Slashdot Mirror
Nano-Scale Memory Fits A Terabit On A Square Inch
prostoalex writes "San Jose Business Journal talks about Nanochip, a company that's developing molecular-scale memory: "Nanochip has developed prototype arrays of atomic-force probes, tiny instruments used to read and write information at the molecular level. These arrays can record up to one trillion bits of data -- known as a terabit -- in a single square inch. That's the storage density that magnetic hard disk drive makers hope to achieve by 2010. It's roughly equivalent to putting the contents of 25 DVDs on a chip the size of a postage stamp." The story also mentions Millipede project from IBM, where scientists are trying to build nano-scale memory that relies on micromechanical components."
I'll be able to store my gigaquads in a compact space.
They were talkig about this a while back on simulatedlucidity.com
Last time I checked, a DVD was (roughly) 4 GB, so 25 DVDs is only 100GB?
<wik>/bin/finger that girl in the back row of machines.
Is that a hardware terabit or a software terabit?
This kind of devices would be incredible for backup purposes, but also, the recording method seems to be also fast, would they accept allmost-unlimited rewrites?, in that case, this technology could finally replace magnetic devices. Solid state is allways better, but so far, the existing alternatives don't offer the durability and flexibility of hard disks.
WTF am I doing replying to an AC at 5 A.M on a Friday night?
Mod me -1 redundant if you like, but for people out there, but 1 trillion b= 125,000,000,000 bytes = 116 GB, or if you're a harddrive manufacturer, its 125 GB.
Cool, the next time I need to send something over sneakernet to someone far away, I'll just send a postcard with 2 stamps on it. 1 postal and 1 storage stamp.
So, you are writing you 10 000 line program, get half way through it today, save to your non persistent memory, shutdown for the night, and what? You really ought to think about it for a while, how often do you use your harddrive? Never, well then you are correct in your idea that persistent memory is a bad idea. However, if you are like any person in the world that boots their OS from a hard drive, or saves their work to a hard drive, or plays games, then you probably want persistent memory
This sig is definitive. Reality is frequently inaccurate.
More information about the company can be found at their website, http://www.nanochip.com.nyud.net:8090[Coral Cache Link].
What are the odds that some idiot will name his mutex ether-rot-mutex!
Warm reboots don't erase memory. Cold reboots usually don't erase memory, either. (There are still fragments of what was left before after doing a cold boot.)
And as almost all data recovery people know, reformatting a hard drive using the conventional disk formatting commands don't really erase anything; they merely create new directory structures. In order to really erase a disk, you have to use something like Eraser or `dd if=/dev/urandom of=/dev/hda`.
Well, he might be using Knoppix or another live-cd, and when finished for the day, burn his accomplishments to cd/dvd (ie persistent, but optical, not magnetic storage).
I have a really elegant proof for Fermat's last theorem. If this sig was only a bit longer...
Opps, looks like it is.
It is non-volatile by nature. But it is not likely to be fast enough to replace RAM. Instead it could replace Flash memory or even (depending on cost) hard drives. The real question is, how long until it's practical to manufacture and use in mass-produced products? The answer seems to be (according to the article) 2007-2010 timeframe.
main(c,r){for(r=32;r;) printf(++c>31?c=!r--,"\n":c<r?" ":~c&r?" `":" #");}
i'm impressed... 25 dvds for 1 terabit. but i think were all holding out until we hit 150 zip disks on a square centimeter or 172 ls-120's on the size of a heineken bottle cap.
"Tread softly because you tread on my dreams"
(b) Testing: How are they going to test this trillion element chip ? Testing complexity grows exponential with number of elements and it will require serious consideration. It may be worthwhile to make smaller components which can be tested easily (modern chips has one-third cost devoted to testing)
(c) Redundancy: Is this process going to give more yield than conventional electronic processes ? If no, common technique of redundancy has to be utilized. This brings in the cost in terms of power, speed and delay. For example if the yield is only 90%, that means you will need ~110% resources. Not only you have to make up for the defective components, you will have to provide lot more redundancy for testing. At some point it becomes worthless as the performance will drop to floor.
But still it is a good work and perhaps will generate some new ideas.
So we must assume they are talking about an ATM, which a largish and complicated peice of equipment. It requires a piezoelctric device to move the tip to the proper placed on the substrate. For years, such devics kept cell phones large. The ATM requires a highly senstive feeback loop to keep the current constant. And is still requires a very delicae tip that can be easily damaged. Durable tips are probably years away and involve carbon nanotubes. Tips that have a lifetime more than a few months are probably even longer away.
It is a neat idea and probably works well in the laboratory on a vibration cancelation table. How would it work on a portable in the train or in the car? Does anyone have any real details on the technology?
"She's a scientist and a lesbian. She's not going to let it slide." Orphan Black
Well, not with the software overhead in various checksums that will be had in 2010:
- MPAA/RIAA field (the "copy checksum")
- Dept. of Homeland Security header (the "red checksum")
- UN Standards bit (the "blue checksum")
- .SUM (the "Microsoft checksum")
Those are apt to take up quite a bit of space. So maybe you'll get 15 DVDs (maybe 20 by paying Microsoft an expansion fee) on that postage stamp.[You have a stable society when some nut guns down a schoolyard and the law doesn't change.]
Some earlier stories were mentioning stacking layers of memory to increase it. So considering structural, voltage, data and addressing layers as well, how much data can we store in a 1 inch cube?
Whatever that number, we'll still be running out of space since Windows 2050 will take 1/3rd of that space and games+movies the remaining 2/3rd.
"Give orange me give eat orange me eat orange give me eat orange give me you." -Nim Chimpsky
So, if we attached a couple square inches of this stuff to a pigeon, or filled a 747 with some of these chips, and flew it around the world, how fast would the transfer rate be?
Hurricane Ivan: A 17th century prison collapsed. All of the inmates escaped.
...So how long before we start seeing those Brainboxes from 3001?
Tluin natha Linux xxizzuss uriu olt bwael mon'tun.
I'd be really surprised if we see this technology on the shelf in anything close to 5 years from now.
http://www.google.com/search?q=1+terabit+in+gigaby tes
1 terabit is 128 gigabytes. That is the definitive answer from google. It's not 116, not 125.
There was an article written (I believe by researchers from IBM) in Scientific American about two years ago regarding Millipede that said they expected technology to come to market in 3 years. Now the article from the post suggests the project is all but dead. What happened? I'm too lazy to actually look at the patents, but it isn't clear at all how this new technology actually differs from Millipede. I'd guess the write and erase mechanisms are different.
My god, it's two dimensional! Our memory limitations are over!
Standard DRAM will maintain its state --- mostly --- for a remarkably long time without refreshing. Unfortunately, it doesn't do so in a useful state.
I once was working on an embedded device that had VGA out. The development cycle was power on, boot from TFTP, run system, wait until it crashed, power off, repeat. When the system switched on, one of the first things the boot loader did was to initialise the video chipset, but without clearing the video memory.
If the board had been off for less than about five minutes, you could still see the last display that had been there when the board crashed.
Without refreshes, the data would gradually fade; the image was always corrupted with snow. The longer you left it switched off for, the worse the snow got. Different RAM chips lasted different lengths of time --- there was one band across the middle that would become completely unintelligable in about 30s, while another one could hold an image for about two minutes.
I suppose you could use this to store data for short periods during a power down, but you'd have to use so much redundancy to ensure that the data would survive the inevitable corruption that it probably wouldn't be worth it, but I'm sure someone, somewhere, could come up with a Nifty Trick(TM)... You couldn't do it at all on PCs, of course --- on boot, they wipe all their RAM, video or otherwise.
It's amazing how lucky these chip manufacturers are. Imagine to what lengths people need to go in other industries in order to convince customers to upgrade. If all you are selling is a damn chocolate bar, there is only so much that you can do to improve it. They had perfectly edible chocolate bars 100 years ago and there isn't much besides slapping "10% free" on the package that you can do. Ditto for things like headphones, ballpoint pens and pretty much everything else.
But the manufacturers of memory chips, hard disks, even CPUs, have it really easy. All they need to do is solve the technological problem of doubling the capacity/performance and the customer is eager to shell out some $$$ to get the new version. No focus groups are needed, no expensive marketing surveys. The only thing you need to do to please the customer is basically improve the obvious performance metric by 100%. You don't need to lie and twist the facts as those guys in cosmetics do with "73% more volume" for your eyelashes or "54% healthier hair" bullshit. You just make your CPU twice as fast and that flash chip twice as large, and you are done.
And if you really want to, you can say it will make Internet faster, or something...
Future Wiki -- If you don't think about the future, you cannot have one.
As the writer says, it's 1 terabit, or 125GB. Which is about 25 DVDs, given that a DVD is about 5GB. And yes, it's denser than hard disks, but not by far.
1's and 0's should be free.
Radical would be dumping the binary numbering system. Both for computing, and storage.
Well, on the plus side since all you'll have to send is the stamp there won't be anything to lick.
The higher the technology, the sharper that two-edged sword.
Where do these people learn their math?
Where did you learn your math? One trillion X is, by definition, a terra X.
See here and here
The IBM Millipede project doesn't use tunneling microscope technology (ATM, or usually STM). It uses a modified AFM tip that can be resistively heated. The hot tip pushes into a polymer surface and creates a hole. The hole can be "erased" by heating close to the surface and the region around the hole melts and fills it in. The reading is done with cold tips using regular AFM technology.
We don't measure HDs in Terabits . 1 Tbit = 128 GBytes or 128 gigs3
Second, converting this from inches to Centimeters, we get slightly less than 20GB/cm^2
Yes ladies and gentlemen, 20 Gigs per Squared centimeters.
That's a nice increase but it sure as hell isn't overwhelming.
Assuming a radius of 5 cm for a 3.5" HD, we get a surface of 80 cm^2 per platter. That comes to 800 Gb per platter. around 8 times the current density.
These new-gen HDs will be at most 8 times bigger than those we have right now.
That's it. 8 times. Not even a single order of magnitude.
Now mod this up or be destroyed!
It's not clear how this new technology is different from the IBM Millipede project, but Millipede took a heated atomic froce microscope (AFM) tip and stuck it into a polymer substrate to form the hole. The holes are erased by heating the surface surrounding the hole until melting happens and the hole just fills in as surface tension makes it flat again. This hole punching and erasing using heating happens really fast since the size scales are so small. Although I'd imagine the write speed is slower than a hard drive or flash memory.
The article says they have working prototypes. Of what? The implication is that it's a device that's a square inch in size, and it holds a terabit of data. But from the usage of "square inch" I think the reality may mean a density of 1 terabit per square inch, not that they have a terabit device. (I hope I'm wrong!). For example, they may have a prototype that stores 1000 bits in an area of a billionth of a square inch. That's a lot different than an actual terabit device! I wish articles had more details...
Rather, non-volatile memory instead has the enormous advantage that you can shut down your computer (physically) without shutting down your software system.
...there is a single atom. Orbiting it is an electron. When it's in a spin up state I consider it to contain a 1. When spin down it's a zero. There: a prototype of a multi exaterapetabit/mm^3 storage device at the end of my nose. Oh wait - I might be able to hype this up more. Oh yes...it's an electron, so it's in a superposition state. It's a multi exapetaterabyte/mm^3 quantum computer at the end of my nose. Surely /. have got to publish this story now.
Doesn't it make you feel good to know that our freedoms are protected by politicans, lawyers and journalists.
Prototype Arrays of Atomic Force Probes?? Is this real technology? I wonder is the talk of a real product by 2007 is credible, or just marketing to attract venture capital. I'm still waiting for products based on NRAM (made up of arrays of carbon nantubes) from Nantero (nantero.com). I wonder if "atomic force probes" are easier to manufacture than "arrays of carbon nanotubes"? Will Nanochip beat Nantero to the marketplace, or will they just burn through venture capital and next year we'll hear about another "Nano-'something'" company with some other "revolutionary technology" that's going to produce a marketable product "real soon now".
About 5 years ago there was a story just like this on slashdot that was making all the commotion. The claim was three dimensional non-volatile memory and the capacity was 660gigs per cubic cm. So far I haven't heard anything since the slashdot story 5 years ago.
It would be nice to actually be able to buy this technology that always seems to be "about to come out". It would also be nice to be at a price comparable to current consumor storage devices.
For now we will still be stuck with the bottleneck of bottlenecks, the spinning harddrive based on technology that was thought up somewhere around the 1960s (or was it even the 50s?).
The goal of computer science is to build something that will last at least until we've finished building it.
This is offtopic but I actually fixed a broken hard drive with dd if=/dev/urandom of=/dev/hdb. It was reporting bad sectors all over the place, and SMART (which isn't really) said it had "Imminent Failure". So, I salvaged what I could, and after trying to format, along with many other things, I just tried overwriting the entire thing. It worked. 2 years later the drive is still in top condition reporting no bad sectors. I think that People could save a lot of hard drives with that small amount of information.
Anthropic principle: We see the universe the way it is because if it were different we would not be here to see it.
That's because a 20Gig drive usually has something like 22-24Gigs of space; the extra space is used to relocate bad blocks.
If you completely overwrite a bad block, the drive's firmware is usually smart enough to move it to a new place. Reading from a bad block until you manage to get (most of) the data, and then re-writing it, will sometimes work (due to the same mechanism).
I'm told some drives are smart enough to try to "fix" bad blocks without being forced to like this, but I don't know of any (mostly likely because there would be no way to tell, since it would be user-transparent).
Occasionally, a drive will have some sort of mechanical shock which will damage a portion of the disk; often, the disk is not "failing," but has simply become partly damaged. A true "failing" disk would mean that the disk material was corroding, or that a poorly designed drive was losing its own low-level formatting from the motor's magnetic fields (I doubt that would ever happen, though), or something pretty ugly like that.
(I don't know if what I've said is completely true; please correct me if I'm talking out of my ass. It's been a long time since I've looked this up.)
--TheOrangeSquid Is it any wonder things seem so awry? We swim in a sea of confusion and don't have to think to survive
yes, because that was the point of my analogy, that the poster could write 5 000 lines of code a day.
This sig is definitive. Reality is frequently inaccurate.
They didn't explain how many volkswagons per metric second.
in other news: lollipop share prices go up!
*grunt* must... lick... something...
The revolution will not be televised... but it will have a page on Wikipedia
Other wise it is similar to Millipede. To increase density, they can move the R/W heads and the media. I've been following this for a while, I have exchanged e-mails with Tom Rust starting back in 1998. Like with fusion, it seems that this has been just a year or two from commercialization ever since...
They have had working prototypes for a long while. I suspect that the problems have more to do with reliably getting it into production.
If you RTFA you will see they are talking about FLASH MEMORY. I've never seen anyone use their flash drives as their RAM. Do you know why this is? Because flash memory is far to slow to be used as RAM.
Most posters seem unimpressed with the storage density they are reporting, but I'd like to point out a couple of things. (Note that I use atomic force microscopes in my "job" -- I do academic research.)
Firstly, the storage density they are reporting is for a prototype setup, and it's already as good as curent HD technology. The exciting thing is not the value they currently have, but rather the fact that this technology can be pushed very very far. Thus, comparing this new technology to a mature technology (magnetic disks) is not really fair. I do believe that if this new technology is investigated for 10 years, it could outperform magnetic drivers in terms of storage density.
Secondly, the data transfer rate can be much higher with this new technology. The millipede project uses an array of thousands of AFM-like tips, which means that in principle 1000 bits of data are read at a time (compared to, for example, 4 bits read at one time in a magnetic disk drive with 4 platters). We all know that HD access is a major bottleneck in modern computers. This new concept could immediately speed that up by 2 orders of magnitude. I think that's worthy of consideration!
That having been said: don't hold your breath. MEMS is a rapidly evolving field, but it will be awhile before it can really beat out the mature magnetic technology. The article also doesn't give any details on how this new technology works. The potential is great, but alot of work has to be done.
Well, this was a 30 gig drive, and was reporting around 25% bad sectors by the time I decided to overwrite everything with random data. Now, the drive works fine. No bad sectors reported. It all seems very mysterious to me. Conspiracy theory alert. Maybe the drive manufacturers recorded something on the drive that told it when to start reporting bad sectors and start dieing. Maybe overwriting the whole thing got rid of that data, and caused the drive to start working againg. But these are big maybes.
Anthropic principle: We see the universe the way it is because if it were different we would not be here to see it.
Boss: What are you two working on? You've been sitting and staring at the screen for hours.
Engineer 1: Uh....the millipede project.
Engineer 2: Yeah. Lots of data stored in two dimensional space.
Boss: Great! Keep up the good work. (Leaves)
Engineer 1: Whew that was close.
Engineer 2: In more ways than one. Look out! Here comes the spider again...
Engineer 1: I love MAME.
A lot of people have complained about how many technologies get reported, and are never heard of again.
;). What I found most interesting was the reference to an agreement with Ovonics.
This is pretty ironic, given that most companies (FUD aside) will only talk about products to a) attract venture capital, or b) sell an actual product.
And any company which has burned all the v.c. without bringing anything to market is hardly to going to trumpet about it.
Whether this technology will be the next best thing or not is open to question (that's what makes the stock market work
The stock market may hate Stan and company, but their list of accomplishments is pretty impressive, including having the word 'ovonics' added to the english language.
Either way, the news is a useful harbringer of things to come. Even if *this* technology doesn't make it, something else will. Somone will ALWAYS have a better idea. This is just a watermark for where the so-called state-of-the-art currently floats.
If you're not living on the edge, you're just taking up space!
For the development of E-books that contain vast libraries. I believe that all the books in the library of congress can be stored on one or two terabytes. Imagine, having all historical books and documents in a single book... From Aristotle to Zinill... All we need is a good powersource and more flexible e-paper and were all set. I believe Philips is working on a good e-paper, and that "new lithium battery we read about last week"might fit the bill for the time being...
Anyone else think this is a good use of the technology?
3 degrees of separation from Vladimir Putin
ignorance. Bits are measured normally, 1000 unit intervals. 1000 bits in a kilobit, 1000 kilobits in a megabit. It's BYTES that use the 1024 convention for kilo, mega, giga, etc, and even then that's not technically correct, as there is another standard for that.
Why can't people just standardize on a common unit of measurement such the number of Encyclopedia Brittanica's or the number of Library of Congress's?
It's not all that much, provided each line begins with a and ends with a .
Buford "Mad Dog" Tannen
but I have to wait 3 weeks for the snail mail request to reach the LoC, the guys to package everything up and the box to reach me eventually, I may be better off downloading the LoC on a slower link that answers immediately.
And nevermind that if the source is persistant and fast, the content is changing or it is impossible to predict which part you'd want later, it might be superior to simply download on demand. The missing factor here though is persistant. URLs move. Torrents die. There is no "repository" to get from. Yet.
Kjella
Live today, because you never know what tomorrow brings
Kinda gives you an idea of how huge a 64 bit address space is. I mean, 116GB is still 24 bits smaller - by about 16 million times (10 bits = 1K, 24=10+10+4) - than the amount of data 64 bits can address.
Could this be an indication of the data volumes we will be dealing with in the future when 32 bit computing on the deskop is obsolete?
Find a job you like and you will never work a day in your life.
I believe the first use was K = kilo = 1,000, M = mega = 1,000,000, G = giga = 1,000,000,000 and so on, since G for grand is, as far as I know, a purely american expression. I think that physicists were using those units long before your G, M and B were in "common use for budgets and gross national products".
but 125gb of storage surely, 8 bits per byte unless I've been living a lie
Nothing costs nothing
And because it will fail after enough writes.
LinuxWorld announced today that 4 of these postage stamp-sized storage devices have been preordered to hold all of the spewage coming from Dvorak about its demise.
Hard drives are cheap. The information that was on them was priceless.
A decent 20G drive costs what, $30 now? When someone's drive fails, they're usually so devasted (unless they had a comprehensive backup in place) that a consolation like, "Well, I was able to save your hard drive that didn't do the job it was supposed to do in the first place" just doesn't make the person feel all that better.
If I was in that situation, I'd probably go ahead and buy a new hard drive unless it was on a machine I really didn't care about, and then why am I bothering to keep it switched on?
Otherwise, why keep a piece of hardware that I know failed in the past? It might not have been the hardware's fault, but why take any chances?
Besides, it's a perfect opportunity to get a newer, more stable drive with more capacity for the same or lower price than I paid for the old drive.
Karma: Chevy Kavalierma.
Indeed, or 1 terranibble per 100 DVD's.
"It's too bad that stupidity isn't painful." - Anton LaVey
...this also means that they *have* to improve. If they don't, or do some bad choices or design, they'd quickly lose marketshare to better competitors.
While for something like chocolate bars, if you've managed to make your brand popular, you can just make more of the same and still get good sales.
Living on a student budget is plenty of reason to use defective hardware. Mind you, I always keep my work on the drive that hasn't failed. And I keep back ups. But when you don't have to money to run out and get new hardware everytime something fails, it's nice to know how to fix it.
Anthropic principle: We see the universe the way it is because if it were different we would not be here to see it.
What do you think about holographic storage devices and their future?