBM’s T.J. Watson Research Center in Yorktown Heights, N.Y. and IBM Zurich Research Lab in Rueschlikon, Switzerland.

Related Stories

EPIC: Building the Perfect Chip

Feb 07, 2008

Three years ago a team from Bell Labs took on a very daunting challenge – put an optical networking system on a commercially manufactured silicon chip, load it with a smorgasbord of sophisticated opto-electronic devices ...

Recommended for you

Restaurants experimenting with pay-in-advance tickets

1 hour ago

With restaurant patrons increasingly jumping on the Internet to make reservations, some high-end eateries here and across the country are adding a new tech wrinkle: having their clientele pay for their meal in advance using ...

Chip maker Infineon to buy California firm for $3B (Update)

3 hours ago

German chip maker Infineon Technologies AG says it has agreed to pay $3 billion in cash for California-based semiconductor firm International Rectifier, which produces power-management components used in everything from cars ...

User comments : 7

Adjust slider to filter visible comments by rank

Display comments: newest first

El_Nose
4.5 / 5 (2) Dec 01, 2010
imagine a cpu that becuase it doesn't use electrical current, just multiplexes of light - doesn't get warm
trekgeek1
4.2 / 5 (5) Dec 01, 2010
Though you'd have less power needed to run the chip, you'd still have heat since anytime light passes through a material you will have some photons absorbed by the medium and given off as heat. This is the reason fiber optic fibers have attenuation despite using light. You lose photons through imperfections. The green house effect shows photons striking materials and becoming heat. Also, once your photons reach the detector, the energy in that photon must go somewhere. A battery runs the lasers, and when it's drained, that energy went somewhere, most likely to a hot battery and tons of photons that lived and died as heat in some detector.
_ilbud
5 / 5 (1) Dec 02, 2010
Yeah there would be no heat, good point. The ridiculous cooling is the problem with ramping up the speed of chips and this should solve it. Mainly though it's just noise to hype lightwave over usb3.
El_Nose
not rated yet Dec 02, 2010
but the lightwave vs USB thing is being pushed by MSFT because that is their technology -- IBM's tech is the interconnect that is on your mobo -- i think
Buyck
5 / 5 (2) Dec 02, 2010
Bye bye petaflop systems... we go to the next level! A thousand times more powerfull system than the current ones!!!

"This is a milestone in science and technology".
JimB135
5 / 5 (4) Dec 02, 2010
I wonder if Microsoft will be able to develop a bloated version of Windows that will be able to slow this beast down??

All joking aside I was trying to conceptualize what might be possible with a machine that could model something in 1 year that previously would have taken a thousand years.
hourifromparadise
5 / 5 (2) Dec 03, 2010
I wouldn't be surprised if research for a zetta flop is already on track.
Maybe it's a good idea to ask proposals of names for beyond a yotta flop.
How can a quantum simulator or quantum computer ever catch up IBM.