German Site Jumps the Gun on Ryzen 3000 Benchmarks

Zarathustra[H]

Extremely [H]
Joined
Oct 29, 2000
Messages
38,739
If you ask me, this is pretty much what I expected.

Pretty much what I expected. Trading blows depending on the title, trailing slightly in the games which are more highly dependent on a single fast thread, but in every case fast enough that you are probably going to be GPU limited before you are CPU limited at typical settings.

I haven't played Far Cry 5, but from my experience with other Far Cry games, the Dunia engine (modified Crytek engine for open worlds) they use always pins the third core, so it is not surprising at all yo me that it may be a worst case title for Ryzen.

I for one am looking forward to getting a 3950x and overclocking the snot out of it.

Credit for finding the link goes to LstOfTheBrunnenG
 
Last edited:
Moved this to the news thread if you don't mind.

I also find it strange they are doing 720 resolution testing. Literally nobody games at that resolution...

It is on purpose. This is always how CPU benchmarks are done.

In every title I've ever tested, at a fixed framerate, changing resolution/graphics settings has no impact on CPU load. Because of this it makes sense to run it at the absolute minimum resolution/graphics settings so that your benchmark figures are not GPU limited.

It is a CPU review, not a full system review, so this way you can see what the CPU is capable of independent of the GPU.

You - of course - have to read these charts with a little intelligence, and realize that depending on your GPU chances are in real world gameplay, you'll never see those framerates due to being GPU limited, and realize that this means that due to GPU limitations many of the top performing CPU's will perform identically in normal use.

It involves a risk that people misinterpret the results, but I don't see how else they could do it and still get to the actual performance of the CPU.
 
What's with Crysis 3 causing 3900x to suck so much powah
 
Apparently they didn't actually retest any of their old CPU tests, and since all the security mitigations are apparently included in the latest version of windows... it seems as though the intel chips probably don't do as well as suggested here... I guess we'll have to wait and see what other sites show up with.
 
Apparently they didn't actually retest any of their old CPU tests, and since all the security mitigations are apparently included in the latest version of windows... it seems as though the intel chips probably don't do as well as suggested here... I guess we'll have to wait and see what other sites show up with.

This could very well be. I'm hoping the good folks over at thefpsreview.com have samples and are doing this retesting with all the latest patches in place.
 
I looked a little further at this, they didn't actually test the intel cpu's on latest windows updates, so this is a bit of a misleading review I think, if all the mitigations are in the new windows update then they should be tested as such.

How did you find this? I thoght only the images from that German site were captured. Not the body of the article and any test methodology?
 
Moving to news post:

da fuk
so far leaks have been literally all over the place, from the 3600 beating the 9900k in gaming, to this shit... I don't buy it until I start seeing actual reviews...

It probably depends very much on which titles you benchmark it in. It's a different architecture than Intels, so we wouldn't expect it to scale linearly in every title. IN some it will do better, in some it will do worse. Far Cry 5 is probably a worst case due to the Dunia engine always seeming to want to pin the third core on every system it runs on.
 
Almost same performance and lower power consumption - pretty impressive for a fraction of the R&D and a less 'mature process'.
But of course power consumption only matters when it's AMD, because 5,000MW for 2% faster in some games is so [H].

Either way interesting to see minimums are very good if it isn't top of a game benchmark. Wonder if more optimization can help there.
 
Moving to news post:



It probably depends very much on which titles you benchmark it in. It's a different architecture than Intels, so we wouldn't expect it to scale linearly in every title. IN some it will do better, in some it will do worse. Far Cry 5 is probably a worst case due to the Dunia engine always seeming to want to pin the third core on every system it runs on.

The whole article is here:
 
Apparently they didn't actually retest any of their old CPU tests, and since all the security mitigations are apparently included in the latest version of windows... it seems as though the intel chips probably don't do as well as suggested here... I guess we'll have to wait and see what other sites show up with.
AMD benchmarks were the same so people couldn't bitch about that. With patches it will be very interesting to see if any gains are made by AMD, also latest win10 release gave quite a few Zen users a boost in some titles.

IDFrga salt harvest is forecast to be 50% over last quarter!
01_photo.jpg
 
Either way interesting to see minimums are very good if it isn't top of a game benchmark. Wonder if more optimization can help there.

This is part of the problem with not knowing their methods and test details.

If I recall, Win 10 1903 supposedly brings a bunch of Ryzen 3000 specific scheduling enhancements. No way of knowing if they used 1903 or not.
 
  • Like
Reactions: N4CR
like this
These are good results, though not as impressive as what the Spanish site leaked earlier. I'll certainly be eager to read the full reviews on Sunday/Monday. I do find it interesting the listed Cinebench single thread score - no appreciable difference between the 3700X and the i9-9900K!
 
  • Like
Reactions: N4CR
like this
Also I'd love to see overclocked results, as that's all that really matters to me anyways as I'm not gonna be running stock ever.
 
Also I'd love to see overclocked results, as that's all that really matters to me anyways as I'm not gonna be running stock ever.

Ditto. Other than a baseline stability test, once I get mine, I'm not even going to bother running anything until I have it at the max overclock my water loop can support.
 
Adjusted for me.

The ryzen 5 3600 will literally have twice the performance of the 3770k in the laptop I have been using the last 8 years.

I usually like doing a stability test with everything stock before I start overclocking just so I know I have a properly functioning system.
 
Last edited:
I'll wait until all the reviews are out. Leaks always smell like covert marketing.
 
Almost same performance and lower power consumption - pretty impressive for a fraction of the R&D and a less 'mature process'.
But of course power consumption only matters when it's AMD, because 5,000MW for 2% faster in some games is so [H].

Either way interesting to see minimums are very good if it isn't top of a game benchmark. Wonder if more optimization can help there.


Ya power consumption only matters for gpu's :p
 
So i can't tell if this is good or not? The 9700k is $329 at micro-center the 3700k is $329.
 
This is part of the problem with not knowing their methods and test details.

If I recall, Win 10 1903 supposedly brings a bunch of Ryzen 3000 specific scheduling enhancements. No way of knowing if they used 1903 or not.


According to the interview with Robert Hallock, 1903 fixed the CCX scheduling issues where windows would assign a thread to one CCX and the other to the second CCX despite the first one have idle cores.

This results in a small to very large penalty (as seen with 32c64t TR with Windows vs Linux).

The 1903 fix applies to every Ryzeb release. Will it help Zen2 SKUs more? Possibly. I'm sure AMD worked hard with MS to clean up their mess.
 
  • Like
Reactions: c3k
like this
According to the interview with Robert Hallock, 1903 fixed the CCX scheduling issues where windows would assign a thread to one CCX and the other to the second CCX despite the first one have idle cores.

This results in a small to very large penalty (as seen with 32c64t TR with Windows vs Linux).

The 1903 fix applies to every Ryzeb release. Will it help Zen2 SKUs more? Possibly. I'm sure AMD worked hard with MS to clean up their mess.


If these leaks are accurate, I am very impressed. Wish we would have seen a 3800X in there as well so even with OC data we would see what the chip would do with the extra TDP.

I think I'm going to save $70 and rolll the dice on the 3700. Still unsure. Thinking of grabbing a Navi 50th as well to see how it does and maybe replace my VII or just keep both.
 
If these leaks are accurate, I am very impressed. Wish we would have seen a 3800X in there as well so even with OC data we would see what the chip would do with the extra TDP.

I think I'm going to save $70 and rolll the dice on the 3700. Still unsure. Thinking of grabbing a Navi 50th as well to see how it does and maybe replace my VII or just keep both.
well the VII is definitely going to be much better than the 5700xt so that'd be a definite downgrade
 
The updated (as of 7/5) chart makes no sense. An i9-9900 @ 3.1Ghz scoring higher than an i9-9900K @ 3.6GHz? Certainly not the only oddity that stands out with that list. Is this a list of golden runs? Are the contributions from random sources?

Also worth noting are the clocks of Ryzen 3000 series are not specified. Kind of important given the context of the benchmark.
 
The updated (as of 7/5) chart makes no sense. An i9-9900 @ 3.1Ghz scoring higher than an i9-9900K @ 3.6GHz? Certainly not the only oddity that stands out with that list. Is this a list of golden runs? Are the contributions from random sources?

Also worth noting are the clocks of Ryzen 3000 series are not specified. Kind of important given the context of the benchmark.
yeah I don't really trust passmark or any of those sites that show up when you search X CPU vs Y CPU on google...
 
The updated (as of 7/5) chart makes no sense. An i9-9900 @ 3.1Ghz scoring higher than an i9-9900K @ 3.6GHz? Certainly not the only oddity that stands out with that list. Is this a list of golden runs? Are the contributions from random sources?

Also worth noting are the clocks of Ryzen 3000 series are not specified. Kind of important given the context of the benchmark.

the i7 9900 can turbo up to 5ghz and it's single threaded and it's margin of error when you consider both the 9900k and 9900 have the same boost clocks.

care to wager what the i7 9900kf boosts to?
 
the i7 9900 can turbo up to 5ghz and it's single threaded and it's margin of error when you consider both the 9900k and 9900 have the same boost clocks.

care to wager what the i7 9900kf boosts to?
If clock boosts are dictated by uncontrollable variables such as temperature, power, and the almighty golden run, then I'll pass on whatever number marketing cooks up.

Also, if that represents margin of error, then all those at the top of the list are effectively equal.
 
If clock boosts are dictated by uncontrollable variables such as temperature, power, and the almighty golden run, then I'll pass on whatever number marketing cooks up.

Also, if that represents margin of error, then all those at the top of the list are effectively equal.

i'm sure that's great news for intel that it's upper echelon 9900k with the 500 dollar price tag is equal to AMD's mid line 199 cpu in single threaded benchmarks.
 
These threads always turn into salt mines because people can't stand that AMD has finally caught up.

I for one welcome our new AMD overlords.

I am happy AMD caught up, will likely buy a 12 or 16 core Ryzen but I still find AMD has more nuances.

Given Intel has random security issues that drop performance, I suppose I’ll stick with AMD....
 
As always, take early reviews with a grain of salt unless you explicit trust the source. We don't know how rushed this review is or what, if any, verification was done on these benches to make sure they are accurate.
 
i'm sure that's great news for intel that it's upper echelon 9900k with the 500 dollar price tag is equal to AMD's mid line 199 cpu in single threaded benchmarks.
Based on your recommendation, I'll be sure my next purchasing decision is based purely on Passmark.
 
Back
Top