HPC with Python: An MPI-parallel implementation of the Lattice Boltzmann Method

The Lattice Boltzmann Method is well suited for high performance computational fluid dynamics. We show by means of a common two-dimensional test case, the lid-driven cavity problem, that excellent parallel scaling can be achieved in an implementation based on pure Python, using the numpy library and the Message Passing Interface. We highlight opportunities and pitfalls for the implementation of parallel high-performance codes in the high-level language Python