[GE users] 'serial' gaussian03

Tom Kuppens tom at hartree4.UGent.be
Wed Apr 6 17:21:34 BST 2005


Hi Reuti,
Thank you for your time.

> you can also integrate Linda, as long as for one parallel job you stay 
> on one type of machine. You just need Linda for all types of machines 
> you have - or just limit parallel jobs to run only on one platform. This 
> can be configured in SGE.
I do that also, ie, running linda on only the same processors (I buy 
them in batches of 6) ... 

> What automatism are you looking for? You could a) use a shell loop to 
> submit the whole bunch of jobs, or b) use a so called array-job, if 
> there is the chance to select an input file by a varying parameter - 
> depends on your workflow. How did you create and submit your jobs up to now?
A shell loop wich automates submitting the jobs to different CPU's.

Untill now I did the job with my own (cshell scripted - I know I 
shouldn't, but it works ;-) scheduler. Jobs are submitted and return, when 
done, back to the master node. Simple, and robust, but when it comes to 
scheduling I want to have more power and maybe SGE is the most economic 
solution. e.g. cc-PVTZ jobs or optimization on big molecules (heavy jobs) 
can not be submitted to slower nodes etc.. It's possible to program that 
but it would take me far away ...

Bye,
Tom

http://allserv.UGent.be/~tkuppens
----
 The game is afoot.
    -- Sir Arthur Conan Doyle






---------------------------------------------------------------------
To unsubscribe, e-mail: users-unsubscribe at gridengine.sunsource.net
For additional commands, e-mail: users-help at gridengine.sunsource.net




More information about the gridengine-users mailing list