[MITgcm-support] MITgcm benchmark

Ali Nazemian alinazemian at gmail.com
Tue Jul 19 07:48:01 EDT 2011


Thanks a lot.

On Tue, Jul 19, 2011 at 3:38 PM, Yuan Lian <lian at ashimaresearch.com> wrote:

>  Hi Ali,
>
> You should look at the end of STDOUT.0000, where you can find something
> like this
> (PID.TID 0000.0001)   Seconds in section "ALL
> [THE_MODEL_MAIN]":
> (PID.TID 0000.0001)           User time:   94993.1709375009
> (PID.TID 0000.0001)         System time:  0.000000000000000E+000
> (PID.TID 0000.0001)     Wall clock time:   95208.4702620506
>
> The total time is given as seconds.
>
>
> Yuan
>
>
>
> On 7/19/11 3:54 AM, Ali Nazemian wrote:
>
> Hi,
> I want to now that is there any possible way to see execution time and
> output report of running MITgcm in parallel mode?
>  mpirun -v -machinefile machine -np 4 ./mitgcmuv > output.txt  wont work
> and output.txt is empty!
> Best Regards.
> --
> A.Nazemian
>
>
> _______________________________________________
> MITgcm-support mailing listMITgcm-support at mitgcm.orghttp://mitgcm.org/mailman/listinfo/mitgcm-support
>
>
>
> _______________________________________________
> MITgcm-support mailing list
> MITgcm-support at mitgcm.org
> http://mitgcm.org/mailman/listinfo/mitgcm-support
>
>


-- 
A.Nazemian
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mitgcm.org/pipermail/mitgcm-support/attachments/20110719/d304b9a8/attachment.htm>


More information about the MITgcm-support mailing list