AMD FX 8370 vs Intel I7 5960x [GTX 970 SLI 4K benchmarks]

[fatfinguh]

Comrades,

 

I got these from Donny Stanley at TechnologyX. I think this is a wonderful article and believe we over-obsess about single thread performance. Doesn't that somewhat defeat the concept or purpose of multi-core technology. So one thousand dollars vs. two hundred dollars gets you . . . __? As a middle class guy who maybe one day gets lucky on a scratch ticket, I'd expect at least a 100% performance increase.

 

http://www.technologyx.com/featured/amd-vs-intel-our-8-core-cpu-gaming-performance-showdown/4/

 

Luke "Well these scores turned out. . . pretty much how I . . . wait. . . no!"

Linus "Whaat?"

*technical difficulties*

 

I actually want to thank Linus for helping me make the decision to cheap out with this processor after watching his bottlenecking guide. Looking forward to DX 12.

 

* I did in fact, find this article linked on AMD's Facebook.

 

*Big shout out to Sintezza for freaking out.

 

“Starting off our 4K benchmarks, we can see that Crysis 3 plays nearly the same on all configurations with a slightly worse frame time on our 5960X. However, once overclocked our FX-8370 delivers the best experience, never dropping below 30 FPS in terms of frame time variance.”

 

"Above we can see that the FX-8370 is about 10% faster in terms of average FPS at both stock and while overclocked. Frame time variance is also much better although both CPUs do drop below 30 FPS, which can lead to some noticeable stutter. Still, the FX-8370 does deliver a smoother experience overall."

 

"Tomb Raider is a title that is definitely not very CPU-bound, and here it shows once again. Performance differences are less than 1% in all instances, except for our stock AMD configuration which displays a slightly lower drop in frame time. Still, all configurations played the game fairly smoothly."

 

"Very interesting results. We can see that in terms of average FPS the 5960X outpaces the AMD chip by at least 5% (about 3-4 FPS). However, looking at our frame time variance it is much worse, showing what would be a fairly sutter-y experience. This is exactly the reason these metrics are so important as they can reveal hidden performance issues."

 

[Sintezza]

This is because at 4K the cpu doesnt realy make that much sense anymore.

You are mainaly gpu limmited.

As you can see, the scaling on both cpu´s is great.

The most interessting fps numbers are allways the minimums, the average and max fps numbers dont make that much sense to me.

 

If we gonne talk about a highend gpu like a GTX980Ti on low res gaming like 1080p.

Then the story is a bit diffrent.

But yeah buying a 980Ti for just 1080p gaming, doesnt realy make much sense in the first place.

[dizmo]

I saw this on my feed for Facebook. Interesting. Can't say I really bothered to look into it since it was sponsored by AMD, so I figured it was a little...tainted.

[Levent]

that screams bullshit to me.

[comicsansms]

WHET?

WHET?

[Br3tt96]

At 4k the gpus take all the strain...

[CtW]

I still won't recommend an  AMD cpu to anyone looking for any vaguely high end build. These are interesting results, but the frame times are an issue. Also, these games aren't very CPU bound.

[Gofspar]

holy fuck this reeks of fucking horse shit

[PerfectTemplar]

Fake benchmarks are 10/10.

[Lays]

In no land does this make sense, the 5960x has lower minimums despite having more cpu horsepower in every aspect. It has more cache more single thread and more threads

[Biggerisbetter]

LTT has far to many fanboys and who can't objectively look at anything without letting their bias out. Until game studios make better AI to use more of the CPU these are the results your going to get for the next few years.       

[dragoon20005]

:huh:  :huh:  :huh:

 

when did the FX ever beat the holy 5960X?

 

that is like comparing a Toyota 4AGE 20V to a V8 Mustang Boss 302 engine

[Lays]

LTT has far to many fanboys and who can't objectively look at anything without letting their bias out. Until game studios make better AI to use more of the CPU these are the results your going to get for the next few years.

How so?? Using less of the cpu would still result in the 5960x winning as it has more single thread performance lol

[niofalpha]

This reeks of bullshit... Intel CPU's have been proven to have a higher IPC and it's losing to an AMD...

 

I saw this on my feed for Facebook. Interesting. Can't say I really bothered to look into it since it was sponsored by AMD, so I figured it was a little...tainted.

It was sponsored by AMD? 

If it is... Didn't Intel get sued for sponsoring false benchmarks in the past?

RIP?

[SurvivorNVL]

I want AMD to succeed so badly, but this doesn't seem right at -all-.  

Edit:  Of course it isn't right.  I really hope it isn't AMD sponsored though.  That wouldn't make me feel all that happy

[xAcid9]

Inbe4 Faceman quote.

[Sintezza]

This is totaly no BS.

At 4K you are simply GPU limmited.

THe cpu doesnt make any significant diffrence at 4k gaming anymore.

With most gpu´s we have right now.

[dizmo]

This reeks of bullshit... Intel CPU's have been proven to have a higher IPC and it's losing to an AMD...

 

It was sponsored by AMD? 

If it is... Didn't Intel get sued for sponsoring false benchmarks in the past?

RIP?

I assume it was. They were touting it with their advertisement.

That alone is enough to turn me off of it.

[Faceman]

Can't.

[MegaDave91]

Not surprising given the GPU dominant nature of 4K. The i7 will wipe the floor with the FX during anything else.

[Sintezza]

lets make an example with some fictive numbers,

But what exaly could happen in real world scenario´s.

 

We play a game called X on 1080p and 4K with a GTX980Ti.

We use 2 cpu´s, a 4790K and a FX8370.

 

1080p, the 4790K + GTX980Ti will score higher on the frame rates, then with the AMD FX cpu.

The reason for this, is the GTX980Ti can simply push allot of frames at 1080p, then you need a cpu with a good per core performance to keep up with it.

Since intel haswell cpu´s have way better per core performance, the 4790K will automaticly perform better.

And the FX will bottleneck.

 

However, now we are going to play the same game at 4K with the same setups.

The GTX980Ti at 4k, is now not that powerfull anymore, and its only able to push half the frames that it could on 1080p.

The load on the cpu it self, isnt going to change at all wenn highering the resolution.

So in other words, you are getting GPU limmited.

 

lets say that the 980Ti in game X at 1080p pushed 100fps on the 4790k and just 70 on the FX8370, this could be a real world scenario.

On 4k (which is double the size of 1080p) it will basicly only be able to push 50fps, on which FX cpu has totaly no any problem keeping up with.

Remember the load on the cpu doesnt change much.

 

So FX cpu´s arent allways crap for gaming perse.

It simply highly depends on the situations, and the games you play.

And ofc how you play them.

[Paranoid Kami]

This is pretty normal for 4k from what I've seen of other benchmarks where the CPU doesn't really change much. Anyways, that being said, I hate how CPU benchmarks are not done in CPU intensive games. Want to not go below 20 FPS and crash during boss fights or WvW in Guild Wars 2? Better look at the Crysis benchmarks to find out which CPU to buy! Drives me insane.

[Biggerisbetter]

This for all the people who either cant read or research. Lets takes tomb raider as my example. Tomb is a CPU agnostic game, meaning fuck the cpu its all about graphics. Here is my proof tomb raider. Here is more proof

[Suika]

You get an entirely GPU dependent situation and expect to see the CPU render an additional 400 frames or something? I really hate 4K benchmarks in a CPU dependent scenario, it makes no damned sense.

[Sintezza]

Some people simply dont seem to understand at all lol

Which is realy funny.