Leaked AMD Ryzen Benchmarks?

4y301f8q0ehy.jpg
 
Cinebench perf is pretty absurd.

I wonder if it translates into performance in other SMT-benefitting apps.
 
pendragon1 said:
now your post about my post is on the front page... wth?! o_O:)
Click to expand...

Your post imagelink didn't come through. I took a guess at what you were trying to post and just dropped the gif into the [H] forum so it's hosted here. Not trying to steal your thunder! Pendragon1 gets the credit for posting first!
 
Romeomium said:
Your post imagelink didn't come through. I took a guess at what you were trying to post and just dropped the gif into the [H] forum so it's hosted here. Not trying to steal your thunder! Pendragon1 gets the credit for posting first!
Click to expand...

Romeomium said:
View attachment 17589
Click to expand...
oh I know your not. that's weird though cause the gif is playing just fine n my system and phone... its out there and making ppl laugh that's the whole point! no biggie just funny to me.
 
lolfail9001 said:
If XFR's impact was 10% then Ryzen ends up only looking as good on IPC as Ivy/Sandy [assuming leaks are correct, of course]. And while for a first arch in the series it is pretty damn good, it would make me personally think twice whether to get Ryzen rig or not in the summer, since i am cooling limited in the first place. If it is just 100mhz (that's the leeway Passmark leaks have in regards to possible clocks between turboless ES and turbo enabled QS), then it makes XFR overhyped, but Ryzen as a whole stays pretty appealing. And if you meant to mean that XFR enabled on retail only, then it would be alright of course, as long as it does not overvolt the hell out of CPU, like AVFS on Bristol Ridge sometimes does.
Click to expand...

OK looks like it is as marginal as say Intel's Max Tech Boost 3.0 on Broadwell 6+ cores (extends a single core above the boost range ceiling by around 10%).
Linus is saying in his vid at around 1min 40s it can increase the core frequency from 4.0 to 4.1GHz (I assume though in this case all cores).
So manual OC is going to be needed, but then I think most were expecting that was the only way to get decent increase (allowing for the cooling).

Mentions at around 1min 40s and context for the 1800X, probably better relative improvement for 1700X as it has a lower max boost but would need to be validated in reviews:



I guess those expecting a lot from XFR are going to be critical, but if I can get 10% OC on the 1800X does it matter?
I must admit I thought XFR would go higher but in a dynamic and not sustained way.
For lower models seems it is still 100MHz increase above boost ceiling.
Cheers
 
Last edited:
CSI_PC said:
I guess those expecting a lot from XFR are going to be critical, but if I can get 10% OC does it matter?
I must admit I thought XFR would go higher but in a dynamic and not sustained way.
Click to expand...

This is with the stock cooler - XFR is supposed to scale with better cooling. No amount of RGB will make the cooling better, no matter how many +5hp stripes/stickers we slap on it. I am sure a better aftermarket air or water cooler will net a few more ghz! If this can hit 4.3-4.4ghz, I think it's a huge win. As always, wait for [H].
 
Color me excited that AMD might have just brought some competition back to the CPU realm. I'll be holding off for now, though. My 5820k @4.4 will likely hold me over for a bit longer. For my purposes, I think jumping to one of the rumored 1080tis would be a better upgrade right now.
 
Romeomium said:
This is with the stock cooler - XFR is supposed to scale with better cooling. No amount of RGB will make the cooling better, no matter how many +5hp stripes/stickers we slap on it. I am sure a better aftermarket air or water cooler will net a few more ghz! If this can hit 4.3-4.4ghz, I think it's a huge win. As always, wait for [H].
Click to expand...
Do you have an explicit quote for that though?
Linus says with appropriate cooling it will hit 4.1GHz for the 1800X, and 3.9GHz for the 1700X.
Seems ou need to manually OC and that is fine by me, XFR as I mention seems more comparable to the subtle behaviour of Intel's Turbo Boost Max Technology 3.0 Frequency (not the same as the normal boost frequency).

I guess the debate on XFR will continue until the reviews.
Cheers
 
Last edited:
Yea I saw the Linus video with all the pre built systems there, some on water. I don't care so much about the auto overclocking, I want to see what can be hit under manual controls and aftermarket cooling.
 
I agree with you. As always, a manual OC will net better results. Too lazy to look for the quotes right now, but with 25mhz stepping, we are likely to see small increases with XFR over stock. We also don't know if this is single core, or all cores, and how that functionality works yet.

No manufacturer will be willing to push things too far, so XFR is probably (hopefully?) a conservative number.
 
CombatChrisNC said:
Yea I saw the Linus video with all the pre built systems there, some on water. I don't care so much about the auto overclocking, I want to see what can be hit under manual controls and aftermarket cooling.
Click to expand...
Yeah totally agree,
but this is the 1st time we had some concrete info on XFR and this tech has generated interest with a broad spectrum of expectations on how it works.
Lolfail9001 was one of only a few who felt it did not work like normal extended overclocking and would be disappointing.
I felt it was subtle mechanism in same way as the Intel Max Tech 3.0 but all cores rather than single as with Intel, or if taking AMD slide literal indicated it was highly dynamic and not sustained.

But seems it is quite marginal and more static, not an issue in general as there is manual OC but has relevance as XFR has been discussed quite at length in the past.

Cheers
 
Last edited:
ryzen does not support 4k HDCP right? Still requires Kaby Lake for that?
 
Romeomium said:
I agree with you. As always, a manual OC will net better results. Too lazy to look for the quotes right now, but with 25mhz stepping, we are likely to see small increases with XFR over stock. We also don't know if this is single core, or all cores, and how that functionality works yet.

No manufacturer will be willing to push things too far, so XFR is probably (hopefully?) a conservative number.
Click to expand...
Linus showed the 25MHz granularity was working within the normal boost frequency range, does not just apply to XFR it seems.
This I think was on the demo running one of the games.
Cheers
 
CSI_PC said:
Linus is saying in his vid at around 1min 40s it can increase the core frequency from 4.0 to 4.1GHz (I assume though in this case all cores).
Click to expand...
Nope, single thread. Multi core boost on Ryzens shown runs at base or ~base+100Mhz frequency.
Plus, there are some serious hints that XFR or not, Ryzen simply does not clock that well in the first place past it's stock frequencies. Another case of AMD extracting all juice out of it's CPUs before overclockers.
Hints are: Zen die is actually AS DENSE AS A FREAKING POLARIS GPU. Plus, it requires almost 1.9V for 5.1Ghz Cinebench LN2 run... Have not seen such stuff in 10 years.

Anyways, i don't care about ya'll but my summer rig gets an R7 1700. If it won't go nuclear at 3.7Ghz all core, i am a happy ITX owner.
 
lolfail9001 said:
Nope, single thread. Multi core boost on Ryzens shown runs at base or ~base+100Mhz frequency.
Plus, there are some serious hints that XFR or not, Ryzen simply does not clock that well in the first place past it's stock frequencies. Another case of AMD extracting all juice out of it's CPUs before overclockers.
Hints are: Zen die is actually AS DENSE AS A FREAKING POLARIS GPU. Plus, it requires almost 1.9V for 5.1Ghz Cinebench LN2 run... Have not seen such stuff in 10 years.

Anyways, i don't care about ya'll but my summer rig gets an R7 1700. If it won't go nuclear at 3.7Ghz all core, i am a happy ITX owner.
Click to expand...
Have you solid proof of that in bold?
If multi-core only runs +100Mhz to base it would mean its SMT is much faster than Broadwell-E.....
The 1700X in Multi-core has a score that is 4% faster than a 6900K.

Broadwell-E will run at or very near max boost clock all cores for Cinebench (it can run nearly at full boost all cores with Prime95 and the Broadwell-E CPUs).
6900K frequency is 3.2 to 3.7GHz.
1700X frequency is 3.4 to 3.8GHz.

So are you really saying the 1700X has a 4% better score multi-threaded while running at base clocks against the 6900K with all its cores at 3.7GHz?
Does not add up to me, because that would be some sensational engineering by AMD that even senior tech journalist/engineers think AMD could only match at best Intel's SMT implementation.
Intel can run nearly at full boost up to 10Core, context being separate to the 4-core desktop CPUs.

Also comparing the 6900K to 1800X.
Multithreaded the 1800X is 9% faster but with frequency range of 3.6 to 4.0GHz.
So AMD has managed to find at least 12% more SMT performance than Intel considering they have the same single-threaded score, an area where senior engineers outside of those companies were expecting parity at best.
Cheers
 
Last edited:
what I understood is that the 1700/1800s launch first. I didn't/havent seen any mention of the lower chips.
 
razor1 said:
They are supposed to launch all at the same time. Don't know about retail sales though.
Click to expand...

From this paragraph from Anandtech,
With a new processor launch, naming the parts and positioning them within the market is critical. So with Ryzen, the processor stack will be split into three based on performance and price: Ryzen 7 at the high end, Ryzen 5 in the middle, and Ryzen 3 for more price-conscious consumers. Both Ryzen 5 and Ryzen 3 are set to be launched later, and Ryzen 7 is the first portion of the family to be released.

Ryzen 7 will have three CPUs to start, all having eight cores and supporting simultaneous multi-threading:

  • Ryzen 7 1800X: 8C/16T, 3.6 GHz base, 4.0 GHz turbo, 95W, $499
  • Ryzen 7 1700X: 8C/16T, 3.4 GHz base, 3.8 GHz turbo, 95W, $399
  • Ryzen 7 1700: 8C/16T, 3.0 GHz base, 3.7 GHz turbo, $329
Ryzen 7 1800X will be the high-end part, featuring a base clock of 3.6 GHz and a turbo of 4.0 GHz, within a TDP of 95W, and for $499. Next to this is Ryzen 7 1700X, launching at $399, with a base/turbo of 3.4/3.8 GHz. The final part for the launch is the Ryzen 7 1700, providing eight cores and sixteen threads for $329 at 3.0/3.7 GHz frequencies.

Processors will initially be available for pre-order from 185 retailers and OEMs worldwide, either as individual parts or pre-built systems.
Click to expand...

Seems like AMD isnt going to launch anything beyond these atm.
 
CSI_PC said:
Have you solid proof of that in bold?
If multi-core only runs +100Mhz to base it would mean its SMT is much faster than Broadwell-E.....
The 1700X in Multi-core has a score that is 4% faster than a 6900K.

Broadwell-E will run at or very near max boost clock all cores for Cinebench (it can run nearly at full boost all cores with Prime95 and the Broadwell-E CPUs).
6900K frequency is 3.2 to 3.7GHz.
1700X frequency is 3.4 to 3.8GHz.

So are you really saying the 1700X has a 4% better score multi-threaded while running at base clocks against the 6900K with all its cores at 3.7GHz?
Does not add up to me, because that would be some sensational engineering by AMD that even senior tech journalist/engineers think AMD could only match at best Intel's SMT implementation.
Intel can run nearly at full boost up to 10Core, context being separate to the 4-core desktop CPUs.

Also comparing the 6900K to 1800X.
Multithreaded the 1800X is 9% faster but with frequency range of 3.6 to 4.0GHz.
So AMD has managed to find at least 12% more SMT performance than Intel considering they have the same single-threaded score.
Cheers
Click to expand...

From AMDs own CB15 bench, it seems to suggest that:
4.1Ghz Ryzen matches Broadwell-E at 3.7Ghz in ST
3.9Ghz Ryzen matches Broadwell-E at 3.5Ghz in MT

That's assuming 100Mhz XFR.

We will see how it turns out when we see reviews.
 
CSI_PC said:
Have you solid proof of that in bold?
Click to expand...
Was in the video with LN2 run that went private. Or perhaps in linus one too. Did state outright, that r7 1700 (no-x) ran at 3Ghz in Handbrake demo against 7700k. Besides the leaks only work if my statement about boost is true, otherwise they do not work at all. Like Shintai's post illustrates ^_^
CSI_PC said:
If multi-core only runs +100Mhz to base it would mean its SMT is much faster than Broadwell-E.....
Click to expand...
It is, 5.14Ghz Zen beats 6Ghz Haswell-E in Cinebench.
 
Shintai said:
From AMDs own CB15 bench, it seems to suggest that:
4.1Ghz Ryzen matches Broadwell-E at 3.7Ghz in ST
3.9Ghz Ryzen matches Broadwell-E at 3.5Ghz in MT

That's assuming 100Mhz XFR.

We will see how it turns out when we see reviews.
Click to expand...
I am looking at the data just released.
1800X mult-threaded score 1,601
6900K multi-threaded score 1,474

1800X single threaded score 162
6900K single threaded score 162.

The clocks for the 6900K is 3.2GHz to 3.7GHz.
I know from other reviews the 6900K can sustain all its cores nearly at 3.7GHz even with Prime95, and other people can sustain high core Intel to max boost up to 10Cores.
Also it has the Max Tech 3.0 that boosts a single core to 4.0GHz - check ARK.

When Linus went around the systems, they gave the 6900K the best possible chance in terms of motherboard and RAM.

How are you coming to those frequencies for the 6900K with the Cinebench test?
Thanks
 
I wanna buy Jim Keller a beer, well done. Now lets hope Vega is competitive and we have AMD firing on all cylinders, attracting more talent and driving innovation further. Glad I told all my friends to hold off on builds, seems the gamble will pay off!
 
lolfail9001 said:
Was in the video with LN2 run that went private. Or perhaps in linus one too. Did state outright, that r7 1700 (no-x) ran at 3Ghz in Handbrake demo against 7700k. Besides the leaks only work if my statement about boost is true, otherwise they do not work at all. Like Shintai's post illustrates ^_^

It is, 5.14Ghz Zen beats 6Ghz Haswell-E in Cinebench.
Click to expand...

http://mirror.ninja/5vixv8
 
CSI_PC said:
I am looking at the data just released.
1800X mult-threaded score 1,601
6900K multi-threaded score 1,474

1800X single threaded score 162
6900K single threaded score 162.

The clocks for the 6900K is 3.2GHz to 3.7GHz.
I know from other reviews the 6900K can sustain all its cores nearly at 3.7GHz even with Prime95, and other people can sustain high core Intel to max boost up to 10Cores.
Also it has the Max Tech 3.0 that boosts a single core to 4.0GHz - check ARK.

When Linus went around the systems, they gave the 6900K the best possible chance in terms of motherboard and RAM.

How are you coming to those frequencies for the 6900K with the Cinebench test?
Thanks
Click to expand...

A 6900K doesn't run all cores as stock at 3.7Ghz. And if it was optimal it would score around 1540 in MT. It does however run 3.7Ghz at ST boost. The boost 3.0 is driver based and needs manual setting.
 
You must log in or register to reply here.
Back
Top