Slashdot Mirror
Supercomputer To Use Optical Router
Izmunuti writes "From a NYTimes article: 'Highlighting a radical departure in the design of the fastest computers, the California Institute for Telecommunications and Information Technology plans to announce on Monday that it will use an optical router
designed by a Texas company as the heart of a
campus-wide supercomputer that will be woven together with optical fibers.'"
Someone figured out that you can pack more bandwidth and less latency into fiberoptics than copper?
More importantly they are actualy using an optical router to prevent what has become a botleneck in resent years. I.e. Data comming off a fiber pipe is converted to electrical signals before being routed to it's next destination where it's converted back to little bity laser beams.
This should be faster than your typical loadsharing super computer (SETI@home) but slower than the miranet using hardcore. With enogh nodes however there is no telling howfast this baby can get.
--= Isn't it surprising how badly I spell ?
RTFA... " Each of the clusters is based on Intel microprocessors and runs the Linux operating system."
I'm not seeing how it's all that revolutionary. Am I wrong in saying it's essentially a Beowulf connected by an optic network?
Also, their statement on the Chiaro Networks "OptIPuter" is here. Caltech is an entirely different animal.
"Prepare for the worst - hope for the best."
Electrical signals travel at around 1/10 the speed of light.
Yay for free subscriptions.. here are some other sources for similar reportings that don't require evil subscriptions.
We're not going back any more than we already are. Ethernet is bits transmitted on a wire via varying voltage levels, which are fundamtally analog. Digital is always based on an analog medium, the only difference is that digital defines a few discrete levels for each chunk of information (eg. 2 for a logic line, 8 or more for POTS modems) rather than the nearly infinite values available for bare analog.
The idea of optical routing is that, even in typical gigabit or any optical based networking media, the bottleneck is the processors in the routers. This is because the light must be converted to electrical signals, and then routing decisions and switching are done on the processor of the router. After being processed, the signals are converted back to optical to be sent out the appropriate port.
Optical switching means that the light coming in on fiber from different devices is never converted to electrical to be routed. The actual light signals are switched from port to port. This was originally planned to be done with very small mirrors! (no joke!) which would aim incoming light to the corresponding outgoing port.
According to the whitepaper on Chiaro's website, they have found a way to avoid the mirrors (which have an obvious bottleneck themselves, as well as potential mechanical failure) and they are able to multiplex or switch the light based on applying an electrical field to some of the optical components which them changes the angle and therefore the destination of the light.
Most of the key people at Chiaro are people who jumped ship from Convex Computer after they were acquired by Hewlett-Packard back in the mid-90s. Convex's claim to fame was to have invented and productized the first mini-supercomputer hitting the sweet-spot between the biggest vax and the smallest cray and they were very successful for about a decade.
Larry Smarr, of UIUC's supercomputing center (aka the place where Mosaic was developed) has always been a big fan of the Convex crowd.
Another bit of trivia - Jeff Christenson, of PERL fame is a convex alum as well as Dave Taylor of Id Software fame and a whole host of other key people now scattered about the world.
When information is power, privacy is freedom.
The innovation has nothing to do with the external connections.
The interesting thing about this switch is that, internally, it routes photons instead of electrons.
Once it sets up a connection, e.g. port-5 to port 17, the photons can "just go". In other words, there are no capacitors(wires) and gates(transistors) to slow things down.
Dispersive media spread impulses. The longer the line, worse the spread, longer the t delta to prevent taking a 1 for a 0 (intersymbolic interference). Coax, waveguides, bifilar couples are dispersive and carry low-freq em waves setting a nasty lower bound on bitrate. Optical WG are the same but max out well within the THz range (serial!) + you can color code signal (multiplex)
Ciao
Mi domando chi à il mandante di tutte le cazzate che faccio - Altan
A new account has been created for the benefit of slashdot users who don't care to register with NYTimes.
Username : SDUser
Password : slashdot
enjoy everybody
click here to login.
In even more breaking news, Slashdot posters stick their feet in their mouths up to the knee.
Electromagnetic radiation isn't electricity, it is light (and associated photons at wavelengths outside the visible portion of the spectrum).
But then again, I could be wrong.
Yes, but the thing to realize about optical switches is that the switching time is on the order of tens of *milliseconds* (as opposed to nanoseconds), because you have to physically move a mirror in order to change the path. It's totally different from an electronic switch in that you're not switching on a packet-by-packet basis.
There are several killer apps for this kind of technology: one is setting up dedicated channels between a server and a client, EG so that you can download a 2GB movie in a couple of seconds. Another is dynamic allocation of channels on the backbone - eg if an ISP gets slashdotted, additional fiber channels could be brought up to the backbone provider or other peers. Finally, you can use it to switch a particular circuit over to an alternate route when a backhoe cuts the fiber, without having to have all the fiber terminated at routers on each end - just move the physical link in between.
It usually doesn't complain when you do whatever it takes to fit it around someone's desk*. Try that with fiber, and you'll rapidly burn through your sense of humor.
.25" radius without damaging it. Fiber is not as fragile as you think, and the pre-cut patch cords are really quite easy to work with.
Obviously you've never worked with fiber. Yes, the big fat cables that go underground are very rugged, and can only be bent to about a 2' radius because of all the reinforcement inside. However, the thin rubber patch cords that you use indoors are very flexible - you could coil it tightly around your finger without damaging the glass inside. The bare glass is even more flexible - you can bend it down to about a
The experiment you reference does NOT show information travelling faster than light.. as is explained in the article.
The waveform appears to exit the apparatus before it enters, but this is not so under scrutiny... as the article says, the beginning of the wave enters the glass (long before the peak) and there is enough information there to re-create the original wave.
There are several phenomenon that appear at first to be superluminal, but they do not violate relativity, and are not actually moving anything faster than light, nor are they transmitting information.
"...optical switches is that the switching time is on the order of tens of *milliseconds*..."
Apparently, this company's optical switch doesn't take tens of milliseconds. They claim it can switch in tens of nanoseconds. They call it an "optical phased array" -- no moving parts. They talk about it a bit on their web site.
To first order, bending fiber does not affect the refractive index. The main problem with bending fiber is that you lose confinement because, from a ray perspective, the light comes in at too steep an angle and you no longer get total internal reflection and you start experiencing significant signal loss. If you go into more detail, bending fiber probably does cause stress-induced birefringence, which does change the refractive index, but this effect is probably small compared with the significant attenuation due to simple geometrical optics considerations.
"It take 9 months to bear a child, no matter how many women you assign to the job."
Strictly speaking, light is a subset of electromagnetic radiation. Thus all light is electromagnetic radiation but, as a general rule, not all electromagnetic radiation is considered light.
"It take 9 months to bear a child, no matter how many women you assign to the job."
The pure optical IP or ATM router is still years away. Optical computing isn't up to optical packet decode and route lookup. Optical buffering isn't ready, either, although you could potentially store packets temporarily in a fibre delay line.
The difference in propagation time is so low that for reaonable-length interconnects, it's going to be meaningless. Light travels around 186,000 miles per second, so under ideal conditions, a fifty-foot interconnect would take you about fifty nanoseconds. We'll use that for the example, it's plenty close for order-of-magnitude calculations.
So, let's say that the difference in propagation speed between copper and fiber is 15%, which is probably pretty high. That would mean a difference of only about 8 nanoseconds.
How much of a difference is that? Considering that the latency of the networking layers is generally measured in milliseconds, or if you're *really* fast, microseconds, that means that the extra latency from the fiber would be anywhere from 3 to 6 orders of magnitude LOWER than that of the networking layers. That's pretty insignificant.
Now if you're talking about running a 1,000 mile interconnect, then the differences become pronounced - but trying to get any decent bandwidth out of copper at that distance is going to be impossible. Ten gigabits over long-haul fiber is commonplace. Currently, the 10 gigabit ethernet over copper attempts have been limitted to a few *feet*.
steve
Oh, you're not stuck, you're just unable to let go of the onion rings.