Non-Stationary Acceleration Strategies for PageRank Computing
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10045/97000
Title: | Non-Stationary Acceleration Strategies for PageRank Computing |
---|---|
Authors: | Migallón Gomis, Héctor | Migallón, Violeta | Penadés, Jose |
Research Group/s: | Computación de Altas Prestaciones y Paralelismo (gCAPyP) |
Center, Department or Service: | Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial |
Keywords: | PageRank | Power method | Non-stationary iterations | Parallel processing | Distributed shared memory | Hybrid MPI/OpenMP |
Knowledge Area: | Ciencia de la Computación e Inteligencia Artificial |
Issue Date: | 1-Oct-2019 |
Publisher: | MDPI |
Citation: | Migallón H, Migallón V, Penadés J. Non-Stationary Acceleration Strategies for PageRank Computing. Mathematics. 2019; 7(10):911. doi:10.3390/math7100911 |
Abstract: | In this work, a non-stationary technique based on the Power method for accelerating the parallel computation of the PageRank vector is proposed and its theoretical convergence analyzed. This iterative non-stationary model, which uses the eigenvector formulation of the PageRank problem, reduces the needed computations for obtaining the PageRank vector by eliminating synchronization points among processes, in such a way that, at each iteration of the Power method, the block of iterate vector assigned to each process can be locally updated more than once, before performing a global synchronization. The parallel implementation of several strategies combining this novel non-stationary approach and the extrapolation methods has been developed using hybrid MPI/OpenMP programming. The experiments have been carried out on a cluster made up of 12 nodes, each one equipped with two Intel Xeon hexacore processors. The behaviour of the proposed parallel algorithms has been studied with realistic datasets, highlighting their performance compared with other parallel techniques for solving the PageRank problem. Concretely, the experimental results show a time reduction of up to 58.4% in relation to the parallel Power method, when a small number of local updates is performed before each global synchronization, outperforming both the two-stage algorithms and the extrapolation algorithms, more sharply as the number of processes increases. |
Sponsor: | This research was supported by the Spanish Ministry of Science, Innovation and Universities Grant RTI2018-098156-B-C54, co-financed by the European Commission (FEDER funds). |
URI: | http://hdl.handle.net/10045/97000 |
ISSN: | 2227-7390 |
DOI: | 10.3390/math7100911 |
Language: | eng |
Type: | info:eu-repo/semantics/article |
Rights: | © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). |
Peer Review: | si |
Publisher version: | https://doi.org/10.3390/math7100911 |
Appears in Collections: | INV - gCAPyP - Artículos de Revistas |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
2019_Migallon_etal_Mathematics.pdf | 890,99 kB | Adobe PDF | Open Preview | |
This item is licensed under a Creative Commons License