• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

TechPowerUp user tests 30 CPUs in gaming performance.

eton975

Senior member
http://www.techpowerup.com/forums/threads/test-of-cpu-for-gaming-30-cpus-compared.200132/

Looks kinda interesting. I'm kinda surprised that the 8350 does so well compared to the 4460/4590 (91% their performance) - I expected much worse results. Of course, there's no mention of minimum frametimes, which could be the big difference.

And like I've been saying to people for ages, the Celeron G1840 isn't that bad, considering the other options in its price range (Athlon 5350, blech).
 
I think it's been known for a while now that gaming is not very processor sensitive, especially once you get to a recent at least 4 core processor.
 
Poor method to assess results as some titles wield a disproportionate amount of clout (A v P and Batman) vs. others.
 
Must be a lot of gpu limited results Just look at 9590 vs 8350. Around 15% faster clockspeed but only 2.5% faster results, even at the lowest resolution. Still not good looking for FX though, as an i3 is neck and neck with 9590, which is priced similarly and uses 3x the power.
 
Poor method to assess results as some titles wield a disproportionate amount of clout (A v P and Batman) vs. others.

Yeah, I would say average relative performance would've been better than accumulated FPS. And you're really picky, I guess you can do weighted average relative performance based on # of copies sold. That way the relative performance would be more reflective of the common case.
 
Yeah, I would say average relative performance would've been better than accumulated FPS. And you're really picky, I guess you can do weighted average relative performance based on # of copies sold. That way the relative performance would be more reflective of the common case.

Yes, average relative performance, maybe tabulated 2 ways: with and without inclusion of gpu limited games. I have to give the poster credit for a lot of work though, even though they are mostly older games.
 
To go through all that work and not include minimum framrates.... wow... It's like building a $400,000 house with no plumbing.
 
Back
Top