Best practices for HPM-assisted performance engineering on modern multicore processors

Abstract. Many tools and libraries employ hardware performance monitoring (HPM) on modern processors, and using this data for performance assessment and as a starting point for code optimizations is very popular. However, such data is only useful if it is interpreted with care, and if the right metrics are cho-sen for the right purpose. We demonstrate the sensible use of hardware perfor-mance counters in the context of a structured performance engineering approach for applications in computational science. Typical performance patterns and their respective metric signatures are defined, and some of them are illustrated using case studies. Although these generic concepts do not depend on specific tools or environments, we restrict ourselves to modern x86-based multicore processors and use the likwid-perfctr tool under the Linux OS. 1 Introduction and related work Hardware performance monitoring (HPM) is regarded as a state of the art advanced tool to guide code optimizations. While there are countless publications about HPM-based optimization efforts, a structured method for using hardware events is often missing