Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > comp.os.linux.misc > #88473 > unrolled thread

IBM - New SUB-Nanometer STACKED Chip

Started byc186282 <c186282@nnada.net>
First post2026-06-28 00:36 -0400
Last post2026-06-29 01:34 -0400
Articles 12 on this page of 72 — 9 participants

Back to article view | Back to comp.os.linux.misc

Contents

  IBM - New SUB-Nanometer STACKED Chip c186282 <c186282@nnada.net> - 2026-06-28 00:36 -0400
    [HK01]IBM研發首款0.7nm晶片 指甲大小塞滿1000億電晶體 效能飆升50% "Mr. Man-wai Chang" <toylet.toylet@gmail.com> - 2026-06-29 00:01 +0800
    Re: IBM - New SUB-Nanometer STACKED Chip Charlie Gibbs <cgibbs@kltpzyxm.invalid> - 2026-06-28 18:09 +0000
      Re: IBM - New SUB-Nanometer STACKED Chip "Mr. Man-wai Chang" <toylet.toylet@gmail.com> - 2026-06-29 13:11 +0800
        Re: IBM - New SUB-Nanometer STACKED Chip c186282 <c186282@nnada.net> - 2026-06-29 01:39 -0400
          Re: IBM - New SUB-Nanometer STACKED Chip "Mr. Man-wai Chang" <toylet.toylet@gmail.com> - 2026-06-29 19:20 +0800
            Re: IBM - New SUB-Nanometer STACKED Chip The Natural Philosopher <tnp@invalid.invalid> - 2026-06-29 12:57 +0100
            Re: IBM - New SUB-Nanometer STACKED Chip c186282 <c186282@nnada.net> - 2026-06-30 05:14 -0400
              Re: IBM - New SUB-Nanometer STACKED Chip "Mr. Man-wai Chang" <toylet.toylet@gmail.com> - 2026-06-30 21:51 +0800
                Re: IBM - New SUB-Nanometer STACKED Chip c186282 <c186282@nnada.net> - 2026-06-30 12:06 -0400
                  Re: IBM - New SUB-Nanometer STACKED Chip Charlie Gibbs <cgibbs@kltpzyxm.invalid> - 2026-06-30 18:51 +0000
                    Re: IBM - New SUB-Nanometer STACKED Chip Paul <nospam@needed.invalid> - 2026-06-30 17:58 -0400
                      Re: IBM - New SUB-Nanometer STACKED Chip c186282 <c186282@nnada.net> - 2026-07-01 01:15 -0400
                        Re: IBM - New SUB-Nanometer STACKED Chip The Natural Philosopher <tnp@invalid.invalid> - 2026-07-01 10:15 +0100
                    Re: IBM - New SUB-Nanometer STACKED Chip rbowman <bowman@montana.com> - 2026-06-30 23:51 +0000
                      Re: IBM - New SUB-Nanometer STACKED Chip c186282 <c186282@nnada.net> - 2026-07-01 03:16 -0400
                        Re: IBM - New SUB-Nanometer STACKED Chip The Natural Philosopher <tnp@invalid.invalid> - 2026-07-01 10:05 +0100
                          Re: IBM - New SUB-Nanometer STACKED Chip rbowman <bowman@montana.com> - 2026-07-01 17:43 +0000
                            Re: IBM - New SUB-Nanometer STACKED Chip The Natural Philosopher <tnp@invalid.invalid> - 2026-07-01 20:23 +0100
                              Re: IBM - New SUB-Nanometer STACKED Chip rbowman <bowman@montana.com> - 2026-07-02 01:57 +0000
                                Re: IBM - New SUB-Nanometer STACKED Chip c186282 <c186282@nnada.net> - 2026-07-02 16:48 -0400
                                  Re: IBM - New SUB-Nanometer STACKED Chip rbowman <bowman@montana.com> - 2026-07-02 21:32 +0000
                                    Re: IBM - New SUB-Nanometer STACKED Chip c186282 <c186282@nnada.net> - 2026-07-02 18:15 -0400
                                  Re: IBM - New SUB-Nanometer STACKED Chip The Natural Philosopher <tnp@invalid.invalid> - 2026-07-03 11:03 +0100
                                    Re: IBM - New SUB-Nanometer STACKED Chip c186282 <c186282@nnada.net> - 2026-07-04 09:32 -0400
                                      Re: IBM - New SUB-Nanometer STACKED Chip Charlie Gibbs <cgibbs@kltpzyxm.invalid> - 2026-07-04 17:06 +0000
                                        Re: IBM - New SUB-Nanometer STACKED Chip "Carlos E. R." <robin_listas@es.invalid> - 2026-07-04 19:24 +0200
                                        Re: IBM - New SUB-Nanometer STACKED Chip rbowman <bowman@montana.com> - 2026-07-04 18:20 +0000
                                        Re: IBM - New SUB-Nanometer STACKED Chip c186282 <c186282@nnada.net> - 2026-07-04 23:37 -0400
                                      Re: IBM - New SUB-Nanometer STACKED Chip The Natural Philosopher <tnp@invalid.invalid> - 2026-07-04 19:20 +0100
                                        Re: IBM - New SUB-Nanometer STACKED Chip Rich <rich@example.invalid> - 2026-07-04 20:28 +0000
                                          Re: IBM - New SUB-Nanometer STACKED Chip rbowman <bowman@montana.com> - 2026-07-04 20:47 +0000
                                          Re: IBM - New SUB-Nanometer STACKED Chip Nuno Silva <nunojsilva@invalid.invalid> - 2026-07-05 00:33 +0100
                                        Re: IBM - New SUB-Nanometer STACKED Chip rbowman <bowman@montana.com> - 2026-07-04 20:42 +0000
                                          Re: IBM - New SUB-Nanometer STACKED Chip c186282 <c186282@nnada.net> - 2026-07-04 23:51 -0400
                                            Re: IBM - New SUB-Nanometer STACKED Chip rbowman <bowman@montana.com> - 2026-07-05 06:57 +0000
                                            Re: IBM - New SUB-Nanometer STACKED Chip "Carlos E. R." <robin_listas@es.invalid> - 2026-07-05 13:38 +0200
                                        Re: IBM - New SUB-Nanometer STACKED Chip c186282 <c186282@nnada.net> - 2026-07-04 23:45 -0400
                                          Re: IBM - New SUB-Nanometer STACKED Chip The Natural Philosopher <tnp@invalid.invalid> - 2026-07-05 10:49 +0100
                                            Re: IBM - New SUB-Nanometer STACKED Chip c186282 <c186282@nnada.net> - 2026-07-06 00:33 -0400
                                              Re: IBM - New SUB-Nanometer STACKED Chip "Carlos E. R." <robin_listas@es.invalid> - 2026-07-06 13:19 +0200
                                                Re: IBM - New SUB-Nanometer STACKED Chip The Natural Philosopher <tnp@invalid.invalid> - 2026-07-06 12:39 +0100
                                              Re: IBM - New SUB-Nanometer STACKED Chip The Natural Philosopher <tnp@invalid.invalid> - 2026-07-06 12:32 +0100
                    Re: IBM - New SUB-Nanometer STACKED Chip c186282 <c186282@nnada.net> - 2026-07-01 00:48 -0400
                  Re: IBM - New SUB-Nanometer STACKED Chip rbowman <bowman@montana.com> - 2026-06-30 23:45 +0000
                    Re: IBM - New SUB-Nanometer.... physics? "quantum"? "Mr. Man-wai Chang" <toylet.toylet@gmail.com> - 2026-07-01 12:24 +0800
                    Re: IBM - New SUB-Nanometer STACKED Chip c186282 <c186282@nnada.net> - 2026-07-01 03:13 -0400
                      Re: IBM - New SUB .... quantum mechanics is quantitative philiosphy? "Mr. Man-wai Chang" <toylet.toylet@gmail.com> - 2026-07-01 15:29 +0800
                        Re: IBM - New SUB .... quantum mechanics is quantitative philiosphy? c186282 <c186282@nnada.net> - 2026-07-01 04:22 -0400
                          Re: IBM - New SUB .... quantum mechanics is quantitative philiosphy? "Mr. Man-wai Chang" <toylet.toylet@gmail.com> - 2026-07-01 23:41 +0800
                            Re: IBM - New SUB .... quantum mechanics is quantitative philiosphy? c186282 <c186282@nnada.net> - 2026-07-02 01:56 -0400
                              Re: IBM - New SUB .... quantum mechanics is FLAT? "Mr. Man-wai Chang" <toylet.toylet@gmail.com> - 2026-07-02 14:04 +0800
                                Re: IBM - New SUB .... quantum mechanics is FLAT? c186282 <c186282@nnada.net> - 2026-07-02 16:50 -0400
                                  Re: IBM - New SUB .... quantum mechanics is FLAT? rbowman <bowman@montana.com> - 2026-07-02 21:26 +0000
                                    Re: IBM - New SUB .... quantum mechanics is FLAT? c186282 <c186282@nnada.net> - 2026-07-02 18:11 -0400
                  Re: IBM - New SUB-Nanometer STACKED Chip Paul <nospam@needed.invalid> - 2026-06-30 22:09 -0400
                    Re: IBM - New SUB-Nanometer STACKED Chip c186282 <c186282@nnada.net> - 2026-07-01 03:29 -0400
                      Re: IBM - New SUB-Nanometer STACKED Chip The Natural Philosopher <tnp@invalid.invalid> - 2026-07-01 10:11 +0100
                    Re: IBM - New SUB-Nanometer STACKED Chip The Natural Philosopher <tnp@invalid.invalid> - 2026-07-01 10:08 +0100
              Re: IBM - New SUB-Nanometer STACKED Chip The Natural Philosopher <tnp@invalid.invalid> - 2026-06-30 16:27 +0100
                Re: IBM - New SUB-Nanometer STACKED Chip c186282 <c186282@nnada.net> - 2026-06-30 12:18 -0400
                  Re: IBM - New SUB-Nanometer STACKED Chip The Natural Philosopher <tnp@invalid.invalid> - 2026-06-30 17:32 +0100
                    Re: IBM - New SUB-Nanometer STACKED Chip rbowman <bowman@montana.com> - 2026-06-30 23:40 +0000
                      Re: IBM - New SUB-Nanometer STACKED Chip c186282 <c186282@nnada.net> - 2026-07-01 02:53 -0400
                      Re: IBM - New SUB-Nanometer STACKED Chip The Natural Philosopher <tnp@invalid.invalid> - 2026-07-01 10:01 +0100
                    Re: IBM - New SUB-Nanometer STACKED Chip c186282 <c186282@nnada.net> - 2026-07-01 00:17 -0400
                  Re: IBM - New SUB-Nanometer STACKED Chip rbowman <bowman@montana.com> - 2026-06-30 23:37 +0000
                    Re: IBM - New SUB-Nanometer STACKED Chip c186282 <c186282@nnada.net> - 2026-07-01 02:33 -0400
                Re: IBM - New SUB-Nanometer STACKED Chip rbowman <bowman@montana.com> - 2026-06-30 23:28 +0000
                  Re: IBM - New SUB-Nanometer STACKED Chip c186282 <c186282@nnada.net> - 2026-07-01 02:04 -0400
                    Re: IBM - New SUB-Nanometer STACKED Chip Paul <nospam@needed.invalid> - 2026-07-01 04:33 -0400
      Re: IBM - New SUB-Nanometer STACKED Chip c186282 <c186282@nnada.net> - 2026-06-29 01:34 -0400

Page 4 of 4 — ← Prev page 1 2 3 [4]

#88538

Fromc186282 <c186282@nnada.net>
Date2026-06-30 12:18 -0400
Message-ID<Db2cnc0287_ocd73nZ2dnZfqnPadnZ2d@giganews.com>
In reply to#88536
On 6/30/26 11:27, The Natural Philosopher wrote:
> On 30/06/2026 10:14, c186282 wrote:
>> On 6/29/26 07:20, Mr. Man-wai Chang wrote:
>>> On 6/29/2026 1:39 PM, c186282 wrote:
>>>>
>>>>     Amazed they were able to get this small - but do
>>>>     expect a wall/seal is pretty much here. We're
>>>>     talking kinda atomic dimensions now - nowhere else
>>>>     to go using any conventional approaches. Anything
>>>>     much further won't be 'electronics' as we know it,
>>>>     some kind of weird quantum stuff.
>>>>
>>>>     STABLE deca-state logic maybe ?
>>>
>>> Can you fabricate 0.000000...0000000001 nm chips?
>>>
>>> Is zero the seal or wall? :)
>>
>>    Um, pretty quick you get to ATOMS ... and, for any
>>    normal electronics, that's IT.
>>
> Actually the limit is a fair bit above atoms

   True ... but 'atoms' can be easily grasped as
   an absolute limit for any conventional electronics.

> GOOGLE AI
> =========
> "Transistor nodes have shrunk dramatically, with leading developers like 
> IBM advancing into the sub-1 nanometre realm (e.g., 0.7-nanometer tech). 
> However, absolute limits are rapidly approaching due to several factors:
> 
>      Quantum Tunnelling: At sizes measuring just a few atoms across, 
> electrons no longer stay neatly in their channels. They start randomly 
> leaking or tunnelling through insulation barriers, resulting in massive 
> power loss and data corruption.
> 
>      Atomic Boundary: The absolute physical limit for a silicon 
> semiconductor is effectively constrained by the size of the silicon 
> crystal unit cell (about 0.54 nm).
> 
>       Heat Density: Shrinking transistors allows more components to be 
> packed together, but it creates extreme heat concentrations. The 
> challenge shifts from building them to keeping them cool without burning 
> out£

   Yep ... shrink too much and yer electrons start
   disappearing and showing up in weird places.

   IBM may have just built the Final Chip, so
   to speak. Better stuff will have to use very
   different technologies.

> .....
> 
> I note that google can't spall 'nanometre' OR 'tunnelling; correctly

   Lots of words I have problems with as well - and I was
   always good at spelling.

   'nanometre' ... sounds almost like a Euro spelling, kind
   of like the Brits use 'colour'  :-)

[toc] | [prev] | [next] | [standalone]

#88539

FromThe Natural Philosopher <tnp@invalid.invalid>
Date2026-06-30 17:32 +0100
Message-ID<1120r3e$171rr$1@dont-email.me>
In reply to#88538
On 30/06/2026 17:18, c186282 wrote:
> 'nanometre' ... sounds almost like a Euro spelling, kind
>    of like the Brits use 'colour'  🙂

A meter has a dial and is used to measure things. Metres are units of 
distance measurement.


-- 
Future generations will wonder in bemused amazement that the early 
twenty-first century’s developed world went into hysterical panic over a 
globally average temperature increase of a few tenths of a degree, and, 
on the basis of gross exaggerations of highly uncertain computer 
projections combined into implausible chains of inference, proceeded to 
contemplate a rollback of the industrial age.

Richard Lindzen

[toc] | [prev] | [next] | [standalone]

#88550

Fromrbowman <bowman@montana.com>
Date2026-06-30 23:40 +0000
Message-ID<naj2g6Fgpa7U2@mid.individual.net>
In reply to#88539
On Tue, 30 Jun 2026 17:32:46 +0100, The Natural Philosopher wrote:

> On 30/06/2026 17:18, c186282 wrote:
>> 'nanometre' ... sounds almost like a Euro spelling, kind
>>    of like the Brits use 'colour'  🙂
> 
> A meter has a dial and is used to measure things. Metres are units of
> distance measurement.

In a few days the US will celebrate the 250th anniversary of telling the 
Brits to piss off. That includes their quaint Eurotrash spelling.

I doubt there will be a 300th anniversary.

[toc] | [prev] | [next] | [standalone]

#88564

Fromc186282 <c186282@nnada.net>
Date2026-07-01 02:53 -0400
Message-ID<RdadnTh6Wu31JNn3nZ2dnZfqnPednZ2d@giganews.com>
In reply to#88550
On 6/30/26 19:40, rbowman wrote:
> On Tue, 30 Jun 2026 17:32:46 +0100, The Natural Philosopher wrote:
> 
>> On 30/06/2026 17:18, c186282 wrote:
>>> 'nanometre' ... sounds almost like a Euro spelling, kind
>>>     of like the Brits use 'colour'  🙂
>>
>> A meter has a dial and is used to measure things. Metres are units of
>> distance measurement.
> 
> In a few days the US will celebrate the 250th anniversary of telling the
> Brits to piss off. That includes their quaint Eurotrash spelling.
> 
> I doubt there will be a 300th anniversary.

   Well, there WILL be - technically.

   Whether it will be anything LIKE the
   originally envisioned/realized USA
   is another question. MANY are keen
   on the Pol Pot Challenge ...

   We DID see a lot of this in the 1960s,
   exact same neo-Marxist slogans/rhetoric,
   but there WAS that "silent majority" of
   moderate Regular Joes/Janes then. No more.

   Insanity rules now. The most absurd rhetoric
   is widely believed as True.

   NOT good !

   Hmmmm ... one New York candidate, media darling,
   wants to eliminate ALL cops/courts/jails etc.
   The Crowd just LOVES her !

   In "A Clockwork Orange" the govt could not control
   the thugs. So, it HIRED them to be the new police
   and such. Very very bad - and it seems like what
   is being pushed NOW. Gangster Rule.

   The thugs are viewed as the new Red Guard - the
   brutal enforcers. The 'elite' decide, the thugs
   CRUSH all opponents.

   The NAZIs did this, as did Stalin and Mao and
   Pol Pot. Empower the evil nobodies and they
   WILL be your most loyal and fanatical adherents.
   Body-count unlimited.

   Did equal/fair/ethical/democratic disappear THIS
   fuckin' fast ? Maybe so. Back to overlords and
   conquerors and fanatics .........

   I'm too old to live in some mountain bunker
   anymore - and TOO much of the world has gone
   more or less commie. Alas both Russia and
   China have DUMPED 'communism' - didn't work
   fer shit.

   So what, Namibia ? Do they have 'golden visas' ?
   FAR off-grid though ... nobody anywhere gives
   a shit ......

[toc] | [prev] | [next] | [standalone]

#88573

FromThe Natural Philosopher <tnp@invalid.invalid>
Date2026-07-01 10:01 +0100
Message-ID<1122l0u$1o867$2@dont-email.me>
In reply to#88550
On 01/07/2026 00:40, rbowman wrote:
> On Tue, 30 Jun 2026 17:32:46 +0100, The Natural Philosopher wrote:
> 
>> On 30/06/2026 17:18, c186282 wrote:
>>> 'nanometre' ... sounds almost like a Euro spelling, kind
>>>     of like the Brits use 'colour'  🙂
>>
>> A meter has a dial and is used to measure things. Metres are units of
>> distance measurement.
> 
> In a few days the US will celebrate the 250th anniversary of telling the
> Brits to piss off. That includes their quaint Eurotrash spelling.
> 
> I doubt there will be a 300th anniversary.

Agreed. Post Trump, there will be no USA

-- 
"The most difficult subjects can be explained to the most slow witted 
man if he has not formed any idea of them already; but the simplest 
thing cannot be made clear to the most intelligent man if he is firmly 
persuaded that he knows already, without a shadow of doubt, what is laid 
before him."

    - Leo Tolstoy

[toc] | [prev] | [next] | [standalone]

#88556

Fromc186282 <c186282@nnada.net>
Date2026-07-01 00:17 -0400
Message-ID<RdadnT16Wu05Cdn3nZ2dnZfqnPednZ2d@giganews.com>
In reply to#88539
On 6/30/26 12:32, The Natural Philosopher wrote:
> On 30/06/2026 17:18, c186282 wrote:
>> 'nanometre' ... sounds almost like a Euro spelling, kind
>>    of like the Brits use 'colour'  🙂
> 
> A meter has a dial and is used to measure things. Metres are units of 
> distance measurement.

   Yea yea ... but you're no fun  :-)

[toc] | [prev] | [next] | [standalone]

#88549

Fromrbowman <bowman@montana.com>
Date2026-06-30 23:37 +0000
Message-ID<naj2ajFgpa7U1@mid.individual.net>
In reply to#88538
On Tue, 30 Jun 2026 12:18:47 -0400, c186282 wrote:

>    IBM may have just built the Final Chip, so to speak. Better stuff
>    will have to use very different technologies.

IBM hasn't really built anything in a while.

https://en.wikipedia.org/wiki/IBM_Microelectronics

A friend spent his entire career at Essex Junction and timed his 
retirement just right. He had interned at Fishkill when we were in 
college, got his PhD, and segued into a full time IBM employee. That's 
relatively unique in the tech industry.

Interestingly the last time I visited him before I moved out of the area 
he had bought a PCjr and wasn't quite sure what to do with it.

[toc] | [prev] | [next] | [standalone]

#88563

Fromc186282 <c186282@nnada.net>
Date2026-07-01 02:33 -0400
Message-ID<RdadnTl6Wu0qKdn3nZ2dnZfqnPednZ2d@giganews.com>
In reply to#88549
On 6/30/26 19:37, rbowman wrote:
> On Tue, 30 Jun 2026 12:18:47 -0400, c186282 wrote:
> 
>>     IBM may have just built the Final Chip, so to speak. Better stuff
>>     will have to use very different technologies.
> 
> IBM hasn't really built anything in a while.
> 
> https://en.wikipedia.org/wiki/IBM_Microelectronics

   They're BEHIND it ... same thing, same $$$

> A friend spent his entire career at Essex Junction and timed his
> retirement just right. He had interned at Fishkill when we were in
> college, got his PhD, and segued into a full time IBM employee. That's
> relatively unique in the tech industry.

   "Dilbert" was based on IBM corporate culture/thinking.

   Yes, sometimes absurd/insane ... but it HAS worked long term.

   Maybe sometimes you NEED some insanity.

   Not selling my stock.

> Interestingly the last time I visited him before I moved out of the area
> he had bought a PCjr and wasn't quite sure what to do with it.

   PC-Jr wasn't a great computer - but would still
   get most everything you needed DONE. More or less
   affordable too.

   IBM was never really geared for Joe Consumer - for
   'biz' and above levels instead. They could not compete
   with Compaq and friends and still make a buck, so they
   just dumped that. Their old ThinkPads were pretty good,
   but once they outsourced them, well, NOT so great.

   For USERS, more than x-amount of home computer power
   is usually just WASTED - advertising hype. I do have
   one fairly strong desktop box - set it up (Linux) and
   parked it in the junk room, never used since. My
   cheapo laptops and mini-boxes are powerful enough
   for anything *I* need now.

   Had to re-install my MX security/streaming box. The
   last install (MX) didn't go quite right and the main
   desktop would HINT, but never actually GET there.
   Burned a lot of CPU doing "nothing" too - box got
   very hot.

   DID save most of the valuable apps/configs though so
   it was fairly easy this time after re-install.

   Good install now, and have CHEATED - used the MX
   "snapshot" utility to create a custom ISO with all
   my goodies on it. IF it craps again I can go right
   back to a fully working install. Taped the thumb
   drive TO the unit so it won't get lost.

[toc] | [prev] | [next] | [standalone]

#88548

Fromrbowman <bowman@montana.com>
Date2026-06-30 23:28 +0000
Message-ID<naj1o0FgbvpU1@mid.individual.net>
In reply to#88536
On Tue, 30 Jun 2026 16:27:24 +0100, The Natural Philosopher wrote:

> "Transistor nodes have shrunk dramatically, with leading developers like
> IBM advancing into the sub-1 nanometre realm (e.g., 0.7-nanometer tech).
> However, absolute limits are rapidly approaching due to several factors:

iirc terms like '5 nm process' no longer refer to any physical dimension 
so I'm curious what the actual gate size is on 0.7 nm tech. 

IBM sold their fab lines to GlobalFoundries and their '7 nm' tech was 
closer to Intel's 10 nm.

[toc] | [prev] | [next] | [standalone]

#88562

Fromc186282 <c186282@nnada.net>
Date2026-07-01 02:04 -0400
Message-ID<RdadnT56Wu1HMNn3nZ2dnZfqnPednZ2d@giganews.com>
In reply to#88548
On 6/30/26 19:28, rbowman wrote:
> On Tue, 30 Jun 2026 16:27:24 +0100, The Natural Philosopher wrote:
> 
>> "Transistor nodes have shrunk dramatically, with leading developers like
>> IBM advancing into the sub-1 nanometre realm (e.g., 0.7-nanometer tech).
>> However, absolute limits are rapidly approaching due to several factors:
> 
> iirc terms like '5 nm process' no longer refer to any physical dimension
> so I'm curious what the actual gate size is on 0.7 nm tech.
> 
> IBM sold their fab lines to GlobalFoundries and their '7 nm' tech was
> closer to Intel's 10 nm.

   Well, SEEMS like they've done the 1, or <1, nm
   stacked chip.

   They'll license that. Old company, but still kinda
   out-front in their tech AND biz sense. NOT gonna
   dump my stock.

   Alas, as mentioned here, this IS about as far as
   conventional electronics can go. Under 1nm the
   quantum issues fuck up everything.

   SO - we need entirely new tech paradigms now.
   For 'electronics' we HAVE crashed into Dr. Moore.

   Meanwhile, the stacked chips DO allow us to do
   more, if not faster, in the same chip profiles.
   There's money in that - for now.

   Five years ... as said, we need Something Completely
   Different. Maybe I'll be dead by then and won't care,
   maybe not, but "transistors" aren't gonna go any
   faster even as "AI" and a lot more DEMAND that.

   Still wonder if "deca-state" logic, where the
   intermediate values are stable and DON'T eat up
   power, can be done. Some 'latching', 'layered',
   design maybe. A few more layers per transistor.
   I have this vague vision in my head ... quantified
   analog, so to speak. One transistor, 2^10th
   possible values.

[toc] | [prev] | [next] | [standalone]

#88572

FromPaul <nospam@needed.invalid>
Date2026-07-01 04:33 -0400
Message-ID<1122jcb$1ns5s$1@dont-email.me>
In reply to#88562
On Wed, 7/1/2026 2:04 AM, c186282 wrote:
> On 6/30/26 19:28, rbowman wrote:
>> On Tue, 30 Jun 2026 16:27:24 +0100, The Natural Philosopher wrote:
>>
>>> "Transistor nodes have shrunk dramatically, with leading developers like
>>> IBM advancing into the sub-1 nanometre realm (e.g., 0.7-nanometer tech).
>>> However, absolute limits are rapidly approaching due to several factors:
>>
>> iirc terms like '5 nm process' no longer refer to any physical dimension
>> so I'm curious what the actual gate size is on 0.7 nm tech.
>>
>> IBM sold their fab lines to GlobalFoundries and their '7 nm' tech was
>> closer to Intel's 10 nm.
> 
>   Well, SEEMS like they've done the 1, or <1, nm
>   stacked chip.

You will need to see the dimensions of the whole thing,
to see which "chance" dimension is 1nm.

  https://newsroom.ibm.com/2026-06-25-ibm-debuts-worlds-first-sub-1-nanometer-chip-technology

     https://filecache.mediaroom.com/mr5mr_ibmnewsroom/201436/IBM-Research_TEM_4.jpg

The diagram here, is too hard to read. The FINFET is on the left. The Gate All Around
device in the center. The stacked P channel and N channel on the right.

  https://www.eetimes.com/ibm-shows-sub-1-nm-chips-targeting-production-in-5-years/

They talk here, of two wafers being bonded vertically. Which might
be how the scheme maintains a semblance of manufacturability. Imagine
an 18" (450mm" wafer, aligned at the atomic level.

  https://www.servethehome.com/ibm-outlines-sub-1nm-nanostack-transistor-technology/

    Paul

[toc] | [prev] | [next] | [standalone]

#88501

Fromc186282 <c186282@nnada.net>
Date2026-06-29 01:34 -0400
Message-ID<VaKcnSZYBtQtnt_3nZ2dnZfqnPudnZ2d@giganews.com>
In reply to#88494
On 6/28/26 14:09, Charlie Gibbs wrote:
> On 2026-06-28, c186282 <c186282@nnada.net> wrote:
> 
>> https://www.techspot.com/news/112907-ibm-unveils-sub-1-nanometer-chip-architecture-stacks.html
>>
>> IBM unveils sub-1-nanometer chip architecture that stacks 100
>> billion transistors onto a fingernail-sized processor
>>
>> . . .
>>
>>     Pretty impressive ... and stacking two (three?) layers
>>     really packs a lot in.
>>
>>     NOT sure how they deal with the HEAT in the stacked
>>     design.
>>
>>     100 billion ... how many in the i4004 ?
> 
> Dunno - but I do remember that manufacturers hit a wall for
> a while when trying to get below 1 micrometer.  It took some
> time before memory chips larger than 64K became available.


   Found it in WikiPedia ... 2300 transistors !

   And yea, I remember how long it took them to
   significantly shrink things.

   "Stacked" chips have long been of interest to
   save real estate and signal path, but again not
   revealed how IBM has managed to cope with the
   heat dissipation issues.

   The sub-nanometer bit ... that IS a significant step.

   BUT, the smaller you make things, the more likely
   natural radiation and even quantum effects will
   sneakily change bits.

   We've pushed Moore further than I thought he could
   be, but ...

[toc] | [prev] | [standalone]

Page 4 of 4 — ← Prev page 1 2 3 [4]

Back to top | Article view | comp.os.linux.misc

csiph-web