'Memtransistor' Brings World Closer To Brain-Like Computing 94
the gmr writes: According to a recent article published in the journal Nature, researchers at Northwestern University's McCormick School of Engineering have developed a "memtransistor," a device that both stores information in memory and processes information. The combined transistor and memory resistor work more like a neuron and purports to make computing more brain-like. The new "memtransistor" would use less energy than digital computers and eliminate the need to run memory and processing as separate functions while also being more brain-like. Lead researcher Mark C. Hersam clarified the brain-like efficacy of the memtransistor: "...in the brain, we don't usually have one neuron connected to only one other neuron. Instead, one neuron is connected to multiple other neurons to form a network. Our device structure allows multiple contacts, which is similar to the multiple synapses in neurons... [but] making dozens of devices, as we have done in our paper, is different than making a billion, which is done with conventional transistor technology today." Hersam reported no barriers to scaling up to billions of devices. This new technology would make smart devices more capable and possibly more seemingly-human. The devices may also promote advances in neural networks and brain-computer interfaces, new technologies also recently reported at Futurism.
Comment removed (Score:5, Informative)
Re:For those unfamiliar with memristors... (Score:5, Informative)
The problem with the passive components is the same as it's always been, and why Von Neumann idealized state machines as computing elements. Adding a state value helps, but causes multiple concurrent states.
Memtransistors don't have checksums, and their state isn't arbitrated in such a way as to give them the capacity to be shared without other active components. Because there is no checksum or CRC easily possible, coupled to the logic that sets (and checks) their value, means that they have limited architectural applications until several facets of their nature can be changed.
Look at 100 people, and 33 of them have faulty neurons. Analogizing states in this way, memtransistors, could also be capacitive arrays, inductive arrays, LC/LCR arrays, and so forth. Their present state of changeability comes nothing close to the high speed memory (transient and charged state--think nv-ram) present today.
There are great potential applications in ASICs, (fp) gate arrays, and other constructions, but just as GPUs don't replace CPUs, arrays made of memtransistors aren't going to replace either CPUs or GPUs, FPGAs, ASICs, etc. They're not more "brain-like", rather, they're a different architectural models whose limitations still haven't been surmounted.
It's not a fully passive device-- it's a resistor with a third leg in terms of boolean logic.
Did you write that or are you a bot? (Score:1)
I have the distinct impression that the above jibberish spew was composed by a buzz word compliant hidden markov model.
Re: (Score:1)
Re: (Score:2)
It's not a fully passive device-- it's a resistor with a third leg in terms of boolean logic.
Before you post something so bafflingly irrelevant maybe re-read the parent's post and wikipedia article. Start with the 5th word in the post title.
Re: (Score:2)
I read both of those. This is a logic gate, a resistor that looks like a standard logic element transistor. If you want to be less baffled, look into electronics engineering as it applies to both computing, and also the history of how microcomputers were originally designed against the state machine model(s).
Re: (Score:3)
I read both of those. This is a logic gate, a resistor that looks like a standard logic element transistor. If you want to be less baffled, look into electronics engineering as it applies to both computing, and also the history of how microcomputers were originally designed against the state machine model(s).
CORRECT.
1T1C (or any two-terminal implementation of a non-volatile memory element) is a goal of extreme interest for the big CMOS foundries. Density!
I believe that it is still 2T2C available on the market, but RAMtron is likely to have fixed that a while ago. It was a hot topic in 2000.
How about you enlighten us (Score:2)
You clearly never red Von Fredircks fifth postulate of public discourse, please read Willhems essayist, and rodgers publik speaking and it's effect on reason, or sargentzi's Das Discobolus in the original German before you recommend better educations to people ob slashdot.
Re: (Score:3)
This is a logic gate
So you DIDN'T read it then. A memristor doesn't have a gate. It's a 2 terminal passive device.
Keep trying. You'll get there eventually.
Re: (Score:3)
Yea I found this summary pretty sensational. I've heard the term you used, "memristors," and how HP was working on them a few years back. I might have understood the concept wrong though. Typically memory is where you store data and registers are units on the processor that act on that data (add, subtract, bitshift, or more complex instructions).
As I understood it, memristors would allow instructions to operate directly on memory without having to load or store. If you had enough memristors to load your pro
Re: (Score:2)
Yea I found this summary pretty sensational. I've heard the term you used, "memristors," and how HP was working on them a few years back. I might have understood the concept wrong though. Typically memory is where you store data and registers are units on the processor that act on that data (add, subtract, bitshift, or more complex instructions).
As I understood it, memristors would allow instructions to operate directly on memory without having to load or store. If you had enough memristors to load your program into them, you'd effectively run everything incredibly fast in place. However this would change the entire way we write programs and compilers.
You'd probably no longer have a stack, the purpose of a program counter would change entirely, and you'd start to get into the very gritty details of immutability and self modifying code. . .
Zero boot-up time! Zero program-loading time! Everything resident in storage is de facto resident in memory, if your Memristor storage is equal to your RAM in size, and are one and the same, then you can do general computing at closer to L3 to L1 cache speeds! Vroom!
Oh, this would open huge new security holes now, wouldn't it? Hmmn.
I imagine that there would be some kind of redundancy built-in --- You don't want your code or purchased apps being altered after installation! Pernicious worms/virii hidde
Re: (Score:1)
Except that a memresistor is not really a passive component as it has state. And there is no "missing" passive component either. I don't know why this obvious BS is being repeated and repeated all over the place. A great success for marketing nonsense, a great loss for actual truth in engineering.
Re: (Score:2)
So I suppose you think capacitors are not passive either, then?
Or do you think that retention of charge doesn't count as "state"?
You may find that your own definition of active vs passive components is not the same as the actual one.
Re: (Score:2)
A capacitor does not have state. It has a potential charge, but that level is not dependent of its history. The history just somehow has to provide that charge, but it is completely irrelevant how it was provided. Furthermore, a capacitor's charge does not influence its behavior (voltage change on charge-change). That is up to a point, of course. When you reach the breakdown voltage, a capacitor does indeed become an active element for a brief time. As this is outside of normal operating parameters, it is n
Re: (Score:2)
No. The capacitor is not changed by the charge in it. Hence the capacitor itself does not have state. Given the same situation, it will always behave the same, no matter its history. (This is for an ideal capacitor of course.)
A memresistor is fundamentally different. Depending on its history, it will behave differently in the same situation. Here the device itself is changed, and hence the device has a state.
You are probably confused by the difference between the state of the device and the state it is in.
Re: (Score:2)
Incidentally, I am not the only one that has noticed that calling memresistors "passive" is bullshit, although that is intuitively clear to anybody with actual experience with electronics :
https://www.researchgate.net/p... [researchgate.net]
Re: (Score:2)
My intent was to point out that your notion of its "state" being tied to whether the device is passive or active is a misguided one.
Mathematically, a passive element is one where at least one of either the current or the rate of current change in a circuit utilizing the device is linearly dependent on either the voltage or the rate of change of the voltage applied to the circuit, and so there must be exactly 4 kinds of passive components.
All other components are considered active components.
It's my u
Re: (Score:2)
What is wrong with all you guys today?
Memristors are *passive* because they keep their state when you switch the power off.
Thats all ...
Re: (Score:2)
Re: (Score:2)
By that definition, inductors aren't passive...
Re: (Score:2)
Yes, and?
I came not up with that stupid active/passive talk that emerged in this thread.
And why would an inductor be "passive"? Why would anyone declare single electric components as either active or passive anyway?
Re: (Score:2)
Yes, and?
And therefore you're mistaken.
I came not up with that stupid active/passive talk that emerged in this thread.
Possibly so, but you were the first I spotted who got it wrong in a really obvious way.
And why would an inductor be "passive"?
This [stackexchange.com] sounds about right.
Why would anyone declare single electric components as either active or passive anyway?
Because they're all stupid, of course.
Re: (Score:2)
Sigh .. the world is so sad in our days ...
Your answer to the question of active/passive shoud/could have been this:
The reason for the distinction is mathematical: You can use certain mathematical approaches to solve the equations of a device that contains only passive elements, while the same approaches would not work with active elements.
But obviously you don't grasp the topic so you can not explain youself :)
Nevertheless, thank you for the link (I hope the information in it is correct, as I'm not interes
Re: (Score:2)
Your answer to the question of active/passive shoud/could have been this:
Uncredited copypasting might be your approach at trying to appear to have a clue; it's not mine.
But obviously you don't grasp the topic so you can not explain youself :)
Yet it was me who had to do basic research in order to educate you, who obviously has even less of a grasp on the topic.
as I'm not interested enough in researching it
Par for the course.
Sigh .. the world is so sad in our days ...
Indeed, and your comment is the best example why that is.
The fact here is however on a different level.
No, it is not. This is only you trying to shift the goalposts in order to retrospectively don't appear as dimwitted.
We are talking abbout computer science and not 'electric engineering'.
Shift it, my special friend.
So a memristor which keeps its state after losing power is considered passeive, just like a magnetic disc. The opposite as in 'active' is a DRAM, which you have to refresh every few milliseconds. You can grasp that?
So DRAM is active because extra circuitry has to refresh it. Yeah, I grasp
Re: (Score:2)
The voltage drop on a perfect inductor is always directly proportional to the rate of change of the current flowing through it. If you remove it from a circuit, there is no change in current, so any state it may have had in an active circuit is always lost when you switch the power off. Perfect capacitors retain state because the change in voltage drop is proportional to the current flowing through it.. so if there is no current, the voltage drop stays constant.
Perfect inductors also retain state because the change in current is proportional to the voltage drop; if you remove a perfect inductor from a circuit by shorting the terminals the voltage drop is zero and the current through the inductor remains constant. Inductors store state via current in the same way that capacitors store state via voltage.
Of course, perfect inductors are a bit hard to find, but a coil made of superconducting material comes very close. As counter-intuitive as it may seem, it is actuall
Re: (Score:2)
Anyway,
in computer science we have a different definition between active or passive.
And pulling the electric engineering definition when it is not relevant (and as far as I can tell an american thing) is pretty pointless.
And your long answer shows: you don't grasp that.
Re: (Score:2)
Depends what you mean with state :D
Perhaps you should define that first?
A resistor has plenty of states to me: resistance in Ohm (which is changing with temperature), a rated max current etc. Current amount of current flowing through it as a function of currently applied voltage, current temperature, current effective resistance ... you could include its size etc. p.p.
Anyway, I guess your point was rather theoretical? If you remove it (the inductor) from a circuit, there is no change in current in a direct
Re: (Score:2)
No. The capacitor is not changed by the charge in it. Hence the capacitor itself does not have state. Given the same situation, it will always behave the same, no matter its history. (This is for an ideal capacitor of course.)
A capacitor is non-Markovian.
A memresistor is fundamentally different. Depending on its history, it will behave differently in the same situation. Here the device itself is changed, and hence the device has a state.
A memristor is Markovian. To what degree is what matters (in application).
Hysteresis, imprint, and the useful number of cycles (10^12 minimum) are also important. The potential to 'reset' a NV-RAM's bits, refreshing them to a predictably imprinted state would be useful. Indeed, it would probably be part of the implementation, perhaps as one of those 3:00 am cron jobs.
Re: (Score:2)
Of course a capacitor has state: it's current charge level and the fact if it is charging or discharging, you could even add the rate of charging/discharging to its state.
Re: (Score:2)
The sad truth is that the marketing wank is what funds the engineering.
Re: (Score:2)
And corrupts it. Indeed.
Re: (Score:3)
Except that a memresistor is not really a passive component as it has state. And there is no "missing" passive component either. I don't know why this obvious BS is being repeated and repeated all over the place. A great success for marketing nonsense, a great loss for actual truth in engineering.
The actual article was sensationalistic. All they did was implement a hybrid memristor (assumed, TL;DR) incorporated with a transistor. So they combined two of the four basic circuit components into one with two leads. Big deal --- Ancillary circuitry will be needed to send "write" currents sometimes, and "read" voltages other times. Those must be put somewhere on the die.
Call the memristor a passive component if you want. The fact is, though, that a memristor can be "set" to a certain resistance, mean
Re: (Score:3)
Yeah, but because we're all stupid now Futurism has a to write the clickbait article as 'new magic component will lead to ELECTRONIC BRAINS'. As if the problem of AI is going to be solved by some low level component as opposed to understanding the high level organisation.
Re: (Score:2)
Re: (Score:3)
Re: (Score:2)
What exactly is "passive" on/in a capacitor or inductor?
Re: (Score:2)
Re: (Score:2)
Capacitors and inductors don't directly modify voltage or current; Rather they store energy. The way in which they do is essentially reciprocal. An inductor stores the energy as a magnetic field, which then collapses when current falls off. This collapse puts energy back into the circuit. In essence, it effectively creates an effect analogous to storing momentum if this were applied to plumbing or hydraulics.
Capacitors store charge by blocking flow and accumulating charge up to their "capacity" with a volta
Re: (Score:2)
I'm not sure, but I think I learned that in 7th grade, thank you for the fresh up.
Did you answer to the wrong person?
P.S. non of your explanations has anything to do with active/passive (for me at least ;D )
Is Slashdot broken or something? (Score:1)
Timeouts, pages hanging... 40x/50x status codes ...what's the deal?
Whole website is dog slow and seems to be getting worse. Not that management cares, but this is usually what precedes a total failure.
Anybody seen this too?
Re: Is Slashdot broken or something? (Score:2)
Yep, same.
Re: (Score:2)
Re: (Score:2)
Yes. Just timeouts, but lots of them for the last several days. At first I suspected a ddos, but then they went down for maintenance, and when they came back up it was worse. Maybe someone's mining bitcoins on the site.
Re: (Score:3)
Perhaps they're using a new server that runs on memristors.
"Okay, what's two plus two?"
-thinks- "... two."
"What happened to the other two?"
"... I forgot about it.
Re: (Score:2)
Perhaps they're using a new server that runs on memristors.
"Okay, what's two plus two?"
-thinks- "... two."
"What happened to the other two?"
"... I forgot about it." [emphasis mine]
That sounds more like a quantum-computer's q-bit effect. Although, DRAM capacitors do indeed have to be re-written after their state is read, so I guess it applies in your example.
A memristor is a two-terminal device, and can be used in logic in this form, but with the added overhead of combining write-lines w/read-signal lines. . . and the same thing with reading it, ostensibly, is an oopsie could erase the persistent state of the memristor bit. I'm not a circuit designer, so can say nothing about whic
Re:Is Slashdot broken or something? (Score:5, Funny)
Re: (Score:3)
My bet is that they installed Meltdown patches and took a massive performance hit.
Re: (Score:2)
Timeouts, pages hanging... 40x/50x status codes ...what's the deal?
Whole website is dog slow and seems to be getting worse.
The FCC revocation of Net Neutrality got published last week, so ...
Re: (Score:2)
And immediately, 100 million programmers skills were rendered obsolete
With RAM == Storage, there will indeed be a paradigm shift. There will be plenty of more work for the programmers to do, such as implementing admin-space cron jobs to 'refresh' the NVRAM at 3:00 every Saturday. . . or something like that.
Also, Hardware Designers are in for a treat as well.
The whole paradigm will shift when we reach that stage. We (researchers) have been working on the physical realization of a CMOS-integrable memristor for about 20 years, so it's about time.
The biggest barrier was the CM
Re: (Score:2)
Terminators are made with conventional resistors, and one is enough. Please hand in your geek-card.
Re: (Score:1)
Indeed. But the Neuro-"sciences" are full of cretins that make grand claims and cannot back them up. Remember how start-of-the-art Neuroscience modelling cannot model a C64? (For reference, a C64 is roughly in the complexity of a single neuron to a very small group of neurons.) Most of these people should be stripped of their PhDs for doing gross damage to the credibility of their field.
And claiming one memresistor + one transistor is "close to a neuron"? That is just a direct, shameless lie.
The only thing
Re: (Score:1)
It is not: https://www.researchgate.net/p... [researchgate.net]
Seriously. And "small on a chip"? What is that nonsense? Ever heard of chips being put into cases and being fitted with leads?
With minimal effort, I found a source that says around 200uA current through a memresistor. That is well within range what you can handle entirely manually on macroscopic scale: http://ieeexplore.ieee.org/doc... [ieee.org]
I think this "memresistor" thing is just another instance of people with no clue seeing the philosopher's stone finally being found
Re: (Score:2)
Courtesy of following links in the Wikipedia RRAM page, I find this [mouser.com], an Panasonic 8 bit CPU with embedded RRAM memory. According to Wikipedia, this was around in mid 2016. (RRAM = resistive RAM, a more general term which would include HP's memristor.)
Re: (Score:2)
Here [adestotech.com] is another. Late 2016, low power EEPROM (electronically erasable programmable read only memory) using RRAM technology. In this case, it looks like they are pushing low power consumption as their niche.
Re: (Score:2)
Re: (Score:2)
It's in the same space as flash, perhaps closer to XPoint, but doesn't really have the investment of either to bring it to market in quantity and then doesn't have the economies of scale to make it competitive. Last I heard, the biggest chips were 64MB. It's hard to compete with flash because of the incredibly high volumes of flash that can be used to amortise R&D costs. Last I heard, HP was hoping that flash would run into a wall in scalability and they'd get more investment for alternatives in the same space, but that doesn't seem to have happened yet.
Intel has not revealed the mechanism of X-Point. It could be a special variant of flash storage (like Samsung also just announced).
64 MB sounds about right. The ones I know are ferroelectric RAM (Fe-RAM), another nonvolatile type of memory technology. RAMtron is the company who makes it, and yes, it is for specific-case niche markets like "high temperature operation" for engines and such. RAMtron was bought-out by a larger player a couple of years ago.
There is a solution to RAMtron's scaling problem (th
And another fine nonsensical headline (Score:1, Troll)
Nobody knows how the brain works. In fact, the closer we look and the more we know, the more mysterious its workings become. Claiming to bring anything "closer" to its working is a direct lie.
Not entirely true (Score:3)
We have a pretty good idea of how neurons work and behave individually and also some brain components are understood up to a point - eg visual system which has allowed some pretty good advances in artificial neural networks. However how individual systems in the brain link up and produce a conciousness - the ghost in the machine - is still frankly anyones guess. There are lots of idea but nobody really has a clue yet.
Re: (Score:2)
So what you're saying is that Artificial Intelligence is just around the corner and we should be giving all of our money to the VCs pushing it?
Welcome to 2008 (Score:2)
How is this different than HPs memristor from a decade ago?
Re: (Score:3)
Completely different. This is a memTrANSistor
Re: (Score:2)
How is this different than HPs memristor from a decade ago?
The memristor was first theorized as the 'fourth basic electronic component' in a paper in the 60's or 70's.
HP gets credit for being first-to-market (with a sub-optimal active-layer material). But, of course, they ran with the material that they had Patent protection for. That keeps their marketplace lead open for a while... Hopefully, they figure out the next leap before everyone catches up with them. (That did not happen.)
In other news... (Score:2)
How much closer? (Score:2)
typical nanotechnology (Score:2)
I am a nanotechnologist, and this is the BS typical of our field.
The effect they're looking at is reversibly changing the gate properties of the transistor by carefully spiking the voltage on one input. This is something you can do with a silicon transistor; the magnitude and reproducibility of the effect is driven by the defect density and thickness of the gate oxide. It's temperature dependent, atmosphere dependent... all this stuff is very scientifically interesting, there are a lot of papers and PhD th