SIGMOD2019_AcceptedVersion.pdf (2.19 MB)
Hyperion: Building the largest in-memory search tree
conference contribution
posted on 2019-04-04, 14:24 authored by Markus Masker, Tim Suss, Lars NagelLars Nagel, Lingfang Zeng, Andre BrinkmannIndexes are essential in data management systems to increase the speed of data retrievals. Widespread data structures to provide fast and memory-efficient indexes are prefix tries. Implementations like Judy, ART, or HOT optimize their internal alignments for cache and vector unit efficiency. While these measures usually improve the performance substantially, they can have a negative impact on memory efficiency. In this paper we present Hyperion, a trie-based main-memory key-value store achieving extreme space efficiency. In contrast to other data structures, Hyperion does not depend on CPU vector units, but scans the data structure linearly. Combined with a custom memory allocator, Hyperion accomplishes a remarkable data density while achieving a competitive point query and an exceptional range query performance. Hyperion can significantly reduce the index memory footprint, while being at least two times better concerning the performance to memory ratio compared to the best implemented alternative strategies for randomized string data sets.
History
School
- Science
Department
- Computer Science
Published in
Proceedings of the 2019 International Conference on Management of Data (SIGMOD '19)Pages
1207 - 1222Citation
MASKER, M. ... et al, 2019. Hyperion: Building the largest in-memory search tree. IN: 2019 International Conference on Management of Data (SIGMOD ’19), Amsterdam, Netherlands, June 30-July 5, 2019, pp.1207-1222.Publisher
ACMVersion
- AM (Accepted Manuscript)
Rights holder
© Owner/AuthorPublisher statement
© Owner/Author 2019. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in Proceedings of the 2019 International Conference on Management of Data (SIGMOD '19), http://dx.doi.org/10.1145/3299869.3319870.Acceptance date
2019-03-11Publication date
2019-06-25Copyright date
2019ISBN
9781450356435Language
- en