across the nodes, namd jobs don't get enough CPU!

From: M. Madhu (madhu7_at_hotmail.com)
Date: Fri Jul 07 2006 - 11:00:59 CDT

• Next message: nisha_at_ncbs.res.in: "Re: OXT in pdb file"
• Previous message: Jérôme Hénin: "Re: TCL Forces and Help on Script"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ] [ attachment ]

Hi,

We are using NAMD_2.6b1_Linux-amd64-TCP on linux machines.

When NAMD jobs run on a single node, each processor (each node has 4
processors)
gets nearly 100% CPU. But when the jobs run accross the nodes (ie., when I
request
more than 4 processors), except one, all other processors get less than 5%
of the
CPU. (At the same time, parallel gromacs jobs across the nodes get nearly
100% CPU.)

Did anyone observe this kind of problem? Or, is there any solution for this
type of
problems?

Thank you.

Madhu

_________________________________________________________________
How good are you in a Formula One car? Play now
http://server1.msn.co.in/sp05/tataracing/onlinegame.asp

• Next message: nisha_at_ncbs.res.in: "Re: OXT in pdb file"
• Previous message: Jérôme Hénin: "Re: TCL Forces and Help on Script"
• Messages sorted by: [ date ] [ thread ] [ subject ] [ author ] [ attachment ]

This archive was generated by hypermail 2.1.6 : Wed Feb 29 2012 - 15:43:48 CST