Slashdot Mirror
Data Transfer Has A Speed Limit
ChrisHanel writes "Yahoo News is reporting that despite the infinite climb data speeds seem to be making, scientists at Stanford say we'll eventually hit a barrier due to the inability to keep the data stable after a certain transfer speed. But no worries just yet; the watermark they've set is still 1,000 times faster than what we have now." Apparently: "The scientists confirmed this problem by firing up the particle accelerator at Stanford University and blasting electrons at a piece of the magnetic material used to store computer data."
Basicly we will just go back to using multiple headers ( so writting in parrel ) or switch to other storage methods other then magnetic storage.
Todays technology may limit what we can store on a magnetized bit storage system, but I do belive that by the time we hit this limit we will be able to store memories from a human mind in realtime. I think that the storagedevice it self may actually be something quite other than what we today think of as "storagedevices", some kind of human-looking clones perhaps? Lets not forget about Terminator II just yet
"-Who said sit down?!"
-- S. Ballmer @ MSDC 2003.
Massive arrays of the will serve as a common memry block used both for working memory and storage memory.
Of course there will also be a thoretical limit to the bandwidth of these cells and any other means, as if nothing else there will be the time necessary to traverse the matrix.
But paralellism like we allready use can nullify any limits.
And if you thought that was boring you obviously havn't read my Journal ;-)
People once believed that if a train went too fast, that all the air would be pushed out of it.
This proposition is just a modern equivalent of that idea.
Perhaps electromagnetic pulses have a physical limitation with data transfer accuracy, but that is by no means the threshold of data speed in any way.
Once again, RTFA. It speaks of EM data - not all data.
Si tacuisses philosophus mansisses. If you had kept quiet, you would have remained a philosopher.
Even if we can load memories directly in the human mind, we're still going to need somewhere to store all the stuff that won't fit, so we can load it later.
How many Libraries of Congress do you think the human mind can store? Using human minds as data storage makes about as much sense as using humans as energy generators in a big matrix...
2^10 = 1024. So we have 10 doublings of the speed of data left to go right? How often do data speeds double? (Using these methods of course).
I wonder sort of progress will be impacted in practical terms. There are limits to everything of course. Just one more limit. I hope I'm alive to run into some of these scientific limits so I can see what innovative workarounds people come up with.
These posts express my own personal views, not those of my employer
This kind of thing crops up now and again in lots of fields. It's basically the same problem that keeps being predicted with our Interstate Highway system. There's a safe limit as to the speed that we can have cars travelling, and if the highways fill up, bumper to bumper all moving at that speed, we've reached capacity.
The most obvious solution there is the same as the obvious solution here: Add more lanes. If you have thirty-two lanes of traffic instead of one, you've increased your capacity roughly 32 times. Same situation here: Transmit 32 bits in parallel (simultaneously) down distinct channels, rather than in serial (one at a time).
Just as building more lanes is expensive, here the expense comes in multiplying all of the necessary hardware to handle wider data busses for as far down the path as necessary to deal with more data in parallel. Right now, we've got parallel busses inside our PCs, but the bits often end up serialized at some point inside our processors, down at the microcode level. All of these bottlenecks need to be categorized and eliminated to overcome such a theoretical data transfer limit. It will be neither easy nor inexpensive, especially when we decide we need to send and process, say, 2048 bits in parallel in order to meet our data processing needs. At some point, it becomes more economical to separate things on a higher level (add more processors, or add more PCs), similar to building additional highways rather than just adding lanes.
It's hard for thee to kick against the pricks.
(very slightly off topic... sorry.) I attended a physics colloquium the other week in which a professor from Duke was presenting the results of his research into the question of whether information could be sent faster than light through the various ways of coaxing wave speeds to be faster than c in anomalously dispersive media. If you concoct a medium in which the index of refraction decreases as the wavelength of light increases, the "group velocity", or the speed at which pulses propagate, can be made to be faster than c. The "phase velocity", or the velocity at which each frequency of light propagates, is still less than c, but the pulse that each frequency is a part of is going faster than light. The problem is that for the most part, the shape of a wave is pretty deterministic once you've seen a fairly small sample of the waveform. So recieving just the first few microseconds / nanoseconds / etc. of the pulse tells you everything about all of the frequencies which make it up. But he added a nondeterministic part to the signal he sent (through this anomalously dispersive media), changing the shape of the pulse midstream depending on whether he was sending a "1" or a "0". He then timed how long it took before his detector could tell whether the incoming pulse was a "1" or a "0", and determined that despite the media appearing to emit the pulse before it recieved the pulse, his detector still could not differentiate between a "1" and a "0" faster than the speed of light. So Einstein (and Maxwell) continues to be vindicated, and information cannot possibly travel faster than the speed of light.
Computers use since ages parallelism to boost performance whenever necessary. Writing a TB file? Just use an array of 10 100GB HD in parallel. Do you need a 1 Tb/s link? Use 100 optical fiber channels at 10 Gb/s speed. etc.
I believe that Heisenberg's uncertainty principle would suggesti a upper bound for how fast data can be transmitted over a single channel using photons. Can any physicist give me a reason why teh following reasoning would not be correct?
dx*dp = h/2*PI (Heisenberg's uncertainty principle)
Which any one with a undertanding of physics would know implies that:
dE*dt = h/2*PI
E = hf would be the energy of a photon of frequency f. Therefore dE = h*df.
h*df*dt = h/2*PI simplifies to dt = 1/2*PI*df.
If we have a two state device, than this would be teh minimum amount of time we would need to detect a single bit change. Simply invert the equation to get the number of bits/second you could transmit over a single channel.
You probually do have a particle accelerator lying around. Your CRT accelerates electrons onto the screen. If you consider X-rays and microwaves as particles, you probually heat your food with one. Your TV produces X-rays. If you have an old smoke detector, you can probually make a quick and dirty Alpha-gun. (Americium decays ejecting alpha particles).
Although, if you want a High-Power accelerator, that's a different matter and it would be very interesting to do it. Hmm... Use your own power generator? I doubt the power company will be able to supply you TeV's through your power outlet, but then you would need your own Nuclear reactor to do that.
If you can make even a GeV accelerator, that would be impressive. If anyone's heard of such a back-yard project, let me know.
Never let your sense of morals prevent you from doing what's right. --Isaac Asimov
erm moores law
is not a law
its on aboservation about a trend in the commercial development of microprcessors
which the manufactirresr adhere to as it is their entire revenue model.
its not a physical rule.
the guy who came up with it set up intel for gawds sake.
Certainly we are not going to start packaging linear accelerators into hard disk drives, so the kinds of speeds achieved in these experiments would never be observed in an actual recording device," Kryder said. "It's not something that's going to impact anything we're contemplating in hard disk drives
and anyways, the top dogs of HD acceleration tech are found here (was slashdotted yesterday)
Show a man some news, distract him for an hour. Show a man some mod points, distract him for the rest of his life.
Everything has a limit, even data transfer.
I have been transfering data at the known limit for nearly my entire life life. It's called "c" for short.
Anyone who can work the on/off switch of a flashlight can do it.
I believe that it is generally acknowledged that this is a true limit that no amount of thinking may resolve (There may be those who disagree, but it is up to them to demonstrate that such is even possible).
Storing the data is a somewhat different issue.
KFG
http://www.geocities.com/duanenavarre/PRISM-HDSS.h tm
http://www.aprilisinc.com/holographic_storage.htm
Peace !
Ex-MislTech
google "32 trillion offshore needs IRS attention"
No, the upper speed limit on any data transfer is c. With quantum entanglement, i.e. teleporting your data, you don't know when your data has arrived and cannot check unless you are sure. Else you blow the whole transfer. To do this you must send across at least one "bit". Say a single photon.
If you do hazard a guess, you must still perform a measurement to retrieve the data.
All this cannot happen faster than c.
Bollocks. Once the link would be set up and information kept flowing using quantum entanglement there's absolutely nothing stopping the information of new events in the other end to reach the other end way faster than with speed of light. It's not information that "travels faster than light" it's actually the localization that get's broken. This has zero impact on causality.
Einstain's remark about information not being able to travel faster than c was because he assumed that there had to be a "carrier". And it's actually also the quantum physics delocalization that is contradictory with general theory of relativity (for the record, it's not the only aspect either, but hell, we've had to deal with this dualism for better half of a century now).
1 Earth is warming, 2 It's us, 3 it's royally bad, 4 we need to take action NOW
Humans are not that special, cows could also serve as energy generators. The reason The Matrix used this energy idea was because the original idea was about using human brains as CPUs and that idea would have gone over the head of most people.
It cannot. On the receiver side, you get one of four states at random. Those four states are such that every measurement you do on your result will have a random outcome from which you cannot conclude what was sent. Only with the information measured on the sender side and then transmitted through classical communication (and therefore, at maximum with the speed of light), you can decode the function.
You can think of it as if during teleportation, the data sent is encrypted with an automatically chosen random one-time pad. Now the sender measures exactly that one-time pad, and sends it classically to the receiver. Until the receiver gets the one-time pad, he has no chance to decode the message.
You missed the point, you're talking about quantum cryptography, which is quite a different thing.
This is about having the photon source in the middle that sends to two superposed photons to opposite directions. Now, what's amazing is that you can force the state of the other photon in the other end to what you want, and if the other end hasn't checked it yet (it has be that wee bit further) it gets opposite state due to the superposition. And there, once the link's up and running, information can be "teleported".
It basically doesn't "travel" faster than light, it's the localization that's broken, but yes information can go from A to B faster than light would.
Setting up the link is slow however, you need the photon source in the middle and it takes time for photons to fly from the middle to the end points, but when you get the steady flow of photons you can send information at an instant.
1 Earth is warming, 2 It's us, 3 it's royally bad, 4 we need to take action NOW
" maybe I won't need memory any more "
I would guess that would be so if you didn't wan't CPU performance increases. Even if the 1000x limit were reached, memory at that time would still be considerably faster than disc.
One problem with that assumption is that it assumes that you don't have to deal with seek times. Mechanical drives are best for long term storage, they are still far better for linear access, unlike RAM, random access on drives slows things down considerably. In short, you'll still need RAM, even if you don't consider it to be any thing more than a few GB or TB of cache (scaling up WRT capacity needs over time), as it is now, system DRAM could already be considered just another level of cache, so that won't necessarily change with faster drives.
Like the Stefan-Boltzmann law that was derived theoretically, not empirically.
The only link I can find substantiating this is Wikipedia's article on Moore's Law, which points out that hard disk performance has significantly lagged behind capacity. If anyone has hard figures for hard disk speed increases since the early 80s, please post.
The point is, that while a 1,000x theoretical limit might be of immediate concern in relation to CPU speed, extrapolating from the hard disk speed trend, we aren't likely to be hitting a 1,000x limit with hard drives any time soon. (And, as people have pointed out, this only applies to a single head in any case.)
These problems won't be prevalent with holographic storage mediums. When they get it right.
except using humans as energy generators is a really good idea when you don't have much choices as how to produce energy. Humans do a remarkable job at converting complex fuels (e.g., food) into usable energy.
Key Word: Food
Without the sun, there is no food unless machines produce it. And the Second Law of Thermodynamics dictates that the amount of energy they expend in creating the food will be greater than the energy stored in the food; and the energy stored in the food will be greater than the energy put out by the human body. Even if they pumped all the energy back into making more food, the system would quickly run down to zero. And if they had another power source that didn't require them to manufacture fuel (nuclear generators, hydrocarbon burners) then keeping humans alive would be an energy sink.
Les Miserables Volume 1 now up with my reading of
This is all pointless anyway, it is more than obvious in the third movie that there were lightning strikes coming from the thick cloud cover. If the machines were really so smart, they would have simply set up a few lightning rods. Considering that the lightning never seemed to stop, so there would be an inexhaustable supply of energy.
And in keeping with the Back to the Future references, we all know that a single lightning strike produces 1.21 gigawatts of electricity.