The CRIL cluster has been providing the laboratory's researchers with computing resources since it was set up in 2009. Since then, the evolution of these resources has been continuous, leading to a heterogeneous architecture in which traditional computing nodes, nodes dedicated to distributed computing, GPU nodes and various servers to drive this computing power cohabit, all driven by the Slurm resource manager. The aim of this talk is to present the calculation tools available, and how to use them (correctly) via Slurm.