Stories
Slash Boxes
Comments

SoylentNews is people

SoylentNews is powered by your submissions, so send in your scoop. Only 18 submissions in the queue.
posted by janrinok on Monday June 20, @12:41PM   Printer-friendly [Skip to comment(s)]
from the always-shrinking dept.

TSMC Reveals 2nm Node: 30% More Performance by 2025:

Taiwan Semiconductor Manufacturing Co. today officially introduced its N2 (2nm class) manufacturing technology, its first node that will use gate-all-around field-effect transistors (GAAFETs), at its 2022 TSMC Technology Symposium. The new fabrication process will offer a [full node's] performance and power benefits, but when it comes to transistor density, it will barely impress in 2025 when it comes online.

Being an all-new process technology platform, TSMC's N2 brings in two essential innovations: nanosheet transistors (which is what TSMC calls its GAAFETs) and backside power rail that both serve the same goal of increasing performance-per-watt characteristics of the node. GAA nanosheet transistors feature channels surrounded by gates on all four sides, which reduces leakage; furthermore, their channels can be widened to increase drive current and boost performance or shrunken to minimize power consumption and cost. To feed these nanosheet transistors with enough power and now waste any of it, TSMC's N2 uses backside power delivery, which the foundry considers to be among the best solutions to fight resistances in the back-end-of-line (BEOL).

Indeed, when it comes to performance and power consumption, TSMC's nanosheet-based N2 node can boast of a 10% to 15% higher performance at the same power and complexity as well as a 25% to 30% lower power consumption at the same frequency and transistor count when compared to TSMC's N3E. However, the new node increases chip density by only around 1.1X compared to N3E.

  N2 vs N3E N3E vs N5 N3 vs N5 N5 vs N7
Speed Improvement @ Same Power 10% ~ 15% +18% +10% ~ 15% +15%
Power Reduction @ Same Speed -23% ~ -30% -34% -25% ~ -30% -30%
Chip Density >1.1X1.3X??
HVM StartH2 2025Q2/Q3 2023H2 2022Q2 2022

I'll wait until takyon does a review - he has a knack of sorting out useful figures from manufacturer's hype.


Original Submission

Display Options Threshold/Breakthrough Reply to Article Mark All as Read Mark All as Unread
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
(1)
  • (Score: 2) by maxwell demon on Monday June 20, @12:45PM (4 children)

    by maxwell demon (1608) on Monday June 20, @12:45PM (#1254589) Journal

    The new fabrication process will offer a full-now performance

    What is a full-now performance?

    --
    The Tao of math: The numbers you can count are not the real numbers.
  • (Score: 5, Informative) by takyon on Monday June 20, @01:03PM

    They combined three multipliers into one weighted chip density multiplier:

    https://www.anandtech.com/show/17453/tsmc-unveils-n2-nanosheets-bring-significant-benefits [anandtech.com]

    *Chip density published by TSMC reflects 'mixed' chip density consisting of 50% logic, 30% SRAM, and 20% analog.

    And they also put a more-than sign in front of it, the trick AMD recently used when describing the single-threaded uplift of Zen 4.

    SRAM and analog are already known to scale worse than logic transistors. N3 vs N5 in the table has been said to be 1.7x density (0.58x area) for logic:

    https://www.anandtech.com/show/16024/tsmc-details-3nm-process-technology-details-full-node-scaling-for-2h22 [anandtech.com]

    Compared to its N5 node, N3 promises to improve performance by 10-15% at the same power levels, or reduce power by 25-30% at the same transistor speeds. Furthermore, TSMC promises a logic area density improvement of 1.7x, meaning that we’ll see a 0.58x scaling factor between N5 and N3 logic. This aggressive shrink doesn’t directly translate to all structures, as SRAM density is disclosed at only getting a 20% improvement which would mean a 0.8x scaling factor, and analog structures scaling even worse at 1.1x the density.

    Modern chip designs are very SRAM-heavy with a rule-of-thumb ratio of 70/30 SRAM to logic ratio, so on a chip level the expected die shrink would only be ~26% or less.

    By including N3E vs N5 in the table and showing us all this confusing information, you could conclude that TSMC is trying to keep things under wraps until later, but is giving a subtle indicator that the density increase will not be as good as we've come to expect. This could be because they are focusing on making sure gate-all-around (GAAFETs) work right the first time around, without being overly ambitious. You will still get decent efficiency and performance gains with the node shrink, although cost per transistor could be out of control.

    --
    [SIG] 10/28/2017: Soylent Upgrade v14 [soylentnews.org]
  • (Score: 1, Touché) by Anonymous Coward on Monday June 20, @08:23PM

    by Anonymous Coward on Monday June 20, @08:23PM (#1254729)

    I'll wait until takyon does a review - he has a knack of sorting out useful figures from manufacturer's hype.

    When there are comments like this, are they from the submitter, or the editor? I presume it is not takyon, but attribution is an important thing.

    aristarchus

  • (Score: -1, Spam) by Anonymous Coward on Tuesday June 21, @06:28PM

    by Anonymous Coward on Tuesday June 21, @06:28PM (#1254979)

    Guess what Dalek? YOU LOSE, hosts work vs. Symbiote C2 server(s) per this line from a MUCH better article than the one used here from bradley13 per "configuration in the binary that used the git[.]bancodobrasil[.]dev domain as its C2 server" from https://www.intezer.com/blog/research/new-linux-threat-symbiote/ [intezer.com] (INTEZER's now owned by Microsoft iirc as well).

    & did I block that in my original posts here https://soylentnews.org/comments.pl?noupdate=1&sid=49835&page=1&cid=1253504#commentwrap [soylentnews.org] on this BOGUS sockpuppet upmodding yourselves shithole website (which also noted FIREWALLS are invaluable here too, per wildcards (or even IP address use, URL domain/subdomain too in many as well)?

    YES I DID! I was correct...

    & YES, hosts work vs. this threat too stupid!

    FACT: hosts files block symbiote C2 servers which is all you really need to do to nullify their communication.

    FACT: Exfiltration isn't possible without orders either.

    FACT: Orders come from C2 servers!

    So YOU LOSE chump... a BETTER ARTICLE than what I used proves it for me!

    * THANKS FOR LOSING TO ME yet again, as always for you... try me again? THIS COMES UP AS PROOF (as well as another I have on YOU regarding using sources where YOU contradict yourself - want quotes of that too? ASK!)

    HOW ESPECIALLY EMBARASSING FOR YOU with your NO-DOUBT self-upmodded by sockpuppet accounts of YOURSELF too - now that YOU have EGG ON YOUR FACE fucko!

    APK

    P.S.=> Do yourself a FAVOR - don't ever, EVER try me ever again OR I WILL MAKE SURE YOU SHIT ON YOURSELF yet again as always, easlly... apk

  • (Score: -1, Spam) by Anonymous Coward on Tuesday June 21, @07:04PM

    by Anonymous Coward on Tuesday June 21, @07:04PM (#1255003)

    Guess what Dalek? YOU LOSE, hosts work vs. Symbiote C2 server(s) per this line from a MUCH better article than the one used here from bradley13 per "configuration in the binary that used the git[.]bancodobrasil[.]dev domain as its C2 server" from https://www.intezer.com/blog/research/new-linux-threat-symbiote/ [intezer.com] (INTEZER's now owned by Microsoft iirc as well).

    & did I block that in my original posts here https://soylentnews.org/comments.pl?noupdate=1&sid=49835&page=1&cid=1253504#commentwrap [soylentnews.org] on this BOGUS sockpuppet upmodding yourselves shithole website (which also noted FIREWALLS are invaluable here too, per wildcards (or even IP address use, URL domain/subdomain too in many as well)?

    YES I DID! I was correct...

    & YES, hosts work vs. this threat too stupid!

    FACT: hosts files block symbiote C2 servers which is all you really need to do to nullify their communication.

    FACT: Exfiltration isn't possible without orders either.

    FACT: Orders come from C2 servers!

    So YOU LOSE chump... a BETTER ARTICLE than what I used proves it for me!

    * THANKS FOR LOSING TO ME yet again, as always for you... try me again? THIS COMES UP AS PROOF (as well as another I have on YOU regarding using sources where YOU contradict yourself - want quotes of that too? ASK!)

    HOW ESPECIALLY EMBARASSING FOR YOU with your NO-DOUBT self-upmodded by sockpuppet accounts of YOURSELF too - now that YOU have EGG ON YOUR FACE fucko!

    APK

    P.S.=> Do yourself a FAVOR - don't ever, EVER try me ever again OR I WILL MAKE SURE YOU SHIT ON YOURSELF yet again as always, easlly... apk

  • (Score: -1, Spam) by Anonymous Coward on Tuesday June 21, @08:24PM

    by Anonymous Coward on Tuesday June 21, @08:24PM (#1255039)

    Guess what Dalek? YOU LOSE, hosts work vs. Symbiote C2 server(s) per this line from a MUCH better article than the one used here from bradley13 per "configuration in the binary that used the git[.]bancodobrasil[.]dev domain as its C2 server" from https://www.intezer.com/blog/research/new-linux-threat-symbiote/ [intezer.com] (INTEZER's now owned by Microsoft iirc as well).

    & did I block that in my original posts here https://soylentnews.org/comments.pl?noupdate=1&sid=49835&page=1&cid=1253504#commentwrap [soylentnews.org] on this BOGUS sockpuppet upmodding yourselves shithole website (which also noted FIREWALLS are invaluable here too, per wildcards (or even IP address use, URL domain/subdomain too in many as well)?

    YES I DID! I was correct...

    & YES, hosts work vs. this threat too stupid!

    FACT: hosts files block symbiote C2 servers which is all you really need to do to nullify their communication.

    FACT: Exfiltration isn't possible without orders either.

    FACT: Orders come from C2 servers!

    So YOU LOSE chump... a BETTER ARTICLE than what I used proves it for me!

    * THANKS FOR LOSING TO ME yet again, as always for you... try me again? THIS COMES UP AS PROOF (as well as another I have on YOU regarding using sources where YOU contradict yourself - want quotes of that too? ASK!)

    HOW ESPECIALLY EMBARASSING FOR YOU with your NO-DOUBT self-upmodded by sockpuppet accounts of YOURSELF too - now that YOU have EGG ON YOUR FACE fucko!

    APK

    P.S.=> Do yourself a FAVOR - don't ever, EVER try me ever again OR I WILL MAKE SURE YOU SHIT ON YOURSELF yet again as always, easlly... apk

  • (Score: -1, Spam) by Anonymous Coward on Tuesday June 21, @09:21PM

    by Anonymous Coward on Tuesday June 21, @09:21PM (#1255069)

    Guess what Dalek? YOU LOSE, hosts work vs. Symbiote C2 server(s) per this line from a MUCH better article than the one used here from bradley13 per "configuration in the binary that used the git[.]bancodobrasil[.]dev domain as its C2 server" from https://www.intezer.com/blog/research/new-linux-threat-symbiote/ [intezer.com] (INTEZER's now owned by Microsoft iirc as well).

    & did I block that in my original posts here https://soylentnews.org/comments.pl?noupdate=1&sid=49835&page=1&cid=1253504#commentwrap [soylentnews.org] on this BOGUS sockpuppet upmodding yourselves shithole website (which also noted FIREWALLS are invaluable here too, per wildcards (or even IP address use, URL domain/subdomain too in many as well)?

    YES I DID! I was correct...

    & YES, hosts work vs. this threat too stupid!

    FACT: hosts files block symbiote C2 servers which is all you really need to do to nullify their communication.

    FACT: Exfiltration isn't possible without orders either.

    FACT: Orders come from C2 servers!

    So YOU LOSE chump... a BETTER ARTICLE than what I used proves it for me!

    * THANKS FOR LOSING TO ME yet again, as always for you... try me again? THIS COMES UP AS PROOF (as well as another I have on YOU regarding using sources where YOU contradict yourself - want quotes of that too? ASK!)

    HOW ESPECIALLY EMBARASSING FOR YOU with your NO-DOUBT self-upmodded by sockpuppet accounts of YOURSELF too - now that YOU have EGG ON YOUR FACE fucko!

    APK

    P.S.=> Do yourself a FAVOR - don't ever, EVER try me ever again OR I WILL MAKE SURE YOU SHIT ON YOURSELF yet again as always, easlly... apk

  • (Score: -1, Spam) by Anonymous Coward on Tuesday June 21, @11:29PM

    by Anonymous Coward on Tuesday June 21, @11:29PM (#1255122)

    Guess what Dalek? YOU LOSE, hosts work vs. Symbiote C2 server(s) per this line from a MUCH better article than the one used here from bradley13 per "configuration in the binary that used the git[.]bancodobrasil[.]dev domain as its C2 server" from https://www.intezer.com/blog/research/new-linux-threat-symbiote/ [intezer.com] (INTEZER's now owned by Microsoft iirc as well).

    & did I block that in my original posts here https://soylentnews.org/comments.pl?noupdate=1&sid=49835&page=1&cid=1253504#commentwrap [soylentnews.org] on this BOGUS sockpuppet upmodding yourselves shithole website (which also noted FIREWALLS are invaluable here too, per wildcards (or even IP address use, URL domain/subdomain too in many as well)?

    YES I DID! I was correct...

    & YES, hosts work vs. this threat too stupid!

    FACT: hosts files block symbiote C2 servers which is all you really need to do to nullify their communication.

    FACT: Exfiltration isn't possible without orders either.

    FACT: Orders come from C2 servers!

    So YOU LOSE chump... a BETTER ARTICLE than what I used proves it for me!

    * THANKS FOR LOSING TO ME yet again, as always for you... try me again? THIS COMES UP AS PROOF (as well as another I have on YOU regarding using sources where YOU contradict yourself - want quotes of that too? ASK!)

    HOW ESPECIALLY EMBARASSING FOR YOU with your NO-DOUBT self-upmodded by sockpuppet accounts of YOURSELF too - now that YOU have EGG ON YOUR FACE fucko!

    APK

    P.S.=> Do yourself a FAVOR - don't ever, EVER try me ever again OR I WILL MAKE SURE YOU SHIT ON YOURSELF yet again as always, easlly... apk

  • (Score: -1, Spam) by Anonymous Coward on Wednesday June 22, @03:39AM

    by Anonymous Coward on Wednesday June 22, @03:39AM (#1255208)

    Guess what Dalek? YOU LOSE, hosts work vs. Symbiote C2 server(s) per this line from a MUCH better article than the one used here from bradley13 per "configuration in the binary that used the git[.]bancodobrasil[.]dev domain as its C2 server" from https://www.intezer.com/blog/research/new-linux-threat-symbiote/ [intezer.com] (INTEZER's now owned by Microsoft iirc as well).

    & did I block that in my original posts here https://soylentnews.org/comments.pl?noupdate=1&sid=49835&page=1&cid=1253504#commentwrap [soylentnews.org] on this BOGUS sockpuppet upmodding yourselves shithole website (which also noted FIREWALLS are invaluable here too, per wildcards (or even IP address use, URL domain/subdomain too in many as well)?

    YES I DID! I was correct...

    & YES, hosts work vs. this threat too stupid!

    FACT: hosts files block symbiote C2 servers which is all you really need to do to nullify their communication.

    FACT: Exfiltration isn't possible without orders either.

    FACT: Orders come from C2 servers!

    So YOU LOSE chump... a BETTER ARTICLE than what I used proves it for me!

    * THANKS FOR LOSING TO ME yet again, as always for you... try me again? THIS COMES UP AS PROOF (as well as another I have on YOU regarding using sources where YOU contradict yourself - want quotes of that too? ASK!)

    HOW ESPECIALLY EMBARASSING FOR YOU with your NO-DOUBT self-upmodded by sockpuppet accounts of YOURSELF too - now that YOU have EGG ON YOUR FACE fucko!

    APK

    P.S.=> Do yourself a FAVOR - don't ever, EVER try me ever again OR I WILL MAKE SURE YOU SHIT ON YOURSELF yet again as always, easlly... apk

  • (Score: -1, Spam) by Anonymous Coward on Wednesday June 22, @06:57AM

    by Anonymous Coward on Wednesday June 22, @06:57AM (#1255253)

    Guess what Dalek? YOU LOSE, hosts work vs. Symbiote C2 server(s) per this line from a MUCH better article than the one used here from bradley13 per "configuration in the binary that used the git[.]bancodobrasil[.]dev domain as its C2 server" from https://www.intezer.com/blog/research/new-linux-threat-symbiote/ [intezer.com]

    & did I block that in my original posts here https://soylentnews.org/comments.pl?noupdate=1&sid=49835&page=1&cid=1253504#commentwrap [soylentnews.org] on this BOGUS sockpuppet upmodding yourselves shithole website (which also noted FIREWALLS are invaluable here too, per wildcards (or even IP address use, URL domain/subdomain too in many as well))?

    YES I DID! I was correct...

    & YES, hosts work vs. this threat too stupid!

    FACT: hosts files block symbiote C2 servers which is all you really need to do to nullify their communication.

    FACT: Exfiltration isn't possible without orders either.

    FACT: Orders come from C2 servers!

    So YOU LOSE chump... a BETTER ARTICLE than what I used proves it for me!

    * THANKS FOR LOSING TO ME yet again, as always for you... try me again? THIS COMES UP AS PROOF (as well as another I have on YOU regarding using sources where YOU contradict yourself - want quotes of that too? ASK!)

    HOW ESPECIALLY EMBARASSING FOR YOU with your NO-DOUBT self-upmodded by sockpuppet accounts of YOURSELF too - now that YOU have EGG ON YOUR FACE fucko!

    APK

    P.S.=> Do yourself a FAVOR - don't ever, EVER try me ever again OR I WILL MAKE SURE YOU SHIT ON YOURSELF yet again as always, easlly... apk

(1)