The development of algorithms for parallel knowledge discovery using graphics accelerators

被引：0

作者：

Zielinski, Pawel ^{[1
]}

Mulawka, Jan ^{[1
]}

机构：

[1] Warsaw Univ Technol, Inst Elect Syst, PL-00661 Warsaw, Poland

来源：

PHOTONICS APPLICATIONS IN ASTRONOMY, COMMUNICATIONS, INDUSTRY, AND HIGH-ENERGY PHYSICS EXPERIMENTS 2011 | 2011年 / 8008卷

关键词：

CUDA; OpenMP; k-nearest neighbors; support vector machines; logistic regression;

D O I：

10.1117/12.904125

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

The paper broaches topics of selected knowledge discovery algorithms. Different implementations have been verified on parallel platforms, including graphics accelerators using CUDA technology, multi-core microprocessors using OpenMP and many graphics accelerators. Results of investigations have been compared in terms of performance and scalability. Different types of data representation were also tested. The possibilities of both platforms, using the classification algorithms: the k-nearest neighbors, support vector machines and logistic regression are discussed.

引用

页数：8

共 20 条

[1]

[Anonymous], 2010, ANN: a library for approximate nearest neighbor searching

[2]

[Anonymous], 2008, P 25 INT C MACHINE L, DOI DOI 10.1145/1390156.1390170

[3]

[Anonymous], 2007, NVidia CUDA Compute Unified Device Architecture: Programming Guide

[4]

[Anonymous], 2007, Uci machine learning repository

[5]

[Anonymous], 2000, WILEY PS TX, DOI 10.1002/0471722146

[6]

[Anonymous], 2009, MPI DOC

[7]

[Anonymous], COMP VIS PATT REC WO

[8]

Chandra R., 2001, Parallel programing in OpenMP, DOI DOI 10.5555/355074

[9] LIBSVM: A Library for Support Vector Machines [J].

Chang, Chih-Chung ;

Lin, Chih-Jen .

ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2011, 2 (03)

[10]

Cherkassky V, 1997, IEEE Trans Neural Netw, V8, P1564, DOI 10.1109/TNN.1997.641482

← 1 2 →