Efektivní implementace k-d stromu v prostředí CUDA
Loading...
Files
Downloads
4
Date issued
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Vysoká škola báňská – Technická univerzita Ostrava
Location
Signature
Abstract
This bachelor's thesis focuses on the implementation of a K-D tree or another data structure for nearest neighbor search in a multidimensional space. The goal is to parallelize this data structure in the CUDA environment and compare its efficiency against other available solutions.
Description
Subject(s)
K-D tree, Ball tree, nearest neighbor search, parallelization, CUDA, GPU, multidimensional space, space partitioning, hyperplane