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!

Advance In PCM Memory Could Dramatically Reduce Power Consumption

Soulskill posted more than 3 years ago | from the freeing-up-electron-bandwidth dept.

Power 74

Zothecula writes "Researchers from the Electrical and Computer Engineering Department of the University of Illinois have developed new low-power digital memory which uses much less power and is faster than other solutions currently available. The breakthrough could give future consumer devices like smartphones and laptops a much longer battery life, but might also benefit equipment used in telecommunications, science or by the military."

cancel ×

74 comments

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

Vaporware (0)

Anonymous Coward | more than 3 years ago | (#35487952)

Another mind-blowing technological advance that you'll never see any hardware from.

Re:Vaporware (-1)

Anonymous Coward | more than 3 years ago | (#35487982)

Another mind-blowing technological advance that you'll never see any hardware from.

Even if it does work chinks will probably just steal the IP.

Re:Vaporware (1)

ZorinLynx (31751) | more than 3 years ago | (#35492614)

This is just another one of those advances that'll eventually make its way into shipping products, and no one will notice because it will be part of the general trend of improving technology.

For instance, look at all the (relatively) recent breakthroughs that make modern tablets possible:

- Efficient white LED backlights
- Li-Polymer batteries
- High density flash memory
- Software defined radios
- Capacitive touchscreens ...there's more, but my point is, there were probably press releases about these years and years before they made it into shipping products, and we completely forgot about them. We just saw an iPad and went "Ooh that's cool!" without realizing the advances made years before which made it possible.

Re:Vaporware (1)

The End Of Days (1243248) | more than 3 years ago | (#35494348)

Well, this is Slashdot. People here saw the iPad and poopooed it because a) it's Apple and/or b) they're super-geniuses and could have created one in their sleep, if they would just lower themselves to something so mundane.

Re:Vaporware (1)

default luser (529332) | more than 3 years ago | (#35494792)

Agreed. And PCM Memory will remove the standby power required for DRAM, which is a significant drain on battery life.

Of course, the jury is still out on whether the writes will take more power than DRAM. If so, the power savings could be much less.

Sheesh... (1, Informative)

ibsteve2u (1184603) | more than 3 years ago | (#35488008)

Five moderator points, and no comments worth reading.

Re:Sheesh... (1)

Anonymous Coward | more than 3 years ago | (#35488042)

That's what happens when you look at a thread minutes after it gets posted.

Re:Sheesh... (2)

twidarkling (1537077) | more than 3 years ago | (#35488300)

No, that's what happens when you read 96% of comments lately. Including this one.

Re:Sheesh... (1)

X0563511 (793323) | more than 3 years ago | (#35505104)

You are perfectly welcome to go elsewhere. I'm not aware of anyone forcing people to use slashdot.

Re:Sheesh... (1)

twidarkling (1537077) | more than 3 years ago | (#35505448)

Why the fuck would I go elsewhere? This place is the best. Someone else even got my joke and gave me a +1 Funny. Just because you lack a sense of humour doesn't mean I do.

Re:Sheesh... (1)

zorblek (938111) | more than 3 years ago | (#35488090)

Mod parent up.

Re:Sheesh... (0)

segin (883667) | more than 3 years ago | (#35489016)

And this is exactly why 96% of the comments aren't worth reading.

Re:Sheesh... (0)

Anonymous Coward | more than 3 years ago | (#35489996)

And this is exactly why 96% of the comments aren't worth reading.

Mod parent up!!!! (but not this one, because it's useless and vain)

Re:Sheesh... (1)

msauve (701917) | more than 3 years ago | (#35489536)

The title and summary aren't worth reading, either. PCM? What's that undefined acronym? Pretty Crappy Marketing? Pulse Control Modulation memory? Huh?

Re:Sheesh... (1)

anomaly256 (1243020) | more than 3 years ago | (#35489670)

Phase Change Memory. Meaning the title actually says '..P[hase] C[hange] M[emory] Memory..' Y'know, like Automatic Teller Machine Machine

Re:Sheesh... (1)

msauve (701917) | more than 3 years ago | (#35489834)

Whoosh....

Re:Sheesh... (0)

Anonymous Coward | more than 3 years ago | (#35489902)

what Whoosh. He replied to your post which has no joke in it.

Re:Sheesh... (1)

anomaly256 (1243020) | more than 3 years ago | (#35491996)

Ditto :)

Re:Sheesh... (1)

gl4ss (559668) | more than 3 years ago | (#35495262)

old idea + carbon nanotubes = grant money

Is this useful? (2)

JoshuaZ (1134087) | more than 3 years ago | (#35488030)

Two questions that hopefully more technically knowledgeable people can comment on. First, this system uses nanotubes- as I understand it, there's no good way of making high-quality naontubes in large batches. Is that still accurate? Second, for most devices isn't the CPU consuming a lot more energy than the memory? If that is the case, won't more efficient memory have only a small impact on overall power consumption?

Re:Is this useful? (1)

jamesh (87723) | more than 3 years ago | (#35488094)

Second, for most devices isn't the CPU consuming a lot more energy than the memory? If that is the case, won't more efficient memory have only a small impact on overall power consumption?

In standby mode where the CPU is more or less idle, maybe the amount of power required to keep the memory refreshed is significant in terms of total power use?

Re:Is this useful? (1)

GooberToo (74388) | more than 3 years ago | (#35491632)

Remember, most low power designs specifically allow for cores to be shutdown when idle. This allows for substantial power savings. But, despite the CPU drawing very little power, the memory still requires full refresh cycles. This is, in part, why suspend exists as it allows memory contents to be flushed to disk, thusly removing the need to continued memory refresh cycles. Accordingly, if you can reduce the power required for memory refresh, you can greatly extend the "standby" life of many devices.

Re:Is this useful? (1)

drinkypoo (153816) | more than 3 years ago | (#35492016)

This is, in part, why suspend exists as it allows memory contents to be flushed to disk,

ITYM "hibernate", the memory is still refreshed in suspend mode. Some fancy RAM has a low-power mode though.

Re:Is this useful? (1)

sexconker (1179573) | more than 3 years ago | (#35492474)

Sleep
Suspend
Standby
Hibernate
Shutdown

Power state naming schemes are retarded.

ON
OFF (with or without a stored memory dump to resume from)
All other states are simply power saving schemes per device. Display, video card, hard disk, speakers (girlfriend's new laptop will turn the speakers off after 10 seconds of silence), some of the CPU, more of the CPU, LAN port, USB ports, whatever.

Re:Is this useful? (1)

drinkypoo (153816) | more than 3 years ago | (#35492758)

Power state naming schemes are retarded.

No argument here. At least ACPI has discrete states which actually mean something... or are supposed to.

ON
OFF (with or without a stored memory dump to resume from)
All other states are simply power saving schemes per device.

I think it is reasonable for the user to distinguish between at least four states. Ideally your computer would only present three.

Re:Is this useful? (1)

Anonymous Coward | more than 3 years ago | (#35488106)

Don't know on the nanotube front, but memory consumes more power than you probably think.

http://www.interfacebus.com/Memory_Module_DDR3_DIMM.html
A DDR DIMM needs 5.4 watts, a DDR2 DIMM needs 4.4 watts and a DDR2 FB-DIMM needs 10.4 watts. DDR3 provide a 30% reduction in power consumption.

Of course this is in a standard PC, they use lower power memory in phones etc, but I bet they are still a decent part of the power budget.

Re:Is this useful? (3, Interesting)

c0lo (1497653) | more than 3 years ago | (#35488140)

TFA quotes

uses much less power and is faster than other solutions currently available

Haven't seen however any info on the speed.

The researchers say that the low-power memory could even lead to previously elusive three-dimensional stacking of chips.

This would be good indeed if achieved.
Speaking of achievements, there's just this snag:

The group has so far created and tested a few hundred bits

On top of it:

The device is also immune to accidental erasure from a passing scanner or magnet.

This may well be, but... what range of temperatures is supported by the phase-change material? (i.e. what good is the low-power/high-speed memory if it melts when overclocking the CPU?)

Re:Is this useful? (5, Informative)

Anonymous Coward | more than 3 years ago | (#35488278)

uses much less power and is faster than other solutions currently available

Haven't seen however any info on the speed.

Unless I'm reading it wrong -- and the wording is a bit ambiguous -- they seem to be claiming speeds higher than other PCM implementations, not DRAM. I would be very surprised if the write speed of phase-change memory could ever exceed that of DRAM, and I say write speed because phase-change devices can be read faster than they can be written.

PCM is much more likely to be a SSD solution than a replacement for main memory, and even then, it's a long, long way from leaving the lab. All this announcement concerns is a proof-of-concept.

Re:Is this useful? (1)

mbessey (304651) | more than 3 years ago | (#35494974)

> I would be very surprised if the write speed of phase-change memory could ever exceed that of DRAM

You might very well be surprised. Individual memory cell write time is not all there is to write speed. There are addressing delays, amplifier settling time, etc. Depending on the design of the memory cells, some of these effects could be a lot lower for phase change memory.

Intuitively, shuffling some electrons into and out of a capacitor seems like it would have to be faster than heating up a bit of crystal enough to change its structure. Of course, if the bit of crystal is small enough, the amount of energy required could well be less than for charging or discharging a DRAM cell. If the total energy requirement is similar, then the write speed is limited by the amount of current flow the drivers can provide.

Re:Is this useful? (1)

Sooner Boomer (96864) | more than 3 years ago | (#35488258)

Two questions that hopefully more technically knowledgeable people can comment on. First, this system uses nanotubes- as I understand it, there's no good way of making high-quality naontubes in large batches. Is that still accurate?

These [swentnano.com] folks seem to have it worked out.

Re:Is this useful? (0)

Anonymous Coward | more than 3 years ago | (#35488260)

Interestingly enough, not as ridiculously expensive or impossible as it used to be. But on your second point yes, CPUs use much more power than memory anyway. A minimal gain. Not surprising as computers are like cars when it comes to the average consumer... "Really? 800 hp and it gets 12 mpg? I think the trade-off is worth it!" /sarcasm

Re:Is this useful? (2)

Avtuunaaja (1249076) | more than 3 years ago | (#35488386)

When running, a cpu uses much more power. But on a mobile phone, (and on your desktop), the cpu spends most of it's time shut down and powergated waiting for an interrupt. RAM, however, has to be refreshed, and will steadily drain your batteries until they run out.

Why phase-change materials are useful (2)

x14n (935233) | more than 3 years ago | (#35488266)

This is the worst /. article *summary* that I've read this week. TFA addresses phase-change materials (PCM)-based memory only. This is the self-same stuff used in writable DVDs, and has some very cool properties. In the above summary, "Faster than other solutions currently available" refers specifically to PCM-based memory. The durability of PCM memory is one big plus -- all those sci-fi plot twists from cosmic ray induced bit-flips in charge-dependent memory? Yeah, not a problem here.

TFA itself is a really neat little paper. It's in Science, which indicates that some reviewers somewhere thought it both important and well-done. It's surprisingly readable, too, which is a little unusual for these sorts of papers. These folks were clearly thinking about Fab-type high volume / high yield questions. For example, the "quality" of the carbon nanotubes (CNTs) isn't important. They're just an easily-broken conductor. Clearly this isn't ready for prime-time, but they didn't just make 1 device, test it, and publish. They made at least 100, while varying conditions.

From TFA's Supporting Online Material:
" In order to create the CNT nanogaps, we performed electrical breakdown of CNTs both in ambient air and under Ar flow. We have also cut CNTs with AFM manipulation, but the elec- trical breakdowns offered a much faster route to obtain a wide range of nanogaps (Fig. 4). Of course, while the CNT breakdown method is extremely useful here, it would not be the preferred route for obtaining nanogaps in a more scalable manufacturing environment. Nevertheless, we believe it is useful to present some observations associated with this technique here.

First, we note that CNT breakdowns under Ar flow were done by flowing Ar (which is heavier than air) from a small nozzle over the entire test chip while probing. Thus, some dimi- nished amount of oxygen was still available for CNT breakdown, unlike the breakdowns per- formed in vacuum in the second panel of Fig. 2C of Ref. (1). There, the CNT break in vacuum could lead to SiO2 damage, which was not seen here either in ambient air or under Ar flow.

Second, we found that nanogaps formed in Ar are always smaller (always
We report additional statistics for all devices measured by AFM in Fig. S7. We find no clear dependence between nanogap size and CNT diameter (Fig. S7A). In a sense, this is encouraging because it suggests that tight control of CNT electrode diameter may not be necessary to make very low power devices. Our simulations (Figs. S3 and S4) also suggest this is the case, because the resistance of the GST bit always dominates that of the CNT (both in the a- and c-GST phase), thus rendering variability in the CNT of less importance. This fact could be important for mass production of such electronics where some amount of CNT variability could be tolerated."

Re:Why phase-change materials are useful (1)

Neil Boekend (1854906) | more than 3 years ago | (#35489420)

-- all those sci-fi plot twists from cosmic ray induced bit-flips in charge-dependent memory?

Not just a sci-fi plot. Bits can be flipped due to cosmic rays. [slashdot.org]
Yeah they say they are not sure why the bit flipped. But this is starting to look ridiculously like a cosmic ray: in the collision zone of true cosmic particles and solar particle a bit flipped without good reason.

Re:Is this useful? (0)

Anonymous Coward | more than 3 years ago | (#35488284)

Second, for most devices isn't the CPU consuming a lot more energy than the memory?

The CPU is using more energy than memory, but it isn't true that it's using MUCH more energy (emphasis added). Especially when you project energy usage out into the future, a significant percentage of power is taken by the memory, and the amount of energy used by memory grows as you increase the amount of memory in the system.

I was about to dig up some references, but got lazy. Google UHPC (it's a DARPA co-funded project): the idea is to increase performance of leading edge super-computers by 1000x while keeping power requirements surprisingly close to flat. Therefore, even if everything in the computer except the memory got 1000x more power efficient, the entire power budget could be blown by the memory energy use.

So this may not be that useful NOW, but it might be very useful in 8-15 years.

Re:Is this useful? (1)

EdIII (1114411) | more than 3 years ago | (#35488288)

I was hoping to have somebody explain to me why the "digital" part is notable. As opposed to analog memory?

Re:Is this useful? (1)

drinkypoo (153816) | more than 3 years ago | (#35489704)

DRAM is analog, SRAM is digital. SRAM is faster and no refreshes but it's more power hungry. DRAM has to be refreshed which means you can only read from it at certain times, which makes it slower. DRAM is designed to give digital answers when you ask it questions but it's analog internally (being made out of capacitors) which is why you have to refresh it. If you refresh it incorrectly then the answer will be wrong. Degradation of the silicon will affect correct answers coming out of DRAM before it will affect SRAM.

So, "As opposed to analog memory?" YES. DRAM is NOT digital, it just pretends.

Re:Is this useful? (1)

aaronpeacock (1945246) | more than 3 years ago | (#35489724)

if you are living in x86 land you may think a cpu needs to suck at least 10 watts and require a fan to do anything useful. embedded computing solved all that ages ago. you have tiny-process SOC with integrated controllers, peripherals, signal processing cores, etc... memory wastes energy. buses waste time. NOC NOC! that desktop you have is computing with some small percentage of its electricity usage, and dissapating heat with the other 99.99% of it. embedded devices can consume portions of a watt. there are milliwatt capable devices even... and yes, carbon nanotubes can be cheaply produced by a variety of methods. tech articles are often outdated and cyclically and mindlessly repeating old info.

Re:Is this useful? (1)

JustinOpinion (1246824) | more than 3 years ago | (#35490970)

as I understand it, there's no good way of making high-quality naontubes in large batches. Is that still accurate?

It's a bit more complicated than that. Actually we now have a variety of very good procedures for making high-quality nanotubes in reasonably large quantities. You can buy carbon nanotubes quite easily now. The nanotubes are long, defect-free, and have low concentrations of impurities (e.g. catalyst). And one can make the nanotubes purely single-walled, or purely double-walled, or multi-walled. We have a high level of control. In these senses, you can certainly say that "high quality" tubes are a reality.

The problem is the purity of tube type. Carbon nanotubes of a given diameter come in a variety of types ("chirality"), depending on how orientation of the graphene network with relation to the tube axis. The various types have different properties: some are 'metallic', some are semiconducting. For some applications you don't care about tube type. For instance if you're loading nanotubes into a material as a strengthening agent, then all nanotubes are equally good.

For electrical applications, there's obviously a big different between metallic/conducting tubes and semiconducting tubes. Since we currently don't have a robust way of separating out the various tube types, it's currently laborious to build devices that require a specific tube type. So in this sense our modern manufacturing methods are terrible: they generate mixtures of tube types and thus are not at all "pure" in that sense.

The state of the art is advancing rapidly. New production methods are able to generate desired tube type in much higher yield (80-90%); others are using DNA as a way to separate different types from mixtures; etc. We're on our way to having access to high-purity nanotube stocks. My guess is that if carbon nanotubes become viable for commercial-scale devices, then industry will rapidly figure out the last details about how to get nanotubes of a single type in large quantities.

Re:Is this useful? (0)

Anonymous Coward | more than 3 years ago | (#35500238)

There are ways of making high-quality nanotubes by using a "seed set." It's still difficult, but the process is such that it could be put into manufacturing.
Also, as for RAM, modern DDR3 memory requires about 10W of power per 128MB. Most smartphone devices mostly utilize a "solid state" type memory scheme, so it's kinda a moot point with current designs.
This is, however, a huge deal for data centers, and in particular to "cloud computing" environments. Nearly all of those put data on a NAS device, and the actual processing is done on machines that are essentially just processors and RAM. If they can get memory to run off 1/100th the power in a data center, than that could mean hundreds of millions of dollars each year for companys that use a data center.

Re:Is this useful? (0)

Anonymous Coward | more than 3 years ago | (#35501564)

Yes and yes.

Good enough for most. (1)

pushing-robot (1037830) | more than 3 years ago | (#35488038)

Noticeably muddier and harsher than DSD memory, though.

Abstract Phase-change materials (PCMs) (2, Informative)

Anonymous Coward | more than 3 years ago | (#35488056)

Abstract

Phase-change materials (PCMs) are promising candidates for nonvolatile data storage and reconfigurable electronics, but high programming currents have presented a challenge to realize low power operation. We controlled PCM bits with single-wall and small-diameter multi-wall carbon nanotubes. This configuration achieves programming currents as low as 0.5 A (SET) and 5 A (RESET), two orders of magnitude lower than state-of-the-art devices. Pulsed measurements enable memory switching with very low energy consumption. Analysis of over 100 devices finds that the programming voltage and energy are highly scalable, and could be below 1 V and single femtojoules per bit, respectively.

Re:Abstract Phase-change materials (PCMs) (0)

Anonymous Coward | more than 3 years ago | (#35488650)

OK, so resetting a 64bit value could possibly require 320 A @ 1 V

Redundant headline (0)

Anonymous Coward | more than 3 years ago | (#35488070)

The headline appears to be redundant. ' Advance in Phase-Change Memory Memory..."

Kind of like Automatic Teller Machine machine.

Re:Redundant headline (2)

White Flame (1074973) | more than 3 years ago | (#35488110)

I didn't read the TFA, but they did use a TLA acronym, so you can GTFO out of here.

Re:Redundant headline (4, Informative)

TheRaven64 (641858) | more than 3 years ago | (#35489256)

Actually, the headline reads 'Advances in Phase-Change Material Memory...' if you want to expand the initialism. PCRAM is the more common abbreviation for phase change (random access) memory. It's a very interesting technology for persistent storage, for two reasons. The first is that, like DRAM, it's byte-addressable. The second is that read speeds are almost as fast as DRAM. This means that you can just map a bit of it into a process's address space, without any copying, to make the data available. It's a good contender for swap / hibernate space, because you can write pages that haven't been modified recently out to PCRAM, update the page tables to point there, and then turn off DRAM chips. Writing to PCRAM is quite a bit slower than writing to DRAM, but is probably fast enough when you're in power-saving mode, so you can turn off all of the DRAM, and only turn it on when the system load increases again.

Great breakthrough, but battery life? (1)

atari2600a (1892574) | more than 3 years ago | (#35488154)

Even w/ AMOLED's 90% of the battery life is eaten up by the screen, w/ the radios a close second (or the inverse of the above)

Re:Great breakthrough, but battery life? (1)

TheRaven64 (641858) | more than 3 years ago | (#35489268)

Depends on the mode. One thing people really hate about mobile devices at the moment is their battery life. The problem with DRAM is that it draws almost the same amount of power, irrespective of the system mode. Every bit in memory is constantly being refreshed, and this draws power. When you put your machine into suspend mode, about the only thing still drawing power is the RAM, and this gets worse the more RAM you put in the machine (which is a big part of the reason why mobile phones have a lot less RAM than laptops, even though 4-8GB of RAM chips would easily fit in a phone). PCRAM, like flash, uses no power when idle, a small amount of power when being read, and a lot more when being written, and is almost as fast to read as DRAM. This means you can do the equivalent of suspend-to-disk / hibernate, but resume almost instantly.

I wonder... (2)

ackthpt (218170) | more than 3 years ago | (#35488162)

Were any Rambus people within earshot? Any patent applications suddenly filed by them?

How do clear bits? (3, Informative)

Michael Woodhams (112247) | more than 3 years ago | (#35488194)

TFA explains how to set a bit (from 0 to 1), but not how to clear the bit.

The actual paper in inaccessible to me (without $$$), even from a university, as it is pre-publication. (I think it will become available on the 17th.)

Re:How do clear bits? (0)

Anonymous Coward | more than 3 years ago | (#35495594)

TFA explains how to set a bit (from 0 to 1), but not how to clear the bit.

The actual paper in inaccessible to me (without $$$), even from a university, as it is pre-publication. (I think it will become available on the 17th.)

Set the bit to 0 to clear it

To top selling fashion designer 2011 (0)

allent (2014632) | more than 3 years ago | (#35488246)

To help you to find out some top brand costume and shoes,
we would like to share with you our shopping website,
over 30000 kinds of brand name products for sale,
free shipping, accept Credit card.,zero tax
Please don't hesitate to visit for assistance you may need and
even before placing your order if required.
We look forward to hearing from you soon.
Website:http://useeshopping.com
Best regards from

Excuse me. (0)

Anonymous Coward | more than 3 years ago | (#35488324)

As long as you are communicating with your operatives, do you mind if I get in on the action? There are some pressing... nevermind.

John has a long mustache. *REPEAT* John has a long mustache.

The die has been cast. God protect us.

Another overhyped materials article. (2)

Animats (122034) | more than 3 years ago | (#35488338)

From the article:

the solution needs to be upscaled. The group has so far created and tested a few hundred bits

It's another one of those overhyped materials-science articles. Here's the hype part:

Pop says that he envisions a point where a device could get its power needs from harvested thermal or mechanical energy or sourced purely from solar. Consumer devices won't be the only beneficiaries, however. "We're not just talking about lightening our pockets or purses," Pop said. "This is also important for anything that has to operate on a battery, such as satellites, telecommunications equipment in remote locations, or any number of scientific and military applications." Server farms or data centers could also benefit from lower energy costs by utilizing the solution. The researchers say that the low-power memory could even lead to previously elusive three-dimensional stacking of chips.

Really. They've come up with yet another alternative to silicon-based memory devices. There are hundreds of such schemes, from Ovonics to silicon-on-sapphire. Many of them work, but each has something that makes it inferior to the mainstream technologies. Some (like this one, probably, since it's heating-based) have slow write times. Some are expensive to fab. Some won't scale up.

The problem with the "elusive 3D stacking of chips" is not that it can't be done, but that it doesn't make systems cheaper. In the technologies developed to date, each new layer of devices costs about as much as making a separate part.

Re:Another overhyped materials article. (1)

dgatwood (11270) | more than 3 years ago | (#35488782)

The problem with the "elusive 3D stacking of chips" is not that it can't be done, but that it doesn't make systems cheaper. In the technologies developed to date, each new layer of devices costs about as much as making a separate part.

Until you factor in the cost of the board space and being able to fab three motherboards out of one copper-clad sheet instead of two or using one PCB instead of two inside the device. Once you reach that point, reducing the board space by stacking chips becomes a significant win.

Re:Another overhyped materials article. (0)

Anonymous Coward | more than 3 years ago | (#35489296)

Really. They've come up with yet another alternative to silicon-based memory devices. There are hundreds of such schemes, from Ovonics to silicon-on-sapphire.

Phase Change Memory (PCM) == "Ovonics". This is a variation on PCM, not a wholly new thing.

But it's an interesting variant. I've been following PCM memory developments for some time, and the last couple years it sounded like one of the key problems preventing commercialization was that write currents were too high for the expected M0 (first metal layer routing) pitch at cell sizes comparable to cutting edge NAND flash. These guys seem to have that problem beat, presumably because the bit cell volume created by forming a nanogap in a carbon nanotube and then filling it with PCM material is substantially smaller than the older, more conventional PCM bit cells, and therefore the amount of heating required to switch the cell is also reduced. Neat.

The downside of course is that those more conventional PCM cells are the ones we have the ability to even think about commercializing today. So far as I know, nobody has a production ready process for depositing CNT wires on a die in a controlled way, much less manufacturing them and then gapping them like these guys are doing.

The problem with the "elusive 3D stacking of chips" is not that it can't be done, but that it doesn't make systems cheaper. In the technologies developed to date, each new layer of devices costs about as much as making a separate part.

Where is your argument that this must hold true forever?

Also, you'd be surprised at how often multi-die packages are used today. Sometimes stacked, sometimes side-to-side. Stacking is more common in memory.

What these guys were talking about is that a significant limitation in die stacking is often power. If any of the dies consume significant amounts of it, it can become much harder to extract the power out of the stack and into a heatsink than it would in a single die or non-stacked package.

Mythical Improvements. (3, Insightful)

coldmist (154493) | more than 3 years ago | (#35488600)

So, everyone said, if we switch to SSDs, longer battery life. Did it happen? No.

Memory does not use up that much power, relative to the whole system. Even switching a laptop's screen to LEDs doesn't help that much.

It's almost the same as the mythical new invention that will be out "in 5 years".

Give it up people. Semiconductors improve year after year, These kinds of breakthroughs that drastically change everything just don't happen.

The only thing I can think of that made that kind of a change in the last 30 years was going to an SSD drive for speed and responsiveness. Other than that, each year gets a bit better. Don't expect that to change any time soon.

Re:Mythical Improvements. (1)

funky_vibes (664942) | more than 3 years ago | (#35492426)

Don't be such a pessimist.
Together, all of the things you talk about have improved battery life. And turned that luggable portable PC we call a laptop from "useless on the road" into useful.
We now have netbooks that on average last 5-6h (with an 8-10h battery)
Quite a difference to the average battery time of older laptops 0.5-1.5h with the same kind of battery.

LEDs instead of a HV fluorescent tube is natural progress, but why are they charging more for it, when it should be less?

SSDs will start shining in energy saved, only when we get rid of the energy wasted on FTL and stop treating them as block devices when they in fact aren't.

Re:Mythical Improvements. (0)

Anonymous Coward | more than 3 years ago | (#35492482)

So, everyone said, if we switch to SSDs, longer battery life. Did it happen? No.

Wha? So to back up this claim, please link me to stats on the battery of a HDD-based smartphone and an SSD-based one from the same era. To be fair, music players will be actually possible to give examples for, and you'll find that SSD-based ones have much, much smaller batteries.

If PCM---or something like it---works, then it will be a radical change. Fast, cheap, bit-addressable NVRAM is something that computers have not had for a long time. See BPFS [ucla.edu] for an example of a project researchers are working on in preparation for such technologies. (Of course, they are in academia, so they can afford to spend time thinking about hardware that might not ever exist.)

Re:Mythical Improvements. (1)

rahvin112 (446269) | more than 3 years ago | (#35493814)

Battery life has been constantly improving. Even 5 years ago those most battery life you could expect on your top of the line low power laptop was 3 hours for the most expensive lightweight laptop available. With all the innovation in low power you can now routinely expect 5-10 hours. That's a 100% improvement in just a few years. Step back even further (before 2000) and the max was about 1.5 hours. Battery life and run times have dramatically improved. I'm simply amazed that my little 10" netbook can do more than 6 hours on battery routinely and close to 10 hours on light web surfing.

Re:Mythical Improvements. (1)

gl4ss (559668) | more than 3 years ago | (#35495308)

are you insane? have you not heard of psion? battery capacities have not improved too dramatically and computers used to need less power.

Re:Mythical Improvements. (1)

owlstead (636356) | more than 3 years ago | (#35498244)

Psion has nothing on my watch. It runs for years on a single battery.

100x (0)

Anonymous Coward | more than 3 years ago | (#35488668)

a hundred times less power consumptive DAYUM but we won't be experiencing this any time soon, the tubes are still a manufacturing issue, expect it to be solved in five years. Then we're in business.

Memristor memory? (0)

Anonymous Coward | more than 3 years ago | (#35488748)

I wonder if they used memristors. From my understanding they are low power consumption, and may not be affected by magnets.

Interesting, but.... (3, Insightful)

pablo_max (626328) | more than 3 years ago | (#35488894)

I, no doubt like most of you, enjoy reading about advancements in technologies. Especially those which can have a direct impact on computer performance!
Lately though, it seems to me, that all of these headlines and articles are exactly the same article. Making some claim about a major breakthrough and how this will make my computer 100 times faster and use 100 times less power....maybe...in the future.
It seems always to the case that in 10 years, "this" will enable us to use a lot less power and have much higher densities and so on and so on.
Basically, why the techs are interesting, the articles are absolute crap. Sensationalizing everything where there is nothing worth do so about. Why can they not just explain the so-called break though, it's probable applications and realistically how long, if at all, until commercialization?

Re:Interesting, but.... (1)

ledow (319597) | more than 3 years ago | (#35489082)

Which is why I have a rule.

Unless I can buy it *today*, *this second*, from a supplier that I'm willing to buy from, it's not worth getting excited about except from a purely scientific standpoint (the same as someone claiming to have invented a new type of tile to use on the Space Shuttle - interesting but I will *never* hype the company that sells it, or end up using the product myself). Until it exists, is in a store I can order from, is in a standard format of some kind, and at a sensible price, I can't plan budgets for it, I can't investigate upgrades, I can't do even preliminary testing, I can't try it out, I can't see my friend's one, I can't do anything about it. So it's not worth anything more than "Oh, that's interesting" and going back to work on a *real*, live, purchased, computer product that exists today. There's no point worrying about the wonderful new operating system that *will* come to replace the current heap-of-junk until it's here, and been tested. Until that point, I *still* have to plan as if it doesn't exist.

This means I steer clear of anything "pre-order" whatsoever. When I can buy it, yeah, then is a good time to wonder if I should buy it. Thus, so far, I haven't wasted money on things like Duke Nukem Forever, or the Pandora console that people are still trying to ship out to the first-day pre-orderers even after 3 years "in production", the "Phantom" console, nor other similar vapourware.

The "new memory technology" thing has been crowed about since I was a child. We'd all have this amazing memory that would survive a reboot, be huge, cheap and fast etc. etc. etc. Flash drives came along and made headlines but until I could actually buy them (i.e. it was not only available but at a price I was willing to pay for those features) it wasn't worth any of my time. In the meantime, several HUNDRED other technologies that all claimed they could do this have come and gone without being used in a single commercial product that I have an interest in using.

If it doesn't exist, you can't "buy" it. Therefore, it's pointless to try to plan for having it at any particular point, even as a future plan because you have no idea whether it will exist or not at the point you need it.

So do what I do. Read about how this particular instance of a technology that's come-and-gone a million times is supposed to work, then carry on as normal. When you first see a commercial PC that supports it, or you first see the chips on sale at your normal suppliers, THEN it's worth looking into them (and that usually means having some other poor mug try it out on your behalf so you don't waste your money on junk).

Re:Interesting, but.... (1)

del_diablo (1747634) | more than 3 years ago | (#35489406)

So well written *sniffle*
Someone mod up!

so? "memristor". (1)

eyenot (102141) | more than 3 years ago | (#35489464)

make that a memristor sandwich and you would have my interest. in fact i've decided not to buy another pc until it features AMOLED and memristor memory. fuck these other "advances", they're just trying to stall the inevitable or grab some of the remaining market time. toshiba just got quaked and everybody's bitching about how memory's going to go up. someone is inevitably going to attempt to capitalize on that, but unless it's the *actual*, new, advance it's not really "advanced". so opt out of planned obsolescence and hold out for memristor from HP.

Absolutely nothing to see here (1)

Ancient_Hacker (751168) | more than 3 years ago | (#35489602)

While these folks may have made something 100x faster than something else, it's still useless.

It's a phase-change -- that means HEAT, which means it takes time for the storage element to heat up, change phase, and then cool down. It's probably better than using punched cards, maybe even better than 1990 flash memory, but not a whole lot better.

    Memory technology today has to work on the nanosecond level-- phase-change is not going to get anywhere near that ballpark.

You also need storage that can be read and written thousands of times without degradation-- phase-change is unlikely to ever get to that level.

oh, so that's why more memory is better (0)

Anonymous Coward | more than 3 years ago | (#35489656)

This place is really going downhill. I mean really, News for Nerds and we have to be told why more memory that uses less power is an advantage?

This story is the official kick off to my searching for a replacement site.

Not medical? (1)

mevets (322601) | more than 3 years ago | (#35489928)

Why wouldn't this mythical device be applicable to medical devices? It seems there are a dozen other industries you left off your list, is it not potentially applicable to them either?

What happened to MRAM? (1)

funky_vibes (664942) | more than 3 years ago | (#35492714)

I was looking forward to new memory that might be more expensive, but has the best of all worlds.
(simple hardware interface, durability and faster than dram write and read speed, ie. like sram but cheaper and only uses energy while active)
The embedded world seriously needs new parts that allows designs and software to become simpler, at the expense of hardware cost.

Re:What happened to MRAM? (1)

owlstead (636356) | more than 3 years ago | (#35498274)

I guess it is still stuck where it was a few years ago :)

Check for New Comments
Slashdot Login

Need an Account?

Forgot your password?