Running Dymola parallel on the cluster

Question

I am trying to run Dymola on the cluster so that everyone in my research group could submit a model and simulate jobs, is it possible to run Dymola on a cluster and utilize the power of HPC?

I could use some flags to make Dymola run parallel on a many-cores computer, but how to run a parallel simulation on many computers?

Answer 1

Parallelization on a single computer:

Parallelizing a Modelica model is possible, but the the model needs to be

• suitable by nature (which doesn't happen too often, at least to my experience), for some examples where it works well see e.g. here
• modified manually by the modeler to allow parallelization, e.g. by introducing delay blocks, see here or some similar approach here.

Often Dymola will output No Parallelization in the translation log, presumably due to the model not allowing parallelization (efficiently). Also the manual states: It should be noted that for many kinds of models the internal dependencies don’t allow efficient parallelization for getting any substantial speed-up.

I'm not an expert on this, but as to my understanding HPC depends on massive parallelization. Therefore, models generated by Dymola do not seem to be a very good application to be run on HPC-clusters.

Dymola on multiple computers:

Running a single Dymola-simulation on multiple computers in parallel is not possible as far as I know.