Multi-GPU Implementation of k-Nearest Neighbor Algorithm

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F14%3APU108815" target="_blank" >RIV/00216305:26220/14:PU108815 - isvavai.cz</a>
Result on the web
<a href="https://ieeexplore.ieee.org/document/7296368" target="_blank" >https://ieeexplore.ieee.org/document/7296368</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/TSP.2015.7296368" target="_blank" >10.1109/TSP.2015.7296368</a>

Result language
angličtina
Original language name
Multi-GPU Implementation of k-Nearest Neighbor Algorithm
Original language description
Using modern Graphic Processing Units (Gills) becomes very useful for computing complex and time consuming processes. CPUs provide high performance computation capabilities with a good price. This paper deals with a multi-GPU OpenCL implementation of k-Nearest Neighbor (k-NN) algorithm. The proposed OpenCL algorithm achieves acceleration up to 750x 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.
Czech name
—
Czech description
—

Project
<a href="/en/project/FR-TI4%2F151" target="_blank" >FR-TI4/151: Research and development of technology for machine emotion detection in unstructured data</a><br>
Continuities
S - Specificky vyzkum na vysokych skolach

Publication year
2015
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings of the 38th International Conference on Telecommunication and Signal Processing
ISBN
978-1-4799-8497-8
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
764-767
Publisher name
Neuveden
Place of publication
Berlin, Germany
Event location
Berlín
Event date
Jul 1, 2014
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000375231000259

Similar results(10)