Slashdot Mirror
Magnetic Processors - Computing's New Future?
metalcoat writes "For the first time researchers have created a working prototype of a radical new chip design based on magnetism instead of electrical transistors. As transistor-based microchips hit the limits of Moore's Law, a group of electrical engineers at the University of Notre Dame has fabricated a chip that uses nanoscale magnetic "islands" to juggle the ones and zeroes of binary code.
Wolfgang Perod and his colleagues turned to the process of magnetic patterning (.pdf) to produce a new chip that uses arrays of separate magnetic domains. Each island maintains its own magnetic field. Because the chip has no wires, its device density and processing power may eventually be much higher than transistor-based devices. And it won't be nearly as power-hungry, which will translate to less heat emission and a cooler future for portable hardware like laptops."
"For the first time researchers have created a working prototype of a radical new chip design..."
I thought this had already happened when they moved from straight cut to crinkle cut??
Time is an illusion. Lunchtime doubly so. - Douglas Adams
...run GNU/Linux?
Will these new processors work when the Earth's magnetic field eventually flip over?
I hope they've patented it!
Craig Steffen
http://www.craigsteffen.net
The processor erases your HDD as it processes.
Bender: "Last time that magnetic psycho nearly cut my head off."
Fry: "Oh right, plus the magnet screws up you inhibition unit and makes you sing folk songs."'
Bender: "What! Who said anything about me secretly wanting to be a folk singer? How ridiculous!"
Funny sigs make your Karma go down.
Since magnetic monopoles dont exist, you have to use magnetic dipoles or higher order moments. this translates in to macoscopic structures. It's hard to see how this could beat monopole electrons in size or group velocity. As for power consumption, it's true that magnetism can have low queiscent power consumption because of it's hysterises making it non-volatile. But you pay aprice for this when you have to switch it's state. on the other hand the ideal transistor consumes no power when it is not switching states. If you got rid of the hysteresis in magnetism to make it faster and lower power then it too will become volatile like electronics.
I can see how this could create dense active bulk storage, such as was done long ago with magnetic bubble memory. But I'm skeptical about a pure magnetic logic system beating electronics.
Some drink at the fountain of knowledge. Others just gargle.
"For the first time researchers have created a working prototype of a radical new chip design.."
Hmm. Maybe.
But this seems a lot like bubble memory to me.
And while the wiki entry doesn't mention using this for direct computation, it is indeed possible.
What happens to my data when my microwave turns on? Can you "erase" my CPU when the feds show up at the door? Yes there are lots of good uses for this new technology.
I didn't see anything in the article about the magnets being faster than transistors. Yes, being able to cram more onto a chip will make a faster processor but are the magnetic "islands" faster in and of themselves?
"the process of magnetic patterning (.pdf) " - isn't that supposed to be a link?
How sensitive will these be to magnetism, static, etc., compared to a normal transistor-based chip? Will exposure to an EMP or other magnetic disturbance (say, my subwoofer) destroy them, or simply cause a crash? I would think it would be difficult to provide sufficient shielding within a reasonably small package.
Unpleasantries.
As transistor-based microchips hit the limits of Moore's Law
The submitter speaks of Moore's law as if it were some actual law governing the physics of silicon based integrated circuits. His "law" was nothing more than an observation regarding the time it took the industry to pack more transistors into a given space. It makes no assertions regarding maximum transistor density, heat dissipation, or any of the other physical limitations chip manufacturers keep overcoming.
Dan East
Better known as 318230.
This sounds like it has possibilities, especially as it'll have very low heat emissions. Plus, presumably, some of the speed limitations will be removed as (in a very basic sense) a magnetic signal travels so much faster than an electical signal. And I especially like the idea from the article that it retains data when the power switches off - true instant on computers at last.
My only reservation is that magnetic memory doesn't seem that reliable in the long term - I've had to throw out a lot of flash based memory after a few years, whereas I've never had a processor fail spontaneously (discounting heat transfer problems, naturally - I can't deny I've had many go up in smoke).
Electicity... magnetism... Bah. Show me a processor working entirely by gravity!
I wonder if fabs are cheaper for magnetic chips?
Ok now let my just slide in my new magnetic processor past my hard drives and... D`OH!
I degaussed the monitor on the cart in the computer room and reset every processor in the compute farm!
The chip industry spends billions in R&D to extend the performance growth of silicon chips. A very large number of engineers know how to design efficient fabs for silicon. Until this technology also attracts a sufficient following of $ and manufacturing experience, I won't count silicon out.
Also, it's not clear that this technology isn't subject to same "limits of Moore's law" (if there is such a thing) as silicon chips. The use of electron-beam lithography would seem to mean that this technology is subject to the some of the same feature-size and practicality limits suffered by silicon chips.
Perhaps this technology will find a place somewhere, it just faces a major uphill battle if it is to supplant silicon.
Two wrongs don't make a right, but three lefts do.
...and next you'll be telling me that tabletop fusion has been discovered, there are parasitic viruses that alter the host's behavior, and that someone invented the plasma drive at NASA. You're ready to swallow all that pseudoscience and yet you all deny me when I try to inform you about the return of the Niburu and Planet X by the great Zecharia Sitchin!!! It's unbelievable just how gullible the Slashdot crowd is and how blind they are to honest truth.
-"...bad old ideas look confusingly fresh when they are packaged as technology" - Jaron Lanier (Digital Maoism on Edge.o
"Since magnetic monopoles dont exist"
That hasn't been proven and actually most GUT theories predict that they do exist.
Ninjas don't carry tic tacs
So, does it make my harddrive now a microprocessor as well? and does it mean I have to purchase a multi-processor Windows license now?
I didn't read anything on how fast the "switching" will be compared to today's silicon.
When do we get to see diamond cpus?
My child walks by the computer with a magnetically mounted family photo frame, sticks it on the side of my computer. CPU ERASED! NOOOOOOOOOOOOOOOOOOOOOOOO!!!!!!
doesnt this pose these limitations?
1. no magnetic devices around... eg: speakers
2. Disturbance to/from other devices?
3. One uber-geek would come up with a nice magnetic reader which when placed on ur CPU, would detect the magetic fields & can actually read the data lines...privacy issues? ( i know this is very hollywood-ish)...
Don't put that subwoofer next to my computer!
---Technology will liberate us if it doesn't enslave us first.
This supervisor poured much time and effort into his team, investigating various concepts of magnetic computation. Then the integrated circuit came along and turned him into a ruined man.
So have we finally come full-circle now, back to magnetic computation? Call me conservative but I don't think it will fare any better this time around.
Wasn't it just a couple of years ago that they were reading keystrokes through walls by way of magnetic induction?
I know "reading" a CPU is a bit more complex (understatement), but given enough time and resources someone will figure it out. We're already broadcasting our keystrokes and network communications, how easy do we need to make it?
120 characters for a sig? That's bloody useless.
....hmm. They have had magnetic amplifiers in navy nuclear power plants (for purposes of controlling the core rods) for upwards of 40 years.
Nothing new under the sun?
eat shiat and bark at the moon
If "metalcoat", "The Winner", submitted the article ONE MINUTE before you did, then, they would have been placed it in the queue and rejeced ALL similar subsequent submissions. In other words, we shall refer to you as "The Loser". Get used to it. Roland P. submits about 400 articles a day. You are lucky if you beat him to the punch one time in six months.
On the down side, the new processor has been known to erase credit cards upon power up and tear zippers from pant fronts. It is surly towards and dismissive of all non-ferrous metals. It is demanding. In early testing, it refused to work for three days until its creators rented the movie Toys and watched the "deviled-egg" scene 111 times (while still cruel, this is not as excessive as it first seems).
Lastly, any user of the processor in an area frequented by Boy Scouts, may find that their home being referred to as "the North Pole", "Santa's Workshop", or something similar.
True, an ideal CMOS doesn't have any leakage; these days, however, the very small feature sizes translate into more and more leakage, mainly because of the tunneling effect. It's not uncommon for the leakage power to be one fifth of the entire power consumption; unfortunately, with future generations, this will only get worse.
The Raven
Now that is a cool name.
autopr0n is like, down and stuff.
if these things are susceptible to external magnetic fields, and why. I know, there are about 20 jokes about it, but no clear answers :(
I think I have a fairly sophisticated chip in my head, but I have not completely figured out yet how it works.
Any takers?
Magnetic processors were a hot-button issue with Stanley "Tookie" Williams. Before he was executed, he spent many sleepless nights in his makeshift jail cell clean room, fruitlessly trying to develop his own magnetic processor.
He was quoted as saying:
"In the end, we will remember not the words of our enemies, but magnetic processors developed by TookieCo."
On a non related note, he also screamed out "I DIDN'T KILL THAT WHITE BITCH!" right before he was executed.
are there polar bears?
and a nigerian guy named eko who's completely awesome?
In somewhat related news, global terrorists are researching large scale EMP devices. Evil hackers, on the other hand, are studying Windows source to find an exploit to cause new magnetic hard drives to generate their own EMP.
Wikipedia entry for Magnetic Bubble memory. I worked on Magnetic Bubble memory at IBM san jose, and the wired article sounds like this is the nano-scale version of this with some big improvements in how they are manipualted. Back then the "bubbles" were a few microns in size. You patterns permaloy onto the surface of a magnetic material. Usually this was a long loop of almost touching chevrons or T-shaped permaloy elements. the bulk materila was polarized one direction (normal to the chip) and inversions in this formed round "bubbles" for reasons simmilar to surface tension these bubbles were stable in one size and liked to stick to the chevron. Under a polarized light microscope you could see the "bubbles" in contrast sticking to the chevrons, giving them their name due to their appearance. one bubble stuck to one chevron. and the presence or absense of a bubble on a chevron was a 1 or 0. in some fancy schema the bubbles could hold internal higher order domain structures to encode more than one bit per bubble but these were never made practical.
A rotating magnetic field transverse to the chip would cause the chevrons to act like little iron bar bagnets pulling the bubble from one side to the other. because the chevron shape is asymetric it acted like a rachet and would only move the bubble unidirectionally. If the field was strong enough the bubble would then "leap" to the next chevron. Under the microscope you saw marching "bits" moving along. so you could move all the bit patterns like a train along the tracks in a bulk matterial with one layer of passive patterning. at one point in the loop track you placed a reader and a writer. this way you had sequential access to any bit and could inject or delete bits in the train.
When the power went off the bubbles stayed put.
It never made it to market (fuji made some) because it's niche was too small. it was slower than ram but faster than a hard drive. it was cheaper than ram but more expensive than a hard drive. At the time it was denser than ram but less dense than a harddrive. Thus it's only use was as a cache between ram and harddrives and in applications where robustness and non-voltility would be valuable like high-radiation sattelites and point of sale terminals. The latter market was eaten by EAROM and then flash memory.
this new material sounds like it uses simmilar concepts but is much smaller and actually performs bubble logic. Not sure about where the clock comes from: perhaps it's still a rotatin mag fiield?
Some drink at the fountain of knowledge. Others just gargle.
I'm still waiting on AtomChip to release my 6.8 Ghz quantum computer, never mind the fact it is made on technology using "optoelectronics".
For the conspiracy theorists among us, this chip can be turned on to a "high-power" mode with the press of a button, which will also eject the hard drive into its direct vacinity, erasing any and all data on it.
Let's see the RIAA sue me when I have a useless hard drive, haha!
(Yes, I know that the magnets wouldn't be powerful enough to do anything to the hard drive.)
They say that a magnetic insulator would have to be used to shield the chip from external interference.
I for one welcome our magnetic field juggling overlords.
Please sign petition to restore sanity to our banking system!!!
http://financialpetition.org/
This sounds weird to me, but what do i know?!
Little kid goes by the computer holding an etch-a-sketch with about 50"... Puts it against the computers side panel and woops...
The processor is now acting up strangelly. A few misshaps later and it's a new processor for you.
Maybe they'll start to put armoured processor with magnetic protective armours to make that etch-a-sketch not be so damaging.
That would be imensly cool! No more talk about heatsinks and fans for modders, just armours for their processors.
Of course by the time this is done computers will run on bullshit...
I submitted it too but I'm not bitter.
...
Well, not that bitter. But there's no real reason to get upset about it. Unless you've got a job that pays bonuses based on Slashdot story submissions.
Is this going to be the Windows ME between silicon and quantum computing? I hope not. I write ECAD software that will produce around 160 million a year in the current market. Designing chips is still a matter of heat and timing control, and until I get a new model to work with, I can't even say whether this will kill a HUGE market. Goodbye Magma, Synopsys, etc.
7h3$3 4r3n'7 7h3 Ðr01Ð$ ¥0 4r3 £00|{1n9 f0r. M0v3 4£0n9. --OB1
Magnetic circuits have been studied for at least 80 years. The basic problem is one of size and speed. A dipole magnet (onr with N and S poles) has a certain minimum size, otherwise it depolarizes itself. That sets a minimum size for any magnetic device. Also it's hard to make magnetic amplifiers with more than a small fan-out. It's also really hard to distribute a clock signal-- magnetic pulses fall off at a 1/r^3 rate, and generating a fast magnetic pulse gets blocked by the inductance of the coil.
Now there *are* cigarette-pack to Taj Mahal sized magnetic voltage regulators in use. Your PC power supply may be using one to regulate the 3.3 volt output. But getting them down to IC-size is going to be really hard to impossible.
Politician: What good are magnetic devices?
Pithy Scientist: Sir, in 20 years, you'll be taxing them.
(-1: Post disagrees with my already-settled worldview) is not a valid mod option.
Let me be the first to say that I welcome our new magnetic overlords.
disclaimer: I've been known to store numbers in my ass for which to dig out when quantities are required.
I was wondering about Electro Magnetic Pulses. Can something like this be hardened for military use? If the military can't use it, I wonder how much money the government would throw into this. I know they aren't the only drivers of technology, but you have to recognize that the military has historically been pretty much one of the largest (if not the largets outright).
-- I ignore anonymous replies to my comments and postings.
However, no-one's yet seen one, so I wouldn't get too worried. Maybe one positive effect of this would be distributing a zillion monopole detectors across the world...
Our netadmin radiates his own individual magnetic field. Sort of.
Magnetic bubbles move. Its principle resembles that of delay line memory used in computers before the invention of core and disk memory: You have huge circulating loops one can access at choosen spots to read a record. (People are working on optical delay line memory to store petabytes and picosecond speeds.)
I interpret this new magnetic technology to be a more compact implementation of programmable logic arrays . PLAs are standard tool in digital circuit design and can theoretically emulate any other digital state machine such as a CPU. Engineers like them because they are like blank circuits you can quickly burn a pattern in them. New high-density PLA chips in the 1980s lead to the rise of the mini-supercomputer industry, with companies like Convex using them. However, general purpose CPUs from Intel and Sun eventually exceeded 1990s PLA speeds and circuit capacities.
How about an abacus... It sort of works on gravity to hold its 'bits' in place. :-)
Pete/Petri "damn, my chainsaw is clogged with 1's and 0's again." --clyde
Magnetic amplifiers have a long and honorable history. They're basically transformers with at least three windings, designed so that the control winding can saturate the magnetic core. This yields gain. Magnetic amplifiers were big and slow, but solidly reliable. Absent major physical damage, they don't fail.
Magnetic amplifiers were used widely in the telephone system for decades. In Western Electric gear, anything with a vacuum tube had to have monitoring and alarm circuitry, but a magnetic amplifier didn't. Millions of little grey boxes with mag amps inside populated the phone system.
Magnetic amplifiers can be built to handle considerable power, so they were used in motor controls. They're still used in welders.
Does this mean we can re-introduce iron-core memory to go with our new magentic-core CPUs???
I've always wanted to find out if 1GB of iron-core memory would completely throw the Earth's magentic field out of whack. And even if it didn't, you'd have that really cool clicking sound on a huge scale as the bits were all flipped.
Ahh, to hear 1GB of little metal rings being flipped over in a large sequential write. That would be awesome.
=)
Lost at C:>. Found at C.
Wolfgang Perod should be Porod.. and /. isnt letting me login
As transistor-based microchips hit the limits of Moore's Law...1 3091816.htm
I don't think so.
http://www.sciencedaily.com/releases/2006/02/0602
The other technology that comes to mind while reading this is the Rapid Single Flux Quantum device (RSFQ). While not as fast as RSFQs, these new circuits are much more practical since they can run at room temperature.
I find it interesting that these new technologies for high speed replacements of transistors are both based on magnetic fields.
Now i understand why the cylons can switch off all computers by just looking at them.
Ok, for 10 points, can you tell me what famous tv show revolving around a black car featured magnetic memory as a plot point in its first episode?
The world is made by those who show up for the job.
I have about 128 bits of it sitting in my closet somewhere. It is not based on a power of two like ram is now, but the length X width of the number of magnets on each side.
A close-up picture of it
As transistor-based microchips hit the limits of Moore's Law
Actually, I don't think "Moore's Law" has a limit. An off-the-cuff comment that the number of transistors in a processor will double every 18 months doesn't have a limit. It just keeps getting higher and higher.
Posted from the wireless couch.
Perod is spelled Porod. The article has already corrected this misspelling.
Nerve impulses travel pretty fast, and reaction time can potentially be near-instant. After all, our brain does a pretty good job. It helped us make silicon computer chips.
Still waiting on Serviscope_minor to wake up to fucking reality and realize that Jessica Price isn't going to fuck him.
Either NAND or NOR gates are enough to perform any logical operation, one doesn't need a combination of both to make an "universal logic gate". If this misleading sentence was on CNN I'd accept it, but Wired should know better...
The AACS key is NOT 0xF606EEFD628B1CA427BEA93A9CA9773F
...demagnitizer....
Oh my, I'm seeing spots, sun spots...
A new lower power level of EMP weapons has been announced, following the announcement of the first commercial Magnetic computing....
But does it run Linux?
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
Computers using the magnetic chips would boot up almost instantly. The magnetic chip's memory is nonvolatile, making it impervious to power interruptions, and it retains its data when the device is switched off.
Why, are they planning on replacing the hard drive and the data bus, the two major bottlenecks in boot speed? Or do they intend a "boot once, suspend thereafter" approach, flashing the computer state to some NVMRAM?
Of course, the whole article has so many implied exclamation points it reminds me of cold fusion.
I vaguely remember a long time ago that Josephson junctions were considered as a contender for logic gates. If I recall correctly, a conductor that carried a current could control a current in another conductor that was perpendicular to the control element via its magnetic field. It had niche aplications, but for processing elements, it was deemed impractical: the devices had to be cooled to cryogenic temperatures, and shearing forces from contraction tended to destroy them. It would be interesting to see if carbon nanotube technology could somehow be a remedy to the problems with using Josephson junctions, or a variant of them in processor applications.
Just a thought. I'm no physicist.
Computers using the magnetic chips would boot up almost instantly. The magnetic chip's memory is nonvolatile, making it impervious to power interruptions, and it retains its data when the device is switched off. This is probably not a desirable trait for anything running a microsoft product. How often is a system re-boot required with MS?
I was an EW technician in the AirForce, we had a processor that used bubble memory. That was about 1981.
That would be crazy if he submits 400 articles a day. Assume it takes him 2 minutes to find and submit each article and that he doesn't submit the same article twice. Thats 400 times 2 minutes = 13.3 hours a day spent on sending articles the /. editors.
http://slashdot.org/comments.
Transistors (except those based on Jopheson junctions which require superconductor properties) operate as the speed of current flow. Current flow is much slower than the speed of light (transmission time for magnetic field changes). So, theoretically at least, this could be faster.
Amazing what they came up with in the 1940's: http://en.wikipedia.org/wiki/Magnetic_core_memory
My hyperlinks aren't worth the paper they're printed on.
What is the technical name for this ?
http://dictionary.reference.com/search?q=hyperbole
Are there any materials that can shield from magnetic fields,
and are not affected, or magnet themselves.
For a school project.
Any help is appreciated.
Scientific American had a rather lengthy article on magnetologic devices not long ago. MRAM is a limited version of them that can only change the magnetization of the top magnetic layer - full magnetologic devices can switch both sides.
Although they're a wonderful technology that in the right hands would permit vast improvements in computation, I'm scared to think what a painful experience it would be to program such a device. We have enough trouble dealing with CPUs that have fixed instruction sets and few enough ASM programmers as it is. Is a person even capable of programming such a device efficiently, or writing software to do the same? I'm pretty sure that just having a 10x10 matrix of them to keep track of would be hard for me - I can't imagine trying to write code to control a whole CPU of them that wouldn't be hopelessly bogged down with getGateStatus()- and setGateStatus()-type functions.
Or would their role be more limited - switching individual gates to be AND/OR/NOT/NAND in hardware, for instance, so you would do setGateFunction(gate_no, wanted_function); LOGIC_OP rather than having a switch? Or perhaps they would be hard enough to program that you would have to use just a handful of pre-written setups for them, optimizing for games or math performance? loadChipSetup(long_math.mag) or loadChipSetup(fast_string_ops.mag)?
Now imagine the next generation of viruses rewiring your CPU to do God-knows-what.
"As transistor-based microchips leave Moore's jurisdiction... "? The range of interpretation of Moore's Law itself appears to follow Moore's Law; with no disrespect to the parent article intended.
Glad to know somebody else remembers magnetic bubble technology. When I first read about it in the 1980s it was supposed to revolutionize storage (like everything else). All the music ever recorded would fit in a unit the size of a cigar box. At least that part has probably been achieved by now, but what happened to the bubbles, and how is this new approach different?
I was gonna say... butcha beat me to it! =D
(Yes, it's my Yahoo id)
Diamond on insulator is what i'm waiting for! I read an article in wired a while back about the guy who sold the whole silicon on insulator process to intel has been working on fabricating diamond wafer to produce chips from.
In the entrance hall of the rochester physics building, Durham University, there was a cool demo of a magnetic 'not' gate. The model was an electric railway. the train had an arrow on it indicating the direction of the magnetic field. When triggered, the train moved round the track into a v shaped grove, the direction of the train was switched as it backed out of the V, as the direction of the field would be switched.
as well as showing (conceptually at least) that this worked, it gave rise to the possibility that the 'supercomputer' in the instituate for computational cosmology was just a really REALLY elaborate trainset..(turntables and everything).
also.. working in the group is a Dr Mike Hunt..
--AlexC
Just because I dont agree with climate change doesnt make me a troll
I have a customer with d.c. power supplys using a saturable core transformer (mag amp) they are rated for 12v, 6,000amp 100% duty cycle. powered with 480v 3 phase, the ripple on the output is lower than the s.c.r. controlled power supplies.
The regulation is poor, there is no voltage drop in the iron core windings unless there is current flow, they are big, noisy, variac controls dc power into bias winding.
schematic for the power supply is dated 1960. three units still running strong after 46 years!
This type of power is used in the plating industry. I have worked on 15v 30,000amp dc power supplies. that's big. 1000amp 480v 3phase powered, water cooled, 360 diodes, each diode rated for 300amp 600volt, e-tech tools include 1-1/4 wrench!
it was like that when I got here.. I wasen't here when that happened... second shift musta done that....
REVERSE THE POLARITY!!!
It's the first CPU that can stick to your fridge!