[gmx-users] about parallel running on PC cluster

[David van der Spoel]

On Mon, 2003-01-13 at 03:25, xu yechun wrote:
Dear all,
 
    We met a very strange problem about parallel running gromacs on PC
cluster.  When we installed Gromacs3.0.5 versiong on one PC cluster, the
system report that mpicc can not compile x86_cpuid.s and other two .s
files in directory /src/gmxlib, then we use gcc -c to compile these
three .s files by hands. After all, we can use 4 cpus to submit our
jobs, when we use more than 4 cpus, the program did not run and did not
give any error information either. It just stopped like this:
......
Getting Loaded...
Reading file full1.tpr, VERSION 3.0.5(single precision)
Reading file full1.tpr, VERSION 3.0.5(single precision)
Loaded with Money
 
starting mdrun 'Protein in water'
5000000 steps, 10000.0 ps.
 
 
 
 
It is really a strange problem for us. We never meet it before. If
anyone else know how to resolve it, please tell us. Any information will
be appreciated.

First of all, it is probably worthwhile to upgrade to gromacs 3.1.4
 
Secondly you need to specify more information (OS, MPI version etc.)

Third, if you don't have high speed network it is probably not useful to
go much beyod 4 processors.
Best regards
 
Xu yechun
 
Center for Drug Discovery & Design     
Shanghai Institute of Materia Medica
294,Taiyuan Road,Shanghai 200031,China
 

________________________________________________________________________
 MSN Messenger 与联机的朋友进行交流
_______________________________________________ gmx-users mailing list
gmx-users at gromacs.org http://www.gromacs.org/mailman/listinfo/gmx-users
Please don't post (un)subscribe requests to the list. Use the www
interface or send it to gmx-users-request at gromacs.org.
-- 
Groeten, David.
________________________________________________________________________
Dr. David van der Spoel, 	Biomedical center, Dept. of Biochemistry
Husargatan 3, Box 576,  	75123 Uppsala, Sweden
phone:	46 18 471 4205		fax: 46 18 511 755
spoel at xray.bmc.uu.se	spoel at gromacs.org   http://xray.bmc.uu.se/~spoel
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++