AMD Ryzen (Summit Ridge) Benchmarks Thread (use new thread)

Page 7 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.
Status
Not open for further replies.

cytg111

Lifer
Mar 17, 2008
23,534
13,107
136
dredsen said that these clocks were 500mhz shy of the rumors he heard. fits this bill.
 

Erenhardt

Diamond Member
Dec 1, 2012
3,251
105
101
Early 8 core prototypes (OR-A1) reached up to 3.6GHz at 95W. The fastest retail part at the same TDP operated 400MHz higher, three major and several minor revisions later (OR-B2G). The absolute fastest retail part, regardless of the TDP (125W) operated 600MHz higher than that (4.2GHz).
These are boost clocks, right? So a 400 to 600 MHz boost for Zen would be just shy of 4GHz
 

SpaceBeer

Senior member
Apr 2, 2016
307
100
116
In my opinion, this is good enough for 8c/16t ES. If the final product ends up at 3.0/3.4, it would still be good enough for many tasks. And I don't see why would be a problem to have 4c/8t CPU clocked at 3.5/4.0, similar to i7-4790 in both clock and performance. I think that is quite possible to achive and still be within 95W TDP range. If they release product with those specs and price <=200$, it would be a very good offer.
 
Aug 11, 2008
10,451
642
126
In my opinion, this is good enough for 8c/16t ES. If the final product ends up at 3.0/3.4, it would still be good enough for many tasks. And I don't see why would be a problem to have 4c/8t CPU clocked at 3.5/4.0, similar to i7-4790 in both clock and performance. I think that is quite possible to achive and still be within 95W TDP range. If they release product with those specs and price <=200$, it would be a very good offer.

Here we go again with the wishful thinking on pricing. 8 cores at 3ghz, Sandy/Ivy IPC, would be basically equivalent to 5820k in heavily threaded scenarios. Do you really think AMD would sell this for 200.00 or less?? Even the top end apus, with much less performance, were priced at nearly that on release (170 or 180 IIRC). As for the quad, it seems like a no brainer, but I believe AMD has specifically stated Zen will be 8 core only for the desktop.
 
Reactions: Arachnotronic
Mar 10, 2006
11,715
2,012
126
Here we go again with the wishful thinking on pricing. 8 cores at 3ghz, Sandy/Ivy IPC, would be basically equivalent to 5820k in heavily threaded scenarios. Do you really think AMD would sell this for 200.00 or less?? Even the top end apus, with much less performance, were priced at nearly that on release (170 or 180 IIRC). As for the quad, it seems like a no brainer, but I believe AMD has specifically stated Zen will be 8 core only for the desktop.

frozen, this happens every four years or so. AMD hypes up an upcoming architecture, enthusiasts who haven't seen this before get super hyped up about AMD potentially "sticking it to Intel" by offering a better and cheaper product, and then those enthusiasts are ultimately disappointed and then they begin to overreact and hate on AMD for not living up to their expectations.

This happened with Barcelona, this happened with Bulldozer, and I strongly suspect it'll happen with Zen. Just sit back, pop yourself some popcorn, and enjoy the show.
 

SpaceBeer

Senior member
Apr 2, 2016
307
100
116
Here we go again with the wishful thinking on pricing. 8 cores at 3ghz, Sandy/Ivy IPC, would be basically equivalent to 5820k in heavily threaded scenarios. Do you really think AMD would sell this for 200.00 or less?? Even the top end apus, with much less performance, were priced at nearly that on release (170 or 180 IIRC). As for the quad, it seems like a no brainer, but I believe AMD has specifically stated Zen will be 8 core only for the desktop.
I don't care about 8c/16t CPU, I was talking about 4c/8t version, which would fit somewhere between i5 and i7. Intel is now selling Skylake i5 for ~200$ (6500 or 6600) and i7-6700 for ~300$. So ST performance of potential 4c/8t Zen based CPU will be lower than i5, and MT performance would probably be between i5 and i7. Plus, those CPUs won't have IGP, so OEMs need to add ~50$ dGPU, if they won't to sell it to advanced home or business users. It will not be competitive product if it costs more than 250$. And last, but not least, there will be no "Intel Inside" on the box So therefore I expect it to be positioned where FX-8350 was at launch, around 200$
 

hrga225

Member
Jan 15, 2016
81
6
11
frozen, this happens every four years or so. AMD hypes up an upcoming architecture, enthusiasts who haven't seen this before get super hyped up about AMD potentially "sticking it to Intel" by offering a better and cheaper product, and then those enthusiasts are ultimately disappointed and then they begin to overreact and hate on AMD for not living up to their expectations.

This happened with Barcelona, this happened with Bulldozer, and I strongly suspect it'll happen with Zen. Just sit back, pop yourself some popcorn, and enjoy the show.

Oh,it will be cheaper than equivalent Intel CPU.AMD is minor player in market,that is their reality.
But that's about it.

Also,why are people jumping to conclusion about performance based on one preliminary result?We don't have enough information.We don't know TDP,cache size,cache speed,micro code revision and so many more things about this ES CPU.

But I have strong feeling that this post will be like speaking to the wall.
 
Reactions: Gikaseixas

SpaceBeer

Senior member
Apr 2, 2016
307
100
116
No it won't, but there is nothing else we can talk about at this moment We might get more official information on 23rd of August
 

AtenRa

Lifer
Feb 2, 2009
14,003
3,361
136
What ever the performance is, i sure hope they will not start the pricing at $600 for the 8C 16T because of the new 14nm process + 16 threads and then 2-3 months down the road cut the price down to half.
 

swilli89

Golden Member
Mar 23, 2010
1,558
1,181
136
So then AMD got the IPC increase they claimed, but had to sacrifice frequency to do so, as was expected.
This is an 8 core CPU.. even Intel has to scale down clocks at 8 cores and thats with them consuming more power, 120 watts TDP I believe compared to 95 watts for this very early Zen 8 core CPU.
 

cytg111

Lifer
Mar 17, 2008
23,534
13,107
136

I am confused I dont understand this post, you are quoting hrg225's post which is about not jumping to conclusions based on ES samples yet the only part of it you quote is about people being brick walls. IIRC you :

..
Anyway, I know there will be some who say "this isn't final" blah blah but at this point I have zero reservations just recommending Intel CPUs to anybody and telling them to not bother to wait for Zen.

So are you revising this stand on this point, or using the quoted block to.. what? at who?
I am not a smart man, help me out.
 

Phynaz

Lifer
Mar 13, 2006
10,140
819
126
This is an 8 core CPU.. even Intel has to scale down clocks at 8 cores and thats with them consuming more power, 120 watts TDP I believe compared to 95 watts for this very early Zen 8 core CPU.

You missed the point. What are the clocks on Piledriver currently?

This has nothing to do with Intel.
 

Insert_Nickname

Diamond Member
May 6, 2012
4,971
1,692
136
This is an 8 core CPU.. even Intel has to scale down clocks at 8 cores and thats with them consuming more power, 120 watts TDP I believe compared to 95 watts for this very early Zen 8 core CPU.

Intel only manages 2.1GHz with a boost to 3GHz on the 85W E5-2620v4. So if AMD can manage 2.8/3.2GHz@95W, it isn't half bad actually.
 

Sweepr

Diamond Member
May 12, 2006
5,148
1,142
131
Intel only manages 2.1GHz with a boost to 3GHz on the 85W E5-2620v4.

Xeon-D: 16C/32T @ 1.7 GHz or 12C/24T @ 2.3 GHz at 65W TDP

 
Last edited:

F-Rex

Junior Member
Aug 11, 2016
19
5
81
frozen, this happens every four years or so. AMD hypes up an upcoming architecture, enthusiasts who haven't seen this before get super hyped up about AMD potentially "sticking it to Intel" by offering a better and cheaper product, and then those enthusiasts are ultimately disappointed and then they begin to overreact and hate on AMD for not living up to their expectations.

This happened with Barcelona, this happened with Bulldozer, and I strongly suspect it'll happen with Zen. Just sit back, pop yourself some popcorn, and enjoy the show.

AMD did not hype anything this time. Amd Said zen would have ipc 40% higher than existing amd cpu... And this first leak seems to confirm it.
This ES works @2.8/3.2GHz which is quite low but we don't know if it's the max frequency achievable for zen or if it's the parametric/ FT yield sweet spot or if it's an amd strategy to hide Real zen max frequency or if it's the historical frequency at which ES are shipped to oem by AMD.

If AMD wanted to keep final zen frequencies closed to chest it would not act differently.
 
Aug 11, 2008
10,451
642
126
The 2.8/3.2 is probably the best they could do without raising the TDP above 95W.

Makes sense. The question then becomes will the final silicon be any better, and how much overclocking headroom will there be. At least for desktop gaming, I would think everyone would overclock. Unfortunately, the early results on polaris are not promising from an overclocking standpoint, but we dont know for sure if that is the GCN architecture or process limitation. In a way I am surprised they limited the TDP to 95 W, since the intel HEDT platform they are competing with has a 140 watt TDP.
 

Phynaz

Lifer
Mar 13, 2006
10,140
819
126
AMD did not hype anything this time. Amd Said zen would have ipc 40% higher than existing amd cpu... And this first leak seems to confirm it.
This ES works @2.8/3.2GHz which is quite low but we don't know if it's the max frequency achievable for zen or if it's the parametric/ FT yield sweet spot or if it's an amd strategy to hide Real zen max frequency or if it's the historical frequency at which ES are shipped to oem by AMD.

If AMD wanted to keep final zen frequencies closed to chest it would not act differently.

This late in the game they would most likely be doing validation at shipping frequencies.
 
Reactions: The Stilt

The Stilt

Golden Member
Dec 5, 2015
1,709
3,057
106
Makes sense. The question then becomes will the final silicon be any better, and how much overclocking headroom will there be. At least for desktop gaming, I would think everyone would overclock. Unfortunately, the early results on polaris are not promising from an overclocking standpoint, but we dont know for sure if that is the GCN architecture or process limitation. In a way I am surprised they limited the TDP to 95 W, since the intel HEDT platform they are competing with has a 140 watt TDP.

When Bonaire on 28nm HPx overclocks better than Polaris 11 on 14nm LPP and there are no major differences in the architecture, it's pretty telling.
 

laamanaator

Member
Jul 15, 2015
66
10
41
Makes sense. The question then becomes will the final silicon be any better, and how much overclocking headroom will there be. At least for desktop gaming, I would think everyone would overclock. Unfortunately, the early results on polaris are not promising from an overclocking standpoint, but we dont know for sure if that is the GCN architecture or process limitation. In a way I am surprised they limited the TDP to 95 W, since the intel HEDT platform they are competing with has a 140 watt TDP.
Well Polaris tells quite a lot about 14nm LPP and it's "overclocking" capabilities. Increasing the core frequency by 200MHz causes a 100w jump in power consumption. (~150W->250W) So I think that AMD did a good decision by keeping the TDP 95W, because a 125W part would get only slight increase in frequency, with much, much bigger power draw. That's if polaris's story tells anything about 14nm LPPs characteristics.
 

SpaceBeer

Senior member
Apr 2, 2016
307
100
116
When Bonaire on 28nm HPx overclocks better than Polaris 11 on 14nm LPP and there are no major differences in the architecture, it's pretty telling.
You could also make comparison between 380X and RX 470. Polaris has ~15% higher clock and ~50W lower TDP. So maybe 14LPP isn't that bad
 
May 11, 2008
20,041
1,289
126
That's not at all how it works.
Consoles have two separate dual-module CPUs (APUs) the console OS runs on the two first cores of the first CPU,and only on those two cores,leaving six cores for the game,now communication between the two CPUs is slower then communication within the same CPU so devs use the 4 cores of the second CPU for the demanding threads and the two "leftovers" for secondary threads (that's why you still see next to no scaling with over 4 cores)
Anyway the only reason we have bad console ports is because the consoles are not a multitasking environment, the games run all alone on their cores with nothing bothering them and devs just can't be bothered to adhere to multitasking rules so the games mess up windows's multitasking/task manager/whatever.

Well, i am very interested where you get that information about the communication between the modules.
I am interested in the details how it functions, but it is hard to find. I am not writing you are wrong, i am interested in what you know.

But i think you should see the bigger picture. Let us agree that the communication between the modules is too slow to for a true cpu unity to be seen by the programmer. I understand that jaguar cores are optimized for easy synthesis for to sell to different customers with possible different foundries. I read that the Xbox uses it Sram as inter communication medium between the modules, but i have this from "hear say". The PS4 seems to have multiple buses between the cpu modules and the memory.. I do not know how the modules communicate or the max bandwidth and latency.

Maybe, with the new PS4 and Xbox scorpio coming, they upgrade the interconnect fabric as well if it is really that worse. Both Sony and Microsoft seem to have a history of listening to what developers would like. If this is really an performance limiting issue. I assume they would tackle this with the new upcoming console revisions. Also, for Microsoft this would play in their cards of the idea of Microsoft everywhere. Windows 10 + DX12 and the xbox live integration in Windows 10 seems to confirm this. A more uniform programming model between the pc and the console would help(And then presenting a console alike pc to replace the pc for people who need a pc for average duties). And deprecating the use of the embedded sram for video graphic related operations will help for the console to pc port.

That bad console port consensus everybody has is also because the game developers have to sort of keep some abstraction layers that are detrimental for performance on the pc.
Close to the metal and proper programming with lot of options and defines for the game developer will help as Doom shows with their vulkan port. Also now that 8 thread ( note that i not say 8 core for the time being) pc become more present will be helpful. But it will be a while before there are true 8 cores on the majority of pc. Give it another year or two. And yes, not all cores are are used ofor the game on game consoles but that should be helpful for pc ports.


Although i am kind of drifting of the subject :
But when that happens, with the strength of pascal and of polaris (and future improved derivations of both architectures) starting from about 2018, we will see that unification. When HBM2 becomes more of a commodity in the pc market, it will also make the entrance in the console market.
And then HSA will be a natural part of the future pc/console (If that may be equiped Nvidia or AMD) . I suspect that for a while we will continue to see a separate GPU die and separate CPU die. Just because when 4k becomes mainstream and virtual reality takes of, the resolution will probably increase again(Of course up to the point that there is no need for it because the human eye retina can only detect so much). Creating a need for more computational power that an apu even with HBM2 for a given power envelope can provide. Nvidia is save for upcoming years. But it would help that by the time that AMD has mastered perfect HSA APUs, that Nvidia should also get an x86-64 license and Intel would master the idea of GPU design.

http://www.eurogamer.net/articles/digitalfoundry-2016-doom-tech-interview
 
Last edited:
Status
Not open for further replies.
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |