- Index
- » Developer
- » OpenModelica development
- » OMoptim for multi-processor machines
OMoptim for multi-processor machines
OMoptim for multi-processor machines
Hello,
I have been wondring whether it could be made possible that the genetic algorithms of OMoptim call the computations for differend children on multiple processors of one computer in parallel ? This would be an immediate speedup proportional to the number of processors.
Of course I do not know whether running the same model multiple times in parallel is possible with the current OpenModelica implementation.
In any case this would be great for 6 processor machines like AMD Phenom x6 processors ...
Thank you very luch for your efforts - OpenModelica is a great achievement B-)
Boris
Re: OMoptim for multi-processor machines
It is not only possible to run several simulations in parallel; it is also very efficient and easy (especially on OS'es that support symlinking). You simply need to create one subdirectory for each process, symlink the executable and put one init.xml file in each directory.
It is also possible to run a single simulation in parallel, but this does not always yield faster code due to synchronization (several times per step vs. once per execution as described above).
- sjoelund.se
- 1700 Posts
- Index
- » Developer
- » OpenModelica development
- » OMoptim for multi-processor machines