top | item 33045445

Core i9-13900KS runs circles around Ryzen 9 7950X in CPU-Z

17 points| ekoutanov | 3 years ago |notebookcheck.net | reply

15 comments

order
[+] marcyb5st|3 years ago|reply
Not having ever used one of these E/P mixed cores CPUs I am curious to know if they are painless to use (especially under Linux). Does it ever happen that processes that should run on E cores run on P cores or viceversa? Do you have to somehow specify affinity in executables or there's some black magic that figures out automatically?

Any insights in this regard would be greatly appreciated as I am in need to change my desktop and I'm really curious regarding these 13xxx CPUs.

[+] TkTech|3 years ago|reply
Intel contributed support which is in kernel versions 3.18 and up. Low priority tasks like the Baloo file indexer in KDE will always try to run on an E core.

You can also manually pin to cores in Linux and some platforms support manual management. When I'm traveling with my Pinebook pro I turn off the big cores which makes the battery last for days (when not watching video).

[+] nicolaslem|3 years ago|reply
These E/P cores were introduced by Intel with the 12th gen. When comparing modern laptops the 12th gen Intel models are at a real disadvantage compared to Ryzen 6000 (which has only normal P cores) in battery life tests.

My conclusion is that for now it is more of a gimmick than anything ground breaking.

[+] mcraiha|3 years ago|reply
Headline is misleading. And same applies to the text. e.g. 928 vs. 900 difference is around 3% (assuming benchmark scores scale linearly) and 18,453 vs. 16,000 difference is around 15%. At least 15% isn't "runs circles around" kind of situation.
[+] hotcoffeebear|3 years ago|reply
> the latter is notorious for underperforming in CPU-Z and one might have to wait for other benchmarks to surface before jumping to conclusions.

Quite a clickbait title

[+] bloqs|3 years ago|reply
Cpu Z is not a benchmark which makes me question the motives of this article
[+] dis-sys|3 years ago|reply
Intel have to put in an extra 8 cores to get similar multi-threaded scores, while the 3% higher single thread score is all about higher frequency.

I am not very excited for Intel's next earning call.

[+] frognumber|3 years ago|reply
I care more about transistors than cores.

If I were designing a CPU and OS from scratch right now, I'd put in at least a hundred cores. An M1 Ultra has over 100B transistors. That's more than 1000x the transistors of an Allendale Core 2 Duo core from 2007 (which had 170M split among two cores). I could literally fit 100 Allendale cores those suckers on less than 10% of the M1 ultra silicon.

I'd probably have 1-4 fast, modern cores for tasks which don't parallelize. I'd then have a massive number of auxiliary cores for tasks which do parallelize.

I'd also make good use of this to isolate processes, so for example, a rowdy browser tab can't slow the rest of my system down.

[+] hulitu|3 years ago|reply
Since when is (has ?) CPU-Z a benchmark ?
[+] zamadatix|3 years ago|reply
~2015 IIRC. It's not a very thorough benchmark though. More something to say "and look these high clocks I reached didn't immediately crash under some load and I got a x% increase in score".