It says "Client: Intel", but I wouldn't necessarily interpret that as the node being Intel 3.
DrMrLordX
Lifer
- Apr 27, 2000
- 22,903
- 12,974
- 136
No, in the old naming scheme, Intel 4 == 7nm+, Intel 3 == 7nm++, and Intel 20A == 5nm.
Didn't see it get mentioned in this thread yet, but Gelsinger claimed LNL and ARL will launch in 2024. Not ramp, not PRQ, just straight up launch in 2024.
And also DMR is on a new platform vs CLR. I don't follow servers much, so I might be wrong, but didn't Intel traditionally launch 2 server products on the same platform? It's weird because SRF and GNR are on the same platform, and CLR is on the same platform as those two as well, but for some reason DMR isn't?
And also DMR is on a new platform vs CLR. I don't follow servers much, so I might be wrong, but didn't Intel traditionally launch 2 server products on the same platform? It's weird because SRF and GNR are on the same platform, and CLR is on the same platform as those two as well, but for some reason DMR isn't?
the catterpillar diagram from 3 years ago???
Lnl as in lunar lake? as far as i recall lunar lake comes after arrow lake, by at least a year or more on mobile. meteor and arrowlake mobile should exist before it. or have things changed at intel?tech power up is reporting intel is changing up their branding which is either good or there marketing dept is using the same coke amd's is when their mobile 8000 or 7000 bs.
ye, lunar lake and arrow lake launch in 2024. Intel 18a sound feasible for that? idk.
LNL won't/can't use 18A with a 2024 launch target. Also they would have mentioned it but they only mentioned Clearwater Forest on 18A which is scheduled for 2025. The latest roadmap from last year indicated LNL uses an external process and the successor of LNL is going to use 18A.
I think Intel's server roadmap has been too much of a mess to really draw any conclusions from history, but switching platforms certainly isn't something to do lightly. Implies some pretty significant SoC changes.
They mentioned Clearwater forest on 18a in their server specific roadmap seminar, not any general future roadmap or earnings call. Their roadmaps are very ambiguous about what constitutes using an 'external process' since they also count the other tiles like SOC or GPU tiles. For example, MTL is also shown to be using an external process. But I do agree, 18A in 2024 for LNL is highly improbable.
I think Intel's skipping GNR+, or whatever that would have entailed, for DMR in late 2025/2026. DMR might end up using Panther Cove or who knows maybe even royal cove if it comes out later. I really think GNR was intended for RWC, GNR+ (I think Intel honestly called this DMR at first) for LNC, but then pushed GNR to 2024 to be what was originally planned to be DMR. It could explain why Pat wanted to rename GNR after they announced that they redefined GNR, because they literally were essentially renaming GNR into what Intel originally planned DMR to be.
It's not my timeline. It's word for word, Pat's. You can go check out the Q1 2023 earnings call transcript, control F "lunar lake", and then see that's exactly what he said. Lunar Lake and Arrow Lake launch 2024.
Pat "(DMR platform)...which will change package architecture, power delivery architecture, memory channel, key steps in memory scalability with our CXL technology"
¯\_(ツ)_/¯ I'm not saying you have to believe it lol I'm just saying that it's Intel's roadmaps not anything I created.
Just curious, anyone know if the ARL 3nm rumors had them on N3 or the N3E process?
Also LNL development timeline (tape out q4 2022) puts it at the end of 2024 launch.
It's a shame Intel didn't make any announcement about ARL taping out, though they did for MTL and LNL.
Though when Pat mentioned having Intel 20A silicon tape outs already early 2023, it's possible he could be talking about having very, very early versions of ARL internally in the foundry. Intel not announcing ARL power on yet isn't exactly the best of signs, especially for a 1H 2024 launch, and if they haven't announced ARL powering on by Q2 earnings report, it should pretty much confirm a 1H 2024 launch is impossible and it's 2H.
As for Intel not announcing this stuff, with their finances looking the way they are, Intel is announcing pretty much every win they can get recently, even if it's internal development stuff.
That's true. Tweeting about the Core Ultra naming change instead of a formal announcement. Clearly, they want people to get excited and get some of the investor heat off their backs.
Intel said clearwater forest in 2025 is the lead product for 18A so it can't be used for lunar lake and with intel 3 being used only in server products I think it's safe to assume lunar lake is going to be on TSMC N3.
srsly? Do you have a quote/link for that? Because if you're right, if Intel did say that then ye it all but confirms LNL will be on TSMC 3nm... very impressive catch.
I got it from this tweet but I don't know where the original quote for it is.
in the Q1 call Pat said
"Clearwater Forest, which is the follow on to Sierra Forest, is coming to market in 2025 and will be manufactured on Intel 18A, the node where we intend to achieve process leadership, and representing the culmination of our five-nodes-in-four-year strategy."
so he didn't really say it was the lead vehicle but if 18a is HVM in H2 2024 it's very unlikely we will see any product on it before 2025
What is the board's opinion of Daniel Nenni (SemiWiki founder)? I know MLID is not popular (for understandable reasons) but he somehow gets these really credible guests on his podcasts that I think are worth a listen.
Anyway, his statements on Intel's foundry services is interesting. As a summary: He says Intel 4 & 3 are both already solid. He seems confident in 18A too, although claims it's success is dependent on the PDK they offer. He thinks IFS offering for Intel 3 is basically DOA against TSMC since they can't compete against their current ecosystem and PDK. Seems Intel's issue with MTL-S (presumably being cancelled) aren't necessarily related to the manufacturing side but rather first adoption of chiplets and early EMIB bugs.
Anyway, his statements on Intel's foundry services is interesting. As a summary: He says Intel 4 & 3 are both already solid. He seems confident in 18A too, although claims it's success is dependent on the PDK they offer. He thinks IFS offering for Intel 3 is basically DOA against TSMC since they can't compete against their current ecosystem and PDK. Seems Intel's issue with MTL-S (presumably being cancelled) aren't necessarily related to the manufacturing side but rather first adoption of chiplets and early EMIB bugs.
From what we know and hear from Intel+leaks Intel 4 looks solid, it's nothing new what he says. MTL-P ES2 already hits or beats base clock speeds of ADL-P and who knows what QS+final samples brings to the table. People who compared it to Cannonlake have no clue. Intel sounds confident about Intel 3 too. MTL-S isn't presumably cancelled, it's presumably limited to i3 and i5 desktop class (maybe renamed into Ultra 3 and 5) and comes together (or close) with ARL-S on a new platform. MTL mobile is late, sure it might have been related to the chiplet implementation rather than a process node issue. First serious IFS will be 18A. Even 20A is basically a client only node for Intel. Nothing really new what he says.
personally i belive him a lot, but regardless of my personal opinion, you should not compare this 2 guys, Tom is a computer hobbyist and he took his hobby to the podcast, while Nenni had high positions in several semiconductor firms and he took it to the Forum/podcast as a consultant to semi firms.
The two individuals have totally different intentions: MLID wants to reach a large audience, while Nenni wants to be the moderator of the next semi conductor symposium, one will be paid from game developer ads or patreon donations, while the other will be paid from semiconductor B2B ads.
Therefore, one of them will have to make bold and outrageous claims to attract the masses , and the other one will have to say those things that will attract the insiders of the industry.
The difference is huge!
mlid was an engineer at gm and he gave that up for his podcasts. either he has a benefactor paying him to do this as his "job" because youtube is not a real job no matter how you frame it unless you're trully well and big or people are stupid enough to pay him what he'd have made at gm or more.
Well that would certainly do it. Interesting that he lists "memory channels". Seems to imply that DMR will move up to 16c on the AP socket.
TRENDING THREADS
-
Discussion Zen 5 Speculation (EPYC Turin and Strix Point/Granite Ridge - Ryzen 9000)- Started by DisEnchantment
- Replies: 25K
-
Discussion Intel Meteor, Arrow, Lunar & Panther Lakes + WCL Discussion Threads
- Started by Tigerick
- Replies: 22K
-
News NVIDIA and Intel to Develop AI Infrastructure and Personal Computing Products- Started by poke01
- Replies: 384
-
Discussion Intel current and future Lakes & Rapids thread- Started by TheF34RChannel
- Replies: 23K
Facebook
Twitter