Sunday, December 5th 2021

Intel Prepares Raptor Lake Designs With 24 Cores and 32 Threads, More E-Cores This Time

With the launch of Intel's Alder Lake processors, Intel has switched from a homogeneous to a heterogeneous design of processors, where smaller, high-efficiency cores are mixed with high-performance cores to create a highly efficient and high-performance processor for all kinds of workloads. And it seems like Intel is not over with adding more E-cores to its future products, as the latest leaks suggest. According to the BAPCO's Crossmark benchmark database, Intel's upcoming Raptor Lake processors will feature more E-cores than the high-performance P-cores in the SoC design. As to why this design choice is present, we are not sure and don't have a definitive answer.

E-Cores are suitable for background tasks, and adding more would potentially leave space for P-cores to do heavier workloads. In the benchmark submission, which is now offline, the samples used were a configuration with eight P-cores and sixteen E-cores. Since the big cores are hyperthreaded, it makes up for a total composition of 24 cores with 32 threads. The platform "RPL-S ADP-S DDR5 UDIMM OC CRB" was used with DDR5-4800 memory, indicating an early stage engineering sample with a probably unfinished memory controller. The Raptor Lake generation will also use LGA 1700 socket, DDR5 memory and be present in the desktop and mobile sector once it launches in Q4 of 2022. It will also use Intel's 7 semiconductor manufacturing process, similar to Alder Lake. The only difference with the next-generation design is the updated Raptor Cove core design that brings a significant IPC uplift.
Sources: Tom's Hardware, KOMACHI_ENSAKA (Twitter), via VideoCardz
Add your own comment

81 Comments on Intel Prepares Raptor Lake Designs With 24 Cores and 32 Threads, More E-Cores This Time

#76
ShurikN
AquinusDid you not see the E-core review that W1zz did? At 4k...
I have. Have you? The application performance is poor compared to P-cores.

At 4k in gaming even bulldozer performs well... Can't believe you used 4k gaming as an argument for cpu performance.
Posted on Reply
#77
Aquinus
Resident Wat-man
ShurikNI have. Have you? The application performance is poor compared to P-cores.

At 4k in gaming even bulldozer performs well... Can't believe you used 4k gaming as an argument for cpu performance.
It shows that they're not nearly as useless as you're claiming. Also Bulldozer would probably use a lot more power doing the same thing.

Would you like to show us on a doll where Intel hurt you?
Posted on Reply
#78
Punkenjoy
AquinusIt shows that they're not nearly as useless as you're claiming. Also Bulldozer would probably use a lot more power doing the same thing.

Would you like to show us on a doll where Intel hurt you?
At 4K, you are really GPU limited meaning a smaller/lower performance CPU will be enough to do the task.

I do not think that it prove they are useful at all in gaming. It just prove that at 4k, people should really focus on upgrading their GPU before CPU.

In game where you really need high IPC, the E-core would suck anyway.

In game that are CPU limited due to the main core having too much thing in serial, they wouldn't be utilized, and another P core would beat them due to the very high latency in scenario where they would be utilized. Also it wouldn't matter if you have 8 or 24 e core in 4K anyway, so i am not sure why someone would want to pay for all those extra cores.


That do not mean they cannot run games, they can. After all, PS4 and Xbox one had CPU that were way worst than those E-cores and managed to do fine (at 30 fps most of the time, true..)

But this is not ideal for gamers.

The E core have been designed to run background task and this is why they have some drawback like latency and lower frequency. It wouldn't matter as much for these kind of task but for high refresh rate gaming, it would not be a good thing.
Posted on Reply
#79
efikkan
dragontamer5788I'm unaware of any CPU made, be it AMD, Intel, or IBM POWER, or ARM, that did data-sharing in "close" caches (L1). All data-sharing is in LLC (last-level cache).
I'm referring to this:

(source)
CrackongMaybe , just maybe, sometime they will come up with 16 cores single ringbus.
But that means a 20 ring stop ringbus.
Will core to core latency become a huge concern ?
I don't think so, core-to-core communication is fairly infrequent compared to e.g. cache and memory accesses. (For comparison even a single cache miss is much more costly, and more frequent) Even most heavily multithreaded tasks will probably be bandwidth starved before this becomes a problem.
Posted on Reply
#80
londiste
ShurikNThe application performance is poor compared to P-cores
Not looking it up right now but IIRC E-cores ended up at around 3300X which is not a bad result at all.
Vs 3300X E-cores were losing ground in single thread - due to lower boost clocks - and gaining ground in multi thread - due to 8c8t vs 4c8t.
Posted on Reply
#81
Mussels
Freshwater Moderator
londisteNot looking it up right now but IIRC E-cores ended up at around 3300X which is not a bad result at all.
Vs 3300X E-cores were losing ground in single thread - due to lower boost clocks - and gaining ground in multi thread - due to 8c8t vs 4c8t.
I recall seeing that as well, and it adds to the concept that AMD were looking at mixing and matching Zen generations as their own hybrid variant

So a Zen4 CPU could have 6x zen 4 cores, and 8x zen 3 cores (with tweaked power efficienct settings)

It'll be interesting to see where this ends up, as zens architecture really does seem better suited to mixing different generations together than intels version
Posted on Reply
Add your own comment
Nov 20th, 2026 21:24 PST change timezone

New Forum Posts

Popular Reviews

TPU on YouTube

Controversial News Posts