[MITgcm-devel] Re: PBS & MPI on altix

[Ed Hill]

On Sun, 2003-12-07 at 20:21, Dimitris Menemenlis wrote:
> Ed, is "testreport -mpi" still under construction.
> There are still a bunch of things that need to be
> done manually when I tried it.


Hi Dimitris,

Yes, "testreport -mpi" does need work.

The main problem is that the MPI libraries and the command(s) needed to
launch MPI are just so inconsistent across machines.  I'm hoping to come
up with a better way.  In the mean time, we can use the "-mpi" option in
conjunction with some sort of user-specified command or shell script as
launched by the "-command" option.  For some docs and examples, please
see:

http://mitgcm.org/devel_HOWTO/devel_HOWTO_onepage/#TESTREPORT
http://dev.mitgcm.org/cgi-bin/viewcvs.cgi/MITgcm_contrib/test_scripts/cg01/

And I'll try add some more examples in:

http://dev.mitgcm.org/cgi-bin/viewcvs.cgi/MITgcm_contrib/test_scripts/

over the next few days.

Ed

-- 
Edward H. Hill III, PhD
office:  MIT Dept. of EAPS;  Room 54-1424;  77 Massachusetts Ave.
            Cambridge, MA 02139-4307
email:   eh3 at mit.edu,  ed at eh3.com
URL:     http://web.mit.edu/eh3/
phone:   617-253-0098
fax:     617-253-4464
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: This is a digitally signed message part
URL: <http://mitgcm.org/pipermail/mitgcm-devel/attachments/20031208/176137fe/attachment.sig>