Difference between revisions of "How to run ESTEL in parallel"
| Line 1: | Line 1: | ||
[[Category:Estel]] | [[Category:Estel]] | ||
| − | + | This article describes how to run parallel jobs in [[Estel | '''ESTEL''']] on "simple" networks of workstations. | |
| − | |||
| − | [[ | ||
| − | |||
| − | + | Note that the methodology differs slightly for real high performance facilities such as [http://www.acrc.bris.ac.uk Blue Crystal] or other [http://en.wikipedia.org/wiki/Beowulf_cluster Beowulf clusters]. Therefore, there is a [[Run ESTEL in parallel on a cluster | dedicated article for clusters]]. | |
| − | == Run a parallel job | + | We call a network of workstations a set of workstations which can "talk" to each other via Intra/Internet. |
| − | start an mpd | + | |
| − | + | = Pre-requesites = | |
| − | + | * You need to have a working MPI configuration on the network of workstations. See the artile about [[Install and configure MPI | installing MPI]]. | |
| + | * The parallel library in the TELEMAC tree needs to have been compiled. This is described [[Install_the_TELEMAC_system#parallel | here]]. | ||
| + | |||
| + | = Run a parallel job = | ||
| + | Before running '''[[ESTEL]]''' in parallel, you need to start an mpd. | ||
| + | |||
| + | Before trying to run real parallel jobs it is interesting to check that the "parallel" library and [[Estel | '''ESTEL''']] are playing nicely together. This can be achieved by running an existing test case with with test case for which you add in the steering file: | ||
| + | <code><pre> | ||
| + | PARALLEL PROCESSORS = 1 | ||
| + | </pre></code> | ||
| + | |||
| + | Using the keyword <code>PARALLEL PROCESSORS</code> will force [[ESTEL]] to use the <code>parallel</code> library instead of the <code>paravoid</code> library. As we request one processor only, no MPI calls will be done. | ||
| + | |||
| + | If this does not work. Stop here and try to understand what is going wrong. You can email error messages (full messages) to [[User:Jprenaud | JP Renaud]] who will help if necessary. | ||
edit estel steering file | edit estel steering file | ||
| Line 17: | Line 27: | ||
estel3d | estel3d | ||
| − | |||
| − | |||
| − | |||
= estel2d particle tracking or domain decomposition = | = estel2d particle tracking or domain decomposition = | ||
Revision as of 11:11, 22 August 2007
This article describes how to run parallel jobs in ESTEL on "simple" networks of workstations.
Note that the methodology differs slightly for real high performance facilities such as Blue Crystal or other Beowulf clusters. Therefore, there is a dedicated article for clusters.
We call a network of workstations a set of workstations which can "talk" to each other via Intra/Internet.
Pre-requesites
- You need to have a working MPI configuration on the network of workstations. See the artile about installing MPI.
- The parallel library in the TELEMAC tree needs to have been compiled. This is described here.
Run a parallel job
Before running ESTEL in parallel, you need to start an mpd.
Before trying to run real parallel jobs it is interesting to check that the "parallel" library and ESTEL are playing nicely together. This can be achieved by running an existing test case with with test case for which you add in the steering file:
PARALLEL PROCESSORS = 1
Using the keyword PARALLEL PROCESSORS will force ESTEL to use the parallel library instead of the paravoid library. As we request one processor only, no MPI calls will be done.
If this does not work. Stop here and try to understand what is going wrong. You can email error messages (full messages) to JP Renaud who will help if necessary.
edit estel steering file
parallel processors = 2
estel3d