GPU-acceleration of neighborhood-based dimensionality reduction algorithm EmbedSOM

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F24%3A10481543" target="_blank" >RIV/00216208:11320/24:10481543 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.1145/3649411.3649414" target="_blank" >https://doi.org/10.1145/3649411.3649414</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3649411.3649414" target="_blank" >10.1145/3649411.3649414</a>

Result language

angličtina

Original language name

GPU-acceleration of neighborhood-based dimensionality reduction algorithm EmbedSOM

Original language description

Dimensionality reduction methods have found vast applications as visualization tools in diverse areas of science. Although many different methods exist, their performance is often insufficient for providing quick insight into many contemporary datasets. In this paper, we propose a highly optimized GPU implementation of EmbedSOM, a dimensionality reduction algorithm based on self-organizing maps. We detail the optimizations of k-NN search and 2D projection kernels which comprise the core of the algorithm. To tackle the thread divergence and low arithmetic intensity, we use a modified bitonic sort for k-NN search and a projection kernel that utilizes vector loads and register caches. The evaluated performance benchmarks indicate that the optimized EmbedSOM implementation is capable of projecting over 30 million individual data points per second.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2024

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

GPGPU &apos;24: Proceedings of the 16th Workshop on General Purpose Processing Using GPU

ISBN

979-8-4007-1817-5

ISSN

—

e-ISSN

—

Number of pages

6

Pages from-to

13-18

Publisher name

Association for Computing Machinery

Place of publication

New York, NY, USA

Event location

Edinburgh

Event date

Mar 2, 2024

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

001223947800003