KIT | KIT-Bibliothek | Impressum | Datenschutz

Performance-Detective: Automatic Deduction of Cheap and Accurate Performance Models

Schmid, Larissa ORCID iD icon 1; Copik, Marcin; Calotoiu, Alexandru; Werle, Dominik 1; Reiter, Andreas; Selzer, Michael 2; Koziolek, Anne ORCID iD icon 1; Hoefler, Torsten
1 Institut für Informationssicherheit und Verlässlichkeit (KASTEL), Karlsruher Institut für Technologie (KIT)
2 Institut für Angewandte Materialien – Mikrostruktur-Modellierung und Simulation (IAM-MMS), Karlsruher Institut für Technologie (KIT)

Abstract:

The many configuration options of modern applications make it difficult for users to select a performance-optimal configuration. Performance models help users in understanding system performance and choosing a fast configuration. Existing performance modeling approaches for applications and configurable systems either require a full-factorial experiment design or a sampling design based on heuristics. This results in high costs for achieving accurate models. Furthermore, they require repeated execution of experiments to account for measurement noise. We propose Performance-Detective, a novel code analysis tool that deduces insights on the interactions of program parameters. We use the insights to derive the smallest necessary experiment design and avoiding repetitions of measurements when possible, significantly lowering the cost of performance modeling. We evaluate Performance-Detective using two case studies where we reduce the number of measurements from up to 3125 to only 25, decreasing cost to only 2.9% of the previously needed core hours, while maintaining accuracy of the resulting model with 91.5% compared to 93.8% using all 3125 measurements.


Verlagsausgabe §
DOI: 10.5445/IR/1000146623
Veröffentlicht am 23.05.2022
Originalveröffentlichung
DOI: 10.1145/3524059.3532391
Scopus
Zitationen: 1
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Informationssicherheit und Verlässlichkeit (KASTEL)
Institut für Angewandte Materialien – Mikrostruktur-Modellierung und Simulation (IAM-MMS)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2022
Sprache Englisch
Identifikator ISBN: 978-1-4503-9281-5
KITopen-ID: 1000146623
Erschienen in ACM International Conference on Supercomputing (ICS '22), Virtual Event, June 28-30, 2022
Veranstaltung International Conference on Supercomputing (ICS 2022), Online, 28.06.2022 – 30.06.2022
Verlag Association for Computing Machinery (ACM)
Schlagwörter automatic performance modeling, empirical performance modeling, experiment design, configurable systems
Nachgewiesen in Dimensions
Scopus
Relationen in KITopen
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page