Workload-Driven Data Placement for GPU-Accelerated Database Management Systems
dc.contributor.author | Schmidt, Christopher | |
dc.contributor.author | Uflacker, Matthias | |
dc.contributor.editor | Meyer, Holger | |
dc.contributor.editor | Ritter, Norbert | |
dc.contributor.editor | Thor, Andreas | |
dc.contributor.editor | Nicklas, Daniela | |
dc.contributor.editor | Heuer, Andreas | |
dc.contributor.editor | Klettke, Meike | |
dc.date.accessioned | 2019-04-15T11:40:42Z | |
dc.date.available | 2019-04-15T11:40:42Z | |
dc.date.issued | 2019 | |
dc.description.abstract | An increase in the memory capacity of current Graphics Processing Unit (GPU) generations and advances in multi-GPU systems enables a large unified GPU memory space to be utilized by modern coprocessor-accelerated Database Management System (DBMS). We take this as an opportunity to revisit the idea of using GPU memory as a hot cache for the DBMS. In particular, we focus on the data placement for the hot cache. Based on previous approaches and their shortcomings, we present a new workload-driven data placement for a GPU-accelerated DBMS. Lastly, we outline how we aim to implement and evaluate our proposed approach by comparing it to existing data placement approaches in future work. | en |
dc.identifier.doi | 10.18420/btw2019-ws-08 | |
dc.identifier.isbn | 978-3-88579-684-8 | |
dc.identifier.pissn | 1617-5468 | |
dc.identifier.uri | https://dl.gi.de/handle/20.500.12116/21829 | |
dc.language.iso | en | |
dc.publisher | Gesellschaft für Informatik, Bonn | |
dc.relation.ispartof | BTW 2019 – Workshopband | |
dc.relation.ispartofseries | Lecture Notes in Informatics (LNI) – Proceedings, Volume P-290 | |
dc.subject | GPU-Acceleration | |
dc.subject | Coprocessor-Accelerated Databases | |
dc.subject | Data Placement | |
dc.title | Workload-Driven Data Placement for GPU-Accelerated Database Management Systems | en |
gi.citation.endPage | 94 | |
gi.citation.startPage | 91 | |
gi.conference.date | 4.-8. März 2019 | |
gi.conference.location | Rostock | |
gi.conference.sessiontitle | 1st Workshop on Novel Data Management Ideas on Heterogeneous (Co-)Processors (NoDMC) |
Dateien
Originalbündel
1 - 1 von 1