Author Topic: dual CPU issues?  (Read 15607 times)

2024-01-05, 10:17:16
Reply #30

andrew1988

  • Active Users
  • **
  • Posts: 11
    • View Profile
have you found the sollution in the end ?
I have some issue with you with my new build dual XEON 8480+


Oh my god!

I just assume my RAM was working in quad channel (octo in 2 slots), using 4 sticks per cpu (8 in total). In fact, typical monitor software tells me my RAM is working in quad-channel, but I didn't try to populate all dimms (cos My boards have 16 slots!).

I will try this solution but I have to buy RAM to check it cos I don't have 16 RAM sticks...

2024-01-08, 11:46:33
Reply #31

Nejc Kilar

  • Corona Team
  • Active Users
  • ****
  • Posts: 1333
    • View Profile
    • My personal website
If it helps knowing I'm running a dual Epyc build that has 8 memory slots per CPU (16 total). Just for the fun of it I tried running the benchmarks (and one rather simple interior) in a 8 sticks vs 16 sticks scenario.

The results were for all intents and purposes identical between the two configs.

I do think that going with less than 8 sticks though would result in slower rendering - I haven't tested it out though.

Do note that each platform can be a bit different so the above might work for my 7B13 Epycs but might not for your dual Xeons.
« Last Edit: 2024-01-09, 10:35:00 by Nejc Kilar »
Nejc Kilar | chaos-corona.com
Educational Content Creator | contact us

2024-01-10, 11:59:32
Reply #32

andrew1988

  • Active Users
  • **
  • Posts: 11
    • View Profile

thanks for your reply !
yes , it have 4 sticks per socket installed , 8 in total, memory runs on quad channel

every benchmark tool runs perfect but the corona 10 benchmark
its weird



If it helps knowing I'm running a dual Epyc build that has 8 memory slots per CPU (16 total). Just for the fun of it I tried running the benchmarks (and one rather simple interior) in a 8 sticks vs 16 sticks scenario.

The results were for all intents and purposes identical between the two configs.

I do think that going with less than 8 sticks though would result in slower rendering - I haven't tested it out though.

Do note that each platform can be a bit different so the above might work for my 7B13 Epycs but might not for your dual Xeons.

2025-02-20, 09:47:13
Reply #33

LazyViCE

  • Active Users
  • **
  • Posts: 5
    • View Profile
All my computers have two processors on board.
Xeon 2696v3 x 2 = 5 System Units
Epyc 7601 x 2 = 1 System Unit
Windows 11 - Enterprise

What problems do I encounter:
* CORONA Benchmark works with drops, the core load drops by 10% every few seconds on all systems
* A similar situation is observed during rendering, but less often. Example:
I am making an animation of a camera flyby in an apartment. In the corridor area, there are constant wild drops and I have no idea what to do with it. I have already tried EVERYTHING! Nothing helps. At the same time, in the hall area, such phenomena are greatly weakened. How to find a relationship, I do not know.
* On Epyc 7601 x 2, rendering from under 3ds max goes ONLY ON 16 CORE! I couldn't solve the problem using Windows, I had to install the Process Lasso program and through it forcibly assign 2 processors in 3ds max. There was no such problem on the Xeon 2696v3.

My Conclusion:
* All software is crooked and cannot fully use the potential of multiprocessor systems
* Corona
* 3ds Max
* Windows
Everything is crooked and needs to be improved, and since all this is an interconnected ecosystem, it will take centuries to fix all this.

2025-02-20, 13:52:48
Reply #34

TomG

  • Administrator
  • Active Users
  • *****
  • Posts: 6092
    • View Profile
BTW improvements have been made to the core Corona for high core counts, and for dual CPU systems. These are improvements since Corona 10, so are not in the Corona 10 Benchmark, meaning it is not very useful on those machines. A new Benchmark will have to be released, probably this year, we've discussed the possibility this might be between Corona 13 and 14.
Tom Grimes | chaos-corona.com
Product Manager | contact us

2025-02-21, 06:26:46
Reply #35

LazyViCE

  • Active Users
  • **
  • Posts: 5
    • View Profile
Thank you very much. I am glad to hear that some activity is going on to improve this situation.
I have been using multi-processor assemblies for 4 years or more and I constantly encounter some new problems that I have not encountered before.
Here is another example:
On a system with EPYC 7601 x 2, I encountered the fact that during the benchmark all cores work at 100%, but periodically there is a wild drop. I have seen this on systems with ZEONs, but at least here all cores work in the benchmark.
But when I try to render from 3DS Max on EPYC, only 16 cores work. I had to force the "process group expander" via Process Lasso to work all 128 threads in the render via 3DS Max.
I constantly have to use some kind of crutches to make everything work in an adequate mode.