CBPGM: A Cache Based Piecewise Geometric Model Index

  • Xiaopei Xu
  • , Guitao Cao*
  • , Yan Li
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Recent works on learned indexes have changed the way we look at the decades-old field of Database Management System indexing. However, they are limited to too many hyperparameters, long model construction time, and not taking full advantage of CPU cache and hardware acceleration. In this paper, we propose a Cache Based Piecewise Geometric Model (CBPGM) Index to address these issues with only one hyperparameter and effectively combines a sampling approach to reduce training dataset size that accelerates the construction procedure and aligns models and data to the CPU cache line to improve search performance. Experimental results show that the CBPGM index can improve the construction speed up to 8× and the query speed by 30% compared with the PGM index.

Original languageEnglish
Title of host publication2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2968-2974
Number of pages7
ISBN (Print)9781665452588
DOIs
StatePublished - 2022
Event2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022 - Prague, Czech Republic
Duration: 9 Oct 202212 Oct 2022

Publication series

NameConference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
Volume2022-October
ISSN (Print)1062-922X

Conference

Conference2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022
Country/TerritoryCzech Republic
CityPrague
Period9/10/2212/10/22

Keywords

  • block sample
  • cache block
  • learned index
  • piecewise linear

Fingerprint

Dive into the research topics of 'CBPGM: A Cache Based Piecewise Geometric Model Index'. Together they form a unique fingerprint.

Cite this