TY - JOUR

T1 - bufferkdtree

T2 - a Python library for massive nearest neighbor queries on multi-many-core devices

AU - Gieseke, Fabian Cristian

AU - Oancea, Cosmin Eugen

AU - Igel, Christian

PY - 2017/3/15

Y1 - 2017/3/15

N2 - 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.

AB - 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.

KW - GPUs

KW - k-d trees

KW - Nearest neighbor queries

KW - OpenCL

KW - Python

UR - http://www.scopus.com/inward/record.url?scp=85008472806&partnerID=8YFLogxK

U2 - 10.1016/j.knosys.2017.01.002

DO - 10.1016/j.knosys.2017.01.002

M3 - Journal article

AN - SCOPUS:85008472806

VL - 120

SP - 1

EP - 3

JO - Knowledge-Based Systems

JF - Knowledge-Based Systems

SN - 0950-7051

ER -