• Competitor rules

    Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.

AMD Zen 5 rumours

alec said:
I actually think latency can explain all of it

In single thread Zen 5 is great, core-to-core latency doesn't affect it
In multithreaded tasks of embarassingly parallel nature (rendering etc), threads don't need to talk to each other, latency doesn't matter only thoughput does. So Zen 5 is good but sometimes held back by IOD bandwidth.

But there are a few benchmarks and modern games where its not fully loading all threads and they do need to talk. And thats the hit and miss area.
The few linux games benchmarked are mostly single thread and don't expose latency. Linux vs Windows is a red herring.

This now looks like a repeat of first gen Threadripper. Chiplets communicated to each other via main memory and caused all kinds of weirdness
Click to expand...

The first gen Threadripper issues was a memory timing issue. That’s why I mentioned flushing.
 
not compared the other ones but on cinebench how did they come up with this ? can we go back to cherry picking at least that was somewhat true
68TQZv1.png

VtEOUbD.png
 
uscool said:
not compared the other ones but on cinebench how did they come up with this ? can we go back to cherry picking at least that was somewhat true
68TQZv1.png

VtEOUbD.png
Click to expand...

Their marketing has clearly decided to go all in on misinformation. This is mild compared to their slides for 5700xt and 5900xt. Look at the hub review for those.
 
So what is the general feeling here? Upset that the performance is so poor or glad that we don't have to pay for a new upgrade yet?

I'm still waiting on the 9800X3D but unless they pull a blinder on that one I will find it hard to justify moving from my 5800X3D for another gen.
 
uscool said:
yeah but by looking at the end notes they used rx6600 so made sense for the results , but I cant understand this one
Click to expand...

The whole point of using a 6600 is to intentionally put out a false narrative.

You’d have to see what power profiles and TDP they used for arrive at that delta in CB. I mean even using a weak cooler and letting the cpu temp throttle can get you there.My point is their marketing is willing to do anything to arrive at whatever dataset is most convenient for them.
 
  • Like
Reactions: TNA
All of the marketing and numbers have been lies from what can see tbh. To point anyone on same software and games aren't even close to what they said. Massaging numbers sure with certain things.

The only thing I can imagine to get the figures they claimed is to have locked down Intels CPU at same power level honestly.
 
Marak said:
So what is the general feeling here? Upset that the performance is so poor or glad that we don't have to pay for a new upgrade yet?

I'm still waiting on the 9800X3D but unless they pull a blinder on that one I will find it hard to justify moving from my 5800X3D for another gen.
Click to expand...
Both honestly. Upset it worse than awful in my view. But yeah glad I can wait for another generation from both vendors and sit with my 5950x for another gen at least.
 
Curlyriff said:
Both honestly. Upset it worse than awful in my view. But yeah glad I can wait for another generation from both vendors and sit with my 5950x for another gen at least.
Click to expand...
Yep I would happily swap my 5800X3D for a 7800X3D/9800X3D if it was just a CPU swap but its a whole new mb and ram.

Thanks AMD looks like I'm saving my money a bit longer.
 
Marak said:
So what is the general feeling here? Upset that the performance is so poor or glad that we don't have to pay for a new upgrade yet?

I'm still waiting on the 9800X3D but unless they pull a blinder on that one I will find it hard to justify moving from my 5800X3D for another gen.
Click to expand...

Something is off and TSMC 4nm is a questionable choice. Zen5 is hit and mis so far.
 
Last edited:
uscool said:
not compared the other ones but on cinebench how did they come up with this ? can we go back to cherry picking at least that was somewhat true
Click to expand...

Handbrake and Blender are difficult ones to test as different encoders, different models and effects, etc. can change the results and some content or settings can be more AMD friendly than others. But those results aren't even close to what reviewers are coming up with - Blender for example over a few reviews averages at +23% and none are close to +56%. And Handbrake results average about +7% and none are close to +55% (the best case scenario on the touted Linux is just over 25%).
 
Last edited:
Marak said:
So what is the general feeling here? Upset that the performance is so poor or glad that we don't have to pay for a new upgrade yet?

I'm still waiting on the 9800X3D but unless they pull a blinder on that one I will find it hard to justify moving from my 5800X3D for another gen.
Click to expand...
depends really unless you have an 4090 and at 1440p can be cpu bound and chase high fps numbers, I currently have 5800x3d with 3080, I'll just be doing gpu upgrade when the new gpu stuff comes up I aint bothered chasing high as possible fps, if its north of 100fps thats fine
 
MLIDs claims:

1) Zen5 was launched in a state similar to engineering samples and with broken software. Hopefully performance can be fixed with future code updates.

2) AMD's marketing team completely lied and made up fake benchmark numbers; much of this is due to poor internal communication between marketing and engineering.




 
Last edited:
Grim5 said:
Hopefully performance can be fixed with future code updates.
Click to expand...
so far we have seen two knee-jerk panic reactions from AMD
- last second update reviewers guide and introduce CCD parking for Ryzen 9
- rumored AGESA update to bump TDP from 65W to 105W

instead I would have expected a press release saying they are aware of performance anomalies and these should be fixed soon
but since its the same people putting numbers on slides out of their ass... what you see is what you get
 
You must log in or register to reply here.
Back
Top Bottom