Publication result detail

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

MAŠEK, J.; BURGET, R.; POVODA, L.; DUTTA, M.

Original Title

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

English Title

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

Type

Peer-reviewed article not indexed in WoS or Scopus

Original Abstract

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.

English abstract

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.

Keywords

Artificial intelligence, big data, comparison, CUDA, GPU, high performance computing, k-NN, multi–GPU, OpenCL.

Key words in English

Artificial intelligence, big data, comparison, CUDA, GPU, high performance computing, k-NN, multi–GPU, OpenCL.

Authors

MAŠEK, J.; BURGET, R.; POVODA, L.; DUTTA, M.

RIV year

2017

Released

10.06.2016

Publisher

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

ISBN

1805-5443

Periodical

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

Volume

5

Number

2

State

Czech Republic

Pages from

101

Pages to

107

Pages count

7

URL

http://ijates.org/index.php/ijates/article/view/142

BibTex

@article{BUT125826,
  author="Jan {Mašek} and Radim {Burget} and Lukáš {Povoda} and Malay Kishore {Dutta}",
  title="Multi–GPU Implementation of Machine Learning Algorithm using CUDA and OpenCL",
  journal="International Journal of Advances in Telecommunications, Electrotechnics, Signals and Systems",
  year="2016",
  volume="5",
  number="2",
  pages="101--107",
  doi="10.11601/ijates.v5i2.142",
  issn="1805-5443",
  url="http://ijates.org/index.php/ijates/article/view/142"
}