Efficient parallelization of a dynamic global vegetation model with river routing

The LPJ dynamic global vegetation and hydrology model with river routing is implemented on a compute cluster in order to reduce the overall computation time. In order to achieve this, a parallel algorithm had to be developed for the river routing part of the LPJ code. It can be shown that the run time of the parallel LPJ model scales well with the number of parallel tasks, even getting a super-linear speedup for 8–128 tasks. The sequential part of the model code can be estimated to be only 0.16%. This offers the opportunity, for example, to apply the model to find optimal climate change mitigation/adaptation paths requiring a multitude of subsequent simulation runs. The algorithm can also be used for networks with a different topology than river routing networks.