AMD "Summit Ridge" ZEN CPU at 2.80 GHz Beats 3.40 GHz Core i5-4670K

[Sempron Guy]

Bwaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaahahahha wow. AMD is the problem bud. People get irritated at THEIR claims, not these leaked benchmarks. The leaked benchmarks are where people first to start FACEPALM off of their claims.

WCCFTECH was the cesspool for "leaks" and "rumors" prior to Bulldozer launch. People literally took it like it's the bible. Sure AMD may have claimed some but these sites did quite a job hyping up even the smallest of bs info.

 

[GhostRyder]

I rarely take anything from WCCFTech as fact. That being said if its at least close to that it will be an interesting chip especially if they price it right. Whats going to matter is how well it clocks, its single threaded performance, and its price. If it hits the marks, then we could finally have some competition again which may bring Intel's 6+ core processors down to a much more reasonable price.

 

[64K]

I rarely take anything from WCCFTech as fact. That being said if its at least close to that it will be an interesting chip especially if they price it right. Whats going to matter is how well it clocks, its single threaded performance, and its price. If it hits the marks, then we could finally have some competition again which may bring Intel's 6+ core processors down to a much more reasonable price.

Competition, Intel needs it in a serious way. I hope they get it with Zen.

 

[medi01]

I wish I knew more about the config.
Not even clear if dedicated GPU was used.

New 8C/16T cpu is slightly faster than old 4C/4T. What a shocker.

New CPU manufactured on process outside Intel's Fab can keep up with it's mid range chips, for the first time since... when, do you remember?

It IS a big deal.

 

[EarthDog]

This engineering sample has a max turbo frequency of 3.2GHZ. The i7 4970's turbo frequency is 4GHz, which 25% higher. If you look at the graph a few posts above this one, you'll see that the i7 4970 is ~9% faster than the 8-core i7 5960X at 3.5GHz.

That is single core...these are multithreaded tests.

 

[Bluescreendeath]

I see some thing good but it's no excellent, looks pretty sub par so far. I do know that i have less hope due to this news.

Price is were it's going matter for a lot of people.

You could all so look at that as 30 playable and 23fps not playable and some 60 playable and 53 not.

That is not how fps scaling works. 23 fps vs 30 fps is 76% performance. 53 fps vs 60 fps is 88% performance. If you apply the same percentage of 88%, you get 26-27 fps vs 30 fps.

 

[G33k2Fr34k]

That is single core...these are multithreaded tests.

What's single core? The graph shows an i7 6700 beating the 8-core i7 5960X. It seems that the AOS benchmark favours higher frequency quad cores over lowered clocked +4-core cpus.

 

[theeldest]

As a point of reference, when Bulldozer numbers were leaked on Engineering Sample chips (A0 stepping) they were at 2.6GHz. When the chips released they launched at 3.6GHz.

 

[RejZoR]

These low clocked ES CPU's are just that, engineering samples. They use them to check if everything is in order architecture, cache and instructions wise. Once they have all that in check, they start properly fiddling with clocks. I mean, essentially this is their base clock they work with, then they can basically overclock them and see how they behave electrically and thermally. It is possible these will ship at 4-4.2 GHz just like 6700K. That one is clocked very high out of the box as well.

 

[EarthDog]

What's single core? The graph shows an i7 6700 beating the 8-core i7 5960X. It seems that the AOS benchmark favours higher frequency quad cores over lowered clocked +4-core cpus.

Turbo.. at least Intel's. I think AMD's work the same in that the higher in frequency you go, the less cores go with it.

In other words, the turbo doesn't matter in multi-threaded tests as when using all cores, the 'turbo' is lower.

 

[Peter1986C]

Indeed. For example the X4 740 I use runs at 3.5GHz (turbo) when more than one core is heavily loaded. Its absolute maximum is 3.7GHz.

 

[Prima.Vera]

Competition, Intel needs it in a serious way. I hope they get it with Zen.

For their Core i3, yes, this will be their main competitor.

 

[TheoneandonlyMrK]

That's a bit harsh its easy to pick out games which favour a CPU ,I'd bench my rig against an I3 and gpu combo in Aos and doom for example and my 8350 wouldn't look so bad.
ES says it all ,good times perhaps ahead.

 

[qurotro]

I see some thing good but it's no excellent, looks pretty sub par so far. I do know that i have less hope due to this news.

Price is were it's going matter for a lot of people.



You could all so look at that as 30 playable and 23fps not playable and some 60 playable and 53 not.

as i can tell the different between a 60hz screen and a 100hz screen by simply moving the mouse...60 is the basic for gaming

 

[NicklasAPJ]

No one said this is a flagship model. Also, have you seen the clocks?

The 8 Core/16 Thends, will be AMD flagship for Desktop user.

Is old news. we knew 40 days ago that the CPU have 2.8Ghz Base clock and 3.2Ghz boost clock.

 

[TheLaughingMan]

The 8 Core/16 Thends, will be AMD flagship for Desktop user.

Is old news. we knew 40 days ago that the CPU have 2.8Ghz Base clock and 3.2Ghz boost clock.

No. We were told that was the frequency of the Engineering samples that were released. That doesn't mean this is a final product or a fully functional chip. This could be a quickly produced test chip to run real world tests on L3 cache, single thread performance, multi-thread testing, etc. For all we know this was just clock speeds they could safely guarantee the system wouldn't crash. Especially consider there is a D1 and D2 sample, something about those chips is different like missing L3 cache, disabled cores, etc.

What I am saying is, despite the source, there is no reason to consider this as reliable. I will wait until they are on final release Eng. samples that have actually been full tested with the retail configuration.

 

[bug]

Let's compare this result to one that was done by a i7 8 core-16thoreads owner guys. Not sure this game fully utilizes more than 6-8 threads in total. A wprime benchmark result would be great for this type of comparisons. And a single-threaded one also to compare the IPC where was the weakness for AMD CPUs and Zen is supposed to cure.

Eh, we're going to need a hell of a lot more benches than that. But until it's released on can only get glimpses at most and gouge our eyes out in the forums, trying to tell the other guy how we've got the right picture and he doesn't. Again

 

[dyonoctis]

Well at least we know that's it's better than a current FX. The FX were already good in heavily multithreaded app, this zen might blew it out of the water. If the pricing is right Zen might be the way to go for 3D rendering/ Video encoding computer. If 6 core/12thread become mainstream, adobe may finally make photoshop use more than 4 thread. When you are working with huge file and fancy brush things can get slugglish.

 

[WaroDaBeast]

We all make mistakes. Now corrected thanks to @Caring1 for pointing it out.

My error was to simply use 'negligent' logic, where 8 is 50 % of 16, 4 is 50% of 8, therefore (falsely) 100% less than 16. Of course, 4 is 75% less than 16.

You know, mathematical mistakes are often actually very interesting. They can almost seem logical.

No probs. Thanks for clarifying.

 

[AsRock]

as i can tell the different between a 60hz screen and a 100hz screen by simply moving the mouse...60 is the basic for gaming

And yet many claim running 120Hz with 120fps is better than running 60Hz with 60fps.

How ever you look at it to me 7 fps is a lot imo for the games i play and keeping it above 30-35fps is a priority, were some claim they are not happy gaming with any thing less than 60fps.

In the end not all people are the same or require the same, i remember i was not able to use CRT screens lower than 75Hz back in the days( i can see the flicker very easy ). But gaming i am perfectly fine as long as it's over 30fps with LCDS.

In the end it don't matter until real benchmarks are released. As hell if i am going buy a AMD cpu just because it runs A game well which to me this benchmark don't really show that.

Time will tell if Zen makes it or not, i hope so as AMD needs it.

 

[silentbogo]

It slightly reminds me of this video

Deceptive benchmarking in which a 4C AMD FX9800p at 3.6GHz beats a dual-core i7-6500U at 3.1GHz by running Dota 2 at unplayable FPS.
And that was just one of many such videos, including a redemption campaign for their 7th gen mobile APUs, and identical benchmarks for FX8800P (which is not a bad CPU, just misadvertised and mishandled by OEMs)

 

[dyonoctis]

It slightly reminds me of this video

Deceptive benchmarking in which a 4C AMD FX9800p at 3.6GHz beats a dual-core i7-6500U at 3.1GHz by running Dota 2 at unplayable FPS.
And that was just one of many such videos, including a redemption campaign for their 7th gen mobile APUs, and identical benchmarks for FX8800P (which is not a bad CPU, just misadvertised and mishandled by OEMs)

I don't really see this as deceptive. This benchmark was all about showing how a R7 igpu is faster than a HD graphics 520 igpu. 30-40 fps is playable if you are not an hardcore player. 30fps is the absolute minimum for gaming, 60 fps is really just a comfort zone.(excluding fps games). at 0:58 they even point out the setting used.

 

[HumanSmoke]

WCCFTECH was the cesspool for "leaks" and "rumors" prior to Bulldozer launch. People literally took it like it's the bible. Sure AMD may have claimed some but these sites did quite a job hyping up even the smallest of bs info.

Sorry, but that is largely erroneous. The principle source of (mis)"information" regarding Bulldozer prior to it's launch was a high profile user going by the moniker "JF_AMD" on various high profile forums such as Anandtech, and OCN. "JF_AMD" was/is John Fruehe - who was as the the time Senior VP of AMD's Server Sales. Fruehe is moderately famous for using his title/standing to have forum members banned if they disagreed with his assertion that Bulldozer would have a much higher IPC than the existing k10.5 architecture despite mounting evidence to the contrary. Fruehe was let go - in large part, some people suspect - to the adverse publicity this generated, and AMD's subsequent dismal server sales.
AMD, during the 2009-10 timeframe also tended to use Donanimhaber as a semi-offical leak source. I don't think wccftech was much of an entity six years ago.

 

[Hockster]

So it's almost as fast as two year old mid range CPU's? Oh goody.

 

[G33k2Fr34k]

Turbo.. at least Intel's. I think AMD's work the same in that the higher in frequency you go, the less cores go with it.

In other words, the turbo doesn't matter in multi-threaded tests as when using all cores, the 'turbo' is lower.

Ok... that still doesn't count as a response to what I said. It's still early to make conclusions about it, but I'd rather see the eight core Zen compared to an 8 core Haswell or Skylake in this benchmark.