Network Coding Parallelization Based on Matrix Operations for Multicore Architectures

Simon Wunderlich, Juan Cabrera, Frank Fitzek, Morten Videbæk Pedersen

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

4 Citations (Scopus)

Abstract

Network coding has the potential to improve the performance of current and future communication systems (including transportation and storage) and is currently even considered for communication architectures between the individual processors on same board or different boards in close proximity. Despite the fact that single core implementations show already comparable coding speeds with standard coding approaches, this paper pushes network coding to the next level by exploiting multicore architectures. The disruptive idea presented in the paper is to break with current software implementations and coding approaches and to adopt highly optimized dense matrix operations from the high performance computation field for network coding in order to increase the coding speed. The paper presents the novel coding approach for multicore architectures and shows coding speed gains on a commercial platform such as the Raspberry Pi2 with four cores in the order of up to one full magnitude. The speed increase gain is even higher than the number of cores of the Raspberry Pi2 since the newly introduced approach exploits the cache architecture way better than by-the-book matrix operations. Copyright © 2015 by the Institute of Electrical and Electronic Engineers, Inc.
All rights reserved
Original languageEnglish
Title of host publicationIEEE International Conference on Ubiquitous Wireless Broadband (ICUWB), 2015
Number of pages5
PublisherIEEE Press
Publication date4 Oct 2015
ISBN (Electronic)978-1-4673-6555-0
DOIs
Publication statusPublished - 4 Oct 2015
Event2015 IEEE International Conference on Ubiquitous Wireless Broadband (ICUWB) - Montreal, Canada
Duration: 4 Oct 20157 Oct 2015

Conference

Conference2015 IEEE International Conference on Ubiquitous Wireless Broadband (ICUWB)
CountryCanada
CityMontreal
Period04/10/201507/10/2015
SeriesIEEE International Conference on Ultra-Wideband (ICUWB)
ISSN2162-6588

Fingerprint

Network coding
Communication systems
Engineers
Communication

Cite this

Wunderlich, S., Cabrera, J., Fitzek, F., & Pedersen, M. V. (2015). Network Coding Parallelization Based on Matrix Operations for Multicore Architectures. In IEEE International Conference on Ubiquitous Wireless Broadband (ICUWB), 2015 IEEE Press. IEEE International Conference on Ultra-Wideband (ICUWB) https://doi.org/10.1109/ICUWB.2015.7324482
Wunderlich, Simon ; Cabrera, Juan ; Fitzek, Frank ; Pedersen, Morten Videbæk. / Network Coding Parallelization Based on Matrix Operations for Multicore Architectures. IEEE International Conference on Ubiquitous Wireless Broadband (ICUWB), 2015. IEEE Press, 2015. (IEEE International Conference on Ultra-Wideband (ICUWB)).
@inproceedings{8b64fa1945a949dba023fe2e5d66702a,
title = "Network Coding Parallelization Based on Matrix Operations for Multicore Architectures",
abstract = "Network coding has the potential to improve the performance of current and future communication systems (including transportation and storage) and is currently even considered for communication architectures between the individual processors on same board or different boards in close proximity. Despite the fact that single core implementations show already comparable coding speeds with standard coding approaches, this paper pushes network coding to the next level by exploiting multicore architectures. The disruptive idea presented in the paper is to break with current software implementations and coding approaches and to adopt highly optimized dense matrix operations from the high performance computation field for network coding in order to increase the coding speed. The paper presents the novel coding approach for multicore architectures and shows coding speed gains on a commercial platform such as the Raspberry Pi2 with four cores in the order of up to one full magnitude. The speed increase gain is even higher than the number of cores of the Raspberry Pi2 since the newly introduced approach exploits the cache architecture way better than by-the-book matrix operations. Copyright {\circledC} 2015 by the Institute of Electrical and Electronic Engineers, Inc.All rights reserved",
author = "Simon Wunderlich and Juan Cabrera and Frank Fitzek and Pedersen, {Morten Videb{\ae}k}",
year = "2015",
month = "10",
day = "4",
doi = "10.1109/ICUWB.2015.7324482",
language = "English",
booktitle = "IEEE International Conference on Ubiquitous Wireless Broadband (ICUWB), 2015",
publisher = "IEEE Press",

}

Wunderlich, S, Cabrera, J, Fitzek, F & Pedersen, MV 2015, Network Coding Parallelization Based on Matrix Operations for Multicore Architectures. in IEEE International Conference on Ubiquitous Wireless Broadband (ICUWB), 2015. IEEE Press, IEEE International Conference on Ultra-Wideband (ICUWB), 2015 IEEE International Conference on Ubiquitous Wireless Broadband (ICUWB), Montreal, Canada, 04/10/2015. https://doi.org/10.1109/ICUWB.2015.7324482

Network Coding Parallelization Based on Matrix Operations for Multicore Architectures. / Wunderlich, Simon ; Cabrera, Juan; Fitzek, Frank; Pedersen, Morten Videbæk.

IEEE International Conference on Ubiquitous Wireless Broadband (ICUWB), 2015. IEEE Press, 2015. (IEEE International Conference on Ultra-Wideband (ICUWB)).

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Network Coding Parallelization Based on Matrix Operations for Multicore Architectures

AU - Wunderlich, Simon

AU - Cabrera, Juan

AU - Fitzek, Frank

AU - Pedersen, Morten Videbæk

PY - 2015/10/4

Y1 - 2015/10/4

N2 - Network coding has the potential to improve the performance of current and future communication systems (including transportation and storage) and is currently even considered for communication architectures between the individual processors on same board or different boards in close proximity. Despite the fact that single core implementations show already comparable coding speeds with standard coding approaches, this paper pushes network coding to the next level by exploiting multicore architectures. The disruptive idea presented in the paper is to break with current software implementations and coding approaches and to adopt highly optimized dense matrix operations from the high performance computation field for network coding in order to increase the coding speed. The paper presents the novel coding approach for multicore architectures and shows coding speed gains on a commercial platform such as the Raspberry Pi2 with four cores in the order of up to one full magnitude. The speed increase gain is even higher than the number of cores of the Raspberry Pi2 since the newly introduced approach exploits the cache architecture way better than by-the-book matrix operations. Copyright © 2015 by the Institute of Electrical and Electronic Engineers, Inc.All rights reserved

AB - Network coding has the potential to improve the performance of current and future communication systems (including transportation and storage) and is currently even considered for communication architectures between the individual processors on same board or different boards in close proximity. Despite the fact that single core implementations show already comparable coding speeds with standard coding approaches, this paper pushes network coding to the next level by exploiting multicore architectures. The disruptive idea presented in the paper is to break with current software implementations and coding approaches and to adopt highly optimized dense matrix operations from the high performance computation field for network coding in order to increase the coding speed. The paper presents the novel coding approach for multicore architectures and shows coding speed gains on a commercial platform such as the Raspberry Pi2 with four cores in the order of up to one full magnitude. The speed increase gain is even higher than the number of cores of the Raspberry Pi2 since the newly introduced approach exploits the cache architecture way better than by-the-book matrix operations. Copyright © 2015 by the Institute of Electrical and Electronic Engineers, Inc.All rights reserved

U2 - 10.1109/ICUWB.2015.7324482

DO - 10.1109/ICUWB.2015.7324482

M3 - Article in proceeding

BT - IEEE International Conference on Ubiquitous Wireless Broadband (ICUWB), 2015

PB - IEEE Press

ER -

Wunderlich S, Cabrera J, Fitzek F, Pedersen MV. Network Coding Parallelization Based on Matrix Operations for Multicore Architectures. In IEEE International Conference on Ubiquitous Wireless Broadband (ICUWB), 2015. IEEE Press. 2015. (IEEE International Conference on Ultra-Wideband (ICUWB)). https://doi.org/10.1109/ICUWB.2015.7324482