What Products Use Intel 10nm? SuperFin and 10++ Demystified
by Dr. Ian Cutress on September 25, 2020 9:00 AM ESTThe AnandTech Decoder Ring for Intel 10nm
The reason why I’m writing about this topic is because it is all a bit of a mess. Intel is a company so large, with many different business units each with its own engineers and internal marketing personnel/product managers, that a single change made by the HQ team takes time to filter down to the other PR teams, but also filter back through the engineers, some of which make press-facing appearances. That’s before any discussions as to whether the change is seen as positive or negative by those affected.
I reached out to Intel to get their official decoder ring for the 10++ to new SuperFin naming. The official response I received was in itself confusing, and the marketing person I speak to wasn’t decoding from the first 2018 naming change, but from the original pre-2017 naming scheme. Between my contacts and I we spoke over the phone so I could hear what they wanted to tell me and so I could tell them what I felt were the reasons for the changes. Some of the explanations I made (such as Intel not wanting to acknowledge Ice Lake 10nm is different to Cannon Lake 10nm, or that Ice Lake 10nm is called that way to hide the fact that Cannon Lake 10nm didn’t work) were understandably left with a no comment.
However, I now have an official decoder ring for you, to act as a reference for both users and Intel’s own engineers alike.
| AnandTech's Decoder Ring for Intel's 10nm | ||||
| Product | 2020+ | First Update |
Original |
|
| Cannon Lake | - | - | 10nm | |
| Ice Lake Ice Lake-SP Lakefield (compute) Snow Ridge Elkhart Lake |
10nm | 10nm | 10+ | |
| Tiger Lake SG1 DG1 |
10nm Superfin |
10+ | 10++ | |
| Alder Lake First Xe-HP GPU Sapphire Rapids |
10nm Enhanced SuperFin |
10++ | 10+++ | |
For clarity, 10nm Superfin is often abbreviated to 10SF, and 10nm Enhanced Superfin to 10ESF.
Moving forward, Intel’s communications team is committed to explaining everything in terms of 10nm, 10SF, and 10ESF. I have been told that the process of moving all internal documents away from the pre-2017 naming to the 2020 naming is already underway.
We reached out for Intel for a comment for this article:
It is widely acknowledged within the industry that there is inconsistency and confusion in [our] nanometer nomenclature. Going forward, we will refer the next generation 10nm products as 10nm SuperFin technology-based products.
My take is that whoever had the bright idea to knock Ice Lake down from 10+ to 10 (and then Tiger from 10++ to 10+ etc.), in order to protect the company from addressing issues with the Cannon Lake product, drastically failed at predicting the fallout that this name change would bring. Sometimes a company should accept they didn't score as well as they did, admit the hit, and move on, rather than try and cover it up. So much more time and effort has been lost in terms of communications between the press and Intel, or the press and engineers, or even between the engineers and Intel's own communications team. Even the basic understanding of dealing with that change has been difficult, to the detriment of the press trying to report on Intel’s technology, and likely even on the financial side as investors try to understand what’s going on.
But, truth be told, I’m glad that Intel moved away from the ++++ nomenclature. It allows the company to now easily name future manufacturing node technologies that aren’t just for pure logic performance, which may be vital if Intel ever wants to become a foundry player again.
Facebook
Twitter
RSS
143 Comments
View All Comments
TheJian - Wednesday, September 30, 2020 - link
They did that to sell old chips stuck in inventory forever; nintendo probably got a great deal on stuff that at that at point was worth $0 to Nvidia. They didn't say whatever dude, they said no margin and robs from core R&D so we passed. The didn't pursue Nintendo, it's old crap that couldn't be sold to anyone else.NV doesn't do poor stuff until forced, or they simply have nothing else to sell more of, get it? If I've tapped out the entire gpu market, making a mint, etc, then make poor stuff if you still have resources. IE, if NV is short on silicon they put out low models LAST (heck they pretty much always do it, smarter).
What kind of soc is in that premium console from nintendo? Hint, it's not 7nm in that first one.
https://arstechnica.com/gaming/2016/12/nintendo-sw...
Hybrid consoles use "LAST GEN TECH". So they didn't waste tons of R&D did they? :) They are also very small chips even with the new ones (the lite model has newer tech, old T4 was ~100mm^2). Xbox/ps4 were 400+. Those puny ones won't steal much from the 3000's right? They went to samsung, so this deal might have been all they could get out of TSMC at the time (apple was buying all 7nm, now moved to 5nm, amd/intel bought a bunch of the freed up stuff).
Selling your own console and a chip in others for $10-15ea is very different, and also brought their store for game sales (income off other's work). Not the same as 450mm^2 console chips for $10-15 each when those could be flagship cpu/gpus that make $100 or more. NV just ran out of cards in minutes. AMD claiming they won't. It would be a lot easier if you weren't wasting silicon on $15 items right? That size is a large AMD gpu not being sold for $500+. IE, 3070 is ~393mm^2. NV makes more than $15 on them. As the poor guy in semi, you should concentrate on INCOME, not units or share. This has nothing to do with being cool, it wasting R&D. It's about money, so yeah, legit. Your comment? Stupid. Intel screwed the lowend when short 10% silicon (couldn't fill about 10% of customers PC's), and moved to HEDT/server. You don't seem to understand the conversation or how these companies work.
Shield was an attempt again, to move old silicon and only cost 10mil to dev both shield TV and the handheld they said...That is a small price to pay to move old chips worth at least as much and collect some money on the store maybe, push streaming, etc etc. It was a small price to pay and a good move business wise at the time. They failed in mobile so tried to recover some of the wasted silicon collecting dust and push new streams of income while doing it. Good management. These end up in AMD writeoffs (see trinity etc IIRC, multiple apu junk).
They are no xbox/sony because they wanted MORE money. You are proving my point. AMD sold out cheap, NV wouldn't. Yeah, you're right. Thanks. They tried to MAKE MONEY, not RIP off MSFT. I wouldn't work for free either basically. :) 15%, in semi? ROFL. Only if I can't make more on something else ANYWHERE. Note xbox360 cost MSFT 3.5B or so, and Sony's lost ~4B...ROFL. Jury still out on ps4/xbox1 etc. AMD thought they might beat NV tech by being in a console and hoping games would aim at them, fixing their perf problems vs. NV gpus. It's not working. See 9% going to NV over TECH. RT+DLSS sells...OUT that is..In minutes.
Wake me when you actually have a data point and learn to debate. See Paul Graham's chart.
Teckk - Wednesday, September 30, 2020 - link
Yes, all fabs at full steam. Funny you forgot about 10nm and 7nm."but it is only until they right the fab ship and they have many ways to do that." like they've been doing it for last 4 SkyLakes? Or was it 5? You're good at counting you will know that for sure.
Come for a bebate when you actually know something about the process nodes and where they are. Play with historical numbers till then. That's what they are. Historical.
Tilmitt - Sunday, September 27, 2020 - link
Is Anandtech aware that Nvidia Corporation has released a new series of 3D accelerator boards?Qasar - Monday, September 28, 2020 - link
they are, but there are these fires in California.......Sychonut - Monday, September 28, 2020 - link
Excessive politics + power hungry Murthy = delaysdeil - Monday, September 28, 2020 - link
I am not sure how reliable that source is, but I heard Intel could not get double-digit yields on 10nmat first, then after making design less "innovative", but yields were okaying, performance was within margin of error from 14nm+++++++++++++
Spunjji - Monday, September 28, 2020 - link
Entirely reliable.In practice, Ice Lake is roughly comparable to Comet Lake in everything but GPU performance; overall what it gained in IPC it lost in clock speed. This was *after* Intel had already relaxed their 10nm transistor density way below their initial claims of 67-100 million transistors per square millimetre.
They finally seem to have fixed that with Tiger Lake, but given the paper-launch nature of that release and their reluctance to discuss the 8-core variants, I'd be happy to surmise that either yields are still not great or they only have some fraction of their 10nm fab resources capable of manufacturing on the new "SuperFin" node variant.
RedOnlyFan - Saturday, October 3, 2020 - link
@spunjji Your delusional comments deserves a praise.Linustechtips12 - Monday, September 28, 2020 - link
Look honestly since intel didn't have completion why wouldn't you stay roughly on the same node it saves money and time somewhat you can argue that they should've been innovation but are people forgetting they own stock in amd toAgent Smith - Monday, September 28, 2020 - link
They're going to drown in those lakes