Intel Xeon roadmap and Intel 3 Progress

https://www.nextplatform.com/2022/02/17/intel-unfolds-xeon-r…

Today, at the Investor Day event that Intel is holding mostly online – there are some onsite events for actual Wall Streeters – the company did indeed put out an official, updated, and wholly real roadmap for the Xeon SP server CPU lineup. And while the real Intel Xeon SP roadmap does not have a lot of detail on it, it does have two interesting things going on that you need to be aware of. We touched base with Ronak Singhal, senior fellow and chief architect for Xeon roadmap and technology – which is a funny way of saying that Singhal bridges between customers, Intel marketing, and Intel chip designers to get the right server CPUs into the field – to get a little more insight into the roadmap that was shown.

The first new item is that the Intel 3 process (what we might have in the past called a 5 nanometer process) is coming along so well in the labs that it is being moved forward a year from 2025, with the speculated “Diamond Rapids” Xeon SP v7 processor, to the now officially acknowledged “Granite Rapids” Xeon SP v6 CPUs due in 2024.

“We are updating Granite Rapids to be on Intel 3, and this speaks to the health of Intel 3 being good enough that we can intercept it now with Xeons in 2024, versus our prior plans,” Singhal tells The Next Platform. “And Granite Rapids, as you expected, will be on a new platform, different from what Sapphire Rapids and its follow-on Emerald Rapids uses, and we are not yet talking about the details of that platform. And as you can image, there will be things that follow after Granite Rapids.”

It is not clear what happened to the Intel 4 process (what we would have called a rev on the 7 nanometer process), but clearly if Intel is going to assert undeniable and unquestioned “transistor performance per watt leadership” by 2025, as it has promised, it needs to leapfrog its own process roadmap at Intel Foundry Services to catch up with what AMD and the Arm collective will be doing with transistor etching techniques from Taiwan Semiconductor Manufacturing Co. It is arguable that Intel 3 will not be able to keep pace, but jumping once process ahead one year ahead is a step in the right direction.

The roadmap above is also the first time that Intel has acknowledged the existence of the “Emerald Rapids” CPU complex for servers, and we think this is just a rev on Sapphire Rapids with more of the cores on each core chiplet activated and tweaks on the cores as well as other features that wrap around them.

The second interesting thing on the Intel Xeon server chip roadmap – and this is something that we have all been wondering about but we did not get into as part of our speculative roadmap story – is that Intel is indeed going to create Xeon SP CPU complexes that make use of its so-called E-core (short for energy efficient, and derived from the Atom line of processors). Up until now, Xeon processors, with the exception of the Xeon Phi “Knights” family of many core processors, have all used the heavy Xeon core, what is now called a P-core (short for performance core) designs.

You can put around four of the E-cores into the same space as a P-core, so that tells you how many more threads you can get into a socket in theory with the “Sierra Forrest” Xeons, which will also be etched with the same 5 nanometer Intel 3 processes used for Granite Rapids. Intel is not saying what it will do, but Singhal did say that the use cases for what we might call the Xeon EP family would evolve as customers see them and deploy them. Even though the Sierra Forrest and Granite Rapids machines will use the same “Mountain Stream” server platform, you cannot mix and match the P-core and E-core processors inside of a single node, and unlike Intel’s client processors, Intel does not seem to be inclined to mix P-cores and E-cores in the same chiplet or socket.

You can put around four of the E-cores into the same space as a P-core, so that tells you how many more threads you can get into a socket in theory with the “Sierra Forrest” Xeons, which will also be etched with the same 5 nanometer Intel 3 processes used for Granite Rapids. Intel is not saying what it will do, but Singhal did say that the use cases for what we might call the Xeon EP family would evolve as customers see them and deploy them. Even though the Sierra Forrest and Granite Rapids machines will use the same “Mountain Stream” server platform, you cannot mix and match the P-core and E-core processors inside of a single node, and unlike Intel’s client processors, Intel does not seem to be inclined to mix P-cores and E-cores in the same chiplet or socket.

I read this and started doing some comparisons, and realized that the marketing game plans for Intel and AMD are very different. Rembrandt AMD’s Zen 3+ APU was announced this week. (As was Intel’s Xeon D refresh.) I won’t go fishing around for the comparisons with Alder Lake mobile parts, but to sum up, Rembrandt is much better when both processors are limited to 45 watts. It makes sense to do that with Rembrandt, but Alder Lake wants a lot more power. Put them on a desk (not on your lap!) and plug them in, and Alder Lake wins most benchmarks. Don’t use on plastic desks, but that’s a detail.

The only reason to discuss Rembrandt here though is that it was a contingency plan in case DDR5 was significantly better than expected or arrived earlier than expected. Rembrandt uses DDR5, and of course, Raphael the new desktop chip later this year will also use DDR5. What comes after that? Actually, AMD does have a roadmap for next year, Granite Ridge is a TSMC N3 part, while Strix Point the mobile part may contain a mix of Zen 5 and Zen 4c cores. (The may there probably should be interpreted as “even if some Strix Point SKUs contain Zen 4c cores, not all SKUs will contain both types of CPU.”)

The important, not to miss, point is that AMD talked a lot about its new products for 2022 at CES, and ignored 2023. 2024 was right out, even for servers. There probably will be a Turin Zen 5c chiplet, and I’d guess Florence for the main Zen 5 server part, based on the actual roadmap AMD has shown. On the other hand, listen to Intel, and they want to talk, not about their 2022 products, but what they intend to do in 2023 and 2024. When all you have is lemons…

Alder Lake is not a lemon as such. But if AMD announces/releases Genoa before Intel does the same for Sapphire Lake Intel is going to hurt. Why? Below a dozen cores or so, choosing a single socket server will depend on a number of factors. But if you need hundreds of cores, the 96-core top end of Genoa tends to dominate any other considerations. A thousand or more cores–and there are lots of machines out there in this class, mostly in government labs and cloud servers–the price/performance picture will be to lopsided to ignore. Oh, and after Genoa comes 128-core Bergamo. The Zen 5 successor to Bergamo may go up to 256 cores, or it may pause at 192. (12 16-core chiplets)