[MITgcm-support] bluesky run
Chris Hill
christophernigelhill at gmail.com
Wed Jun 8 13:21:44 EDT 2005
Actually its probably right to classify my messages as spam.
Chris
Ed Hill wrote:
> On Wed, 2005-06-08 at 11:24 -0400, Mike Spall wrote:
>
>>Constantinos et al,
>>
>>Thanks for the suggestion to remove -qhot, that compiles much
>>faster. Now for the next problem (keeping in mind that I know
>>very little of MPI and NCAR machines). I tried to run the
>>following script using llsubmit
>>(I am not showing all the file copies, etc):
>>#
>>#@output=./out
>>#@error=err
>>#@job_type=parallel
>>#@network.MPI=csss,shared,US
>>#@node=1
>>#@tasks_per_node=4
>>#@wall_clock_limit=00:02:00
>>#@class=share
>>#@queue
>
>
> Hi Mike & Chris,
>
> Below is a message from Chris that didn't get through our spam filter
> because Chris didn't subscribe it. So I've copied it and added Chris's
> new address to an accept filter so that future emails from him will get
> through.
>
> Ed
>
> ===
>
> Hi Mike,
>
> Not sure whether the help-desk message is relevant.
>
> However, Patrick and Constantinos do run on bluesky a lot, I think,
> so
> I'm guessing it has more to do with jobs scripts.
>
> In the testscript Ed runs at NCAR - see -
>
> http://mitgcm.org/cgi-
> bin/viewcvs.cgi/MITgcm_contrib/test_scripts/ncar/bluesky_ll_testreport_all?rev=1.1&content-type=text/vnd.viewcvs-markup
>
> there is no #@tasks_per_node=4
>
> Maybe that is the problem?
>
>
> Chris
>
More information about the MITgcm-support
mailing list