Implementation of 802.11n on 128-CORE Processor
Nizhny Novgorod State Technical University, Nizhny Novgorod, 603950, Russia
ISCA 21st International Conference on Parallel and Distributed Computing and Communication Systems, PDCCS 2008
@inproceedings{DBLP:conf/ISCApdcs/AkapyevK08,
author={A. Akapyev and V. Krylov},
title={Implementation of 802.11n on 128-CORE Processor},
booktitle={ISCA PDCCS},
year={2008},
pages={56-60},
crossref={DBLP:conf/ISCApdcs/2008},
bibsource={DBLP, http://dblp.uni-trier.de}
}
This article presents the results of a research in applying modern Graphics Processing Units in the field of telecommunications. The most recent Wireless Local Area Network protocol, 802.11n, was studied, as it introduces a significant increase of computational complexity. Taking into consideration the concept of Software Defined Radio, the implementation of PHY algorithms was devised on a modern programmable 128-core GPU. It was shown that a significant performance increase could be obtained through applying this novel approach. Our experiments had shown more than 8x performance boost. The article also discusses the approach of utilizing a GPU as a networking device. The author shows how a GPU could be effectively used as a Digital Signal Processing unit of a real communication device.
December 19, 2010 by hgpu
