Luxtera Lights Up Sun

Ambitious Luxtera Inc., a startup developing photonics in silicon, is getting a big publicity boost from a Sun Microsystems Inc. (Nasdaq: SUNW) win being announced today. But Luxtera continues to snub the telecom world, saying its time is better spent on applying optical interfaces to computing.

The company is working on 40-Gbit/s interfaces -- four lanes of 10-Gbit/s apiece -- for Sun and will demonstrate some of its technology at this week's SC|05 supercomputing show in Seattle.

You might recall Luxtera as the startup claiming to outdo (Nasdaq: INTC) and others in the silicon photonics game. While Intel is pursuing a silicon laser, Luxtera is skipping that piece, instead targeting the other optical parts such as modulators and transimpedance amplifiers. (See Luxtera Chases Silicon Photonics.)

The goal in all this is to build optics using complementary metal-oxide semiconductor (CMOS) methods -- that is, to make them from the same stuff as commonplace chips, rather than from materials such as indium phosphide (InP). Such a step could lower the cost of photonics dramatically, as well as increase manufacturing yields.

Moreover, CMOS carries the promise of integration, further shrinking the size and power requirements of optics. Systems vendor Infinera Inc. has shown some extensive photonic integration in InP. But to do it in CMOS could open a greater spectrum of commercial possibilities. (See Infinera Declares WDM War.)

Alas, Luxtera doesn't want to apply that dream to telecom circles. It's looking like the company's first commercial applications will be for interconnects inside a computer, because that's where the money appears to be. Sheesh.

"There are two primary areas of application for the technology right now. One is DWDM for datacom applications. The other is for vanilla 10-Gbit/s data communications," says Alex Dickinson, Luxtera CEO. Luxtera's first commercial chip, slated to sample in February, will tackle the latter case, he says.

Luxtera is keeping its telecom options open by concentrating on wavelengths in the 1550nm range. For today, though, the spotlight is on the company's chances in supercomputing.

Luxtera's announcement today is tied to the U.S. government's High Productivity Computing Systems (HPCS) program, where Sun is competing with Cray Inc. (Nasdaq: CRAY) and IBM Corp. (NYSE: IBM) for the final contract. The nine-year Defense Advanced Research Projects Agency (DARPA) program started in 2002, with the final vendor or vendors chosen in 2007.

The computers involved here are ridiculously large. Not surprisingly, something that big tends to be inefficient. "It's not uncommon for an application to only realize 5 percent of the peak performance of the system," says Mike Vildibill, Sun's director of HPCS product planning.

Part of the problem is the increasing number of processors needed inside large computing systems. More processors means more interconnects, or even more wires connecting racks or linking far-apart chips. It all adds up to more delays.

So, a key to Sun's HPCS architecture is the interconnects. Sun's HPCS machine is partitioned into modules of densely packed chips. Modules close to one another can speak via a Sun-designed, high-speed electrical interconnect. But for Hail Mary kinds of distances, Sun wanted to shift to DWDM optics, starting at four wavelengths of 10-Gbit/s apiece with the potential to use dozens of wavelengths later.

What made Luxtera right for the job was its CMOS technologies, Sun officials say. That gives Sun the potential to combine Sun's special electrical interconnects and the longer-range DWDM links onto one chip, further shrinking the size -- and the power requirements -- of those chip modules. Eventually, the result could be "tens of terabits per second" worth of interconnect per square millimeter, Vildibill says.

Luxtera is far from unique in trying to apply silicon optics to computing. Just this month, IBM announced lab results that slowed light significantly in silicon, which could become a step towards processing information optically. (For other examples of research in this area, see Scientists 'Stop' Light In a Solid and Storing Light).

"People are working on various building blocks" related to optics and computing, says Fred Zieber, an analyst with Pathfinder Research. "IBM said one of the reasons they were working on it was as a potential chip-to-chip interconnect within a supercomputer. You're still a few years away from functional applications."

— Craig Matsumoto, Senior Editor, Light Reading

Page 1 / 5   >   >>
Pete Baldwin 12/5/2012 | 2:54:13 AM
re: Luxtera Lights Up Sun Any readers out there have experience in optical computing R&D? Anything from optical chip interconnects to sci-fi-style optical routing. It's a bit beyond the LR scope, but I'm curious how much overlap there is.
icenine 12/5/2012 | 2:54:13 AM
re: Luxtera Lights Up Sun I don't get it.

This is LX4 at 10G per channel. A cost reduction play? I doubt it.

What about directly modulated VCSELs at 850nm or 1300nm with one of those Corona bricks? Oh yea, Corona and others are belly up.

I'm confused. There is no optical computing here, just intergrated modulators. Why do that?
DataCenterDunce 12/5/2012 | 2:54:10 AM
re: Luxtera Lights Up Sun They have a White Paper on their website which makes a compelling case for why this is important. Basically the only reason to pull copper was the cost of the optical tranciever and now because of them it means fiber is better technically, operationally and financially.

Unfrtunately I dont understand these issues but it is a very detailed White paper that makes a compalling case - at least to the ignorant

fiberous 12/5/2012 | 2:54:08 AM
re: Luxtera Lights Up Sun Craig, Luxtera team and Sun have been working on a interconnect strategy for a while.
Both these companies are in the doldrums.
Are you hurting for good rumors?

Pete Baldwin 12/5/2012 | 2:54:07 AM
re: Luxtera Lights Up Sun Fibrous -- It wouldn't surprise me if Luxtera was struggling, but the announcement is a data point in the progress of silicon optics. That made it worth noting, I thought.

As for Sun and Luxtera working on this for a while ... sure, but yesterday was the formal announcement, so the story had a timely news hook.
DataCenterDunce 12/5/2012 | 2:54:05 AM
re: Luxtera Lights Up Sun DW and Fiberous

Do you think the white paper is wrong? Where are the holes in it?

Because if it is not wrong then I can see no reason to use Copper for 10G and if that is the case surely these guys are going to be worth a maountain of cash. Aftre all the VC's have funded at least 6 10G over copper startups to the tune of circa $300 and counting!!

Unless you believe that 10G is never going to happen surely this is important and you are wrong to trivialize it?

DarkWriting 12/5/2012 | 2:54:05 AM
re: Luxtera Lights Up Sun Maybe they can get enough power out of a silicon based LED/VCSEL to drive a short "inside the box" interconnect which is why there is no application to telecom.

More likely just some hype to get more VC money. Sun probably is an investor or has employees who were given pre IPO "friends and family" stock. Surprised you fell for this. I thought those days were over but perhaps this is how the startup business has and always will work.

deauxfaux 12/5/2012 | 2:54:02 AM
re: Luxtera Lights Up Sun I don't understand what is compelling about this at all. Assume that the modulator is free now that it is in CMOS. Unfortunately, you still need InP lasers, all of the hermetic packaging associated with coupling them into your "free" modulator and of course, all of the stuff necessary to couple the modulated light into the fiber.

Or...you could use a directly modulated laser (VCSEL or edge emitter becuase, of course, they both have "free" modulators too) and only pay for the coupling into a little Si mux/demux ONCE.

Cool technology, smart guys, insane economics
DataCenterDunce 12/5/2012 | 2:54:01 AM
re: Luxtera Lights Up Sun Everybody seems to be reacting assuming that they know all the answers without doing any research. The following is from an EE Times Article and seems to answer some of your queries.

The company has a proprietary subwavelength holographic lens that couples an MTRJ optical-fiber package directly to its die without the need for expensive free-space optics. The chip itself, made in a standard 130-nm CMOS silicon-on-insulator process at Freescale Semiconductor Inc., routes and modulates light through silicon paths on the die.

Luxtera has proven out the designs of the germanium-based optical photodiodes and modulators used on the chip. It is now finishing the digital design of the device, which could fit into a few square millimeters of silicon, Gunn said. The company is also in an advanced design stage for a 100-Gbit chip commissioned by the Defense Advanced Research Projects Agency. That part uses an array of 10G modulators and photodiodes in an architecture that can scale to terabit data rates, he added

I am trying to understand if what they claim to have done they have actually have done is it a big deal?

The white paper made what seems to be a compelling case for 10G over Fibre and forget about copper.

What pieces are they missing. If they can do it for $100 is it a big deal?
Stevery 12/5/2012 | 2:54:00 AM
re: Luxtera Lights Up Sun I am trying to understand if what they claim to have done they have actually have done is it a big deal?

They've shown singleton devices in a cool technology.

What pieces are they missing?

A business case.

If they can do it for $100 is it a big deal?

No. See DF's description, I think it's pretty accurate. The summary is: If you have a cool optical widget that has a cost of $0, you still pay a bundle of $$ while hooking it up (and lighting it up) in your system.
Page 1 / 5   >   >>
Sign In