Experience of Porting and Optimization of Seismic Modelling on Multi and Many Cores of Hybrid Computing Cluster

In this paper, we report our experience of porting and optimization of legacy seismic acoustic modelling application on multi and many cores of hybrid architecture of PARAM Yuva II. This application was developed using MPI and used domain decomposition as parallelization approach across parallel processors. The same application has been modified for domain decomposition at node level and the parallel performance was improved using OpenMP within the node. The resultant application was optimized using different optimization techniques for multi core architecture of Intel's Xeon, which further improved the performance of the application along with efficiency. The optimized application was then ported on many core architecture of Intel's Xeon Phi in native and symmetric modes. The details of porting, optimizations and execution on Intel's Xeon and on Xeon Phi in native and symmetric modes are given in the paper. Performance, scalability and efficiency of the application has been studied using multi and many cores and experimental results are presented.