- Titel
- SIMD-MIMD cocktail in a hybrid memory glass: shaken, not stirred
- Zitierfähige Url:
- https://nbn-resolving.org/urn:nbn:de:bsz:14-qucosa2-766710
- Konferenz
- SYSTOR '21: Proceedings of the 14th ACM International Conference on Systems and Storage. Haifa, Israel, 14. - 16.06.2021
- Quellenangabe
- Proceedings of the 14th ACM International Conference on Systems and Storage (SYSTOR ´21)
Erscheinungsort: New York, NY
Verlag: ACM
Erscheinungsjahr: 2021 - Erstveröffentlichung
- 2021
- Abstract (EN)
- Hybrid memory systems consisting of DRAM and NVRAM offer a great opportunity for column-oriented data systems to persistently store and to efficiently process columnar data completely in main memory. While vectorization (SIMD) of query operators is state-of-the-art to increase the single-thread performance, it has to be combined with thread-level parallelism (MIMD) to satisfy growing needs for higher performance and scalability. However, it is not well investigated how such a SIMD-MIMD interplay could be leveraged efficiently in hybrid memory systems. On the one hand, we deliver an extensive experimental evaluation of typical workloads on columnar data in this paper. We reveal that the choice of the most performant SIMD version differs greatly for both memory types. Moreover, we show that the throughput of concurrent queries can be boosted (up to 2x) when combining various SIMD flavors in a multi-threaded execution. On the other hand, to enable that optimization, we propose an adaptive SIMD-MIMD cocktail approach incurring only a negligible runtime overhead.
- Andere Ausgabe
- Link zum Artikel, der zuerst in der ACM Digital Library erschienen ist
DOI: 10.1145/3456727.3463782 - Freie Schlagwörter (DE)
- Hybridspeicher; spaltenorientierter Speicher; SIMD; MIMD; Optimierung
- Freie Schlagwörter (EN)
- hybrid memory; column store; SIMD; MIMD; optimization
- Klassifikation (DDC)
- 621.3
- Verlag
- ACM, New York
- Förder- / Projektangaben
- Deutsche Forschungsgemeinschaft (DFG)
Individual project
ID: LE-1416/27-1
European Commission (EC)
H2020 | RIA
Integrated Data Analysis Pipelines for Large-Scale Data Management, HPC, and Machine Learning (DAPHNE)
ID: 957407
Deutsche Forschungsgemeinschaft (DFG)
Reinhart Koselleck Projekt
ID: LE-1416/28-1 - Version / Begutachtungsstatus
- angenommene Version / Postprint / Autorenversion
- URN Qucosa
- urn:nbn:de:bsz:14-qucosa2-766710
- Veröffentlichungsdatum Qucosa
- 23.11.2021
- Dokumenttyp
- Konferenzbeitrag
- Sprache des Dokumentes
- Englisch
- Lizenz / Rechtehinweis
