Exabit Transmission Speeds May Be Possible 98
adeelarshad82 writes "Scientists at UC Berkeley were able to shrink a graphene optical modulator down to 25 square microns in size (small enough to include in silicon circuitry) and were able to modulate it at a speed of 1GHz. The researchers say that modulation speeds of up to 500GHz are theoretically possible. According to the research, due to the high modulation speeds, a graphene modulator can transmit a huge amount of data using spectral bandwidth that conventional modulators can only dream of. Professor Xiang Zhang, in an attempt to boil his group's new findings into consumer-speak, puts it this way: 'If graphene modulators can actually operate at 500GHz, we could soon see networks that are capable of petabit or exabit transmission speeds, rather than megabits and gigabits.'"
Re: (Score:2)
Re: (Score:2)
Think of what a boon this will be to the wireless telcos on SMS fees:
That's about a half dozen US annual GDPs of SMS charges racked up every second, over one thin fiber!
Pointless? (Score:1)
I fail to see the point unless we also get processing speeds able to keep up with the data.
And specially storage speeds. SSDs don't cut it.
Re: (Score:1)
Just like airplanes, telephones, and cars. All of them. Completely. Pointless.
Re: (Score:2)
I have no idea why people come to slashdot just to post as an AC and denounce every new bit of technology.
Luddites are alive and well in the 21st century, it's just amazing how much effort goes into it these days.
Re: (Score:1)
Considering the speed of tech, it requires a lot of effort. When you carry a mobile multifunction computer in your pocket, it's a little hard to denounce progress.
Re: (Score:2)
Duh [wikipedia.org]
Re: (Score:1)
You beat me to it :P
Damn you!
Re: (Score:2)
With transmissions speeds that fast, processing and storage can both be dumped on someone else without worrying about filling the pipe.
Re: (Score:2)
Many systems connected to many systems. It doesn't have to be to/from a single CPU or storage device. You can put your datacentre where it is most efficient in energy or cooling terms, but have it appear to be where you want it operationally. Or you can aggregate datacentres scattered across the globe into a unified system, load sharing as the peak load moves round the globe. It makes the physical attributes of "the cloud" more possible.
Re: (Score:2)
Re: (Score:3)
And specially storage speeds. SSDs don't cut it.
Oh of course they do. You just have to use more than one, in parallel / striping mode. Think of a "real" NAS or an IBM DASD with dozens of drives in parallel.
Probably this will be used mostly for DWDM style stunts... Find the fastest system and its press release. Insert two in a box twice as big. Issue press release to the mass media, and sadly, /., reporting "new world record of twice the libraries of congress per second". The general public responds with "who cares" because that kind of press release
Re: (Score:2)
Re: (Score:1)
Uhmm, need I point out the obvious? ... 1 Exabit/sec / 100,000,000 users = 10 Terabit/sec bandwidth per user. Yes, I know there's overhead, distribution across large distances, etc, etc that would lower the realistic bandwidth. But, it means each user could still have a crazy amount of bandwidth.
Re: (Score:2)
At those speeds, why would you need to store anything locally?
Re: (Score:2)
i agree with you that is it pointless. mostly because this statement, "we could soon see networks that are capable of petabit or exabit transmission speeds", incorrectly uses "we". "we" being large ISP's and people in academia, maybe. "we" being the people getting bandwidth to our homes, completely unlikely. "we", being the later in most U.S. locations, can't even get fucking fios in our neighborhood!
Dispersion! But On-Chip Networks... (Score:3)
I haven't done the math, but at 500 GHz it seems like dispersion [wikipedia.org] would make any network longer than a single chip fundamentally unable to use that kind of frequency.
For a mesh network-on-a-chip though, you could probably dumb down the routers a lot (you'd have to to let them operate at that freq), and basically trade inefficient routing for a way higher link rate... basically operate the network such that you can deliver a message 100 times faster than than you can send 1 message. The routers may not even n
Faster than silicon (Score:3)
That just leaves two fatal flaws:
1. You need to modulate the electric signal with useful information at 500ghz. I'm not an expert, but it seems like we're a long way off from being able to do that. Can anyone comment?
2. How do you demodulate such a signal?
Re:Faster than silicon (Score:5, Informative)
1. there is a logic which is nearly fast enough. It's called RSFQ, but interfacing it to graphene may be difficult.
2. with RSFQ ADCs.
If its about analog mixing, you could use bolometer mixers, interfacing to RSFQ circuits.
Re: (Score:1)
1. there is a logic which is nearly fast enough. It's called RSFQ, but interfacing it to graphene may be difficult.
Dude, Reading Something Freakin Quick won't cut it.
Re: (Score:2)
Building it on a meaningful level is hard enough, as it requires supraconductivity. Costs would be astronomical.
That said, tech mentioned in OP, unlike RSFQ doesn't even exist yet. It's just a working theory. By the time it's working, there are bound to be ways to use it.
Re: (Score:2)
Pulse tube coolers are not terribly expensive and they are off the shelf components: http://www.oxinst.com/products/low-temperature/pulse-tube-coolers/single-stage-tube/Pages/single-stage-pulse-tube-cooler.aspx [oxinst.com]
As a matter of fact, RSFQ id being tested right now for space constrained situations for transceivers. And it may pay off at some point to replace parts of conventional cell base stations by RSFQ ADCs.
Re: (Score:1)
Re: (Score:1)
Re:Faster than silicon (Score:5, Informative)
Re: (Score:2)
And that's the key problem: you can't just replace the 40-GHz modulators in a 50-channel x 40-Gbit/s fiber system, because the optical frequencies of the channels must be spaced widely enough that the channels won't overlap. These ultra-high-speed modulato
Re: (Score:1)
You fan in and fan out in several stages, the later of which are graphene based.
Re: (Score:2)
It's nice to think about this tech on a large (optic-fiber networks) scale, but the applications on a small (silicon wafer) scale are, IMHO, more interesting.
Re: (Score:2)
1. By the time graphene is ready to be modulated at 500GHz we will almost certainly have the technology to modulate the graphene at 500GHz. It requires a transistor with unity gain at roughly 1000GHz to do that. State of the art university and military researchers are building both analog and (very simple) digital circuits in the 300+GHz region using transistors with unity gain frequencies at 1THz and above. They are using group III-V heterostructure devices such as InGaAs/InP heterojunction bipolar tran
The race is on (Score:2)
Will graphene computing be the new quantum computing henceforth?
Re: (Score:2)
Not really. Even 500GHz processors would still be extremely slow compared to quantum computers for crypto stuff, though this technology could presumably be used to make a very nice system bus, useful for graphics processing and other bandwidth intensive applications..
Re: (Score:2)
Re: (Score:2)
data storage? (Score:1)
Re:data storage? (Score:5, Interesting)
It's all well and good having super fast transmission capabilities but do we have anything that can process/store data as quickly? It's an honest question as I've always been lead to believe that data storage is the bottleneck.
Infrastructure is where this is important. There are these extremely expensive cables made of glass under the ocean connecting various land masses. It's extremely convenient to be able to upgrade the boxes at either end instead of laying more tubes (*warning* simplification!). You don't need to store the data (at least not in one box), you just need to switch it. This is why fiber is so awesome; people just keep on discovering new ways to jam more down those pipes!
Re: (Score:2)
There are these extremely expensive cables made of glass under the ocean connecting various land masses.
More importantly, the fibers themselves aren't that expensive anymore as you can see from FiOS/FTTH deployment. Getting new cables in place is what costs an arm and a leg. So more capacity over same cable is very, very cost efficient.
Also a comment to the GP:
It's an honest question as I've always been lead to believe that data storage is the bottleneck.
If you have streaming, is storage really all that necessary? With Spotify etc. for music, Netflix etc. for movies - and assume you can stream BluRay quality effortlessly, what do most people need TBs to local storage for? Yes, there are niches like when
Re: (Score:1)
Can these modulators replace existing ones or does the entire cable network need an upgrade for this? If it's just the modulators, then wow!
Re: (Score:2)
Good question, as far as I can tell there are some variations in fiber optic cables so impossible to say. Most cables are built to work in some rather narrow bands at extreme speeds, you might get the 500GHz with regular cables but probably not full spectrum. This is mostly guesswork though.
Re: (Score:2)
For all the software they use but never paid for and have no intention of every paying for, porn, personal documents, porn, backups, porn, backups of porn, music, porn, backups of music and porn, home movies, porn, games, porn, porn games, pictures, porn, emails, porn, porn emails, and of course, porn.
Not everyone wants their stuff in "the cloud". Having something at your location gives you faster access than going to a site, no matter the transmi
Re: (Score:2)
This is why fiber is so awesome; people just keep on discovering new ways to jam more down those pipes!
Same reason why porn is so awesome.
Re: (Score:1)
Not at all levels (Score:4, Informative)
You have to remember that the more bandwidth you want to deliver to the end user, the more you've got to have in the backhaul. Like if at work you want to deliver true 1 gigabit to 1000 people's desktops, you can't very well then have a 1 gigabit connection out to your data center. They won't get a gigabit of performance.
So while speeds like this wouldn't be needed for servers or such, they could be for big links. You want to link big_router_a with big_router_b which have all sorts of very fast connections to smaller routers then maybe this interests you.
Re: (Score:2)
No, but you probably don't need 1000 gigabit either. At the giant LAN party "The Gathering" this easter they had 5200 people and a 100 Gbps uplink, but the traffic mostly stayed in the 10-12 Gbps range. True, the ~140 table routers were limited to 2 Gbps each, but that is still only 5-6 of those maxed. And those are pretty much all computer enthusiasts spending their easter there.
The NIX (Norwegian Internet eXchange) in Norway tops out at about 70-80 Gbps maximum for 4.96 mio people - that isn't all Interne
Re: (Score:2)
True, you don't need 100% backhaul. The more people you have, and the faster the connection, the more you can pack in to a given connection. People use in spurts and it all kind of evens out. However it still gets to be pretty massive. The connections their teir-1 ISPs have between each other and between big points are massive.
Also I think we'll be able to find a use for quite a bit more bandwidth to the home. I've got a 50mbit line (officially, actually seems to be more like 100mbit most of the time) and I
Re: (Score:2)
I can assure you that there will still be plenty of "promises", no matter how fast things get..
Re: (Score:1)
Re:data storage? (Score:4, Insightful)
Latency is why. It doesn't matter how fast the link to your storage is, if it's several ms away from you the delay gets annoying *real* fast.
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
Yes, but is it OVER 9000?! (Score:2)
Re: (Score:1)
Actually you can have a torrent of torrents; at least rtorrent has the ability to scan specified directories for new .torrent-files, and automatically add them to your queue (and move them to destination folders if finishied, so you can download your torrent-torrent to that directory and automatically add them to your conventional torrent-dir. However, I'd go for a simple zip-file and a web-interface where you can check the torrents you want to download, and then download and unpack the zip file with all th
Re: (Score:1)
Re: (Score:1)
Amazing (Score:2)
Woohoo! (Score:2)
With all this extra bandwidth, AT&T will up their quotas from 150GB to 200GB!
Re: (Score:2)
Re: (Score:1)
Re: (Score:2)
If anything, they will increase a few cryptic line items on your bill to "support" the rollout of the technology, then cackle all the way to the bank while you use up your monthly cap in only a few seconds.
Assuming a growth rate similar to Moore's law... (Score:2)
This technology should be ready for market in about 13.5 years. Going from 1 ghz to 500 ghz with a doubling every 18 months will take 9 periods. Let's add a few years for developing the tools necessary to mass produce and we are at 15-20 years. Obviously there is no reason to believe that this technology will follow a similar growth curve. It likely will be substantially worse. It's nice to know we have some theoretical headroom but there is even less to get excited about here than when there is the pr
Use it for data storage (Score:2)
Re: (Score:1)
The delay line memory [wikipedia.org] inventors would be very happy to see their technology used again....
Seriously though, such delay lines are actually used in routing to avoid storing incoming packets in memory.
Re: (Score:2)
I'll just be happy when I can get one of these exabit transmissions for my pickup.
Well... (Score:1)
They might be possible, but then how would the telecomm giants justify drastically inflated bandwidth prices?
Always look for the money...
But... (Score:2)
How many porn movies per second is this?
Xzibit? (Score:2)
Yo Dawg,
I heard you like me so we put my music videos on Xiang Zhang's graphene modulator network so you can watch Xzibit on Exabit.