Implementation of random linear network coding using NVIDIA'S CUDA toolkit

Research output: Contribution to book/Conference proceedings/Anthology/Report › Conference contribution › Contributed › peer-review

Contributors

  • Péter Vingelmann - , Budapest University of Technology and Economics (Author)
  • Frank H.P. Fitzek - , Aalborg University (Author)

Abstract

In this paper we describe an efficient GPU-based implementation of random linear network coding using NVIDIA's CUDA toolkit. The implementation takes advantage of the highly parallel nature of modern GPUs. The paper reports speed ups of 500% for encoding and 90% for decoding in comparison with a standard CPU-based implementation.

Details

Original languageEnglish
Title of host publicationNetworks for Grid Applications
EditorsAnastasios Doulamis, Joe Mambretti, Ioannis Tomkos, Theodora Varvarigou
Pages131-138
Number of pages8
ISBN (electronic)978-3-642-11733-6
Publication statusPublished - 2010
Peer-reviewedYes
Externally publishedYes

Publication series

SeriesLecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering (LNICST)
Volume25 LNICST
ISSN1867-8211

Conference

Title3rd International ICST Conference on Networks for Grid Applications, GridNets 2009
Duration8 - 9 September 2009
CityAthens
CountryGreece

External IDs

ORCID /0000-0001-8469-9573/work/162348324

Keywords

ASJC Scopus subject areas

Keywords

  • Cuda, Gpgpu, Parallelization, Random linear network coding