Since molecular dynamic simulations are very calculation heavy tasks, load balancing is one of the key points which should be optimized to gain an optimal runtime. In this thesis, three load balancing strategies of the simulation framework ls1-MarDyn and their optimizations will be discussed. Since ls1-MarDyn uses MPI as its communication protocol, some time is spent inside of the MPI-routines and therefore falsifies the measured time which is used as the input parameter for the load balancing. A way will be shown how to reduce this parameter by the time spent inside of the MPI-routines. Furthermore, this implementation is evaluated using three different simulation setups. The newly reduced time leads to an overall better performance - but this only applies if it is used in combination with a diffusive domain decomposition.     «

Since molecular dynamic simulations are very calculation heavy tasks, load balancing is one of the key points which should be optimized to gain an optimal runtime. In this thesis, three load balancing strategies of the simulation framework ls1-MarDyn and their optimizations will be discussed. Since ls1-MarDyn uses MPI as its communication protocol, some time is spent inside of the MPI-routines and therefore falsifies the measured time which is used as the input parameter for the load balancing....     »