A parallel data mining algorithm for pagerank computation

Massinissa Saoudi; Massinissa Lounis; Ahcène Bounceur; Reinhardt Euler; Tahar Kechadi

doi:10.1145/3010089.3010118

A parallel data mining algorithm for pagerank computation

Massinissa Saoudi
, Massinissa Lounis
, Ahcène Bounceur
, Reinhardt Euler
, Tahar Kechadi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

We study the utility of graphics processing units (GPUs) for an acceleration of the data mining PageRank algorithm and a reduction of the memory size of the web graph. We first present a new web graph representation using a compressed format in order to reduce the memory allocation of the web graph. Then, this web graph is simply partitioned into small chunks to be processed on the GPUs' device. The basic steps of the algorithm are then split up into parallel oper- ations allowing to exploit the computing power of GPUs in the CUDA language as best as possible. In the experiments, we have tested the algorithm using GPUs with a set of real web data, and compared the computation with a CPU-based one. The obtained results show that the proposed PageR- ank computation on GPUs outperforms the CPU version by a factor of 100, reducing at the same time the web graph memory storage by 93; 928%.

Original language	English
Title of host publication	Proceedings of the International Conference on Big Data and Advanced Wireless Technologies, BDAW 2016
Editors	Djallel Eddine Boubiche, Hani Hamdan, Ahcene Bounceur
Publisher	Association for Computing Machinery
ISBN (Electronic)	9781450347792
DOIs	https://doi.org/10.1145/3010089.3010118
State	Published - 10 Nov 2016
Externally published	Yes
Event	2016 International Conference on Big Data and Advanced Wireless Technologies, BDAW 2016 - Blagoevgrad, Bulgaria Duration: 10 Nov 2016 → 11 Nov 2016

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	2016 International Conference on Big Data and Advanced Wireless Technologies, BDAW 2016
Country/Territory	Bulgaria
City	Blagoevgrad
Period	10/11/16 → 11/11/16

Bibliographical note

Publisher Copyright:
© 2016 ACM.

Keywords

Big Data
CUDA
Data Mining
PageRank
Parallel Computation

ASJC Scopus subject areas

Software
Human-Computer Interaction
Computer Vision and Pattern Recognition
Computer Networks and Communications

Access to Document

10.1145/3010089.3010118

Cite this

Saoudi, M., Lounis, M., Bounceur, A., Euler, R., & Kechadi, T. (2016). A parallel data mining algorithm for pagerank computation. In D. E. Boubiche, H. Hamdan, & A. Bounceur (Eds.), Proceedings of the International Conference on Big Data and Advanced Wireless Technologies, BDAW 2016 Article a33 (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3010089.3010118

Saoudi, Massinissa ; Lounis, Massinissa ; Bounceur, Ahcène et al. / A parallel data mining algorithm for pagerank computation. Proceedings of the International Conference on Big Data and Advanced Wireless Technologies, BDAW 2016. editor / Djallel Eddine Boubiche ; Hani Hamdan ; Ahcene Bounceur. Association for Computing Machinery, 2016. (ACM International Conference Proceeding Series).

@inproceedings{f6e257c376f5486f9531e5f22471d2de,

title = "A parallel data mining algorithm for pagerank computation",

abstract = "We study the utility of graphics processing units (GPUs) for an acceleration of the data mining PageRank algorithm and a reduction of the memory size of the web graph. We first present a new web graph representation using a compressed format in order to reduce the memory allocation of the web graph. Then, this web graph is simply partitioned into small chunks to be processed on the GPUs' device. The basic steps of the algorithm are then split up into parallel oper- ations allowing to exploit the computing power of GPUs in the CUDA language as best as possible. In the experiments, we have tested the algorithm using GPUs with a set of real web data, and compared the computation with a CPU-based one. The obtained results show that the proposed PageR- ank computation on GPUs outperforms the CPU version by a factor of 100, reducing at the same time the web graph memory storage by 93; 928\%.",

keywords = "Big Data, CUDA, Data Mining, PageRank, Parallel Computation",

author = "Massinissa Saoudi and Massinissa Lounis and Ahc{\`e}ne Bounceur and Reinhardt Euler and Tahar Kechadi",

note = "Publisher Copyright: {\textcopyright} 2016 ACM.; 2016 International Conference on Big Data and Advanced Wireless Technologies, BDAW 2016 ; Conference date: 10-11-2016 Through 11-11-2016",

year = "2016",

month = nov,

day = "10",

doi = "10.1145/3010089.3010118",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

editor = "Boubiche, \{Djallel Eddine\} and Hani Hamdan and Ahcene Bounceur",

booktitle = "Proceedings of the International Conference on Big Data and Advanced Wireless Technologies, BDAW 2016",

}

Saoudi, M, Lounis, M, Bounceur, A, Euler, R & Kechadi, T 2016, A parallel data mining algorithm for pagerank computation. in DE Boubiche, H Hamdan & A Bounceur (eds), Proceedings of the International Conference on Big Data and Advanced Wireless Technologies, BDAW 2016., a33, ACM International Conference Proceeding Series, Association for Computing Machinery, 2016 International Conference on Big Data and Advanced Wireless Technologies, BDAW 2016, Blagoevgrad, Bulgaria, 10/11/16. https://doi.org/10.1145/3010089.3010118

A parallel data mining algorithm for pagerank computation. / Saoudi, Massinissa; Lounis, Massinissa; Bounceur, Ahcène et al.
Proceedings of the International Conference on Big Data and Advanced Wireless Technologies, BDAW 2016. ed. / Djallel Eddine Boubiche; Hani Hamdan; Ahcene Bounceur. Association for Computing Machinery, 2016. a33 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A parallel data mining algorithm for pagerank computation

AU - Saoudi, Massinissa

AU - Lounis, Massinissa

AU - Bounceur, Ahcène

AU - Euler, Reinhardt

AU - Kechadi, Tahar

PY - 2016/11/10

Y1 - 2016/11/10

N2 - We study the utility of graphics processing units (GPUs) for an acceleration of the data mining PageRank algorithm and a reduction of the memory size of the web graph. We first present a new web graph representation using a compressed format in order to reduce the memory allocation of the web graph. Then, this web graph is simply partitioned into small chunks to be processed on the GPUs' device. The basic steps of the algorithm are then split up into parallel oper- ations allowing to exploit the computing power of GPUs in the CUDA language as best as possible. In the experiments, we have tested the algorithm using GPUs with a set of real web data, and compared the computation with a CPU-based one. The obtained results show that the proposed PageR- ank computation on GPUs outperforms the CPU version by a factor of 100, reducing at the same time the web graph memory storage by 93; 928%.

AB - We study the utility of graphics processing units (GPUs) for an acceleration of the data mining PageRank algorithm and a reduction of the memory size of the web graph. We first present a new web graph representation using a compressed format in order to reduce the memory allocation of the web graph. Then, this web graph is simply partitioned into small chunks to be processed on the GPUs' device. The basic steps of the algorithm are then split up into parallel oper- ations allowing to exploit the computing power of GPUs in the CUDA language as best as possible. In the experiments, we have tested the algorithm using GPUs with a set of real web data, and compared the computation with a CPU-based one. The obtained results show that the proposed PageR- ank computation on GPUs outperforms the CPU version by a factor of 100, reducing at the same time the web graph memory storage by 93; 928%.

KW - Big Data

KW - CUDA

KW - Data Mining

KW - PageRank

KW - Parallel Computation

UR - https://www.scopus.com/pages/publications/85015023853

U2 - 10.1145/3010089.3010118

DO - 10.1145/3010089.3010118

M3 - Conference contribution

AN - SCOPUS:85015023853

T3 - ACM International Conference Proceeding Series

BT - Proceedings of the International Conference on Big Data and Advanced Wireless Technologies, BDAW 2016

A2 - Boubiche, Djallel Eddine

A2 - Hamdan, Hani

A2 - Bounceur, Ahcene

PB - Association for Computing Machinery

T2 - 2016 International Conference on Big Data and Advanced Wireless Technologies, BDAW 2016

Y2 - 10 November 2016 through 11 November 2016

ER -

Saoudi M, Lounis M, Bounceur A, Euler R, Kechadi T. A parallel data mining algorithm for pagerank computation. In Boubiche DE, Hamdan H, Bounceur A, editors, Proceedings of the International Conference on Big Data and Advanced Wireless Technologies, BDAW 2016. Association for Computing Machinery. 2016. a33. (ACM International Conference Proceeding Series). doi: 10.1145/3010089.3010118

A parallel data mining algorithm for pagerank computation

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this