AMD Says It Won’t Follow Intel’s P-Core & E-Core Hybrid Approach, Talks Zen 5, x86S & More
By: Hassan Mujtaba
Source: https://wccftech.com/amd-says-it-wont-follow-intel-p-core-e-core-hybrid-approach-talks-zen-5-x86s-more/
AMD has said that they won’t be following Intel’s approach to Hybrid cores and architectures and also talked about what to expect from Zen 5 CPUs in an interview with TechpowerUp.
AMD’s Vice President Says Not Following Intel’s Hybrid Architecture Approach, Bringing Zen 5 To Desktops As Quickly As Possible
In the interview, AMD’s Corporate Vice President and General Manager, Client Channel Business at AMD, David McAfee, talked about the company’s existing portfolio and upcoming products & how they plan to expand upon it. The talk was initiated with AMD’s Ryzen AI which is a huge part of the new Ryzen 7040 mainstream laptop lineup codenamed “Phoenix”. David goes into a lot of detail on Ryzen AI and it is definitely worth a read over at TPU (full interview here).
The most important revelation made by David is regarding their hybrid CPU architecture. We know that AMD has now two types of Zen 4 cores, the standard Zen 4 and the density-optimized Zen 4C. David says that one way of doing hybrid is to go the P-Core and E-Core route but that isn’t what the red team is planning to take at all. The rationale is that having two different cores with different ISA capabilities makes it harder to fine-tune the OS & applications around the right cores. Intel solves this by using the Thread Director technology but it looks like AMD wants to use similar yet different tuned architectures for its own hybrid approach.
We know that Zen 4 and Zen 4C have the same ISA with small changes in between that don’t make them a completely new chip. And making sure that the right core is scheduled for the right tasks is more important. AMD finds little use of such cores on an unconstrained platform such as Desktops but finds that they can offer a bigger advantage in constrained designs such as laptops. It is said that we will see AMD’s hybrid approach get adopted much more quickly on the laptop front and the first products may be shipping with the upcoming Strix Point line of APUs.
I know that Mark Papermaster talked a lot of about different core types coming into our portfolio. I guess what I would say is that as we’ve looked at different core types there’s probably two things that are overarching factors that we think about in terms of how they fit into the portfolio. One is the notion that P-Cores and E-Cores that the competition uses is not the approach that we plan on taking at all. Because I think the reality is that when you get to the point of having core types with different ISA capabilities or IPC or things like that, it makes it very complicated to ensure that the right workloads are scheduled on the right cores, consistently.
Does that make its way into a desktop processor where you’re power-unconstrained, I think that’s a harder argument to make. We’re constantly looking at different core types, how they might fit into our architectures in the future, but I think there’s some more obvious places where different core types come in and bring an advantage much more quickly than in the desktop space.
I think laptops are a far more practical application for where you might see that adopted much more quickly.
David also talks about Zen 5 and how they are going full steam ahead to bring their latest and greatest architecture to desktops as quickly as possible. The chip design is already on-track for 2024 release and will be available as the Ryzen 8000 Desktop CPUs with additional RDNA 3.5 graphics cores. You can find more details on the upcoming Zen 5 “Ryzen 8000” Desktop family here.
It is also highlighted that core count increase is something that is proportional to the bandwidth available. You can scale core counts up as much as you want to say that hey, we got the most amount of cores/threads on our chip, but it won’t matter if the core bandwidth isn’t there. The excess of cores won’t scale into linear performance. Such a design will end up with performance regression and that’s the limitation associated with dual-channel memory platforms. So once faster memory is available on these platforms for higher bandwidth, we might see another leap in core counts but it looks a lot like that we will be sticking with 16 cores for now on the Zen 5 lineup.
What we are looking for with Zen 5 is to bring it into the desktop space as quickly as we possibly can. As excited as we are about Zen 4, I think what you’ve seen from AMD is that every step in that processor core architecture gives us just such an amazing uplift in terms of capability, in terms of IPC, in terms of performance across every possible workload that you see in desktop and mobile applications. We’re working very, very hard to get it into the market as fast as possible, I know that Mark has talked in the past about how Zen 5 is on-track, it’s in-design, it’s taped-out etc so we are working very hard on it and I think you’re going to be very excited when you see that product come to market.
Talking about APUs, it looks like Phoenix AM5 Desktop chips are already in the works since AMD finds a market for them. It’s not as big in the DIY space but the OEM users who want a chip that houses a GPU and lets them do the entirety of their tasks in a SFF or a commercial PC is definitely big enough to warrant such a product. So AMD says that if there’s a PC market for users who want such chips, then they’ll definitely support such customers.
This is especially a good thing considering that they are several reports of AMD Ryzen 7000G or Phoenix AM5 Desktop APUs being pushed back to later this year or early 2024. We do hope that AMD gets a proper DIY and OEM release since these APUs offer a lot of value within the budget segment, especially considering the pricing of discrete GPUs which are hardly available below the $200 US range. A sub-$200 US chip with RDNA 3 GPU which performs similarly to a $100-$150 US discrete GPU will be great for gamers.
As the Ryzen Desktop Guy I think about that question a lot. You know even in our AM4 portfolio there are very different customers who buy a 5600G vs a 5600X. There’s a class of buyers who wants to build SFF desktops, that wants to do things like APU based gaming. I think there will be a set of people where a Phoenix-based desktop APU would be very attractive for them, with RDNA3 graphics and Zen 4 CPU cores. I think there will be some people that will want that.
And lastly, on the x86S topic which was recently proposed by Intel as a means to pave the way for 64-bit only architectures, AMD says that they are absolutely looking at that & have been evaluating similar proposals for a long time and find Intel’s proposal very intriguing.
We have absolutely been looking at that. We’ve been evaluating similar proposals for a long, long time. It is both incredibly beneficial to make that break, also very, very complicated. I think it is a non-trivial exercise to strip out legacy compatibility in a core architecture as well as time that in a way so that it matches up perfectly with an OS transition that also eliminates a lot of these legacy compatibilities. I would say “very interesting,” something that really, we would have to look at as an industry and make that move in concert. We find Intel’s proposal pretty intriguing as we look at that.
Overall, that’s a pretty nice interview from David and we can’t wait to see the new chips in action with hybrid approaches and especially the AM5 launches which include both Zen 5 and APUs for budget DIY and OEM markets.