Figure 10From: On the impact of heterogeneity-aware mesh partitioning and non-contributing computation removal on parallel reservoir simulationsCommunication overhead, i.e., time usage of DUNE’s copyOwnerToAll function on the Abel (a) and Saga (b) clusters. Multiple computational nodes are used when the number of MPI-processes exceeded 16 on Abel (a) and 40 on Saga (b)Back to article page