Evaluation and Mitigation of Performance Variability of OpenMP Applications on Modern Multicore Systems

Paper i proceeding, 2025

In high-performance computing (HPC), OpenMP has become the de facto programming model for shared-memory systems. However, running OpenMP-based parallel applications on multicore systems often faces the challenge of performance variability, particularly as core counts increase in modern HPC clusters. This poster evaluates execution time variability across various multicore systems in modern HPC clusters, using multiple OpenMP benchmarks and a real-world mini-app. We analyze the effects of core resource reservation, OpenMP scalability, frequency scaling, and platform-specific core configurations in the hybrid architecture, by jointly considering thread-pinning and simultaneous multithreading (SMT) effects. Our findings reveal the complex interplay of these factors in performance variability and propose lightweight mitigation strategies to enhance the stability of OpenMP programs for developers and system users.