bufferkdtree: a Python library for massive nearest neighbor queries on multi-many-core devices

Fabian Cristian Gieseke*, Cosmin Eugen Oancea, Christian Igel

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearch

2 Citations (Scopus)

Abstract

The bufferkdtree package is an open-source software that provides an efficient implementation for processing huge amounts of nearest neighbor queries in Euclidean spaces of moderate dimensionality. Its underlying implementation resorts to a variant of the classical k-d tree data structure, called buffer k-d tree, which can be used to efficiently perform bulk nearest neighbor searches on modern many-core devices. The package, which is based on Python, C, and OpenCL, is made publicly available online at https://github.com/gieseke/bufferkdtree under the GPLv2 license.

Original languageEnglish
JournalKnowledge-Based Systems
Volume120
Pages (from-to)1-3
Number of pages3
ISSN0950-7051
DOIs
Publication statusPublished - 15 Mar 2017

Keywords

  • GPUs
  • k-d trees
  • Nearest neighbor queries
  • OpenCL
  • Python

Cite this