Author Topic: Corona 1.3 Benchmark  (Read 82255 times)

2019-03-07, 19:50:22
Reply #195

dnmorato

  • Users
  • *
  • Posts: 1
    • View Profile
Hello there guys!

Right now I work with 5 pcs for render, using it in DR! I was wondering if it will ever be a Benchmark so see how well the network rendering perform.
Now I'm using an old Dual XEON + 3 i7 4790K + 1 i7 3820 and I'd love to know if it was worth upgrading all the machines or just sell everthing and by the best one on the market (in terms of Brazilian market of course... over here a XEON is worth at least two livers!)

Thanks in advance!

2019-03-22, 12:57:35
Reply #196

cexec

  • Active Users
  • **
  • Posts: 55
    • View Profile
I've used corona benchmark a lot recently to test some workstations with OC that would be used as rendernode, I've noticed a big difference in watt consumption and temperature of cores between the benchmark and the actual render with v2/3, to the point that I dropped the benchmark completely. I assume it's because the latter uses the new AVX instrunction and a more recent version of embree, among other changes. Are there any plans to release an updated version of the benchmark? I believe it would be helpful also to show the difference between the newer CPUs.

Hi, I also think update to Corona Benchmark would be good. In our case overclocked i9 machines tested with Benchmark 1.3 were completely fine (while running Corona 2.0 on daily basis), but they all started to overheat once we updated renderers to Corona 3.0. (temperatures over 105C). I believe new benchmark could prevent such incidents, adjusting overclocking settings would be easier knowing Corona's behaviour in latest updates.

2019-06-17, 14:29:48
Reply #197

ale.castano

  • Active Users
  • **
  • Posts: 8
    • View Profile
Hello all,
I remember I saw this around but can't find the right answer, so sorry for asking again. Why in the benchmark results many Ryzen Threadripper are x4? As long as I know you can't have double processors, but maybe I'm not well informed.
Anyone knows about this and can explain? Thanks

2019-06-18, 01:16:28
Reply #198

SairesArt

  • Active Users
  • **
  • Posts: 663
  • Pizza | The Cheesen One
    • View Profile
    • SairesArt Portfolio
Anyone knows about this and can explain?
If you mean in general, multi socket boards have existed since forever.
In case of threadripper you are correct, there are no multi socket boards for thread ripper, only for the epyc line up.

The Corona benchmark accidentally counts the multiple dies as multiple CPUs. Whilst you could make the argument, that the way thread ripper is set up it's not too far away from that idea, it's a bug.

2019-06-18, 08:44:48
Reply #199

Ondra

  • Administrator
  • Active Users
  • *****
  • Posts: 8884
  • Turning coffee to features since 2009
    • View Profile
yes, the benchmark was released before ryzens/threadrippers, so we didnt know the detection will give incorrect results.
Rendering is magic.
Private scene uploader | How to get minidumps for crashed/frozen 3ds Max | Sorry for short replies, brief responses = more time to develop Corona ;)