Performance Analysis and Optimization of a Hybrid Distributed Reverse Time Migration Application

TL;DR

This paper analyzes the performance of a hybrid MPI+OpenMP Reverse Time Migration application on multicore clusters, using performance tools to identify bottlenecks and achieve a 30% speedup.

Contribution

It demonstrates how applying HPCToolkit and hardware counters can optimize hybrid parallel seismic applications, providing insights into domain decomposition and core utilization.

Findings

Performance improved by approximately 30%

Insights into domain decomposition effectiveness

Enhanced understanding of core functional unit utilization

Abstract

Applications to process seismic data employ scalable parallel systems to produce timely results. To fully exploit emerging processor architectures, application will need to employ threaded parallelism within a node and message passing across nodes. Today, MPI+OpenMP is the preferred programming model for this task. However, tuning hybrid programs for clusters is difficult. Performance tools can help users identify bottlenecks and uncover opportunities for improvement. This poster describes our experiences of applying Rice University's HPCToolkit and hardware performance counters to gain insight into an MPI+OpenMP code that performs Reverse Time Migration (RTM) on a cluster of multicore processors. The tools provided us with insights into the effectiveness of the domain decomposition strategy, the use of threaded parallelism, and functional unit utilization in individual cores. By applying insights obtained from the tools, we were able to improve the performance of the RTM code by roughly 30 percent.