Parallel search algorithm for finding the closest object in a collection of polygonal models

Fuente: Zenodo
Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Aksoy Tevfik Oguzhan
Format: Recurso digital
Sprache:Russisch
Veröffentlicht: Zenodo 2023
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866902179690840064
author Aksoy Tevfik Oguzhan
author_facet Aksoy Tevfik Oguzhan
contents <p>In this paper, we consider the problem of finding an element of a collection of polygonal models that is closest to a given object using parallel computing. Options for parallelizing the solution to this problem are proposed, with static and dynamic load balancing, which made it possible to significantly speed up the search process. The developed algorithm was implemented in the Python programming language using the MPI for Python library, which supports parallel computing, and tested on a collection of several thousand models on a local machine and on the IBM Polus high-performance computing system. The results of computational experiments have shown that the developed algorithm significantly outperforms the sequential search for the closest object in terms of computation speed. The algorithm proposed in this paper can be used in various fields, such as computer graphics, computer vision, robotics, and others.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_8064031
institution Zenodo
language rus
publishDate 2023
publisher Zenodo
record_format zenodo
spellingShingle Parallel search algorithm for finding the closest object in a collection of polygonal models
Aksoy Tevfik Oguzhan
<p>In this paper, we consider the problem of finding an element of a collection of polygonal models that is closest to a given object using parallel computing. Options for parallelizing the solution to this problem are proposed, with static and dynamic load balancing, which made it possible to significantly speed up the search process. The developed algorithm was implemented in the Python programming language using the MPI for Python library, which supports parallel computing, and tested on a collection of several thousand models on a local machine and on the IBM Polus high-performance computing system. The results of computational experiments have shown that the developed algorithm significantly outperforms the sequential search for the closest object in terms of computation speed. The algorithm proposed in this paper can be used in various fields, such as computer graphics, computer vision, robotics, and others.</p>
title Parallel search algorithm for finding the closest object in a collection of polygonal models
url https://doi.org/10.5281/zenodo.8064031