[MITgcm-support] MITgcm on Sun Fire cluster

Martin Losch Martin.Losch at awi.de
Mon Jun 2 12:14:43 EDT 2008


Hi Abbas,

"my" sunfire no longer exists, so I cannot test this opt file  
anymore, but in general the SunOS is always picky. I guess you can  
ignore the make warnings, as long as you get an executable.
The optimization in sunos_sun4u_mpf77+mpi_sunfire is already quite  
aggressive, but you can try to crank it up one more notch (-O5 is  
possible, I think).

In general my experience with out Sunfire was poor because the  
internal network was terrible and the processors were slow (we had a  
SF15000, with 1GHz Cpus). Scaling broke down as soon as there were  
more than one parallel job, etc ... But maybe your domain is too  
small to scale? The scaling on your desktop is poor to, isn't it?

Martin


On 2 Jun 2008, at 17:55, Abbas Dorostkar wrote:

> Hi all,
>
>
>
> I have been running a test case -internal wave test case in  
> nonhydrostatic mode- with MPI on a SunFire cluster. Unfortunately,  
> the performance of the model on the cluster is terrible in  
> comparison with the same run on my desktop computer.
>
> Here, I mentioned the wall clock times for both systems:
>
> On the cluster , Sun Fire 2500 server with 72 (2 MB on-chip L2  
> cache and 32 MB L3 cache)  dual-core UltraSPARC-IV+ 1.5 GHZ  
> processors with 676 GB of RAM:
>
> serial-- > 457 s
>
> np=2 -- > 353 s
>
> np=4 -- > 275 s
>
> np=6 -- > 315 s
>
>
>
> On my Desktop (Intel core 2 Due - 2.4 GHZ - 4 MB cache - 1066 MHZ  
> FSB ):
>
> serial -- > 171 s
>
> np=2 --->  162 s
>
>
>
> I use the sunos_sun4u_mpf77+mpi_sunfire optfile shipped with the  
> MITgcm model (v 1.4 2007/02/18). I have to mention that I get  
> following warnings while I compile the model on the cluster:
>
> make: Warning: Too many rules defined for target PACKAGES_CONFIG.h
> make: Warning: Too many rules defined for target AD_CONFIG.h
> make: Warning: Too many rules defined for target FC_NAMEMANGLE.h
> make: Warning: Too many rules defined for target BUILD_INFO.h
>
>
>
> Does anyone  know what is going wrong? Should I change something in  
> the optfile (e.g adding some optimization flags)?
>
>
>
> Your help is much appreciated!
>
>
>
> Abbas
>
>
>
>
>
>
> _______________________________________________
> MITgcm-support mailing list
> MITgcm-support at mitgcm.org
> http://mitgcm.org/mailman/listinfo/mitgcm-support




More information about the MITgcm-support mailing list