“…A hybrid programming model allows running a combination of MPI processes for distributed computation and threads for lightweight parallelization within compute nodes (Ippen et al, 2017). NEST scales well throughout an entire range of platforms -from laptops to supercomputers (Jordan et al, 2018), and it supports advanced model components, for example neuromodulated plasticity (Potjans et al, 2010), structural plasticity (Diaz-Pier et al, 2016), coupling between neurons via gap junctions (Hahne et al, 2015), and non-spiking neurons with continuous interactions such as rate-based models (Hahne et al, 2017). The simulation code used for the benchmarks is based on the NEST 2.14 release, with Git SHA ba8aa7e (4g) and 0f8d5b5 (5g), respectively.…”