Design-time performance modeling of compositional parallel programs

Performance models are powerful instruments for understanding the performance of parallel systems and uncovering their bottlenecks. Already during system design, performance models can help ponder alternative development options. However, creating a performance model – whether theoretically or empir...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Parallel computing Jg. 108; H. C
Hauptverfasser: Czappa, Fabian, Calotoiu, Alexandru, Höhl, Thomas, Mantel, Heiko, Nguyen, Toni, Wolf, Felix
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States Elsevier 11.09.2021
Schlagworte:
Computer Science
Design pattern
MapReduce
MATHEMATICS AND COMPUTING
MPI
Performance modeling
ISSN:0167-8191, 1872-7336
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Performance models are powerful instruments for understanding the performance of parallel systems and uncovering their bottlenecks. Already during system design, performance models can help ponder alternative development options. However, creating a performance model – whether theoretically or empirically – for an entire application that does not exist yet is challenging. In this paper, we propose to generate performance models of full programs from performance models of their components using formal composition operators derived from parallel design patterns. As long as the design of the overall system follows such a pattern, its performance model can be predicted with reasonable accuracy without an actual implementation. In conclusion, we demonstrate our approach with design patterns of varying complexity, including pipeline, task pool, and eventually MapReduce, which is representative of a broad class of data-analytics applications.
Bibliographie:SC0015524; 323299120; 320898076; 449683531
USDOE Office of Science (SC)
German Research Foundation (DFG)
ISSN:0167-8191
1872-7336