Corona 1.3 Benchmark

[dnmorato]

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!

[Ink Visual]

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.

[ale.castano]

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

[FrostKiwi]

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.

[Ondra]

yes, the benchmark was released before ryzens/threadrippers, so we didnt know the detection will give incorrect results.

[gpz]

Just one question.
I have a Ryzen 7 2700.
Searching on the benchamark results this kind of cpu gives 1:40 min to rendering, in my pc instead is 2.40.
Why?

[hrvojezg00]

We just finished a new node, a dual 7742 ES and get very funny result of 36 sec. Cinebench R20 scales correct to 30k. Any insights on this?

Thanks,
H

[Juraj]

We just finished a new node, a dual 7742 ES and get very funny result of 36 sec. Cinebench R20 scales correct to 30k. Any insights on this?

Thanks,
H

What's the Ray/s on production scene though?

Also, can you send me an email about this if you feel particularly Christmass-ly :- )

[hrvojezg00]

12k, email sent!

[hrvojezg00]

I'm also getting poor performance in corona too, cinebench r20 is around 30k so that is correct. Are there any limitations to core number or something in corona?

[3dvizual]

Corona 1.3 Benchmark Finished
BTR Scene 16 passes
AMD Ryzen Threadripper 3970X 32-Core Processor
Real CPU Frequency [GHz]: 3.88
Render Time: 0:00:29, Rays/sec: 16,312,300

[xbaroka]

My new amazing Ryzen  PC ;)

Corona 1.3 Benchmark

Ryzen 3950x CPU @ 4.200GHz all core

Render Time: 0:00:53, Rays/sec: 9 101 310

Best cpu for your money that sure !!!

[newnew]

Can not to run Benchmark...what can i do???

[maru]

Can not to run Benchmark...what can i do???

Do you have internet connection?

[newnew]

Can not to run Benchmark...what can i do???

Do you have internet connection?

Of course......