Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Data stream statistics over sliding windows: how to summarize 150 million updates per second on a single node

Chrysos Grigorios, Papapetrou, Odysseas 1978-, Pnevmatikatos Dionysios, Dollas Apostolos, Garofalakis Minos

Simple record


URIhttp://purl.tuc.gr/dl/dias/D3411926-5317-40D6-A869-3071D319742B-
Identifierhttps://doi.org/10.1109/FPL.2019.00052-
Identifierhttps://ieeexplore.ieee.org/document/8892241-
Languageen-
Extent8 pagesen
TitleData stream statistics over sliding windows: how to summarize 150 million updates per second on a single nodeen
CreatorChrysos Grigoriosen
CreatorΧρυσος Γρηγοριοςel
CreatorPapapetrou, Odysseas 1978-en
CreatorPnevmatikatos Dionysiosen
CreatorΠνευματικατος Διονυσιοςel
CreatorDollas Apostolosen
CreatorΔολλας Αποστολοςel
CreatorGarofalakis Minosen
CreatorΓαροφαλακης Μινωςel
PublisherInstitute of Electrical and Electronics Engineersen
Content SummaryTraditional data management systems map information using centralized and static data structures. Modern applications need to process in real time datasets much larger than system memory. To achieve this, they use dynamic entities that are updated with streaming input data over a sliding window. For efficient and high performance processing, approximate sketch synopses of input streams have been proposed as effective means for the summarization of streaming data over large sliding windows with probabilistic accuracy guarantees. This work presents a system-level solution to accelerate the Exponential Count-Min (ECM) sketch algorithm on reconfigurable technology. Different reconfigurable architectures for the sketch structure that correspond to different cost and performance tradeoffs are presented. We map the proposed system-level ECM sketch architectures to a high-end modern HPC platform to achieve guaranteed and best-effort update rates up to 150 and 180 million tuples per second respectively. We compare the performance of the implemented system against the best optimized multi-thread software alternative and show that our scalable full-system accelerators outperform software solutions by 5-7.5x for Virtex6 devices and in excess of 10x for current Ultrascale devices.en
Type of ItemΠλήρης Δημοσίευση σε Συνέδριοel
Type of ItemConference Full Paperen
Licensehttp://creativecommons.org/licenses/by/4.0/en
Date of Item2020-04-27-
Date of Publication2019-
SubjectECM sketchen
SubjectExponential histogramen
SubjectReconfigurable architectureen
SubjectReconfigurable computingen
SubjectStream processingen
Bibliographic CitationG. Chrysos, O. Papapetrou, D. Pnevmatikatos, A. Dollas and M. Garofalakis, "Data stream statistics over sliding windows: how to summarize 150 million updates per second on a single node," in 29th International Conferenceon Field-Programmable Logic and Applications, 2019, pp. 278-285. doi: 10.1109/FPL.2019.00052en

Services

Statistics