Beta

×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Magnetic Transistor Could Cut Power Consumption and Make Chips Reprogrammable

Soulskill posted about a year and a half ago | from the reprogram-ranch-chips-to-sour-cream dept.

Hardware 126

ananyo writes "Transistors, the simple switches at the heart of all modern electronics, generally use a tiny voltage to toggle between 'on' and 'off.' The voltage approach is highly reliable and easy to miniaturize, but has its disadvantages. First, keeping the voltage on requires power, which drives up the energy consumption of the microchip. Second, transistors must be hard-wired into the chips and can't be reconfigured, which means computers need dedicated circuitry for all their functions. Now, researchers have made a type of transistor that can be switched with magnetism. The device could cut the power consumption of computers, cell phones and other electronics — and allow chips themselves to be 'reprogrammed' (abstract)."

cancel ×

126 comments

Sorry! There are no comments related to the filter you selected.

Chips are "reprogrammable" (0)

HotNeedleOfInquiry (598897) | about a year and a half ago | (#42775503)

Been so for 25 years. It's called FLASH memory.

Re:Chips are "reprogrammable" (5, Insightful)

mrbluze (1034940) | about a year and a half ago | (#42775545)

Been so for 25 years. It's called FLASH memory.

They mean the transistors are programmable. If you can change the chip logic, you can get custom behaviours at top speed. Flash is for firmware, but doesn't change the chip itself. This stuff is awesome if it can be made to be as fast as a regular transistor. OTOH magnetism itself is a bit of a worry, as the chip could get wiped quite easily.

Re:Chips are "reprogrammable" (0)

Anonymous Coward | about a year and a half ago | (#42775553)

If it gets wiped, just reprogram it again.

Timing is critical (1)

Taco Cowboy (5327) | about a year and a half ago | (#42775827)

What if that chip got wiped in the middle of a very critical mission?

Current crop of chips made of silicon transistors don't have that problem, unless the force of electro-magnetic interference got so great that it fries the chips.

Re:Timing is critical (1)

camperdave (969942) | about a year and a half ago | (#42775861)

Mission critical circuitry could still be made from standard transistors. Besides, can't they throw a soft iron box around the chip to divert any stray magnetic fields.

Magnetic Shielding (2)

Sooner Boomer (96864) | about a year and a half ago | (#42776059)

mu-Metal works better than iron. It has 80-100 times better shielding capability. It's also lighter (kinda a big thing for space use...)

Re:Magnetic Shielding (1)

Anonymous Coward | about a year and a half ago | (#42776157)

Yeah, the Best Buy guy told me I need mu-metal shielded, nitrogen filled hdmi cables with gold and unobtanium coated connectors if I REALLY want to get the best picture out of my new $400 tv. Fortunately they keep just the thing on the shelf, and I wouldn't cheap out.

Re:Magnetic Shielding (2)

master5o1 (1068594) | about a year and a half ago | (#42776315)

You know, the material of the shield doesn't matter when someone suggests it as a possibility.

we have very fast FPGA too (2)

rubycodez (864176) | about a year and a half ago | (#42775557)

programmable gate arrays that can operate in the gigahertz. some specially made for networking

Re:Chips are "reprogrammable" (1)

sunderland56 (621843) | about a year and a half ago | (#42775615)

They mean the transistors are programmable.

Xilinx, Altera, and others have made reprogrammable chips for years. This new technology could potentially provide a different/better/cheaper/faster way of making a FPGA, but it isn't anything brand new, just a different way of doing the same thing.

Re:Chips are "reprogrammable" (3, Insightful)

Anonymous Coward | about a year and a half ago | (#42775723)

You could say the same thing about transistors vs vacuum tubes.

Re:Chips are "reprogrammable" (1)

anyanka (1953414) | about a year and a half ago | (#42775867)

An FPGA gate is basically just a lookup table for a logical function, stored in a tiny memory cell. Routing, etc. is also configured using memory (flip-flops). I would guess the magnetic transistor would at least make FPGAs less power hungry (no need to power the flip-flops), or they might allow the chip to be built from programmable transistors, rather than using lookup tables and dedicating part of the chip area to conventional memory and arithmetic circuitry.

Re:Chips are "reprogrammable" (1)

solidraven (1633185) | about a year and a half ago | (#42776547)

Yes, but a magnetic field needs a current. FPGAs are electrostatic in nature, once you're past the big startup current it levels off. To keep a magnetic field going (small as it might be) you need to have a current flowing...

Re:Chips are "reprogrammable" (4, Informative)

ByteSlicer (735276) | about a year and a half ago | (#42776813)

To keep a magnetic field going (small as it might be) you need to have a current flowing...

And that's why I have wires and batteries connected to all my fridge magnets...

Re:Chips are "reprogrammable" (1)

mrbluze (1034940) | about a year and a half ago | (#42776835)

From my understanding the magnetic field is only required to configure the tranistor not sustain it.

Re:Chips are "reprogrammable" (2)

Electricity Likes Me (1098643) | about a year and a half ago | (#42776853)

You don't need a current to sustain the magnetic domain in something like a hard disk, which is the impression I get of what this technology is about.

Re:Chips are "reprogrammable" (4, Interesting)

AK Marc (707885) | about a year and a half ago | (#42776553)

EEPROMs as flash RAM or firmware is old, very old. But the idea of a processor being field reprogrammable *is* new. It's so new, nobody has anything that would benefit yet. Think of something like Cisco booting based off the startup config, then optimizing the processors based on the config. Port 2 shutdown? Divert the gates to process something else. Want to be able to turn anything on and off without any delays? Then consider dynamic memory allocations. Not dynamic storage, the way everyone thinks, but looking at whether there are 64 bit requirements, and if not, programming it as parallel 32-bit CPUs for extra speed, and if 64-bit is requiring, booting up in 64-bit mode. Got an idle encryption ASIC? Now you have another general processor.

You claim it is common, but has anyone ever released a CPU that changed dynamically? Rather than optimizing code for the CPU, optmize the CPU for the code. I see this being biggest in the area where ASICs are biggest, networking gear. Need more hardware encryption? Need more QoS profiles?

Re:Chips are "reprogrammable" (0)

Anonymous Coward | about a year and a half ago | (#42776671)

Xilinx, Altera, and others have made reprogrammable chips for years. This new technology could potentially provide a different/better/cheaper/faster way of making a FPGA, but it isn't anything brand new, just a different way of doing the same thing.

EEPROMs as flash RAM or firmware is old, very old. But the idea of a processor being field reprogrammable *is* new. It's so new, nobody has anything that would benefit yet.

<snip>

You claim it is common, but has anyone ever released a CPU that changed dynamically? Rather than optimizing code for the CPU, optmize the CPU for the code. I see this being biggest in the area where ASICs are biggest, networking gear. Need more hardware encryption? Need more QoS profiles?

Yes, Xilinx, Altera and others have made reprogrammable chips for years. It's called an FPGA, just sunderland56 said. They weren't talking about EEPROMs.

Re:Chips are "reprogrammable" (1)

funkboy (71672) | about a year and a half ago | (#42776745)

EEPROMs as flash RAM or firmware is old, very old. But the idea of a processor being field reprogrammable *is* new. It's so new, nobody has anything that would benefit yet. Think of something like Cisco booting based off the startup config, then optimizing the processors based on the config.

Let's see if Cisco can "optimize" IOS to not crash because of stupid memory leaks & buffer overruns first :-)

Re:Chips are "reprogrammable" (1)

Rockoon (1252108) | about a year and a half ago | (#42777353)

It's so new, nobody has anything that would benefit yet.

I think more than a few people have ideas... here is one: a chip that can switch between AMD64 and ARMv8 instruction sets, even supporting both simultaneously...

I think the reality is that no big chip manufacturer wants such a thing to exist.. how is ARM going to get its licensing fee if you can just download the instruction set from the pirate bay?

Re: this will not change how logic are implemented (0)

Anonymous Coward | about a year and a half ago | (#42777055)

Having yet another non-volatile transistor would only change how the configuration data are stored, not how the programmable logic is implemented.

All the FLASH based CPLD these days actually are SRAM based and load itself up with configuration data from FLASH somewhere else on the same chip/or multi-die package. The reason being is that SRAM uses less area, faster, more flexible as logic element and thus higher density for the logic/less propagation delay. FPGA use SRAM based logic cell (CLB).

Re:Chips are "reprogrammable" (2)

flargleblarg (685368) | about a year and a half ago | (#42775997)

OTOH magnetism itself is a bit of a worry, as the chip could get wiped quite easily.

Not really. Magnetism trails off with the cube of the distance, rather than the square of the distance.

Re:Chips are "reprogrammable" (0)

Anonymous Coward | about a year and a half ago | (#42776101)

In the far field away from a the source of the magnet. If you are anywhere near the magnet, it can drop off a lot slower or faster, including being roughly constant over some distance depending on the arrangement.

Re:Chips are "reprogrammable" (0)

Anonymous Coward | about a year and a half ago | (#42776063)

great now we will have pc that are vulnerable to damage by magnets again just when ssd removed the last magnet vulnerable device from the pc. I wonder how it gets programmed if it is built into the chip itself or if something like a write head will need to be placed on the chip.

Re:Chips are "reprogrammable" (0)

Anonymous Coward | about a year and a half ago | (#42776281)

Where this is a great idea is for SDR's

Instead of having to include dozens of signal amplifer parts and various logic for GSM,LTE,TD-SCDMA,CDMA,WCDMA,etc only enough logic needs to be included for the largest piece, and if needed to switch carriers, it can switch programming logic to whatever the new carrier is.

Re:Chips are "reprogrammable" (1)

blue_teeth (83171) | about a year and a half ago | (#42776395)

It is called IGBT [wikipedia.org]

Re:Chips are "reprogrammable" (3, Informative)

ByteSlicer (735276) | about a year and a half ago | (#42776887)

If you can change the chip logic, you can get custom behaviours at top speed.

That's what we thought about FPGAs, but it didn't quite work out that way. Using this technology won't change that, it will just allow us to make better FPGAs.

Reprogramming an FPGA is slow (many switches to reconfigure, usually serially), which means it would only increase overal performance if you can use the custom function long enough, and it only works if you don't have to switch functions too often.

Writing software for an FPGA is difficult (it's more logic design than software) and requires specialized software. Reconfiguring it in a wrong way could damage the silicon (though modern devices and software have some protections and checks). So any custom functionality would come in the form of libraries, written by specialists.

The amount of extra interconnect and transistors needed to make a CPU reprogrammable are also significant, resulting in higher die area (and thus cost), lesser transistor density (=slower speed), and overall higher energy consumption.

The result of all this is that FPGAs are only used in very custom hardware (usually low volume), with the programming remaining largely static, only to be altered when there are bugs found or improvements needed (once a month or less).

SPACE dammit! (1)

Anonymous Coward | about a year and a half ago | (#42775597)

Magnetic states aren't as easily harmed by cosmic rays, thanks to spin majorities. That's why MRAM (magnetic RAM) is good for space applications. Now just bring in the magnetic processors, courtesy of this new magnetic transistor switch, and you can have a robust system that's much more capable of standing upto the harsh radiation environment of outer space without suffering crashes and glitches that can jeopardize a mission.

Re:SPACE dammit! (0)

Anonymous Coward | about a year and a half ago | (#42775699)

There are already space-rated ("rad-hard") FPGA based on antifuse and Flash. Look up Actel (now Microsemi).

Plus, the "transistor" described in the paper is switched by magnetism : how do you switch magnetism itself ? THAT consumes a great deal of power ! OTOH CMOS can be designed to have extremely low losses. Look at the above FPGAs.

Re:SPACE dammit! (1)

robot256 (1635039) | about a year and a half ago | (#42775705)

Actually, only chips made using processes on the order of 50-200nm are really susceptible (my numbers may be off, but I know the idea is right). When you get them small enough, down to 45nm, 32nm, 28nm etc the chips and transistors are so small that the probability of a charged particle actually hitting a transistor becomes almost negligible. Once we start actually flying those modern processes, dealing with radiation will become much easier. I don't know how much if any the magnetic transistors will be able to improve upon this.

Re:SPACE dammit! (0)

Anonymous Coward | about a year and a half ago | (#42775811)

As the process size goes down, the probability of any given transistor getting hit goes down. But unless the total die size changes, the probability of some transistor getting hit will stay roughly the same. But now the threshold for data flips will be smaller, so more stuff hitting it will be influential. Maybe you can use that decreased size to fit more redundant parts on the same chip, and hope radiation hitting some other part of your vessel doesn't spray the whole chip with a shower of particles.

Re:SPACE dammit! (0)

Anonymous Coward | about a year and a half ago | (#42775873)

Recent figures from specialists indicate that the smaller the transitors, the more data are damaged.

If you have an array of Flip-Flops using the latest technos, an average of 30 bits will be flipped from one high energy neutron because its energy has to spread and dissipate somehow.... These don't just pass through but there are complex interactions and a shower of secondary particles...

And triple redundancy is the minimum today.

Re:SPACE dammit! (0)

Anonymous Coward | about a year and a half ago | (#42776231)

I believe the effect of cosmic radiation is due to electron hole pair generation as it intersects the the well of the device, so while the device gate may be 28 nm, the well is actually much larger than that and still has a significant cross section for interaction. Given that as well the fact that the operating margins are smaller, I believe that the effect of cosmic radiation becomes greater with advanced technologies, not less

Re:SPACE dammit! (1)

Teancum (67324) | about a year and a half ago | (#42775729)

Of course it is magnetic states that are the key to core memory systems.... one of the earliest kind of computer memory systems.

Seriously, this whole suggestion sounds like what was once old is now new again. I'm sure there are some impressive miniaturization factors here and some interesting technology, but the "discovery" of magnetic memory is one of the oldest ideas in computer engineering. Voyager 2 is using one of the last operational core memory systems in the Solar System right now.... at least as long as it remains here and how far you want to stretch that definition.

I don't want to pay the $40 for just the article, so I can't read the details. Still, I'm sure there is something in this concept that goes a little beyond what has been done in the past. You don't get everything you want in computer technology "for free", so I'm sure there are some drawbacks to this method. I would guess that memory density and speed are two significant trade-offs from this approach. It would be better than magnetic storage systems like a hard drive or floppy disc, but I just can't see something like this competing against current chip technology in all aspects, nor is it being claimed.

sensors anyone ? (0)

Anonymous Coward | about a year and a half ago | (#42775831)

but the "discovery" of magnetic memory is one of the oldest ideas in computer engineering.

It's not the discovery of magnetic memory, but magnetic switching.

Cool, I'll be able to replace inductors, reed relays and hall effect sensors :-)

Re:Chips are "reprogrammable" (1)

Nemyst (1383049) | about a year and a half ago | (#42775697)

No. The chip interprets a program, but in itself cannot do anything it was not designed to do at the factory. You can't add a new command (e.g. Assembly ops), and all commands need some form of hardware implementation to work (I'm not a chip designer, gross simplifications etc. etc.).

This would allow the chip to be reprogrammed, perhaps even by itself. For example, you could have a circuit do addition, but then change it so it does division. The closest we have to this right now would be field-programmable gate arrays (FPGAs), but those require significantly more circuitry to be reprogrammable as each gate needs to be able to perform any of a set of basic commands depending on what the current setup is.

It's too early to say whether this'll pan out, but it's definitely interesting research and not useless as you seem to imply.

Re:Chips are "reprogrammable" (1)

camperdave (969942) | about a year and a half ago | (#42775885)

No. The chip interprets a program, but in itself cannot do anything it was not designed to do at the factory. You can't add a new command (e.g. Assembly ops), and all commands need some form of hardware implementation to work (I'm not a chip designer, gross simplifications etc. etc.).

.

Sorry, but CPUs have had microprogrammed instruction codes for decades.

Re:Chips are "reprogrammable" (2)

flargleblarg (685368) | about a year and a half ago | (#42776013)

Sorry, but CPUs have had microprogrammed instruction codes for decades.

Sorry, but microprogrammed instruction codes are still several layers above the transistor switch level.

Re:Chips are "reprogrammable" (1)

tibit (1762298) | about a year and a half ago | (#42775995)

FPGAs essentially have "gates" that are not merely gates but small look up tables (LUTs), they also have storage elements, some dedicated arithmetic units for DSP (powerful ones do that), and a whole bunch of routing resources. If you want programmable logic of any sort, you'll need all that no matter what technology is used to reprogram the transistors. An FPGA usually has either internal or external configuration source (FLASH, a download from a CPU, etc.), and a volatile configuration storage that's attached directly to the transistors/gates to control their operation. Magnetic technology there would merely reduce power consumption by those volatile configuration storage elements. It'd not reduce the need for wiring the write elements for those configuration storage bits into a memory array of some sort, and any sort of magnetic technology would probably occupy way more space per bit of configuration data due to the size of the write elements - unless you can somehow make a multi-layer design where the circuitry for the write elements doesn't take up real estate from underlying CMOS circuitry. Sure the storage elements may be tiny, but the write elements needed to flip their magnetic state will not be so tiny, even if done using MEMS techniques. That's what I make of it.

Re:Chips are "reprogrammable" (1)

vlm (69642) | about a year and a half ago | (#42776951)

The power consumption claims sound a lot more like plain old static ram, even older than 25 years.
In sleepy mode, a large sram draws a current low enough that there's no need to use anything bigger than a rechargeable AA battery, because the battery self draining current of an AA is already a multiple of the sram current so the battery will last almost as long as it would take to die on the shelf. Maybe shortening the "shelf life" by a couple hours or even a day.
Dallas Semiconductor makes a lot of interesting controllers for this task. Something like the DS1210 senses when the main power is shutting off, then it slams the sram its connected to into sleep mode and disables CPU access so it doesn't get messed with by the powering off CPU. Just soldered one in last weekend for a little experiment, but its really old tech. It likes a very clean power supply, otherwise it thinks the power is failing and disables the sram, which can be annoying... it has to be more sensitive to the supply voltage than any realistically connectable CPU would be, otherwise it might leave the CPU connected to the SRAM while the CPU is in low voltage bonkers mode thus defeating the purpose of having a backup...

One of the minor mfgrs, maybe DS don't remember, used to sell a big and chunky DIP package with a lithium watch battery and associated hardware that was plug compatible with traditional sram except it had an almost magic 10 year battery backup. That was over a decade ago and I remember it was a PITA when they all started croaking. There is a way to dremel the package open and stick a new battery inside, supposedly anyway.

next up, mobile hackers (0)

Anonymous Coward | about a year and a half ago | (#42775513)

walking around with magnets and chip reprogrammers.

Considering you'll need a Faraday cage to keep the (0)

Anonymous Coward | about a year and a half ago | (#42775517)

instructions from getting overwritten, I would say it's going to eat plenty of power.

Re:Considering you'll need a Faraday cage to keep (2)

Electricity Likes Me (1098643) | about a year and a half ago | (#42776877)

Not sure you understand how a Faraday cage works - they are not powered.

Reprogrammable!=Reconfigurable (0)

Anonymous Coward | about a year and a half ago | (#42775543)

Apparently this allows reconfigurable logic, except it does not say now it gets reconfigured, and mentions we don't have a good manufacturing process. So basically, its like an FPGA we can't build yet. TFA claims people already us magnets for memory, but maybe TFA means hard drives, or even magnetic core memory?

Re:Reprogrammable!=Reconfigurable (1)

Genda (560240) | about a year and a half ago | (#42775851)

The whole field of spintronics is opening up and includes quantum computing. Here's an interesting article on a new 3D spintronic memory which could produce new memory chips 1000s or even 1000,000s of times denser that existing devices with high speeds and all the advantage mentioned in this article [pcpro.co.uk] mentioned about magnetic technologies.

Bubble memory again? (0)

Anonymous Coward | about a year and a half ago | (#42775559)

Sounds like bubble memory is about to make a comeback.

theres more than one type of transistor (3, Interesting)

Osgeld (1900440) | about a year and a half ago | (#42775563)

one that requires voltage to keep it on, one that requires voltage to keep it off (P channel vs N channel FET's), ones that require current levels to keep it on and off (npn and pnp BJT's)

so to say

"First, keeping the voltage on requires power"

is a broad statement, yea something that uses power requires power

Then

"Second, transistors must be hard-wired into the chips and can't be reconfigured"

well yea, but we have long established configurations of transistors that can be reconfigured to suit needs, its called programable logic and spans the life of PAL's, GAL's, CLPD's, and upto FPGA's

so, what exactly are you trying to tell me other than magnets can drop power consumption since they have a physical state memory, we already know that from core memory.

Re:theres more than one type of transistor (0)

Anonymous Coward | about a year and a half ago | (#42775881)

Keeping a voltage on (steady) for infinite time may have zero power consumption if current is zero. Also actually most of the power is consumed when switching, not steady-state in most logic circuit.

Re:theres more than one type of transistor (2)

tibit (1762298) | about a year and a half ago | (#42776001)

Except that the smaller geometry CMOS you use, the higher the leakage current. In modern CPUs, the leakage wastes on the order of 10% of power IIRC, perhaps even more. As you go down to single dozens of nanometres, the leakage takes over dynamic current consumption -- IIRC, of course.

Re:theres more than one type of transistor (2)

Macman408 (1308925) | about a year and a half ago | (#42776167)

It's actually closer to half the power in current process technology, I believe. Obviously, that's a big enough problem that many things are done to mitigate it; for example, turning off power to parts of a chip that aren't in use. Or reduce voltage and slow down the clocks. Or even better, just finishing up as much work as possible, turn off the power to the whole chip for some amount of time, then wake up and take care of whatever needs doing (and do this all much faster than a human would even notice - small fractions of a second). And, of course, the materials scientists are doing a lot on this front as well; typically, a design can choose from a number of different types of transistors that have different balances of leakage, speed, operating voltage, size, current drive capacity, etc. etc. etc.

Re:theres more than one type of transistor (2)

dutchwhizzman (817898) | about a year and a half ago | (#42775899)

I think you can summarize this as we now have something that doesn't require physical changes (PROM) or large electrical fields (FLASH) to contain a state.

RAM used require some form of power; to keep current flowing you need a voltage difference and to keep a voltage difference on FETs there is still some current going because you need it to switch in less than eons.

Now all you need to do is build up a magnetic field (which still uses power) but then the state will remain for a considerable time without having to apply any more power.

You are right in saying that we already had configurable logic arrays, so the novelty in that isn't really there. I wonder what this technology will change in those.

Re:theres more than one type of transistor (1)

Osgeld (1900440) | about a year and a half ago | (#42776225)

you just discribed capacitive FRAM which has been around commercially for nearly a decade

Re:theres more than one type of transistor (2)

Stormbringer (3643) | about a year and a half ago | (#42776099)

Sorry, I couldn't let this pass uncommented. Yeah, yeah, -1 Pedantic.

"one that requires voltage to keep it on, one that requires voltage to keep it off (P channel vs N channel FET's),"

The ones that need a voltage to stay on are enhancement-mode MOSFETs. The ones that need a voltage to stay off are depletion-mode FETs, either MOSFET or JFET. All of those come in N- and P-channel flavors. They're symmetrical other than for P-type having less mobility. (And thus being more tolerant of dirty processes, which is why MOS IC technology started out with P-channel. 17 volts across a chip just to get it to light up... Ugh...)

About those magnetic transistors... Lately DARPA's been making noises about 'destructible' logic. If all you have to do to deconfigure an FPLA beyond recovery is swipe a strong magnet across it... Is that what this is about?

FPGA Chips? (0)

Anonymous Coward | about a year and a half ago | (#42775571)

Can someone explain to me how this is different from an FPGA chip?

Re:FPGA Chips? (0)

Anonymous Coward | about a year and a half ago | (#42775779)

FPGAs exist for long enough that their founding patents have expired, and can be bought in high volume and/or very low cost.

Re:FPGA Chips? (1)

Luckyo (1726890) | about a year and a half ago | (#42776123)

Don't FPGA chips require logic on top of transistors to function? This suggestion appears to make this unnecessary as transistor level hardware becomes reprogrammable without additional stuff on top.

Re:FPGA Chips? (1)

Osgeld (1900440) | about a year and a half ago | (#42776267)

logic is made out of transistors

Yes, but the same will apply here. (1)

evanh (627108) | about a year and a half ago | (#42776327)

FPGA's are about addressability of combinations. The finer the grain the more configuration and potential interconnect is needed to achieve flexibility.

Conversely, the larger the blocks are the more capacity can be fitted but the less combinations possible.

The cool part is possible efficiency savings - assuming it can also beat SRAM for speed and thereby get used right in the heart of processors.

The new function is MRAM - good for DRAM replacement. I don't see it beating flash any time soon simply on the basis of density. But as a DRAM alternative it has real potential.

After that, the risky part becomes coming up with ways to design hardware that can't get in a lockup state. Because a power down won't rescue you any more than the reset button does. It'll give a whole new variety of bricks!

That brings us to CMOS. CMOS was claimed to basically be a no power draw static fabrication technology too. But over the years, as the tech got miniaturised more and more it eventually started leaking so much that, on average, the leakage dominates.

These new spintronic techs will prolly end up having the similar leakage issues at similar scales.

Huh. Sorta like the way living cells work. (1)

davide marney (231845) | about a year and a half ago | (#42775577)

The idea of mutating the hardware directly sounds akin to the regulation of gene expression [wikipedia.org] in living cells. For example, the "software" of a virus takes control over the "hardware" of a cell's DNA production, and forces it to make copies of itself. That sounds pretty interesting. (And dangerous) In that kind of a system, you'd need an analogue of white blood cells to seek out and "destroy" (re-wire) captured logic gates.

The summary is awful. (0)

Anonymous Coward | about a year and a half ago | (#42775607)

Uh, not all traditional forms of logic require power to sustain a high output signal. CMOS, for example: http://en.wikipedia.org/wiki/CMOS#Power:_switching_and_leakage. Quoting, "Static CMOS gates are very power efficient because they dissipate nearly zero power when idle."

Re:The summary is awful. (1)

ChrisMaple (607946) | about a year and a half ago | (#42775745)

That was my thought also, but especially at small geometries CMOS has leakage everywhere. Flash devices can have zero leakage, but they have programming speed and durability problems. Magnetic devices could have zero standby current, but I have substantial doubts about the practicality of very small devices. On the other hand, there is already a supplier of ferroelectric RAM, Ramtron (now a part of Cypress Semiconductor).

Re:The summary is awful. (0)

Anonymous Coward | about a year and a half ago | (#42775865)

Oh yes, as you scale CMOS down, the leakage increases. But the summary didn't specify that. It just said, "The voltage approach is highly reliable and easy to miniaturize, but has its disadvantages. First, keeping the voltage on requires power...", which would imply that this is an intrinsic property of traditional logic, regardless of scale. That's where my beef is, it misleads laypeople who are trying to approach the subject.

Re:The summary is awful. (1)

tibit (1762298) | about a year and a half ago | (#42776011)

Exactly. For a decent 150nm process I think you can keep the leakage at microamps per a million transistors, or did I get that wrong? Alas, for a 30nm process, it's like 4-5 orders of magnitude worse.

Save power? (0)

Anonymous Coward | about a year and a half ago | (#42775631)

Yeah, if we gave a fuck about saving power... We wouldn't have wall warts spread all over the house and a bunch of devices that are never actually OFF.

After having gotten a kill-a-watt i was amazed how much power i 'wasted' because all of these devices built today are never actually OFF!.
Cheap o power strips and real on/off switches have saved me a little over $25 a month. Month after month.

april fools? (1)

jsprenkle (2009592) | about a year and a half ago | (#42775635)

This is very comparable to the field effect transistor. So the flow of electrons is controlled with magnetism instead of an electric field. Ok, but it still requires energy to create the gating field. Unless it requires less energy to create the magnetic field than it does to create the electrical field I don't see how this is in any way superior.

There's nothing that explains how the transistors are going to be dynamically reconfigured either.

I think either the reporter didn't understand or this is a joke.

IT IS CALLED CORE MOTHERFUCKERS !! (2)

Anonymous Coward | about a year and a half ago | (#42775649)

Core !! Old as the hills !! So old, it has come back around !! Probably some shit unix time wrap failure !!

Re:IT IS CALLED CORE MOTHERFUCKERS !! (0)

Anonymous Coward | about a year and a half ago | (#42775717)

(magnetic) core memory is entirely different, because it only contains one bit of information (and requires crazy timings, plus you have to rewrite the data when you read it, quite fun...)
Here it describes a magnetism-controlled resistor, which is another thing.

Re:IT IS CALLED CORE MOTHERFUCKERS !! (1)

camperdave (969942) | about a year and a half ago | (#42775935)

(magnetic) core memory is entirely different, because it only contains one bit of information (and requires crazy timings, plus you have to rewrite the data when you read it, quite fun...)

You have crazy timing and you have to rewrite the data when you read it from DRAM as well.

Re:IT IS CALLED CORE MOTHERFUCKERS !! (0)

Anonymous Coward | about a year and a half ago | (#42776015)

But not SRAM :-)

Re:IT IS CALLED CORE MOTHERFUCKERS !! (1)

tibit (1762298) | about a year and a half ago | (#42776019)

Oh yes. A DDR3 device datasheet is more complex than that of quite a few peripheral chips from the 80s.

Re:IT IS CALLED CORE MOTHERFUCKERS !! (0)

Anonymous Coward | about a year and a half ago | (#42776179)

We're actually using GNU tw and so it's taken us this long to get a working implementation. If we'd been using the BSD tw then we'd have something working by now, but the other developers were worried that their changes could be taken out of the public domain.

Malware writers dream (0)

Anonymous Coward | about a year and a half ago | (#42775655)

Take over your OS, pfft. With this they can repurpose your hardware entirely.

Captcha: suspect

Translation from journalist-speak (4, Insightful)

gman003 (1693318) | about a year and a half ago | (#42775661)

It's a standard field effect transistor, except the gate can hold a magnetic charge on its own, with no voltage applied. You only need to apply a charge to change its state. It actually looks sort of like a flash cell, except as the gate of a transistor.

However, it's made with indium antimonide, which apparently doesn't work well with existing fabrication methods. And I have to wonder what the switching times on it would be - if it can handle the multi-gigahertz frequencies in modern processors.

The whole "reconfigurable" bit is journalist bullshit. Pay no attention to it.

Re:Translation from journalist-speak (1)

TechyImmigrant (175943) | about a year and a half ago | (#42775679)

>However, it's made with indium antimonide, which apparently doesn't work well with existing fabrication methods.

So it's dead then.

Re:Translation from journalist-speak (1)

mrbluze (1034940) | about a year and a half ago | (#42775709)

>However, it's made with indium antimonide, which apparently doesn't work well with existing fabrication methods.

So it's dead then.

Yep, slashdotted in one fell swoop. This is the place where great ideas go to die.

Re:Translation from journalist-speak (2)

phantomfive (622387) | about a year and a half ago | (#42775983)

Just so you know, none of the high-end chips that will be around in seven years work well with existing fabrication methods. Each new generation of chip requires new technology, some of it very impressive.

Re:Translation from journalist-speak (0)

Anonymous Coward | about a year and a half ago | (#42775741)

It doesn't look exactly like a field effect transistor to me... But there is potential for a diode effect.

Bad journalism example :

The voltage approach is highly reliable and easy to miniaturize, but has its disadvantages. First, keeping the voltage on requires power, which drives up the energy consumption of the microchip.

Oh yeah : mistaking current and voltage. The CURRENT is consumed, while you can leave voltage indefinitely if there is no way for the electrons to flow. And FET need really really little current.

Furthermore, the article shows no sign that the conductive state is controlled by another voltage or current, but only magnetism. And how do you create a magnetic field ? you need some sort of current...

There are probably interesting applications for this device but FPGA ?...

Re:Translation from journalist-speak (1)

tibit (1762298) | about a year and a half ago | (#42776023)

In modern small geometry chips, the leakage current starts to drive thermal/power performance, last I heard :( So no, you don't need very little current. Yeah, maybe per transistor, but you get a billion of them, and suddenly leakage plays a major role even if the clocks are stopped.

Re:Translation from journalist-speak (1)

Required Snark (1702878) | about a year and a half ago | (#42775821)

This is similar to a memristor http://en.wikipedia.org/wiki/Memristor [wikipedia.org]

In the indium antimonide device, the retained state is stored magnetically. In the HP titanium dioxide device state is held by the movement of oxygen ions. There are many memristor devices that use different mechanisms to store state, including magnetic spin. Check the Wikipedia article for details.

Besides memory, one of the uses for the HP style of memristor is configuration of FPGAs. If this works it would shrink the size of FPGA cells, which would tend to bring the price down. The indium antimonide magnetic transistor could have a similar use. Describe this to a technically illiterate journalist and you get the kind of confused prose that is in this article.

Re:Translation from journalist-speak (1)

Acapulco (1289274) | about a year and a half ago | (#42776047)

Even if journalism bullshit at the moment, it would be really cool if one day actual reconfigurable chips where available. Imagine downloading the configuration for the next Intel chip, and applying it onto the same board as the previous gen. Or maybe even on-the-fly reconfiguring capabilities, such that certain parts of the processor change to suit the needs of instructions currently executing. Maybe part of the processor can work as a GPU if you are gaming, and as a multithreaded-optimized config if you need heavy computing. Running financial simulation? reconfigure to optimize for it, etc.
 
That would be really neat! computation power could be used much more efficiently, no?

Re:Translation from journalist-speak (0)

Anonymous Coward | about a year and a half ago | (#42776449)

See http://en.wikipedia.org/wiki/FPGA : this exists commercially since 1985.

In practice, the overhead of reconfiguration is such that specialised blocks take much less room and are faster than reconfigurable parts.

Iron core (1)

Sla$hPot (1189603) | about a year and a half ago | (#42775683)

Just found a closeup picture of a similar device:
http://en.wikipedia.org/wiki/File:Project_Whirlwind_-_core_memory,_circa_1951_-_detail_1.JPG [wikipedia.org]

Re:Iron core (0)

Anonymous Coward | about a year and a half ago | (#42775797)

Memory is different from switches. You would need a "memory" core (holding the magnetic flux) to control the switch, BTW.

CMOS (1)

johndoe42 (179131) | about a year and a half ago | (#42775759)

First, keeping the voltage on requires power, which drives up the energy consumption of the microchip.

Barely. Almost every digital chip out there uses CMOS [wikipedia.org] logic. The whole point of CMOS logic is that, when the gates aren't switching, no current flows. That means that no power is drawn. In practice, a little bit of current leaks, but this is a small effect at all but the smallest process sizes.

It's not all clear from the abstract how the authors expect to maintain a magnetic field without any static power consumption. Perhaps using ferromagnets, but I wouldn't hold my breath -- MRAM still hasn't happened.

Re:CMOS (1)

Mr Z (6791) | about a year and a half ago | (#42775855)

Sure, very little current flows through the transistor's gate. But, the transistors themselves are imperfect switches, and so you get some current flowing from Vdd to Vss all the time anyway. For the products I tend to work on, around half or more of the power consumption comes from leakage, amazingly.

For the uninitiated: CMOS gates consist of a pair of complementary switches. One set connects Vdd (the positive voltage indicating a logic '1') to the output node, and the other set connects Vss or GND (the zero voltage indicating a logic '0') to the output node. The way CMOS works, there should only be one path from either Vdd or Vss to the output node. All other paths must be open.

The simplest example is an inverter. It has two switches. The switch from Vdd to output opens with the input is 1 and closes when the input is 0. The switch from Vss to output does the opposite: Closes when the input is 1 and opens when the input is 0.

CMOS burns power two main ways. The first and most obvious way is through switching, also called dynamic power. When the output goes to '1', the gate outputs a high voltage. This voltage then charges all of the gates connected to that output. Even if the gates don't leak, they still end up taking on a certain amount of charge due to their capacitance. The total charge taken on is V*C, where V is the voltage and C is the total capacitance of all the inputs this gate drives. Later, when the gate's output switches to 0, all that charge flows back out to ground. The more often you switch an output from 1 to 0, the more charge you ratchet from Vdd to Vss. Furthermore, while you're switching, there's often a very brief period when the two switches are both slightly closed. You can get some current racing directly from Vdd to Vss at this time.

The second, perhaps less obvious way CMOS burns power is through leakage. Modern transistors are far from perfect switches. When they're closed, they conduct, and when they're open they also conduct, just not as well. This leads to a phenomenon known as leakage. That is, even when the gates aren't switching, there's a constant current from Vdd to Vss, because the transistors haven't completely cut off the current flow. You can sometimes address this by lowering the input voltage or using transistors with different threshold voltages, but that trades off speed for leakage.

So, while the promise of CMOS is that no current flows when gates don't switch, the actuality is that tiny transistors in modern processes aren't as good at holding up to that ideal.

Re:CMOS (1)

tibit (1762298) | about a year and a half ago | (#42776037)

Exactly. And when you get a billion of those imperfect leaky transistors on a chip, suddenly a big chunk of power gets wasted right there -- to a point where not only you can't ignore it, but it defines the limits of what you can achieve. Leakage is a big problem these days.

Re:CMOS (1)

jkflying (2190798) | about a year and a half ago | (#42776147)

TI has a working implementation of FRAM, they use it in their ultra-low-power MCUs.

FRAM Technology Overview
Welcome to the future of embedded memory

As the world demands faster and higher performance in every application, new memory technology is needed to enable smarter solutions. FRAM from Texas Instruments provides unified memory with dynamic partitioning and memory access speeds 100 times faster than flash. FRAM is also capable of zero power state retention in all power modes, which means that writes are guaranteed, even in the event of a power loss. And with a write endurance of over 100 trillion cycles, EEPROM is no longer required. All of this is possible at less than 100A/MHz active power consumption – a first for the semiconductor industry.

http://www.ti.com/mcu/docs/mcuproductcontentnp.tsp?familyId=1751&sectionId=95&tabId=2840&family=mcu [ti.com]

Re:CMOS (0)

Anonymous Coward | about a year and a half ago | (#42776633)

100 Amps per MHz ? Seriously, you don't mean milliamps?

Re:CMOS (1)

EmagGeek (574360) | about a year and a half ago | (#42776971)

Mod parent up, please.

Reprogrammable Memristors (1)

MarkvW (1037596) | about a year and a half ago | (#42775803)

We gonna have some real smart robots someday.

Magnetoresistance ? (0)

Anonymous Coward | about a year and a half ago | (#42775913)

It seems that the whole thing might be going into the wrong direction, this technique certainly has more potential as a sensor.

Some magnetism sensors are : Hall effect, magnetoresistance (quite similar, no ?), reed relays, eventually coils when movement is involved. Well now there is a cousin of magnetoresistance... This one seems to be able to be miniaturised below the point of Hall effect sensors :-)
For example it could be used to measure the power consumption of a chip, or something like that, but then you'll have to shield is from external fields...

http://en.wikipedia.org/wiki/Magnetoresistance

Bubble memory again? (0)

Anonymous Coward | about a year and a half ago | (#42775921)

Sounds like bubble memory is making a comeback.

The possibilities (0)

Anonymous Coward | about a year and a half ago | (#42775949)

Can wait to drive around with a junk yard car magnet!

This article is almost 100% weasel words. (1)

RocketRabbit (830691) | about a year and a half ago | (#42776021)

This article is almost 100% weasel words. Of course, just like optical computers and 3d storage cubes, it's 5-10 years away, right?

Jeez.

Re:This article is almost 100% weasel words. (0)

Anonymous Coward | about a year and a half ago | (#42777315)

Oh god, i still had the Amiga when there was '3d storage' right around the corner

prepare the tinfoil hats... (0)

Anonymous Coward | about a year and a half ago | (#42776321)

If EMP's weren't bad enough now they would most defiantly scramble all tech.

Magnetic Transitor... Like Relays? (0)

Anonymous Coward | about a year and a half ago | (#42776331)

http://en.wikipedia.org/wiki/Relay

Hereby Making Possible the True Apocalypse (1)

caspy7 (117545) | about a year and a half ago | (#42776561)

Remember all those post-apocalyptic shows in which a giant EMP reverts the world to a technological wasteland?
Put this these in all our electronics and we might get to find out what that's like.

Frist1 pso4t! (-1)

Anonymous Coward | about a year and a half ago | (#42776601)

when IDC recently Everyday...Redefine HAPLESS *BSD duty 7o be a big things in to have regular and the Bazaar OS I do, because

Frances Hellman was onto this years ago... (1)

MindPrison (864299) | about a year and a half ago | (#42776619)

Check this video out:

http://www.youtube.com/watch?v=pEof8E2cF8o

Back then I was thinking of how this could overcome the heating problem we would get if we could change the characteristics of each transistor in a 3D layered transistor array. Imagine having a FPGA with 10x10x10 layers, all cross addressable and connectable, Diagonally as well as parallel.

Load More Comments
Slashdot Login

Need an Account?

Forgot your password?
or Connect with...

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>