Kreutzer, Sebastian ; Arzt, Peter ; Rickert, Jonas ; Lehr, Jan-Patrick ; Iwainsky, Christian ; Bischof, Christian (2024)
Overhead-Guided Instrumentation Refinement.
2024 International Conference for High Performance Computing, Networking, Storage and Analysis. Atlanta, USA (17.11.2024-22.11.2024)
doi: 10.1109/SCW63240.2024.00198
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Instrumentation is a widely used technique for gathering performance data. However, excessive instrumentation can lead to significant runtime overheads, potentially skewing performance analysis results. In this work, we propose a novel approach to automatically generate and refine instrumentation configurations (ICs) to maximize measurement coverage while adhering to a user-defined overhead budget. Our approach formulates the problem of selecting instrumented functions as a binary knapsack problem, integrating dynamic profile data and static call-graph information to estimate costs. We implement this approach within the PIRA profiling infrastructure and demonstrate its effectiveness with the LULESH, AMG2013, MILC and ASTAR proxy applications, achieving relevant hot spot coverage while staying within the specified overhead limit.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2024 |
| Autor(en): | Kreutzer, Sebastian ; Arzt, Peter ; Rickert, Jonas ; Lehr, Jan-Patrick ; Iwainsky, Christian ; Bischof, Christian |
| Art des Eintrags: | Bibliographie |
| Titel: | Overhead-Guided Instrumentation Refinement |
| Sprache: | Englisch |
| Publikationsjahr: | 2024 |
| Verlag: | IEEE |
| Buchtitel: | Proceedings of the Workshops of the SC'24 International Conference for High Performance Computing, Networking, Storage and Analysis |
| Veranstaltungstitel: | 2024 International Conference for High Performance Computing, Networking, Storage and Analysis |
| Veranstaltungsort: | Atlanta, USA |
| Veranstaltungsdatum: | 17.11.2024-22.11.2024 |
| DOI: | 10.1109/SCW63240.2024.00198 |
| Kurzbeschreibung (Abstract): | Instrumentation is a widely used technique for gathering performance data. However, excessive instrumentation can lead to significant runtime overheads, potentially skewing performance analysis results. In this work, we propose a novel approach to automatically generate and refine instrumentation configurations (ICs) to maximize measurement coverage while adhering to a user-defined overhead budget. Our approach formulates the problem of selecting instrumented functions as a binary knapsack problem, integrating dynamic profile data and static call-graph information to estimate costs. We implement this approach within the PIRA profiling infrastructure and demonstrate its effectiveness with the LULESH, AMG2013, MILC and ASTAR proxy applications, achieving relevant hot spot coverage while staying within the specified overhead limit. |
| Freie Schlagworte: | High-performance computing, Instrumentation, Performance profiling |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Scientific Computing Zentrale Einrichtungen Zentrale Einrichtungen > Hochschulrechenzentrum (HRZ) Zentrale Einrichtungen > Hochschulrechenzentrum (HRZ) > Hochleistungsrechner |
| Hinterlegungsdatum: | 15 Jan 2025 13:44 |
| Letzte Änderung: | 15 Jan 2025 13:44 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum