Search Update Optimization of a B^+Tree in a Hardware Aided Semantic Web Database System

Dennis Heinrich, Stefan Werner, Christopher Blochwitz, Thilo Pionteck, Sven Groppe

Abstract

This paper presents a hybrid architecture for accelerating search and update operations on Semantic Web indices. This database system uses a B^+-tree index structure distributed in a Field Programmable Gate Array (FPGA) and a CPU-based host system. The index is divided into two parts. The host system stores the values and the keys of the lower levels of the B^+-tree while a certain amount of the frequently accessed levels including the tree root is stored in the FPGAs internal and attached memory. Inside the FPGA we accelerate search operations by exploiting the parallel nature of the FPGA. By this, update operations can benefit from the speed up of their necessary searches. Furthermore, we estimate the performance based on the given experiments in a worst case scenario.
Original languageEnglish
Title of host publicationProceedings of the 7th International Conference on Emerging Databases
EditorsWookey Lee, Wonik Choi, Sungwon Jung, Min Song
Number of pages11
Place of PublicationSingapore
PublisherSpringer Singapore
Publication date14.10.2018
Pages172-182
ISBN (Print)978-981-10-6519-4
ISBN (Electronic)978-981-10-6520-0
DOIs
Publication statusPublished - 14.10.2018
Event7th International Conference on Emerging Databases: Technologies, Applications, and Theory - Busan, Korea, Republic of
Duration: 07.08.201709.08.2017
Conference number: 200819

Research Areas and Centers

  • Research Area: Intelligent Systems
  • Centers: Center for Artificial Intelligence Luebeck (ZKIL)

DFG Research Classification Scheme

  • 409-04 Operating, Communication, Database and Distributed Systems

Fingerprint

Dive into the research topics of 'Search Update Optimization of a B^+Tree in a Hardware Aided Semantic Web Database System'. Together they form a unique fingerprint.

Cite this