Intel's Process Roadmap to 2025: with 4nm, 3nm, 20A and 18A?!
by Dr. Ian Cutress on July 26, 2021 5:00 PM ESTCustomers Customers Customers
As a roadmap announcement today, the focus isn’t so much on the customers but on the technology. Because Intel is moving into a phase where it expects its IFS offerings to compete against the established players, it has to consider its disclosures with respect to both its internal use and any external interest, which is a new concept for the company – at least on this scale compared to its previous foundry efforts.
Intel CEO Pat Gelsinger, in the company’s Q3 financial call last week, was keen to point out that they already have a large hyperscaler customer signed up for their next generation packaging technology, however today there would appear to also be another customer in the mix. Now we assume that Intel’s Foundry Services is talking to 100s of chip companies, big and small, but it doesn’t take much to sign an NDA to start to talk – what will be interesting is when customers start making commitments to using Intel’s facilities, and if any of those are volume orders.
As part of the announcement today, Intel held a little bit back from us, saying that they are saving some of the details specifically for the event that is going on as we publish this piece. All we know is that our draft press release has a big yellow bar that says ‘[customer news]’ on it, right next to Intel’s 20A process node details.
For reference, Intel 20A is a 2024 technology using first generation Gate-All-Around transistors, marketed as RibbonFETs, as well as backside power delivery, marketed as PowerVias. At this time Intel expects to have second/third-generation EMIB available as well as fourth-generation Foveros Direct. So if a customer is already committing to Intel 20A, there’s going to be a lot of potential here.
When the announcement is made, we will update this news article.
To conclude, Intel maintains that these roadmaps will showcase a clear path to process performance leadership* by 2025. It’s a tall order, and the company has to execute better than it has in recent memory - but that’s kind of why the company has rehired a number of former Intel experts and fellows in research, product design, and execution.
*as measured by performance per watt at iso-power
Here's a secondary comparison chart (compared to the one on page one) with all three main foundry offerings listed in each of the main segments that Intel has discussed today.
326 Comments
View All Comments
shabby - Monday, July 26, 2021 - link
Lol this guy is a great comedian 😂at_clucks - Tuesday, July 27, 2021 - link
They're also preparing the elusive 0nm process. Really tiny, great power consumption too.RealBeast - Tuesday, July 27, 2021 - link
Don't get sucked into those 0nm chips, wait for the negative nm the following year. ;)linuxgeex - Wednesday, July 28, 2021 - link
Intel's minds have come up with a new complex plane process. They measure their feature size by taking the square root of the height of the gate. By extending the gate downward, their measurements start at -1, leading to measurements in the scale of i, which tickles their marketing department no end. Sadly, i doesn't deliver on a real timeline.mode_13h - Thursday, July 29, 2021 - link
:DSantoval - Sunday, October 24, 2021 - link
Do not disregard complex timelines so casually. Intel can well deliver in a + bi, where a = Q (quarter), b = year and i is, you know, the imaginary thingy.Assuming a claimed Q1 2025 delivery in the real plane of Intel's RibbonFET 20A parts, in the complex plane where Intel lives the actual delivery would be in Q1 + 2025i.
Let's say Jan 2025i; right after the complex holiday season of 2024 / 2025, complete with an imaginary Santa and complex elves.
nandnandnand - Monday, July 26, 2021 - link
"Isn't Intel Just Trying To Pull The Wool Over Our Eyes?"Yes. Otherwise there's no need for the marketing dept to magically shrink the fake 10nm node to become a fake 7nm.
ianmills - Monday, July 26, 2021 - link
When everyone lies nobody is wrong...nandnandnand - Monday, July 26, 2021 - link
As long as they put out accurate transistors per square millimeter estimates, everything's fine.Who is the biggest liar now? Probably Samsung.
DigitalFreak - Monday, July 26, 2021 - link
Nope. Still Intel.