Generic Library Interception for Improved Performance Measurement and Insight

TL;DR

This paper introduces a method in Score-P for creating wrappers around C/C++ libraries to facilitate detailed runtime performance analysis, helping understand complex application behaviors.

Contribution

It presents a novel approach for intercepting library calls in Score-P, enabling comprehensive and flexible performance measurement of complex applications.

Findings

Supports intuitive creation of library wrappers

Enables detailed tracking of library interactions and timing

Improves understanding of application performance in complex environments

Abstract

As applications grow in capability, they also grow in complexity. This complexity in turn gets pushed into modules and libraries. In addition, hardware configurations become increasingly elaborate, too. These two trends make understanding, debugging and analyzing the performance of applications more and more difficult. To enable detailed insight into library usage of applications, we present an approach and implementation in Score-P that supports intuitive and robust creation of wrappers for arbitrary C/C++ libraries. Runtime analysis then uses these wrappers to keep track of how applications interact with libraries, how they interact with each other, and record the exact timing of their functions.