GPU-acceleration of neighborhood-based dimensionality reduction algorithm EmbedSOM

Kód výsledku v 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>

Výsledek na webu

<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>

Jazyk výsledku

angličtina

Název v původním jazyce

GPU-acceleration of neighborhood-based dimensionality reduction algorithm EmbedSOM

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

GPU-acceleration of neighborhood-based dimensionality reduction algorithm EmbedSOM

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

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

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název statě ve sborníku

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

ISBN

979-8-4007-1817-5

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

13-18

Název nakladatele

Association for Computing Machinery

Místo vydání

New York, NY, USA

Místo konání akce

Edinburgh

Datum konání akce

2. 3. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001223947800003