Suche nach Personen

plus im Publikationsserver
plus bei Google Scholar

Bibliografische Daten exportieren
 

A performance- and energy-oriented extended tuning process for time-step-based scientific applications

DOI zum Zitieren der Version auf EPub Bayreuth: https://doi.org/10.15495/EPub_UBT_00005336
URN zum Zitieren der Version auf EPub Bayreuth: urn:nbn:de:bvb:703-epub-5336-3

Titelangaben

Kalinnik, Natalia ; Kiesel, Robert ; Rauber, Thomas ; Richter, Marcel ; Rünger, Gudula:
A performance- and energy-oriented extended tuning process for time-step-based scientific applications.
In: The Journal of Supercomputing. Bd. 76 (2021) . - S. 3484-3515.
ISSN 1573-0484
DOI der Verlagsversion: https://doi.org/10.1007/s11227-020-03402-y

Volltext

[thumbnail of Kalinnik2021_Article_APerformance-AndEnergy-oriente.pdf]
Format: PDF
Name: Kalinnik2021_Article_APerformance-AndEnergy-oriente.pdf
Version: Veröffentlichte Version
Verfügbar mit der Lizenz Creative Commons BY 4.0: Namensnennung
Download (2MB)

Abstract

Scientific application codes are often long-running time- and energy-consuming parallel codes, and the tuning of these methods towards the characteristics of a specific hardware is essential for a good performance. However, since scientific software is often developed over many years, the application software usually survives several hardware generations, which might make a re-tuning of the existing codes necessary. To simplify the tuning process, it would be beneficial to have software with inherent tuning possibilities. In this article, we explore the possibilities of tuning methods for time-step-based applications. Two different time-step-based application classes are considered, which are solution methods for ordinary differential equations and particle simulation methods. The investigation comprises a broad range of tuning possibilities, starting from the choice of algorithms, the parallel programming model, static implementation variants, input characteristics as well as hardware parameters for parallel execution. An experimental investigation shows the different characteristics of the application classes on different multicore systems. The results show that a combination of offline and online tuning leads to good tuning results. However, due to the different input characteristics of the two application classes, regular versus irregular, different tuning aspects are most essential.

Weitere Angaben

Publikationsform: Artikel in einer Zeitschrift
Keywords: time-stepping methods; ordinary differential equation; particle simulation; offline tuning; online tuning; multicore
Themengebiete aus DDC: 000 Informatik,Informationswissenschaft, allgemeine Werke > 004 Informatik
Institutionen der Universität: Fakultäten > Fakultät für Mathematik, Physik und Informatik > Institut für Informatik > Lehrstuhl Angewandte Informatik II > Lehrstuhl Angewandte Informatik II - Univ.-Prof. Dr. Thomas Rauber
Fakultäten
Fakultäten > Fakultät für Mathematik, Physik und Informatik
Fakultäten > Fakultät für Mathematik, Physik und Informatik > Institut für Informatik
Fakultäten > Fakultät für Mathematik, Physik und Informatik > Institut für Informatik > Lehrstuhl Angewandte Informatik II
Sprache: Englisch
Titel an der UBT entstanden: Ja
URN: urn:nbn:de:bvb:703-epub-5336-3
Eingestellt am: 17 Mrz 2021 11:22
Letzte Änderung: 17 Mrz 2021 11:22
URI: https://epub.uni-bayreuth.de/id/eprint/5336

Downloads

Downloads pro Monat im letzten Jahr