Jump to content

Why no CPUs with 4 fast cores and additional slower cores?

Hi!

 

Gaming with capturing, streaming and also video editing seem to be a quite popular demand now.

 

Games afaik currently perform best with cores (4) on very high speeds.

 

Are there limitations for manufacturers to make a sort of "hybrid" cpu?

 

For example:

4 fast cores for gaming

4 - 8 additional slower cores for other operations

 

Is this something inconvenient or unpractical?

 

If so, why? I'd like to learn! 

 

Thank you very much!

Link to comment
Share on other sites

Link to post
Share on other sites

You would effectively have to have a board that can support more than one type of cpu at a time in a single socket which isn't possible. even in the server world on multisocket machines all the cpu's must match each other.

The amount of time needed for developing not only hardware but also software that can determine which core is slower and which is faster and which task should be allocated to what type of core would be nuts vs just making every core the same thus eliminating the need to program the machine to assign a specific task to a specific core.

Link to comment
Share on other sites

Link to post
Share on other sites

Desktop and most laptop CPUs do not use ARM, that supports big.LITTLE type of architecture. x86-64 instruction set just does not have support for this kind of scheduling, therefore it hasn't been made. And changing this is way too much work.

 

ARM has been in constant development from scratch and adding it there was much simpler and worth the effort as it gave a pretty nice efficiency boost. Desktops don't really need this, getting more cores is much simpler these days as you have much more room to play with (in terms of power consumption, heat output etc). Laptops could benefit from better battery life, but changing a long existing architecture is not that easy and most likely is not cost-efficient. The R&D costs simply will be too much compared to how much additional income it would bring (which, I doubt, will be much).

 

If you want power efficiency, look at ARM.

HAL9000: AMD Ryzen 9 3900x | Noctua NH-D15 chromax.black | 32 GB Corsair Vengeance LPX DDR4 3200 MHz | Asus X570 Prime Pro | ASUS TUF 3080 Ti | 1 TB Samsung 970 Evo Plus + 1 TB Crucial MX500 + 6 TB WD RED | Corsair HX1000 | be quiet Pure Base 500DX | LG 34UM95 34" 3440x1440

Hydrogen server: Intel i3-10100 | Cryorig M9i | 64 GB Crucial Ballistix 3200MHz DDR4 | Gigabyte B560M-DS3H | 33 TB of storage | Fractal Design Define R5 | unRAID 6.9.2

Carbon server: Fujitsu PRIMERGY RX100 S7p | Xeon E3-1230 v2 | 16 GB DDR3 ECC | 60 GB Corsair SSD & 250 GB Samsung 850 Pro | Intel i340-T4 | ESXi 6.5.1

Big Mac cluster: 2x Raspberry Pi 2 Model B | 1x Raspberry Pi 3 Model B | 2x Raspberry Pi 3 Model B+

Link to comment
Share on other sites

Link to post
Share on other sites

They dont because manufacturing wise it doesnt make sence. 

 

It is simply a whole extra layer of effort needed in the sqedualler that is useless for most people. 

 

You are most likely looking at ARM processor that have bigLITTLE setup of 4 bigger cores and 4 smaller cores. Though it is nice in the boost in efficiency, the extra RnD to create a seperate core and put it on the same die doesnt pay of. (AMD can have 2 different dies due to infinity fabric, but they dont have the money to go through with such measures as the only gain is power efficiency and they do not have a ultralowpower iGPU)

Link to comment
Share on other sites

Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now

×