Publication detail

Multi–GPU Implementation of k-Nearest Neighbor Algorithm

MAŠEK, J. BURGET, R. KARÁSEK, J. UHER, V. DUTTA, M.

Original Title

Multi–GPU Implementation of k-Nearest Neighbor Algorithm

English Title

Multi–GPU Implementation of k-Nearest Neighbor Algorithm

Type

conference paper

Language

en

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 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 4.1GHz 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 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 4.1GHz 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, GPU, high performance computing, k-NN, multi–GPU, OpenCL.

RIV year

2014

Released

01.07.2014

Location

Berlin, Germany

ISBN

978-1-4799-8497-8

Book

Proceedings of the 38th International Conference on Telecommunication and Signal Processing

Pages from

764

Pages to

767

Pages count

4

BibTex


@inproceedings{BUT107205,
  author="Jan {Mašek} and Radim {Burget} and Jan {Karásek} and Václav {Uher} and Malay Kishore {Dutta}",
  title="Multi–GPU Implementation of k-Nearest Neighbor Algorithm",
  annote="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 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 4.1GHz 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.",
  booktitle="Proceedings of the 38th International Conference on Telecommunication and Signal Processing",
  chapter="107205",
  howpublished="online",
  year="2014",
  month="july",
  pages="764--767",
  type="conference paper"
}