IBM Says It Can Fit Nearly 100 Billion Transistors On a Chip (zdnet.com) 111
IBM has unveiled "what it says is the world's first sub-1-nanometer chip technology," reports ZDNet, "designed to pack nearly 100 billion transistors on a fingernail-size die, roughly doubling the density of IBM's earlier 2-nm test chip, first shown in 2021... Today, the smallest, most powerful chips top out at about 80 billion transistors."
At the heart of the announcement is NanoStack. This is a three-dimensional, nanosheet-based transistor design that scales vertically, or along the z-axis, by stacking and staggering CMOS devices. Unlike today's nanosheet architectures, which IBM also pioneered and which are being adopted by leading foundries at 3 nm and 2 nm, NanoStack bonds two nanosheet transistors into a single vertical structure, with each tier optimized independently and contacted from opposite sides. Each transistor in the demonstrated structure uses three sub-5 nm-thick nanosheets, about "15 silicon atoms" across, separated by roughly 9 nm spacers. Two such devices are then bonded vertically using an ultra-thin dielectric process IBM describes as a key innovation. Because the top and bottom devices can use different channel materials, dielectrics, and metals, IBM argues NanoStack is less a single trick and more a transistor platform that can be extended through multiple generations: 7 angstrom (Å), 5 Å, 3 Å, and potentially down to 1 Å in its internal roadmap.
An angstrom, by the by, is one ten-billionth of a meter. In terms of chips, an angstrom is a tenth of a nanometer. "This is the world's first sub-1 nanometer chip technology with a new transistor architecture," said Jay Gambetta, Director of IBM Research and IBM Fellow, during a press briefing. "We're not just making smaller transistors, we're reinventing how chips are built to deliver dramatically more power and energy efficiency...." Based on internal benchmarking against its 2 nm node, the company said its new chips will deliver up to 50% higher performance at the same power, or up to 70% lower power for the same performance. Big Blue also highlighted a 40% improvement in the scaling of static random-access memory (SRAM) cell area relative to its 2 nm technology.
This is a change IBM described as a "step the industry hasn't seen in over a decade" and one that could be particularly important for AI accelerators that live or die on on-chip memory bandwidth... According to Huiming Bu, IBM's VP of silicon technology R&D, NanoStack is a new paradigm. It's moving chips to scaling fully into three dimensions and giving the industry at least "another decade" of logic advances as it crosses from nanometers into angstroms... The 40% SRAM density bump could also help architects push caches and on-die memory closer to compute units, cutting data movement overhead in training and inference workloads.
IBM sees a path to production use "in as early as the next 5 years", according to the article, and "expects NanoStack to eventually underpin CPUs, GPUs, mobile SoCs, and SRAM arrays."
IBM's VP of silicon technology R&D says the new innovation "can improve performance by 50% compared to the best available chip today, and at the same time can reduce power by 70%."
An angstrom, by the by, is one ten-billionth of a meter. In terms of chips, an angstrom is a tenth of a nanometer. "This is the world's first sub-1 nanometer chip technology with a new transistor architecture," said Jay Gambetta, Director of IBM Research and IBM Fellow, during a press briefing. "We're not just making smaller transistors, we're reinventing how chips are built to deliver dramatically more power and energy efficiency...." Based on internal benchmarking against its 2 nm node, the company said its new chips will deliver up to 50% higher performance at the same power, or up to 70% lower power for the same performance. Big Blue also highlighted a 40% improvement in the scaling of static random-access memory (SRAM) cell area relative to its 2 nm technology.
This is a change IBM described as a "step the industry hasn't seen in over a decade" and one that could be particularly important for AI accelerators that live or die on on-chip memory bandwidth... According to Huiming Bu, IBM's VP of silicon technology R&D, NanoStack is a new paradigm. It's moving chips to scaling fully into three dimensions and giving the industry at least "another decade" of logic advances as it crosses from nanometers into angstroms... The 40% SRAM density bump could also help architects push caches and on-die memory closer to compute units, cutting data movement overhead in training and inference workloads.
IBM sees a path to production use "in as early as the next 5 years", according to the article, and "expects NanoStack to eventually underpin CPUs, GPUs, mobile SoCs, and SRAM arrays."
IBM's VP of silicon technology R&D says the new innovation "can improve performance by 50% compared to the best available chip today, and at the same time can reduce power by 70%."
Wow! (Score:2)
That's a one followed by eleven zeroes. Can you count that high?
Re: (Score:2)
Yes, if you give me more lifetimes.
Can someone tell me if this is a 'good thing' so tjhat they can hardcode more algorithms, like AES, onto the chip?
Re: (Score:1)
Re: (Score:2)
The thing is, it's very hard to make electronics this small, as the current processes are basically still "lithography" techniques. A technique that goes back to etching acid into rock. Modern chip lithography evolved from photo lithography, the technique used to etch circuit boards.
The ability to "draw" at sub-millimeter (1000 micron) requires using a light spectrum laser with a wave length small enough. So EULV is literately "extreme ultra violet" 13.5nm, which is basically x-ray wavelengths. Yes you hear
Re: (Score:2)
"The Naming Convention: The "0.7 nm" label is an industry generation name (or "process node") rather than an exact physical measurement of any single component on the chip.
The Vertical Solution: Because physically shrinking individual parts any further causes extreme electricity leakage and quantum interference, IBM stopped trying to make the individual components thinner laterally. Instead, they achieved this density by stacking the nanosheets vertically across two layers using their 3D NanoStack architecture."
-LLM
"The 0.7nm (7 Angstrom) label refers to a marketing process node representing equivalent density, while the physical nanosheet layers in IBM's new chip are roughly 5 nanometers thick. By adopting a 3D "Nanostack" architecture to build upward rather than shrinking components, IBM achieved 100 billion transistors on a single chip. For more details, visit Memeburn."
Re: (Score:2)
Re: (Score:2)
Is that 100 billion transistors in that chip or are you just happy to see me?
Re: (Score:2)
Re: (Score:2)
Re:Wow! (Score:5, Funny)
Interestingly enough if you count out loud your lips won't touch in the middle until you get to a million.
Billion continues that deviation from the lower numbers.
Re: (Score:1)
Re: (Score:2)
-1
Can't count that high (Score:2)
Eleven? No
Amazing if it works (Score:5, Insightful)
While I like to come here and rant about stupidity and enshittification, this story gives me a moment to reflect on the amazing achievements we've made as a species. We long ago blew through the wavelengths of visible light, and are now encroaching on X-rays and approaching the sizes of some of the larger atoms with manufactured, active structures. Impressive.
Re: (Score:3, Informative)
I try to remind myself of things like this all the time. For every time you see some awful story on the news about things getting worse and people being awful to each other, remember that humans are also capable of things like building at the atomic level, sending people to and bringing them home from other celestial bodies, eradicating diseases, and creating masterpieces like the Night Watch and the ceiling of the Sistine Chapel. We're an amazing species and everyone needs to remember that now and then.
Re:Amazing if it works (Score:5, Insightful)
We're an amazing species and everyone needs to remember that now and then.
Yes, amazing how after all the improvements we made on technology we're still waging wars, oppress, steal, believe fantasy characters are real, are selfishly raiding and polluting our only home at the cost of other living beings.
We haven't improved as a species, we only modernised.
SOME people are waging wars, oppressing, stealing, destroying. I don't believe fantasy characters are real, I don't wage wars. I am trying to not destroy the earth. I thought about modding this shitpost down, but I'd like to point out that it's jerky comments like this that keep everyone divided. Not everyone is perfect, just like not everyone is an asshole.
Re:Amazing if it works (Score:5, Informative)
We're an amazing species and everyone needs to remember that now and then.
Yes, amazing how after all the improvements we made on technology we're still waging wars, oppress, steal, believe fantasy characters are real, are selfishly raiding and polluting our only home at the cost of other living beings.
We haven't improved as a species, we only modernised.
SOME people are waging wars, oppressing, stealing, destroying. I don't believe fantasy characters are real, I don't wage wars. I am trying to not destroy the earth. I thought about modding this shitpost down, but I'd like to point out that it's jerky comments like this that keep everyone divided. Not everyone is perfect, just like not everyone is an asshole.
And it's also worth remembering that we wage far less war than ever before, and engage in far less of the rest as well. Stephen Pinker's "The Better Angels of Our Nature" documents this very well and I highly recommend it.
Just consider one example: Animal cruelty. Of course some people are still quite cruel to animals, but they're the exception, and this was not historically the case. For example there are historical accounts of a common festival entertainment in medieval France, where cats were put in sacks or baskets or hung from poles and burned alive so their yowling could amuse crowds of festival-goers. Bear-baiting, bull-baiting and cockfighting were other examples. These weren't underground, deviant activities, they were public, family events that whole communities anticipated and attended with great enjoyment.
We're far from perfect, but we're getting better, and not just technologically.
Re: (Score:2)
Just consider one example: Animal cruelty. Of course some people are still quite cruel to animals, but they're the exception, and this was not historically the case.
Are they the exception? Given what we know about shelters [bbc.com], there's no shortage of cruelty. The difference is that instead of enjoying it, we pretend it doesn't happen. On one hand that's better because it's not a celebration, and on the other hand it's pathetic weakling bullshit with people too cowardly to face the results of their own actions. And that's before we even get into how CAFOs didn't even exist before the 1940s or so... Everyone who eats meat (myself included) is funding whole new levels of inst
Re:Amazing if it works (Score:4)
It's NOT an advance to PRETEND that you're not cruel.
Yes, it is
When the norms and the expectations move from considering something cruelty to be funny or enjoyable to merely accepted and then to shameful or hidden -- and even illegal -- those steps are progress.
Related: "Hypocrisy is the homage that vice pays to virtue." While the individual hypocrite may not be better than the person who engages in open vice, and might be worse, the fact that people feel the need to keep their vices secret is a positive indication about society as a whole. Assuming, of course, that the "vice" is actually bad.
That's another area where our society has been improved... we're more tolerant, having realized that many things we considered bad are merely different. We still have progress to make on that front, too, but don't let perfect be the enemy of progress.
Re: (Score:2)
Re: (Score:2)
Or, possibly, when a shelter acts counter to the way most shelters act, it's newsworthy. "Animals shelters across the world continue to be caring and humane places" isn't going to sell a lot of outrage clicks.
Re: (Score:2)
Are they the exception?
Yes they are. Given what we know about our population related to the links you share it's clear that it's an exception.
Statistics is hard I get it.
Re: (Score:2)
Re: (Score:1)
And it's also worth remembering that we wage far less war than ever before, and engage in far less of the rest as well.
Wars are much more costly now that they were in the past. Wars destroy (material/human) capital a lot and that leads to huge productivity drops. So it is logical that we do less wars and we would do so even if we were perfectly selfish and psychopathic. ... so why to risk doing crime.
Even common people do less crime likely because law enforcement is better and we live well enough even without crime
Maybe animal cruelty is down primarily because we have much better fun activities like sports, movies, gaming
Re: (Score:2)
And it's also worth remembering that we wage far less war than ever before, and engage in far less of the rest as well.
Wars are much more costly now that they were in the past.
Nope. Wars used to regularly cause widespread famines, as well as being far more directly bloody. Murdering all the children was for millennia an accepted practice. You should read the book.
Re: (Score:2)
But very little material capital was required for production and people had plenty of kids. Eliminating some of them to scare the rest to compliance with the new upper class was likely an economical decision. Almost no education was required for productivity. Kids could economically contribute to society somewhere from the age of 10. No or almost no education was needed. In a way people were a relatively cheap renewable resource back then.
Also an important factor is that the work was much less sophisticate
Re: (Score:2)
War has in the past, and still does today, give local economic advantage to the conquerors.
Re: (Score:2)
Yes, overall for all of us together, war is always worse than negotiated settlement about the division of resources over which the disagreement is. That is not an issue. It was so in the past, it is so now and it always will be so in the future as well. The reason for that is very simple: the war is costly (it damages economic resources). This cost does not need to be incurred if a negotiated settlement happens instead of a war. I think everybody agrees with that. It is kind of obvious.
But I disagree with
Re: (Score:2)
War may not be better (when compared to the situation before the war) even for the side which does win
Often it is.
Re: (Score:2)
War may not be better (when compared to the situation before the war) even for the side which does win
Often it is.
Yes, I think it is likely.
Re: (Score:2)
Re: (Score:2)
TLDR: Agreed, if it is taken directly. But indirectly the strategic leaders must take the broader population into account ... and therefore the economy. People who do not behave strategically are very unlikely to become leaders. Therefore decision-makers not taking broader economy of a war into account are very unlikely.
Leaders in democracies are quite limited by laws and parliaments. They cannot go to war only on their own whim. Quite a lot of persons need to be on-board i.e. agree that the war has sense f
Re: (Score:2)
It's a sad fact of life that this level of consumption is only possible through systematized large scale cruelty to animals with current technology.
I don't agree. In fact you could fix a lot of what's wrong without even spending more money to do it than it would have cost to do right in the first place. Modifications to slaughterhouses like having the cows go through a curved passage so they can't see what's happening to others in front of them for example. Obviously you can't fix feedlots without eliminating them, so some things are basically unsolvable, except that we don't actually need feedlots and could eliminate them.
Therefore I'd say the sad fac
Re: (Score:2)
Rome invented factory farming a long time ago. I don't think you're looking at a useful metric.
Re: Amazing if it works (Score:2)
I'm a perfect asshole, so I have a foot on both sides of the line.
Re: (Score:2)
Re: Amazing if it works (Score:1)
Obviously you've never watched a cat at play, and maybe eating.
Re: (Score:2)
There are about 8 billion of us that are not directly involved in war right now. While I think a zero tolerance policy for war is quite admirable, I don't think it is a useful pass/fail metric.
Re: (Score:1)
Re:Amazing if it works (Score:4, Interesting)
The transistors aren't actually smaller. It's standard in the field to market the next chip generation as a smaller size when they mean equivalent to the new size. In this case the transistors are stacked vertically so looking down you get layers X areal density of the 2 dimensional surface. We don't do this with flash stacks, which now have up to 321 layers and are mapped to 1000+.
lolol offtopic (Score:2)
Nobody is less familiar with history than Slashdotters, who think they're smarter than everybody.
This is why average people hate techbros.
Re: (Score:2)
Nobody is less familiar with history than Slashdotters
Have you been to Digg?
Re: (Score:2)
And I look at the environment and observe how we are heating ourselves to extinction along with most of the critters. Some plants may survive.
Using Z (Score:5, Informative)
The angstrom scale business is marketing fluff to make the density increase understandable to consumers. But this is one of the developments leveraging the Z dimension that are legitimate progress. The Z dimension gives more than just the same chip folded like origami. The net distance traveled by a signal in a cycle can be reduced, which yields massive improvement in performance without additional cost of power/heat.
Re: (Score:2)
Just like the nanometer business. Really, using a linear measurement to indicate density was not-what-you-think from the beginning, so toss micrometers in there too.
Consumers don't care. People contracting foundry services care.
Re: (Score:2)
Re: (Score:1)
Re: (Score:2)
Re: (Score:2)
The transistors aren't actually smaller. They fit more of them in the same 2 dimensional area by using layers. The layers are the Z dimension. The thermals are an interesting question.
Re:Using Z (Score:4, Interesting)
In the old times, nanometer scale measured the length of the gate in a MOSFET transistor.
When we switched away from MOSFET, it became a marketting term. 2nm node means: technology as efficient as a hypothetical 2nm MOSFET. There is nothing in there that is 2nm in size. The transistors are no longer getting smaller, instead they find ways to pack more of them together, such as routing the power from the bottom and building vertical structures (FINFET and GAA)
Basically we use nanometer/angstrom scale to describe chip technology in the same way that we use horse power to describe engines.
Re: (Score:2)
Endurance athletes can sustain about
Re: (Score:2)
Re: (Score:2)
Not completely true. Only a small portion of the power / heat comes from moving signals between transistors. The most significant amount comes from the transistor gate itself.
Z stacking creates a very real problem in that heat concentrates more in a small space as there are multiple heat sources overlapping. Not only do you have more power/heat (though proportionally lower than a 2D layout) but you also have a requirement to move heat away from the source faster as hotspots would be more severe.
We're alread
Chinese working on 3D chips also (Score:3)
Definitely a promising path. Extracting heat becomes a challenge in 3D silicon.
Re: (Score:3)
And it has always been thus.
Stacking is not new. Heat dispersion problems that kill it are not new. A chip when heat-dispersed with a heat sink apparatus has known characteristics, but non-linear things happen when you heat both sides without some kind of temperature control method; chips bend, and then strange things happen.
This is news to cook the stock price, and maybe this generation of "advance".
1 Angstroem (Score:2)
IBM argues NanoStack is less a single trick and more a transistor platform that can be extended through multiple generations: 7 angstrom (Ã...), 5 Ã..., 3 Ã..., and potentially down to 1 Ã... in its internal roadmap
How would that even work? Isn't single-Angatroem count basically the size of an atomic layer? What's there even left to make a circuit from?...
Re: (Score:3)
Re: (Score:1)
if the industry wants to decouple node labels from specific physical dimensions they should probably stop using specific physical dimensions as those labels.
this just makes you wonder if they're stupid or just think we are.
Re: (Score:2)
Keep in mind it's not and hasn't been a specific measure of something in particular in a while. It's a rough analogy for how a traditional process would have to make gate length to achieve the same density. So it's impossible to make a gate length that small, but by taking other measures it is supposed to be "just like getting them that small".
Re: (Score:2)
Nanometers have been about precision, not size. (Score:3)
- Why yes the nanometer ratings are like that bridge they have to sell you.
100 Billion? (Score:4, Funny)
Re: (Score:2)
Or maybe a congressman trying to win re-election.
Human brain (Score:2)
Reminder of what I read in a magazine some decades ago, that the human brain utilizes just 25 to 50 watts and uses electric and chemical impulses while immersed in conductive fluid. When playing chess, a grandmaster can evaluate at best about 6 moves per second while a computer evaluates millions .. yet the computer is only two or three times better than a human.
Re: (Score:2)
That must have been a while ago. Computers are effectively unbeatable at chess. One of the best programs was written by a Norwegian nerd in his spare time and then forked by an impatient Italian. It will run on your phone and will almost certainly kick your ass, although if you want to be sure of beating every human who's ever lived you might want to give it a desktop computer.
Re:Human brain (Score:4, Interesting)
Yeah but the computer is running millions of move simulations, but a grandmaster is doing 1 millionth of that computation and still playing well. If we restricted the computer to only do a few thousand evaluations per second it would fail miserably. Same thing with self-driving a car. A human can learn with 20 hours of driving school, meanwhile the FSD training models need tens of billions of miles driven in simulation and all kinds of scenarios reasoned through for it.
We're missing some fundamental thing(s) when it comes to computation. I have no idea what it is -- we only know that there's a way to do it but we don't know how. Somebody, or AI itself will figure it out soon (like within a century, maybe even a decade or two).
Re: (Score:2)
Re: (Score:2)
No, the grandmaster is doing many, many more calculations, just in parallel instead of serial. The human is also not blindly searching a tree of possible moves but spending a lot of computation on figuring out which are promising branches to prioritize. Modern chess programs are so good because they do the same thing.
No, they can't. We don't generally let humans even attempt driving for something like 16 years. They're also pretty shit at it until they have a
IBM has been making big promises (Score:4, Insightful)
It's a good way to keep the stock price elevated*.
But what has IBM actually delivered in any of these areas in recent years?
*like Sam Altman and AGI for instance
Maybe not so recently (Score:2)
Copper interconnect and silicon-on-insulator were both pioneered by IBM. They have had serious semiconductor R&D over the years.
Re:IBM has been making big promises (Score:5, Interesting)
But what has IBM actually delivered in any of these areas in recent years?
A great deal. IBM licenses, partners and consults with semiconductor manufacturers globally, and runs a thriving IP business from their huge R&D facility in Albany, NY. Samsung, Rapidus, AMD, ST, SMIC and others are all paying for IBM tech in recent deals. GlobalFoundries bought out IBM Microelectronics for IBM's 300mm tech. IBM is among the most prolific patent filers in the world.
The real story here is this: ASML has a new machine for a new process node. ASML is obligated to perform much of their R&D in the US due to strict export and technology sharing agreements with the US government. IBM operates huge, world class R&D lab in Albany, heavily subsidized by the state and US government. The new process that this story is about is really IBM working as an R&D partner with ASML to refine the process and get it ready for commercial operation.
In a few years, when they get the yields to something plausible, ASML customers will buy the new machines, and IBM will be in the room, taking their cut for IP, consulting, support etc.
Re: (Score:2)
Just little old me. This is a big deal. The density increase here is basically Moore's law surviving another decade, with all that that implies. The zdnet puff piece annoys me. ASML is only mentioned in passing. The truth is ASML is right at the heart of this: it's their machine. And that's not me blowing ASML's trumpet: the story is the deeper relationship going on here. The Albany site is basically the US government (successfully) using IBM as their domestic lab operator to facilitate US strategic
Re: (Score:2)
Further, it puts the lie to all the yap about the US "falling behind" and failing because "capitalism" and some mythical abhorrence for "public-private" partnership, etc. The US does all of that, and it does this at least as well as everyone else.
Long-term changes in funding of higher education and more recent changes in funding of basic scientific research are more concerning to me on this front.
Re: (Score:3)
ASML is obligated to perform much of their R&D in the US due to strict export and technology sharing agreements with the US government.
It is not really. ASML's R&D divisions are based on regional expertise. The majority is still done in Eindhoven. In California there's an R&D hub looking at advances in EUV light sources and in Connecticut they focus on mirror fabrication (pun... get it?) while the majority of ASML's current equipment has mirrors developed by Zeiss. They do R&D the world over based on localised expertise, and for some components that happens to be in the USA. ASML does significant R&D in China too with a lot
Re: (Score:3)
A lot of the stuff IBM works on ends up in their mainframes so as a consumer you'll likely never hear about it. https://www.redbooks.ibm.com/r... [ibm.com]
Re: (Score:2)
Re: (Score:2)
IBM invents the stuff that TSMC, Samsung, Intel, and the big fabless designers adopt. They are an important player in chip design, even if they don't own any fabs themselves. For instance they design their own mainframe chips.
You're right that their claims on quantum computing have fallen flat - in fact that entire industry is going nowhere IMO. Their "Blue Jay" 2000 qbit is now slated for >2034 ffs. In their own charts they were promising >10k qbits by this year. All those old promises seem to be gon
Which is it? (Score:2)
>IBM's VP of silicon technology R&D says the new innovation "can improve performance by 50% compared to the best available chip today, and at the same time can reduce power by 70%."
One of these things is not like the other.
Re: (Score:2)
Um, what? (Score:5, Interesting)
Re: (Score:1)
Re:Um, what? (Score:4, Informative)
It is in character for the tech giantâ"its research division produced the first prototype for a 2 nanometer node chip back in May 2021.
With that development, âoewe highlighted the research, and now all leading foundries are manufacturing theseâ
Just because they don't make it doesn't mean they can't license the patent to the foundries.
Re: (Score:2)
What IBM is referring to is the transistor design, from the sounds of it. That, and / or some sort of circuit layout that sounds like it eliminates the need for TSVs (through-silicon vias). Maybe they've invented a successor to FinFET, as well.
So IBM may not manufacture, but they still design chips for their POWER series, and they also conduct R&D. The R&D group is where this research may have been conducted - if IBM can invent a radical new technology, it can win by licensing. Licensing is the high
How many can IBM fit on a chip today? (Score:2)
Fitting so many is one thing... (Score:2)
making it work reliably and being able to manufacture with good yields is an entirely different set of problems
Re: (Score:1)
why the subterfuge (Score:2)
"IBM is explicit that "0.7 nm" and "7 angstrom" should be read as generational node names, not literal gate lengths or pitches, in line with the broader industry trend of decoupling node labels from specific physical dimensions. Internally, the company said it benchmarked NanoStack's critical dimensions—such as gate pitches and contacted gate pitch—against a projected 1 nmclass node, then pushed scaling by going vertical."
Someone needs to come up with a new nomenclature. What if ASML develops a
Check date (Score:2)
Transistors (Score:2)
Chip nerds, is "transistor" still a useful metric anyway? Aren't modern chips that much more advanced that splitting their compute into single transistors doesn't make sense?
Re: (Score:1)
DRAM memory is a bit different, only the high-speed cache(SRAM) is built from transistors. DRAM uses a capacitor to store a bit and is WAY WAY slower than SRAM which just keeps passing a bit back/forth between multiple transistors to store it.
Re: (Score:2)
So there is no more efficient "building block" than combining transistors? I get the appeal of simplicity, I just would have thought that one might be slightly faster with a more complex element than by combining several transistors for some operations.