[lakeat]

ya, it's helpful, thank you, Carsten!
I found CPU caches are of great importance for the speed.
Can you share about your cpu info, Carsten? Thanks a lot

[lakeat]

Originally Posted by stidulsis

I am glad to find your site - now I know what a good one looks like.
Very good topic to share with us. Great info.
** spam link removed **

SPAM?????

[7islands]

You can report the spam following this guide (click the Report Post icon at the left of each post, which I have done this time already).

T

[puneet336]

Originally Posted by fhy

Hi Srinath and Jens,

Thanks for your reply and suggestions!

I increased the node density from (20,20,1) to (100, 100,1) and decrease the deltaT to 0.001 to satisfy CFL condition (of the icoFoam/cavity case). With longer runtime, I did observe speedup. However, parallel efficiency dropped to < 50% with 8+ processors.

I checked the benchmark wiki page. Most parallel results only have maximal 4 cpu result.

Jens, can you point me some cases that scales with large number of processors? I am looking for some test cases that can scales to 64 cpus.

I understand that scaling is depending on application as well as system. That's why I am looking for some cases which already show good scaling in other systems. I want to make sure the bad scaling in my local system is not due to application.

Thanks,
Huiyu

Hi,
Tried your setting with 100,100,1 and deltaT 0.001, it worked.
However i am looking for a longer benchmark - 1000,1000,1 in which Courant number increase seems to be causing floating point exception.

Could you please advice here ?