Numerical modelling of dynamical interaction between seismic radiation and near-surface geological structures: a parallel approach

Abstract

We investigate a faster and easier way to parallelise seismological codes able to simulate the dynamical interaction between seismic radiation and near-surface geological structures. This is important in assessing strong ground motion, in the mitigation of seismic hazard and for studies concerning site effects. Our chosen case study is representative of a set of seismological problems dealing with the interaction of anti-plane seismic wave propagation in a heterogeneous viscoelastic 2D media. High Performance Fortran and OpenMP tools of parallelisation are considered. Third party and IBM SP3 native compiler performances are also analysed. Results such as Speed-Up and Efficiency are shown and discussed. We have found that the most simple and efficient method to parallelise a given code belonging to the set of serial codes represented by our case study depends mainly on computational size: if the RAM of a single multiprocessor machine is sufficient for the program memory requirements, OpenMP should be preferred. If more RAM is needed, the greater advantages in using HPF become apparent with the utilisation of a higher number of multiprocessor machines in a cluster. We also demonstrate how successful porting from serial to parallel codes is realised by way of minimal instructions, provided that an ad hoc profiling analysis of the serial code is first performed.