High Performance Parallelization of COMPSYN on a Cluster of Multicore Processors with GPUs

In this work we propose a high performance parallelization of the software package COMPSYN, devoted to the production of syntethic seismograms, on a cluster of multicore processors with multiple GPUs. To design and implement the proposed high performance version, we started from a naive parallel version of COMPSYN. The naive version consists in a simple parallelization on both device side, obtained by exploiting CUDA, and host side, obtained by exploiting the MPI paradigm and OpenMP API. The proposed high performance version implements several practical techniques of CUDA programming and deeply exploits the GPU architecture, thus achieving a much better performance with respect to the naive version. We compare the performance of the proposed high performance version and that of the naive one with the performance of the version running on the cluster of multicore processors without invoking the GPUs. We obtain for the high performance GPU version a speedup of 25x over the version running on the cluster of multicore processors without GPUs against the 10x of the naive version. Regarding the sequential version, we estimate about 380x the speedup of the high performance GPU version against the about 140x of the naive version.