Leaner and Meaner: Network Coding in SIMD enabled Commercial Devices

Chres Wiant Sørensen, Achuthan Paramanathan, Juan Cabrera, Morten Videbæk Pedersen, Daniel Enrique Lucani Roetter, Frank Fitzek

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

10 Citations (Scopus)

Abstract

Although random linear network coding (RLNC) constitutes a highly efficient and distributed approach to enhance communication networks and distributed storage, it requires additional processing to be carried out in the network and in end devices. For mobile devices, this processing translates into energy use that may reduce the battery life of a device. This paper focuses not only on providing a comprehensive measurement study of the energy cost of RLNC in eight different computing platforms, but also explores novel approaches (e.g., tunable sparse network coding) and hardware optimizations for Single Instruction Multiple Data (SIMD) available in the latest generations of Intel and Advanced RISC Machines (ARM) processors. Our measurement results show that the former provides gains of two- to six-fold from the underlying algorithms over RLNC, while the latter provides gains for all schemes from 2x to as high as 20x. Finally, our results show that the latest generation of mobile processors reduce dramatically the energy per bit consumed for carrying out network coding operations compared to previous generations, thus making network coding a viable technology for the upcoming 5G communication systems, even without dedicated hardware.
Original languageEnglish
Title of host publicationWireless Communications and Networking Conference (WCNC), 2016 IEEE
Number of pages6
PublisherIEEE
Publication date2016
ISBN (Electronic)978-1-4673-9814-5
DOIs
Publication statusPublished - 2016
EventIEEE Wireless Communications and Networking Conference - Doha, Qatar
Duration: 3 Apr 20166 Apr 2016

Conference

ConferenceIEEE Wireless Communications and Networking Conference
CountryQatar
CityDoha
Period03/04/201606/04/2016
SeriesI E E E Wireless Communications and Networking Conference. Proceedings
ISSN1525-3511

Fingerprint

Network coding
Linear networks
Hardware
Reduced instruction set computing
Processing
Mobile devices
Telecommunication networks
Communication systems
Costs

Cite this

Sørensen, C. W., Paramanathan, A., Cabrera, J., Pedersen, M. V., Roetter, D. E. L., & Fitzek, F. (2016). Leaner and Meaner: Network Coding in SIMD enabled Commercial Devices. In Wireless Communications and Networking Conference (WCNC), 2016 IEEE IEEE. I E E E Wireless Communications and Networking Conference. Proceedings https://doi.org/10.1109/WCNC.2016.7565066
Sørensen, Chres Wiant ; Paramanathan, Achuthan ; Cabrera, Juan ; Pedersen, Morten Videbæk ; Roetter, Daniel Enrique Lucani ; Fitzek, Frank. / Leaner and Meaner : Network Coding in SIMD enabled Commercial Devices. Wireless Communications and Networking Conference (WCNC), 2016 IEEE. IEEE, 2016. (I E E E Wireless Communications and Networking Conference. Proceedings).
@inproceedings{378343ed5484421d86c518e506ad1f74,
title = "Leaner and Meaner: Network Coding in SIMD enabled Commercial Devices",
abstract = "Although random linear network coding (RLNC) constitutes a highly efficient and distributed approach to enhance communication networks and distributed storage, it requires additional processing to be carried out in the network and in end devices. For mobile devices, this processing translates into energy use that may reduce the battery life of a device. This paper focuses not only on providing a comprehensive measurement study of the energy cost of RLNC in eight different computing platforms, but also explores novel approaches (e.g., tunable sparse network coding) and hardware optimizations for Single Instruction Multiple Data (SIMD) available in the latest generations of Intel and Advanced RISC Machines (ARM) processors. Our measurement results show that the former provides gains of two- to six-fold from the underlying algorithms over RLNC, while the latter provides gains for all schemes from 2x to as high as 20x. Finally, our results show that the latest generation of mobile processors reduce dramatically the energy per bit consumed for carrying out network coding operations compared to previous generations, thus making network coding a viable technology for the upcoming 5G communication systems, even without dedicated hardware.",
author = "S{\o}rensen, {Chres Wiant} and Achuthan Paramanathan and Juan Cabrera and Pedersen, {Morten Videb{\ae}k} and Roetter, {Daniel Enrique Lucani} and Frank Fitzek",
year = "2016",
doi = "10.1109/WCNC.2016.7565066",
language = "English",
booktitle = "Wireless Communications and Networking Conference (WCNC), 2016 IEEE",
publisher = "IEEE",
address = "United States",

}

Sørensen, CW, Paramanathan, A, Cabrera, J, Pedersen, MV, Roetter, DEL & Fitzek, F 2016, Leaner and Meaner: Network Coding in SIMD enabled Commercial Devices. in Wireless Communications and Networking Conference (WCNC), 2016 IEEE. IEEE, I E E E Wireless Communications and Networking Conference. Proceedings, IEEE Wireless Communications and Networking Conference, Doha, Qatar, 03/04/2016. https://doi.org/10.1109/WCNC.2016.7565066

Leaner and Meaner : Network Coding in SIMD enabled Commercial Devices. / Sørensen, Chres Wiant; Paramanathan, Achuthan; Cabrera, Juan; Pedersen, Morten Videbæk; Roetter, Daniel Enrique Lucani; Fitzek, Frank.

Wireless Communications and Networking Conference (WCNC), 2016 IEEE. IEEE, 2016.

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

TY - GEN

T1 - Leaner and Meaner

T2 - Network Coding in SIMD enabled Commercial Devices

AU - Sørensen, Chres Wiant

AU - Paramanathan, Achuthan

AU - Cabrera, Juan

AU - Pedersen, Morten Videbæk

AU - Roetter, Daniel Enrique Lucani

AU - Fitzek, Frank

PY - 2016

Y1 - 2016

N2 - Although random linear network coding (RLNC) constitutes a highly efficient and distributed approach to enhance communication networks and distributed storage, it requires additional processing to be carried out in the network and in end devices. For mobile devices, this processing translates into energy use that may reduce the battery life of a device. This paper focuses not only on providing a comprehensive measurement study of the energy cost of RLNC in eight different computing platforms, but also explores novel approaches (e.g., tunable sparse network coding) and hardware optimizations for Single Instruction Multiple Data (SIMD) available in the latest generations of Intel and Advanced RISC Machines (ARM) processors. Our measurement results show that the former provides gains of two- to six-fold from the underlying algorithms over RLNC, while the latter provides gains for all schemes from 2x to as high as 20x. Finally, our results show that the latest generation of mobile processors reduce dramatically the energy per bit consumed for carrying out network coding operations compared to previous generations, thus making network coding a viable technology for the upcoming 5G communication systems, even without dedicated hardware.

AB - Although random linear network coding (RLNC) constitutes a highly efficient and distributed approach to enhance communication networks and distributed storage, it requires additional processing to be carried out in the network and in end devices. For mobile devices, this processing translates into energy use that may reduce the battery life of a device. This paper focuses not only on providing a comprehensive measurement study of the energy cost of RLNC in eight different computing platforms, but also explores novel approaches (e.g., tunable sparse network coding) and hardware optimizations for Single Instruction Multiple Data (SIMD) available in the latest generations of Intel and Advanced RISC Machines (ARM) processors. Our measurement results show that the former provides gains of two- to six-fold from the underlying algorithms over RLNC, while the latter provides gains for all schemes from 2x to as high as 20x. Finally, our results show that the latest generation of mobile processors reduce dramatically the energy per bit consumed for carrying out network coding operations compared to previous generations, thus making network coding a viable technology for the upcoming 5G communication systems, even without dedicated hardware.

U2 - 10.1109/WCNC.2016.7565066

DO - 10.1109/WCNC.2016.7565066

M3 - Article in proceeding

BT - Wireless Communications and Networking Conference (WCNC), 2016 IEEE

PB - IEEE

ER -

Sørensen CW, Paramanathan A, Cabrera J, Pedersen MV, Roetter DEL, Fitzek F. Leaner and Meaner: Network Coding in SIMD enabled Commercial Devices. In Wireless Communications and Networking Conference (WCNC), 2016 IEEE. IEEE. 2016. (I E E E Wireless Communications and Networking Conference. Proceedings). https://doi.org/10.1109/WCNC.2016.7565066