Samsung Foundry: 2nm Silicon in 2025
by Dr. Ian Cutress on October 6, 2021 1:02 PM EST
One of the key semiconductor technologies beyond 3D FinFET transistors are Gate-All-Around transistors, which show promise to help extend the ability to drive processors and components to higher performance and lower power. Samsung has always announced that its first generation GAA technology will align with its ‘3nm’ nodes, with its 3GAE and 3GAP processes. As part of the Samsung Foundry Forum today, some more insight was put into the timeline for the rollout, as well as talk of its 2nm process.
It has been widely expected that once the standard FinFET runs out of steam that the semiconductor manufacturing industry will pivot to GAAFET designs. Each of the leading edge vendors call their implementation something different (RibbonFET for Intel, MBCFET for Samsung), but it is all using the same basic principle – a flexible width transistor with a number of layers helping drive transistor current. Where FinFETs relies on multiple quantized fins for source/drain and a cell height of multiple tracks of fins, GAAFETs enable a single fin of variable length, allowing the current for each individual cell device to be optimized in power, performance, or area.
All the big vendors have been discussing GAAFETs in technical semiconductor conferences for a number of years. For example, at the International VLSI conference in June 2020, then Intel CTO Dr. Mike Mayberry showcased a diagram with the enhanced electrostatics of moving to a GAA design. At the time we asked about Intel’s timescale for implementing GAA in volume, and were told to expect them ‘within 5 years’. At present Intel’s RibbonFET is due to come with the 20A process, likely to be productized by the end of 2024. TSMC by contrast is introducing its equivalent technology with its 2nm process nodes, stating that they can extend the life of their FinFET technology for another generation in 3nm. Exact timeline for TSMC's rollout is still quite blurry at this point, as the company expects its N5 and N3 offerings to be extensive long life-time nodes.
Samsung actually surprised us a couple of years back, announcing that it had a version of its GAA technology in prototype in early 2019. The company said that it was shipping its v0.1 development kit to its partners, allowing them to experiment with the early design rules that Samsung required. That has improved over time, and at a presentation a couple of months ago at a China-only conference, the company said that a version of its 3nm GAA technology would be on track for 2022 deployment. Today Samsung is confirming and extending those expectations.
Speaking to Samsung’s MoonSoo Kang, Senior VP of Samsung’s Foundry Market Strategy, he outlined the following timetable for Samsung’s GAA process nodes:
- 3GAE will go into mass production by EoY 2022
- 3GAP will follow in one year for mass production at EoY 2023
- 2GAP will take another couple of years, mass production in 2025
He did add the caveat that these are mass production schedules – product on the shelves will be dependent on customers and their own deployments. From that we usually add one or two quarters (3-6mo) after these times, so 2GAP is realistically a 2026 product for end-users based on these schedules.
This is the first that Samsung is talking about its 2nm process technology, and it comes across as an iterative optimization with what Samsung expects to provide with the 3nm variants. Exact details about performance expectations of these process nodes may be presented later today at the Samsung Foundry Forum 2021 event. Stay tuned for additional coverage.
Facebook
Twitter
RSS
29 Comments
View All Comments
zepi - Wednesday, October 6, 2021 - link
Inflation is really kicking in. 7 -> 2nm in just a few years...geoxile - Wednesday, October 6, 2021 - link
No mention of scaling? Doesn't the new 4nm scale density higher than previous 3GAA estimates?Threska - Wednesday, October 6, 2021 - link
Well in four years Covid-19 will be over. Hopefully.yeeeeman - Thursday, October 7, 2021 - link
after getting a million shots, yeahKangal - Thursday, October 7, 2021 - link
No it won't.This virus-type will continue to mutate, propagate, and infect. However, the severity and mortality-rate would probably be reduced by a large factor. Case in point; the WW1 "Spanish Flu" which killed around 3% of the world's population was never eradicated. It mutated and kept causing several other pandemics. The "Seasonal Flu" that we get, is actually a strain directly linked back to the original Spanish Flu. There is a very high probability that SARS-Cov-2 is going to follow a similar pathway.
It is our "New Normal". And just why we need to be diligent about disease, both in controlling them, and in our personal lives. As the numbers show, most active and healthy people are naturally resistant to covid, and most of the illness and deaths follow obese people, un-active people, and the immunocompromised. Which is why our response to the Ebola outbreak (a frighteningly nasty disease) several years ago was harsh but justified. Anyways I've rambled on for too long, I won't hijack the comment section any longer, as this isn't the space for this topic.
FreckledTrout - Thursday, October 7, 2021 - link
They have found a antibody, S309, that kills all forms of Covid. My hope is they make that into a treatment or better yet reverse engineer it into a vaccine that causes our bodies to produce said antibody.Oxford Guy - Monday, October 25, 2021 - link
'They have found a antibody, S309, that kills all forms of Covid. My hope is they make that into a treatment or better yet reverse engineer it into a vaccine that causes our bodies to produce said antibody.'Until people are forced to vaccinate, as happened with polio, it will continue to mutate in the anti-vaxxers.
web2dot0 - Thursday, October 7, 2021 - link
This generalization of covid affecting mostly "obese people, un-active people, and the immunocompromised" is what drives anti-vaxxers to continue to not vaccinate. Plenty of perfectly healthy people have died from covid. Many pro atheletes get very ill from covid as well, and affected them with last effects.Hardly the same as a regular flu.
The only way to control the spread of this virus is vaccine. Not "being healthy or build natural immunity".
Please don't hijack the comment section to spew unhelpful "facts"
vortmax2 - Thursday, October 7, 2021 - link
"This generalization of covid affecting mostly "obese people, un-active people, and the immunocompromised" is what drives anti-vaxxers to continue to not vaccinate."No, most people who don't get vaxxed are not 'anti-vaxxers' at all, but people that were waiting for full FDA approval, or fearful of the new mRNA tech, or concerned about the fetal cells used for early testing and/or manufacturing, or have had strong allergic reactions to other vaccines. Don't be so hasty in your judgement.
The data clearly shows that the VAST majority of people (90%+) severely impacted by Covid and/or killed are people with comorbidities. This is fact and truth. Long-Covid is also real, a little scary, but something that needs additional research, However, 'long-flu' and other viruses are very real as well and haven't been studied enough. Hopefully Covid's focus will bring additional focus to these other viruses' long-term impacts.
"The only way to control the spread of this virus is vaccine. Not "being healthy or build natural immunity"."
It's actually both.
vortmax2 - Thursday, October 7, 2021 - link
Another reason why people aren't getting the vaccine is simply because they don't want to be told what to do or be forced into it. Also, some people figure they have to mask still after being fully vaccinated and lose confidence and/or motivation. The CDC is not helping the cause...still recommending remote Holidays for fully vaxxed people? Really?