Question Zen 4 builders thread

Page 30 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

Markfw

Moderator Emeritus, Elite Member
May 16, 2002
25,740
14,772
136
Your CPU is not on 24/7 so yours is probably running colder due to that.

Interesting how AMD Implementation of AVX-512 Is every bit as good as Intel's implementation
I was running 32 threads/tasks of WCG at the time, I did not pause them. And I am running -25 CO/PBO.

I guess the small difference proves you can save power and not affect your performance much.
 

Chaotic42

Lifer
Jun 15, 2001
33,929
1,098
126
Bluetooth and USB3 on my motherboard seem to be freaking out systemd-udevd on Debian 11.5. It's constantly refreshing them burning up one core. Disabling BT is fine, but USB3 is a little more important. Anyone else running Zen 4 on Linux?
 
Reactions: lightmanek

Markfw

Moderator Emeritus, Elite Member
May 16, 2002
25,740
14,772
136
Bluetooth and USB3 on my motherboard seem to be freaking out systemd-udevd on Debian 11.5. It's constantly refreshing them burning up one core. Disabling BT is fine, but USB3 is a little more important. Anyone else running Zen 4 on Linux?
Mint 20.3. What am I supposed to notice ?
 

Det0x

Golden Member
Sep 11, 2014
1,055
3,087
136
Can any of you good folk make a CPU-Z AVX-512 Bench and see what it gets? Thanks.

Hi!
Did you manage to test what can be achieved in MT (e.g. CBR23 or Blender bench 3.3 / LinpackX) in OC mode? How's the cpu behave (temps, power) and what OC voltage and frequency were set?
And how does the behavior and performance when OC'ed compare to PBO2 tuned curve and, let's say 300W PPT, current/thermal limits maxed out (and what their peak values were, especially EDC)?
I will share some real benchmarks shorty, just need to figure out what i need to hide first ^^
 

Det0x

Golden Member
Sep 11, 2014
1,055
3,087
136
Hi!
Did you manage to test what can be achieved in MT (e.g. CBR23 or Blender bench 3.3 / LinpackX) in OC mode? How's the cpu behave (temps, power) and what OC voltage and frequency were set?
And how does the behavior and performance when OC'ed compare to PBO2 tuned curve and, let's say 300W PPT, current/thermal limits maxed out (and what their peak values were, especially EDC)?
Y-cruncher madness

25mil = 0.321s


1b = 15.546s


2.5b = 43.169s


Next up we have Cinebench galore

R11 = 4.04 ST and 76.19 MT


R15 = 347 ST and 7013 MT


R20 = 847 ST and 16566 MT


R23 = 2182 ST and 42719 MT


When i need to travel and take the files with me

7-Zip v19 = 261088 MIPS


Newer 7-Zip v22 = 267.759 GIPS


Next post will be 3dmarks with 7950x+3090 results
 

Chaotic42

Lifer
Jun 15, 2001
33,929
1,098
126
I don't know what I am looking for or at, here is top sceenshot
View attachment 69663

Interesting. Here's mine:



It's constantly polling the USB 3.0 and BT controller for some reason. I can only find spotty information on it online, and the fix involves messing with some systemd config files which are large and device specific. I'm not super worried about it, it's just kind of weird.
 

Det0x

Golden Member
Sep 11, 2014
1,055
3,087
136
...continuation of my bench marathon










Zen4 seem really strong in firestrike cpu bench (physics score) ^^

CPU profiler ST and max threads:


 

Det0x

Golden Member
Sep 11, 2014
1,055
3,087
136
Did also managed to update some of my geekbench scores, here are the current standing:







Other random benchmark:

Passmark global score = 14,243



A few game benches left then i'm done
 

gdansk

Platinum Member
Feb 8, 2011
2,489
3,379
136
I finally found some DDR5 ECC UDIMMs in stock. So I order 2x32GB. I wonder if it will work in ECC mode in Windows. I somehow doubt it will work as ASRock removed ECC support from the product page in between the time I ordered the motherboard and now. But I continue the experiment regardless.

I'll post an update for anyone else curious when it arrives.
 
Last edited:

Chaotic42

Lifer
Jun 15, 2001
33,929
1,098
126
Out of curiosity, I ran Linpack Xtreme and got these results. s-tui claims my CPU isn't getting above 43C, which seems a little suspect.



Edit: This is having hopefully killed off the systemd resource issue.
 

Det0x

Golden Member
Sep 11, 2014
1,055
3,087
136
Nice, thanks!
Have you used any of Yuri's tool to configure your CPU or it's just PBO2?
(clocks spread looks unusual in GB5 log)
Yuri haven't shared any tools as far as i know (?)
Have mostly been playing around with that asus tool, can pretty much do everything there

But those GB runs above were done with plain old PBO + CO +"midboost" as it called in asus bios.. It basically disregard the 5.5ghz boost -lock limit for allcore workloads (in light memory stresstest its normal to see ~~5850/5600mhz allcore boosting)
 
Reactions: Kaluan

ericgandt

Junior Member
Sep 25, 2011
12
1
71
I have a 7950X, also have a ASUS Pro ART and MSI MEG ACE MB (for other very painful reasons), on both platforms, I've noticed that remote connections are always stable and local connections are stable until I install the AMD drivers (including the latest Adrenalin 22.10.2 WHQL),
On the MEG ACE Windows locally just hangs on 3 of 4 boots after a short period, the other never had issues (my guess is the driver had crashed and was not restart on that one, but only a guess)
On the ProART Windows will hang, but more likely I get errors that the Adrenalin software has crashed is running in safe mode, this repeats regularly while flickering the screen, often it to will hang Windows after a few of these occur.

Both occurrences seem very odd as I'm not using the iGPU output but an NVIDIA card, in all cases simply not installing the software (and then disabling the device to be safe, but not required) solves the issue, but seems strange, almost as if the CPU has a bad GPU. This occurs on two MB. and both Windows 10 and Windows 11, so that is 4 different combinations, yet a fifth I only tried using the MEG ACE (Kubuntu 22.10 has not issues again using the NVIDIA card for output) so it seems like either a iGPU issue or a serious driver issue to me, thoughts?

For now I've simply disabled in Windows, as I can not find any BIOS option to disable on the Port ART (which is what I'm using now). But I would like a better solution.

ERIC
 
Reactions: igor_kavinski

alexruiz

Platinum Member
Sep 21, 2001
2,836
556
126
I have a 7950X, also have a ASUS Pro ART and MSI MEG ACE MB (for other very painful reasons), on both platforms, I've noticed that remote connections are always stable and local connections are stable until I install the AMD drivers (including the latest Adrenalin 22.10.2 WHQL),
On the MEG ACE Windows locally just hangs on 3 of 4 boots after a short period, the other never had issues (my guess is the driver had crashed and was not restart on that one, but only a guess)
On the ProART Windows will hang, but more likely I get errors that the Adrenalin software has crashed is running in safe mode, this repeats regularly while flickering the screen, often it to will hang Windows after a few of these occur.

Both occurrences seem very odd as I'm not using the iGPU output but an NVIDIA card, in all cases simply not installing the software (and then disabling the device to be safe, but not required) solves the issue, but seems strange, almost as if the CPU has a bad GPU. This occurs on two MB. and both Windows 10 and Windows 11, so that is 4 different combinations, yet a fifth I only tried using the MEG ACE (Kubuntu 22.10 has not issues again using the NVIDIA card for output) so it seems like either a iGPU issue or a serious driver issue to me, thoughts?

For now I've simply disabled in Windows, as I can not find any BIOS option to disable on the Port ART (which is what I'm using now). But I would like a better solution.

ERIC

If you are not using the iGPU, disable it at the UEFI
There is no reason to install AMD graphics drivers, so uninstall it.
Make sure you are installing chipset drivers. A lot of people overlook them, but they are extremely important. Grab them from AMD's website
 

AdamK47

Lifer
Oct 9, 1999
15,313
2,915
126
I tried something that may seem counterintuitive. I wasn't able to pass Prime95 small to large FFT with a -10 in Core Optimizer. It would fail between 30 minutes to an hour. I added a +0.0250 offset to the CPU voltage. I'm still seeing a performance improvement despite the added voltage offset. The same tests that failed earlier now pass. Even a -12 passes.
 
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/    |