|
[Sponsors] |
Problem with parallelization speedup using many CPUbs |
|
LinkBack | Thread Tools | Search this Thread | Display Modes |
January 23, 2009, 06:59 |
Hi Andreas!
Yes, definitely
|
#21 |
Member
Carsten Thorenz
Join Date: Mar 2009
Location: Germany
Posts: 34
Rep Power: 17 |
Hi Andreas!
Yes, definitely you're running on a single CPU. This explains the strange results. About your job-script: I had similar problems when trying to run with the supplied OpenMPI and PBS. Do you use OpenMPI? If yes, you should try to change your execution line to: mpirun -hostfile m_nodes -np $nrnodes $solver $PBS_O_WORKDIR $casename -parallel This delives the names of the "slaves" to mpirun. Bye, Carsten |
|
Thread Tools | Search this Thread |
Display Modes | |
|
|
Similar Threads | ||||
Thread | Thread Starter | Forum | Replies | Last Post |
Superlinear speedup in OpenFOAM 13 | msrinath80 | OpenFOAM Running, Solving & CFD | 18 | March 3, 2015 05:36 |
speedup questions | tony | CFX | 5 | February 3, 2008 17:26 |
cluster - parallel speedup | George | Main CFD Forum | 3 | March 29, 2005 11:32 |
cluster - parallel speedup | George | FLUENT | 0 | March 25, 2005 05:54 |
About the parallelization | ptyue | Main CFD Forum | 8 | January 26, 2003 23:29 |