[Mitgcm-support] barrier

mitgcm-support at dev.mitgcm.org mitgcm-support at dev.mitgcm.org
Wed Jul 9 15:36:33 EDT 2003


Alistair,

I have a short question on the actual implementation of the PALACE
floats. For writing output I would need a masterprocess collecting data
from all tiles and write the data into a file. Unfortunately all other
processes than process 0 have already left the subroutine that the
values are not available anylonger (and I want to store them only
temporarily).

My question: Is there a sort of global barrier that causes all processes
to wait for a master process? I fould only _BARRIER but that seems to
work only per processor for all tiles per processor.

Ciao,
	Arne

P.S. Sorry about my lagging work on the MATLAB scripts. Currently I have
not the time to update them. But if you have new ideas I would be happy
to incorporate them later. My changes are mostly due to the large arrays
(of the global 1/6 model) and I do not want to incorporate them into the
public version.

-- 

Dr. Arne Biastoch
Scripps Institution of Oceanography        phone: +1-858-822-3787
Physical Oceanography Research Division    fax  : +1-858-534-9820
MS: 0230                                   email: abiastoch at ucsd.edu
8605 La Jolla Shores Dr.            
La Jolla, CA 92093-0230, U.S.A.   http://www.ecco.ucsd.edu/~biastoch




More information about the MITgcm-support mailing list