While TSMC formally started mass production of chips on its N3 (3nm-class) process technology late last year, the company is set to finally ship the first revenue wafers in the current quarter. During the most recent earnings call with analysts and investors, the company said that demand for 3 nm products was steady, and that numerous designs for smartphones and high-performance applications are incoming later this year. Furthermore, N3E manufacturing node is on track for high-volume manufacturing later this year.

"We are seeing robust demand for N3 and we expect a strong ramp of N3 in the second half of this year, supported by both HPC and smartphone applications," said C.C. Wei, chief executive officer of TSMC, during the company's earnings. Call with financial analysts and investors.

Previously the company never commented on applications that use its initial N3 fabrication process, but for now it actually disclosed that devices that are in mass production are designed for smartphones as well as HPC applications, which is a vague term which TSMC uses to describe everything from handheld game consoles all the way to heavy-duty smartphone SoCs. 

For customer privacy reasons, TSMC does not disclose which customers are using N3. Though historically, Apple has been TSMC's alpha client for its leading-edge process technologies, so they're the most likely candidate to be the biggest consumer of TSMC's N3 output. 

TSMC's baseline N3 node (aka N3B) is an expensive technology to use. It features up to 25 EUV layers (according to China Renaissance and SemiAnalysis) with TSMC using EUV double-patterning on some of them to make for higher logic and SRAM transistor density than N5. EUV steps are expensive in general, and EUV double patterning drives those costs up further, which is why this fabrication process is only expected to be used by a handful of customers who are not as concerned about the high expenditure required. 

For those who are more cost sensitive, there is N3E, which can 'only' use up to 19 EUV layers and does not use EUV double patterning. Good news is that TSMC expects to commence mass production on this node to Q4 2023.

N3E has passed qualification and achieved performance and yield target and will start volume production in the fourth quarter of this year," said Wei.

Source: TSMC

Comments Locked

21 Comments

View All Comments

  • NextGen_Gamer - Friday, July 21, 2023 - link

    Going to be an exciting Apple event later in September with the 3-nm A17 Bionic SoC :)
  • Dante Verizon - Saturday, July 22, 2023 - link

    I can't even imagine why anyone cares. 20% gain on synthetic benches, useless AI and such... Yeah, Huge Win
  • Zoolook - Saturday, July 22, 2023 - link

    While the SoCs undoubtedly will be high performers, the most interesting thing nowadays with moving to a new node isn't about absolute performance but increased efficiency, you can do more with the same energy.
  • akdj - Sunday, July 30, 2023 - link

    True Zoolook,
    Like unplug your laptop and get the same performance, have it last a full day getting real work done and not worrying about low power modes, etc
  • brucethemoose - Saturday, July 22, 2023 - link

    If they shipped with 32GB of RAM, I would.

    That is enough for Llama 70B.
  • tipoo - Saturday, July 22, 2023 - link

    Weelll, I sorta do for a different reason than peak performance, iPhones may have a screen boost mode in the sun now, but they still quickly dim the screen and then start throttling the SoC in the sun, I hope 3nm and the new shrunk display driver help with both things.

    Also - the rarer RAM jumps from Apple phones are a bigger deal in my experience than the year to year chip upgrades, 8GB should be a nice upgrade.
  • escksu - Monday, July 24, 2023 - link

    Its more of efficiency rather tha outright performance gains. This could translate into slight longer battery life (notoriously short these days).
  • akdj - Sunday, July 30, 2023 - link

    I care. 20-30-40% increases in speed and decreased energy consumption around the similar savings in objective measurements of power, speed and efficiency - EG exporting stills; RAW or motion or rendering and finalizing the motion or audio you’re fixing to export.

    My iPhone 14 Pro Max and iPad M2 obliterate my two or three year old computers… PC/Mac alike when it comes to getting real work done.

    I don’t pay attention to synthetic benchmarks, who does?

    I use software that is in some cases designed cross platform (macOS/Windows) or iOS/iPadOS and Android - and your example of a 20% ‘gain’ is the equivalent of working 10 hours a day or 8. Or keep working 10 and make 20% more cash.
  • GC2:CS - Saturday, July 22, 2023 - link

    A17 should rather be great if Apple wants to compete with what intel and AMD is cooking at 3nm
  • tipoo - Saturday, July 22, 2023 - link

    The lead of the last decade since A7 seems to be the smallest it's ever been, with SD8 gen 2 being pretty close on CPU and actually leading on GPU (plus having hw rt on it, its use in phones being questionable but should be good for M3) compared to A16, so I do wonder if having the lions run on N3 will let Apple leap out ahead again with a significant increase in per core performance. I wonder if they'll also ever move past 2+4 on phones.

    Excited to see M3 though, that's probably the MBA I'll get.

Log in

Don't have an account? Sign up now