|
[Sponsors] |
August 29, 2006, 08:52 |
Parallel Processing
|
#1 |
Guest
Posts: n/a
|
Hello,
I am using fluent to conduct my thesis on a UNIX system. I am unable to run the software on multiple processors in parallel. The File/Run task bar will not appear in fluent so I cannot use the select solver panel. I have created a run file so that I can type: fluent 3d -g (MediumTest.run)& MediumTest.out& rc MediumTest.cas solve/init/init solve/dti 500 50 wd MediumTestInter.dat wc MediumTestInter.cas solve/dti 500 50 wd MediumTestFinal.dat wc MediumTestFinal.cas I was wondering whether anyone could help me figure out where I need to instert the code to use parallel processors. Thanks for your time. If any further information is required please don't hesitate to ask. Drew |
|
August 29, 2006, 09:04 |
Re: Parallel Processing
|
#2 |
Guest
Posts: n/a
|
You have to specify number of processors x
fluent 3d â€"tx â€"g I have 2 processors so I write fluent 3d â€"t2 â€"g |
|
August 29, 2006, 13:35 |
Re: Parallel Processing
|
#3 |
Guest
Posts: n/a
|
That works for multiple processors on a single machine. For multiple machines (i.e. a parallel network) you have to specify which machines to run on. Read through the users guide, chapter 1.1 on starting Fluent and chapter 32.2 on running in Parallel for more info. It depends on the setup for your system. Sometimes you have to define the MPI (message passing interface?).
An example run line could be: fluent 3d -tx -cnf=sample.hosts -g < inputfile >& outputfile & where x (in -tx) is the number of compute nodes you want to use and sample.hosts is a text file that lists the computers you want to connect to. If that doesn't work, you have to define a communicator: fluent 3d -pcomm -tx -cnf=sample.hosts -g < inputfile >& outputfile & where -pcomm is the communicator (-pnmpi, -ptmpi, -psmpi... there's a whole list of them in UG Chapter 32.2.1). Some communicators don't allow you to "spawn nodes" within Fluent, so you ahve to use a hosts file, but some communicators do allow you to, so you could potentially drop the -tx -cnf=sample.hosts from the runline and manually spawn the nodes within Fluent. Hope this helps, and good luck, Jason |
|
Thread Tools | Search this Thread |
Display Modes | |
|
|
Similar Threads | ||||
Thread | Thread Starter | Forum | Replies | Last Post |
Parallel processing of OpenFOAM cases on multicore processor??? | g.akbari | OpenFOAM Running, Solving & CFD | 31 | November 1, 2017 10:25 |
multiphase solver - parallel processing - GAMG | thibault_pringuey | OpenFOAM Programming & Development | 2 | August 27, 2013 23:03 |
HP MPI warning...Distributed parallel processing | Peter | CFX | 10 | May 14, 2011 07:17 |
bubbly flow and parallel processing | mvee | FLUENT | 0 | September 12, 2007 06:08 |
About parallel processing in Linux | tuks | CFX | 10 | August 8, 2005 09:22 |