Multi– GPU Implementation of Machine Learning Algorithm using CUDA and OpenCL

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F01962001%3A_____%2F16%3AN0000002" target="_blank" >RIV/01962001:_____/16:N0000002 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/00216305:26220/16:PU119308

Výsledek na webu

<a href="http://ijates.org/index.php/ijates/article/view/142" target="_blank" >http://ijates.org/index.php/ijates/article/view/142</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/http://dx.doi.org/10.11601/ijates.v5i2.142" target="_blank" >http://dx.doi.org/10.11601/ijates.v5i2.142</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Multi– GPU Implementation of Machine Learning Algorithm using CUDA and OpenCL

Popis výsledku v původním jazyce

Using modern Graphic Processing Units (GPUs) becomes very useful for computing complex and time consuming processes. GPUs provide high–performance computation capabilities with a good price. This paper deals with a multi–GPU OpenCL and CUDA implementations of k–Nearest Neighbor (k– NN) algorithm. This work compares performances of OpenCL and CUDA implementations where each of them is suitable for different number of used attributes. The proposed CUDA algorithm achieves acceleration up to 880x in comparison with a single thread CPU version. The common k-NN was modified to be faster when the lower number of k neighbors is set. The performance of algorithm was verified with two GPUs dual-core NVIDIA GeForce GTX 690 and CPU Intel Core i7 3770 with 4.1 GHz frequency. The results of speed up were measured for one GPU, two GPUs, three and four GPUs. We performed several tests with data sets containing up to 4 million elements with various number of attributes.

Název v anglickém jazyce

Multi– GPU Implementation of Machine Learning Algorithm using CUDA and OpenCL

Popis výsledku anglicky

Using modern Graphic Processing Units (GPUs) becomes very useful for computing complex and time consuming processes. GPUs provide high–performance computation capabilities with a good price. This paper deals with a multi–GPU OpenCL and CUDA implementations of k–Nearest Neighbor (k– NN) algorithm. This work compares performances of OpenCL and CUDA implementations where each of them is suitable for different number of used attributes. The proposed CUDA algorithm achieves acceleration up to 880x in comparison with a single thread CPU version. The common k-NN was modified to be faster when the lower number of k neighbors is set. The performance of algorithm was verified with two GPUs dual-core NVIDIA GeForce GTX 690 and CPU Intel Core i7 3770 with 4.1 GHz frequency. The results of speed up were measured for one GPU, two GPUs, three and four GPUs. We performed several tests with data sets containing up to 4 million elements with various number of attributes.

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

IN - Informatika

OECD FORD obor

—

Projekt

<a href="/cs/project/TH01010277" target="_blank" >TH01010277: BriskMiner - Efektivní nástroj pro pokročilou analytiku podnikových procesů</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2016

Kód důvěrnosti údajů

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

Název periodika

International Journal of Advances in Telecommunications, Electrotechnics, Signals and Systems

ISSN

1805-5443

e-ISSN

—

Svazek periodika

5

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

CZ - Česká republika

Počet stran výsledku

7

Strana od-do

101-107

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—