Title: AutoBench: Finding Workloads That You Need Using Pluggable Hybrid Analyses
Speaker: Andrea Rosà (PhD student, Università della Svizzera italiana, Switzerland)
Date/time: Friday, March 11, 2016. 11:00-12:00
Location: W911, Building West #8, Ookayama Campus, Tokyo Tech
Researchers often rely on benchmarks to demonstrate feasibility or efficiency of their contributions. However, finding the right benchmark suite can be a daunting task — existing benchmark suites may be outdated, known to be flawed, or simply irrelevant for the proposed approach. Creating a proper benchmark suite is challenging, extremely time consuming, and also — unless it becomes widely popular — a thankless endeavor. This talk introduces AutoBench, a novel approach to help researchers find relevant workloads for their experimental evaluation needs. AutoBench relies on the huge number of open-source projects available in public repositories, and on unit testing having become best practice in software development. Using a repository crawler employing pluggable static and dynamic analyses for filtering and workload characterization, AutoBench allows users to automatically find projects with relevant workloads. In this talk, we illustrate AutoBench’s methodology to find, filter, and characterize real-world workloads from public open-source repositories, and show several motivating scenarios. Preliminary results towards automatic generation of benchmark suites are also presented, arguing that unit tests can provide a viable source of workloads, and that the combination of static and dynamic analyses improves the ability to identify relevant workloads that can serve as the basis for custom benchmark suites. Finally, a short introduction to DiSL – a framework that eases the instrumentation of Java bytecode – complements the talk and exemplifies program analyses employed by AutoBench.
Andrea Rosà received the MSc degree from Politecnico di Milano, Italy, in 2013. Currently, he is working toward the PhD degree at the Faculty of Informatics, Università della Svizzera italiana (USI), Switzerland. His research interests include characterization, modeling, and optimization of parallel and distributed systems, with particular focus on system reliability, application failures, and scalability.