Slashdot Mirror
Holy Grail "Opt-Chip" - 100GB/sec?
silicon_synapse writes, "ZDNET has a story about the new Opto-chip which can supposedly transfer data at 100GB per second. Yes, gigaBYTES. A two-hour digital movie could download in 1/20th of a second. The only problem is making the rest of the computer fast enough to take advantage of it. " The researchers are being published today in Science magazine and claim that the U.S. military will be using this as early as next summer. However, I think this is going to be another case of wait-and-see - the technology sounds a little too good - "spray on" application and such.
Argh! Typo again! I've got to cut down on the jellybeans. Try: this link.
It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
The number of routers you'd need to network up every household at this speed would be phenominal, as each chassis has only a very limited number of connections. On the other hand, if you built a national backbone from these, say at 128 Tbits (not unreasonable - 32-64 fibres would not be expensive, and enough routers to load-balance and direct the data would not be inordinate), then built metropoliton networks for each town and city, at the 2-3 Tbit level (again, well within the capacity of these devices and well within what could be sensibly installed, run and maintained), and finally ran 1 Gigabit lines to each house, you could have a genuine broadband network.
(As a totally pointless exercise, I sketched out, for myself, a crude network map, based on this design, and costed it. The numbers look like a Windows serial number, but that's probably still pocket-money for Bill Gates.)
It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
There IS a way to get the full potential of this device, using existing PC technology.
It'd be great for 4-way C&C, or 20-way Netrek. (Who plays Quake anyway? :)
It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
As I understand them, the docs say route. Try this link, instead. (Why they couldn't use Apache, with the spelling check on, I don't know. :)
It's a small world and it smells funny; I'd buy another if it wasn't for the money; Take back what I paid (SoM)
From a quick look at the technical specs, it is routing IP packets (unlike so-called wavelength routers, which just switch DWDM wavelengths). They talk about doing WFQ (Weighted Fair Queuing) etc.
r .html) which is being implemented in Linux, BSD (via AltQ), Windows 2000, and most routers.
All in all, this is a pretty impressive box - other boxes from Juniper and Cisco are already available but don't scale so high. For a good article on the benchmarketing involved in terabit routers, see http://www.lightreading.com/, which also has a great piece on how to succeed in an optical networking startup ('at all costs, stop your engineers from developing a product'...)
Access lists are not very relevant on core routers - all use of access lists, e.g. for multiple-field classification (IP addresses, port numbers, IP Protocol, URL, etc.) should be done on the edge of the network, where the available CPU power per Mbps is much higher. This is part of the standard DiffServ model (details at http://www.ietf.org/html.charters/diffserv-charte
The idea of DiffServ is that the edge routers do the hard classification, then encode this in the packet in the TOS byte in a 6-bit number called the DiffServ codepoint. From that point, all routers just have to check the TOS byte to see which queue to use for a packet, which is pretty fast and much easier to do in hardware. Linux has pretty good DiffServ support - see the Advanced Routing HOWTO for details, or the article in Linux Journal this month.
- It mentions that the substance can be "painted on". How would it be applied to create the type of etched patterns required for a microprocessor, ram chip, etc.?
- Digital applications require on/off transistors. Does the fact that the substance has a really fast transmission rate mean anything in an of itself, or is there another fundamental discovery (how to make a transistor out of it) required?
- What about bleed over/cross talk?
- Switching speed?
As you can see, I'm limited in my knowledge of anything but the basic electronics, but that's where everything starts. So I invite y'all to fill in the blanks, so I can sit back and learn from the commentary....Open Source isn't the only answer -- but it's almost always a better value than the alternatives...
Does anyone else remember this article from a year ago about the first "photonic circuits" being developed by a company called Nanovation? The link to the story in that article is dead, but I found another one. Ever since then, I've been pondering how to get around the hideous bottleneck that modern memory is, and the only solution I've arrived at is to make an optical RAM equivalent based on similar technology. The only problem is that, I haven't been able to figure out a way of connecting it to the CPU without basically including it as an unupgradeable L2 or L3 cache with normal slow memory beyond it.
Now, however, we have a device capable of nicely interfacing with an optical cable for 100 GB/sec speeds. This may be the interface we need for making "slots" for upgradable optical RAM. Cool! I can't wait to get to move to fully optical computers. This is the technology of the future. I just hope that the people creating these technologies will be willing to license their patents out to other companies.
If it's for-profit but free, you're not the customer -- you're the product (e.g., the Slashdot Beta's "audience").
This is hilarious. I just read the first 5 posts on this article. All ACs, all score 0, but all good posts. What is wrong with the moderators? Why are these posts at the same level as the grits guy? Read at -1 moderators! In my opinion it signals a big problem that the /. moderation system wasn't designed to handle. Now that /. was a much larger readerbase, not everyone will be a member, and not everyone will bother to make an account. Also with the hidiously increasing number of trolls, moderators are increasingly moving to reading at 1 or above. That leaves out a lot of ACs who have a good point, but either don't want to bother to create an account, or have an unpopular viewpoint and don't want to endanger their account. I suggest that the moderation system be changed to something so you can browse based on what it was moderated to, not just the score. So people you could browse by insightful, or AC, and ignore the troll or flamebait posts. This would also require moderator to more activly moderate down the trolls, but they are more willing to do that than moderate up the ACs.
A deep unwavering belief is a sure sign you're missing something...
Some of the cool stuff some researchers are doing is integrating a laser onto a normal ASIC.... That means that the connection from the chip to the rest of the world is optical rather then the usual bondwires and (relatively) slow electrical ones.... That means that if you have a chip with a 1GHz internal clock the whole system can move data around at the same speed - stick a few of the lasers in parallel on the same chip and youve got a 1GB/s connection with the rest of your system...
Now all we need is a way of producing RAM and peripherals that keep match with the speed....
StormChaser
100 GB/s periphs are not useless in todays market. Just because your rusted-out Pacer can't handle the Autobahn doesn't mean it can't cruise along at 55. Say the bus could techically handle 400 MB/s. That's still three times faster than the realized throughput from a pair of Yellowfin Gig Ether, and ten times as useful!! A 100 GB/s limit is like money in the bank!!
.sig: Now legally binding!
Recently there was a web design contest that had a very interesting constraint. All entries had to be less than 5K, with no server side help (Note: The contest is closed now). There were over 1,000 entries and it really generated a lot of buzz. Many egos are at stake here! The FAQ indicates that there were five DHTML recreations of Space Invaders, four versions of Simon, and six 3d Maze games! All less than 5K. People can do more with less.
The reason I mention this is that file size, download time, and bandwidth are critically important to all kinds of people. The contest I mention reflects a kind interesting return to the basics. What can you do with as little as possible? People of all types, from programmers to artists to system admins, actually want to do more with less, but they don't for a number of reasons. Argh!
Perhaps the internet pipes that companies are building are less necessary than we are being told. Certainly the need would decrease if we could remove layer after layer of bloat.
While some applications need the power, many don't. More and more features don't necessarily mean you're getting a better application. Quite the opposite is often true.
Theory: More bandwidth is being requested because too people are lazy or because executives are too stupid to facilitate good coding and project management. The average geek certainly doesn't want to be lazy; the average geek is detail oriented and they want to kick ass. Small, useful applications are beatiful things. In any event, I wonder how much a pipe most people really would need to have if we were all able to be more effecient from day to day.
John S. Rhodes
Usability and a whole lot more...
http://webword.com
How to Download YouTube Videos
"Damn what I could do with a 100 GB/s download speed. What are some of the things you'd do?"
Isn't that just internal transfers? I mean you will not be able to download at 100GB/s with a 56k modem.
Slashdot social engineering at it's finest
Gods - just imagine if you could actually get EXERCISE moving through those multiplayer RPG worlds, or perhaps playing those virtual fighting martial arts games. You'd have entire generations of Conans & Bruce Lees, who might have never left their house!
maybe wiring CAT5 into every room of every house, same as electricty and phone?).
Why not? Does this sound so laughable to you?
No, it sounds like a damn good idea. But a lot of people just aren't getting it yet. I (along with 3 other people) are going to be leasing a house starting May 1. It was just rebuilt from scratch. Is there CAT5 installed? No. Is there conduit so we can easily put it in? No. It's very very frustrating. We're looking at HomePNA stuff but I'm not sure if any of it works with Linux. I may end up having to get a seperate DSL line from the other 3. It's just a big pain in the ass. Arrrghh!!!
Actually, silica (glass) and sapphire make much better fiberoptics then any polymers do. It is true that Organic materials are easier to process then glass, but they provide too much optical interference to be useful for longer then a few feet. A single glass optic cable can run for miles with little or no quality loss.
On optical chips, they are using tiny (<1um) cylinders made out of sapphire to bend light in a sharp 90 degree angles. This is part of what makes devices like this possible. In the past light had to be bent in long optic cables with a large radius, or be reflected. These cylinders, refract the light at 90 degrees and will hopefully make more "optic circuits" possible in the near future.
I'm Finishing up my Masters Degree in Ceramics Engineering
-
As people have pointed out in previous threads, actually backing up modern disk capacities is a nightmare; my current machine has over 50 Gb of storage, and there's no consumer backup media that can realistically cope with that sort of capacity in any reasonable timeframe.
Remote mounting an encrypted partition on a remote server could work quite nicely. In fact, with the sort of bandwidth that's being quoted here, you could quite happily boot off it, although the access times could be a pain.
I'm still sceptical about the claim that this is more bandwidth than we can use, though; internet users have proven themselves to have an almost limitless capacity for pornography, and streaming DVDs would eat a lot of network... :)
I'm a little spaced out due to tremendous studying, which is coincidentally on a topic similar to this. My question is, "Didn't they basically just make fast, efficient transducer?" If the answer to that is, "Yeah", then we really don't have that much to get excited about.
There's still the ultimate problem of increasing the speed of electrical processing. We've got optical routers, so this new material would basically just be used once the data is ready to be processed. And then it's back to transistor sizing, copper traces, barrier tunneling, and all that wicked stuff that nobody is ready to solve.
It's kinda like an old grandma driving a Diablo... you know the car can go faster, but you know that SHE can't ;)
-- Dr. Eldarion --
Wow that's pretty slick. Unlike all the other people who've posted so far, I'm not going to complain about not being able to use this bandwith, instead I'm going to reflect on the sheer amount of porn that one could download it. I mean with ethernet I, I mean someone, has the leg up on 90% of the us population, but with this EVERyBODY could get their porn. New age of democracy is what I'd call it. It gets my thumbs up.
One other thing, I am AMAZED that the porn industry doesn't sponspor more internet technology, according to my statistics 90% of the bandwith is used for this purpose alone. If only we could get like porn only aisles through the internet.
sweetness.
-dennis the kid.
And you have a system that can keep up with the byte firehose...
Then we would finally have the bandwidth required to push enough information down the pipe to a system to create a true, functional, VRML interface. Get some gloves and a vision rig, munge up some software to do the data to image translation (which is being worked on for the Internet2 project) and let the games begin!
Who'd care about flatscreen monitors then? Would carple tunnel be a thing of the past? Would it make information overload a true psychological problem? You decide!
The article stated that the device would be useful as a modulator converting signals from fiber optic cables or satellites. Aren't these two completely different problems? Satellite signals would need modulation through an antenna, and optical fiber signals would need modulation through an optical input.
Does this logically mean that the chip has 3 input/outputs? And can switch effortlessly between any 3? What physical form would a modulator like this take?
Also, the material can be sprayed on, but what method do they then use to etch circuits? Are there any scientists out there who can answer these questions?
PS, please check out my new Privacy and Security forum at http://www.idmaweb.com.
Busses need to be wider, not just faster. Considering that the adaptation of 32 bit computing was hampered for years by a prevalent operating system manufacturer, it seems GNU/Linux may finally come into it's own as hardware architectures diverge from x86 standards. Given that 64bit processor support has been shoehorned into Linux for quite awhile now, Linux stands in an excellent position to foster competing cpu architectures, as opposed to differing brand names essentially presenting the same product. Bring on the cheap 64 and 128 bit processors, Linux can be compiled to adapt. Whats more, single chip multi-processors may be a little down the road. We seem to be at the threshold of a GNU era for hardware nerds. -Gary
Not really... it's just like fiber.. the thing can support pretty fast traffic, but noone has the capacity to feed it fast enough. Suddenly we have a fiber interface (this..thing...) that can go at fiber speeds... Now nobody can feed the interface fast enough :)
I'll preface my remarks by saying that I haven't read the Science article and the ZDnet article seems pretty short on scientific details. That said, this is one of my research topics, so I know a little bit about the area.
First off, I've seen some questions about the quote of "spraying" onto a chip. There are a variety of techniques, but I'm guessing they're talking about spin-coating or CVD (Chemical Vapor Deposition), which are both used routinely in manufacturing.
Secondly, these electro-optic devices use "second order nonlinear optics" (for all you physics geeks). Basically, people have been using crystalline modulators like lithium niobate for years, but they're very expensive and hard to make. So most of the research in the area has gone into making organic/polymer/self-assembled modulators. The idea is that you encase your chromophore molecule (the "active ingredient") in a polymer or other strong-film environment. Then you use this film in a waveguide and use it like a switch. The best mental picture would be a railroad switch--the electrical signal switches optical tracks for the optical beam.
Without reading the published results, it's hard to know if this is really a breakthrough. My questions would be whether it's actually a new chromophore that's giving better results, a better preparation method, or something else. It sounds like they're making some change to the preparation of polymer devices, which are behind the self-assembled films many labs are making now.
Suffice to say, the *real* revolution will come if anyone can get a usable third order NLO device. This would allow optical-optical switching.
-Geoff
Stupid question time - what is the maximum switching frequency of a plain old phototransistor?
Exotic technologies are very neat, but I'm wondering if more conventional technologies might already work.
If phototransistor switching speed is comparable to ordinary transistor switching speed, you could probably build an optical transciever more cheaply by using closely packed frequency channels with bandwidth comparable to the switching speed, and a prism or diffraction grating to split them for parallel reading.
I think you are missing the point here. The Bell Labs benchmark was done at 40gbs a channel. This story is talking about 800gbs on one stream of light or channel. (Not that I think /. is very current on its news either...)
"The experimental GigaChannel Ethernet multiplexer combines up to eight independent gigabit Ethernet signals into a single 10 Gb/s signal
stream."
It sounds dopey, but it actually makes sense - what they are saying is that they can fit 8 Gigabit ethernet channels into a single OC-192 carrier (OC-192 is an industry standard, ~10Gbps SONET optical data rate) They can't fit 10, because there is overhead in any SONET stream, and they'd need extra overhead to split out the 1Gbps channels from one another. It seems like they ought to be able to fit 9 channels in there, if they really wanted to.
A thought just occurred to me - they may not be TDM muxing the 8 signals at all, but rather they are saying that they can cram 8 1Gbps carrier signals into the same frequency range that would normally carry a single OC-192 carrier. This would make it easier (read: cheaper) to split out one channel to drop it out at it's destination without having to have expensive 10Gbps/1Gbps mux hardware at each terminus, and it is consistent with them needing to have guard bands [dead frequencies between the carriers so one signal doesn't stomp on the one next door] between the 8 carriers. The more I think about it, the more I'm convinced this must be what they are doing - the other way would be *way* too expensive.
So, loopy as it sounds, fitting 8 Gigabit Ethernet channels into the 'space' of a 10Gbps optical channel makes perfect sense when taken in context.
I hate it when people talk about discovering more bandwidth that we can use ( or process ). When has this _ever_ been a problem in our history. My immediate reaction to this is that if the MPAA were to read that article, they'd be needlessly ultra paranoid about DeCSS. I say this because you and I will NOT be able to practically download entire DVD's any time soon. In order for us to have 100G / s bandwidth right now with that technology, it would have to be an isolated point to point network. Which means that you will probably be very familiar with the other end of the connection. The fear of DVD copying usually involves complete access to the entire web and a random end point for transmittion. The statistical likelihood of a desired DVD being on your other end are rather slim.
Another use for this 100G network would be in an office situation but again, unless you've got a point to point star network, you're multiplexing someone's data which will reduce your bandwidth ( to well within a computer's processing capability ). Still, it's a hell of a lot more than what we have now.. But again, live video feeds are from static, known points ( mainly within your building, or between a finite number of known buildings ).
So then, let's apply this technology to general publicly available internet connections. What do we have.. Raw bandwidth that will be soaking up by Linux distribution downloads, pr0n and general web-site traffic. Meaning if you put more bandwidth up, then the population will increase the volume of it's downloads to fill it. It's a basic trend that I'd be hard pressed to not call fact. And lets put this into perspective.. These 100G connections out on the internet are hardly going to be noticed over the existing high bandwidth lines where the routers are the slow point. Yes you can put high perf routers, and yes you'll eventually be able to maximally traffic this data, but your 56K modem or 1Mps cable network is not going to take advantage of it. And I'm doubting that we'll see home connections any time soon. Buisnesses that can afford such a connection are probably going to be saturating it. This is because it's probably not going to be cheap, and a business doesn't usually indulge in a technology for economic efficiency reasons.
Will this help? Of course. Will it be great? Hell yeah. Will you realize any benifit? No. Because it's like a savings account interest rate when there's inflation. You may be getting 10% interest in your savings account, but if inflation is 15%, that doesn't get you anything more tomorrow than you have today ( you'll just be hurting less than if you only got 2% interest ).
The biggest threat I see to the internet is video feeds ( hence my focus in this article ). If the public sees high bandwidth, they typically chant video, which, in my mind, if it ever comes to fruition then imagine the effect of thousands of homes leaving their internet TV connection on all night ( like we do our internet radio here at work ). This is just a rant, but it reflects my current paranoia about public bandwidth.
-Michael
-Michael
Now now now, don't forget yourself. If you realy wanted to increase bandwidth, on a board, you'd either need fiber chanels or massively wide busses. Both of which are rather expensive, not just for the motherboard, but for the periferal manufacturers. The whole driving force in the PC industry has been supply and demand. IBM pushed MCA back in the 386 days ( absolutely better than ISA ( and probably even better than EISA ) ), but obviously the world didn't stampeed to this technology ( just like they don't stampeed to Alpha's apparent superiority, even though they can technically still run the same programs ). Granted IBM was proprietary. But the point is that the PC industry _can't_ just supe up their systems, because that costs money, and S & D requires an equilibrium for profit maximization ( and in the PC world, that just about breaks you even ).
There's also the case of compatibility. Even if you could produce as superior device in both performance _and_ price, you run the risk of lack of compatibility and thus you can only play a nitch and thus S&D kills you again.
The reason the PC industry has been technologically advancing so quickly is because there has been competition for maximally compatible components that simply run faster. ( Plus a segmented market with some willing to pay premium, and a large majority demanding the cheapest ). If we didn't have that diverse market, we'd still be running a 486 class machine today. ( And Alpha's wouldn't be windows 3.5 compatible )
-Michael
-Michael
- more pins (# bits/clock)
- higher clock rates (greater bits/time)
- move the bus on chip meaning you can't just plug in a new card
The first two mean more power - power being (very) roughly proportional to the number of pins and how fast they are waggling - and as a result hotter chips. The more pins solution breaks down pretty fast - you can double the bandwidth by doubling the bus width only so many times before running into packaging problems - remember at high frequencies you need 1 power/ground pin for every 3-4 signal pins - also plug-in card with >64 data pins are probably impractical Bumping the clock rate while keeping the bus narrow seems to be the way some parts of the industry's going (1394, RamBus, the new fast USB etc).For most of the PC space the third option is probably going to be what you see - more integration - buses going away or being pushed on-chip meaning that the chances for plug-in high bandwidth goodies are virtually non-existant - instead you get what was chosen for you by the person who chose the chip when they put the motherboard together.
Anyway the thing to remember TANSTAAFL - everything is a compromise.
... download a Jon Katz article without having to go for a cup of tea?
But seriously, this sounds like a great technology, and one needed to implement the "Internet of the Future", whatever that may be, put it is only one technology out of a host which are required. Sure, in the short term this will give rise to improvements in data transmission, but until a series of other breakthroughs are made this won't reveal its true potential.
So yeah, 100Gb/second is possible, but not for quite a while yet.
Some of the cool stuff some researchers are doing is integrating a laser onto a normal ASIC....
[...]
Now all we need is a way of producing RAM and peripherals that keep match with the speed....
For the RAM, at least, the answer is straightforward. Keep latency at its current range, but _heavily_ interleave RAM both on a bank level and a chip level. You now have RAM that can get 100 cache row requests and service all of them with a batch latency of 7 ns (or 5 ns or [etc]).
This would let you, say, put 8 or 16 cores on a die without worrying about cache misses slowing you down (as long as you have a deep miss buffer).
This would also be useful for transferring vast amounts of data with good locality in a known pattern (for instance, triangle or texture data) from RAM to a peripheral.
This is probably what busses will look like in a decade or two, as it's much easier to eliminate cross-talk and interference on an optical bus than on an electrical one.
Here is a research that is done at Lucent Technologies:
Instead of switching from optical wave to an electrical charge they use optical repeaters with mirrors and optical amplifiers.
"The DWDM-ready GigaChannel has been demonstrated over 40 kilometers of standard single-mode fiber using WaveStar MetroPoint and also over Lucent's flagship long-reach product, the Wavestar OLS 400G, using multiple 80-kilometer fiber spans with online erbium-doped optical amplifiers and dispersion compensation."
However it's only 10GB/s. Maybe they'll learn to do better than that.
"The experimental GigaChannel Ethernet multiplexer combines up to eight independent gigabit Ethernet signals into a single 10 Gb/s signal stream, enabling switches, routers and servers to connect at 10 Gb/s in native Ethernet format without the need for protocol conversion. The prototype complies with today's IEEE Gigabit Ethernet standard."
You can't handle the truth.
IO performance has always been a problem with PC's. We've had PC's around for how long... and all we have to show for it is AGP 4X????
While CPU horsepower has been following Moore's law pretty well, the PC world has lagged behind in terms of bus bandwidth. "100GB/sec" peripherals are useless when your bus runs at 133Mhz.
Let's start pushing chipset and memory manufacturers to start putting out faster busses and memory subsystems, and then PC's will finally begin to approach supercomputer-level performance.
________________________________
Terabit and faster networking isn't totally cutting edge anymore. Lucent is talking about sending many terabits per second over a single fiber.
What is interesting is the ability to process packets at that speed. This chip is critical in converting that optical stream into an electronic stream. The other part is a CPU or multi-CPU architecture to process the data. I'm sure Cisco is very interested in this.
So with Lucent figuring out how to send multiple terabits per second over a single fiber, this company able to convert those signals into electronic form, and hopefully soon Cisco being able to process and route data at those speeds, we'll soon be able to forget about bandwidth issues on the Internet. Or to be more precise, the bandwidth issues will become almost entirely limited to the link between consumers and their ISPs.