Finite Element Simulation of Seismic Elastic Two Dimensional Wave Propagation: Development and Assessment of Performance in a Cluster of PCs with Software DSM

摘要

In this work we approach the seismic wave propagation problem in two dimensions using the finite element method (FEM). This kind of problem is essential to study the structure of the earth's interior and exploring petroleum reservoirs. Using a representative FEM-based application, we propose and evaluate two parallel algorithms based on the inverse mapping and on the mesh coloring, respectively. The distinguishing feature of our parallel versions is that they were implemented in a distributed shared-memory system (SDSMs), which offers the intuitive shared-memory programming model on a cluster of low-cost high-performance PCs. Our results for several workloads show that the inverse mapping scheme achieved the best speedup at 7.11 out of 8 processors, though the mesh coloring algorithm scales well. Overall, these preliminary results we obtained indicate that cluster-based SDSMs represent a cost-effective friendly-programming platform for developing parallel FEM-based applications.