Evaluation of Message Passing Communication Patterns in Finite Element Solution of Coupled Problems

Abstract

Abstract. This work presents a performance evaluation of single node and subdomain communication schemes available in EdgeCFD, an implicit edgebased coupled fluid flow and transport code for solving large scale problems in modern clusters. A natural convection flow problem is considered to assess performance metrics. Tests, focused in single node multi-core performance, show that past Intel Xeon processors dramatically suffer when large workloads are imposed to a single node. However, the problem seems to be mitigated in the newest Intel Xeon processor. We also observe that MPI non-blocking pointto-point interface sub-domain communications, although more difficult to implement, are more effective than collective interface sub-domain communications.

Numerical simulation of particle‐laden flows by the residual‐based variational multiscale method

“…To compute such operations more efficiently, we have used an edge‐based data structure as detailed in . The computations are performed in parallel using a distributed memory paradigm through the message passing interface library, using point‐to‐point communication . The parallel partitions are generated by the Metis library , whereas the information regarding the edges of the computational grid is obtained from the EdgePack library as described in .…”

Parallel implementation and performance analysis of a linear octree finite element mesh generation scheme

“…For each node, there is a linked list containing the processes that share that node. However, our mesh generator has implemented a point‐to‐point communication strategy based on a master–slave relationship between the processors as presented by Elias et al , to make the mesh ready to be used in computational simulations. The master–slave relationship is established by creating a hierarchy based on host partition numbers.…”