Absolutely correct.
-----Original Message-----
From: Carlos Simmerling [mailto:carlos.simmerling_at_sunysb.edu]
Sent: Monday, March 19, 2001 12:03 PM
To: amber_at_cgl.ucsf.edu
Subject: Re: Problem of running sander on Linux cluster
In my experience with MPICH you also need the "-nolocal"
flag if the machine where you start your script is not
in the machinefile, or it will start 1 process locally anyway.
Carlos
Thomas A. Spraggins wrote:
> The problem is almost certainly in your machinefile. Processes are
> allocated round-robin, using the entries in this file, which may be in a
> place like /usr/local/mpich/utl/machines/machine.LINUX.
>
> If you want two processes on the same machine, create a file like:
>
> machine1.mydomain
> machine1.mydomain
> machine2.mydomain
> ...
>
> then run with: mpirun -np 2 -machinefile <whateveryoucalledyourfile>
> and you'll get the desired result.
>
> Tom Spraggins
> tas_at_virginia.edu
>
> -----Original Message-----
> From: chomsri upkaew [mailto:uchomsri_at_hotmail.com]
> Sent: Monday, March 19, 2001 10:25 AM
> To: amber_at_cgl.ucsf.edu
> Subject: Problem of running sander on Linux cluster
>
>
> Dear Ross Walker and netters,
>
> I can compile sander with parallel on Linux cluster as Ross's suggestion.
> However, I have some problem.
>
> My Linux cluster contains 12 boxes and 2 processors in each box (total 24
> processors). When I submitted my job on box2 (or other boxes which are not
> box1) with command
>
> % mpirun -np 2 $AMBERHOME/exe/sander -O -i input -o output -c ...
>
> I want to run 2 process on the same box (box2).I found that 1 process was
> running on box2 and another process was running on box1. I don't know why?
> Could you please give my the suggestion?
>
> Sincerely Yours,
> Uchom
>
>
> Ross Walker wrote:
>
>> Hi Chomsri,
>>
>> Try the following:
>>
>> 1) Resinstall MPICH manually specifing the compilers
>>
>> e.g ./configure -prefix=/usr/local/mpich-1.2.1 -fc=g77 -cc=gcc
>>
>> Then do make / make install etc.
>>
>> Then try recompiling amber. Make sure you do a make clean in
./amber6/src
>> first.
>>
>> All the best
>> Ross
>
> _________________________________________________________________________
> Get Your Private, Free E-mail from MSN Hotmail at http://www.rosswalker.co.uk/adsense_alternatives/.
--
===================================================================
Carlos L. Simmerling, Ph.D.
Assistant Professor Phone: (631) 632-1336
Department of Chemistry Fax: (631) 632-7960
SUNY at Stony Brook Web: http://comp.chem.sunysb.edu/carlos
Stony Brook, NY 11794-3400 E-mail: carlos.simmerling_at_sunysb.edu
===================================================================
Received on Mon Mar 19 2001 - 10:54:49 PST
