Enhancing the performance of the aggregated bit vector algorithm in network packet classification using GPU

Enhancing the performance of the aggregated bit vector algorithm in network packet classification using GPU

Packet classification is a computationally intensive, highly parallelizable task in many advanced network systems like high-speed routers and firewalls that enable different functionalities through discriminating incoming traffic. Recently, graphics processing units (GPUs) have been exploited as eff...

Full description

Bibliographic Details
Main Authors: Mahdi Abbasi, Razieh Tahouri, Milad Rafiee
Format: Article
Language:English
Published: PeerJ Inc. 2019-04-01
Series:PeerJ Computer Science
Subjects:
Parallel processing
Aggregated bit vector
GPU
Performance
Analysis
Online Access:https://peerj.com/articles/cs-185.pdf
id doaj-2eb7504a05364979bee2d2362376120b
record_format Article
spelling doaj-2eb7504a05364979bee2d2362376120b2020-11-25T01:02:58ZengPeerJ Inc.PeerJ Computer Science2376-59922019-04-015e18510.7717/peerj-cs.185Enhancing the performance of the aggregated bit vector algorithm in network packet classification using GPUMahdi Abbasi0Razieh Tahouri1Milad Rafiee2Department of Computer Engineering, Engineering Faculty, Bu-Ali Sina University, Hamedan, IranDepartment of Computer Engineering, Engineering Faculty, Islamic Azad University of Hamedan, Hamedan, IranDepartment of Computer Engineering, Engineering Faculty, Bu-Ali Sina University, Hamedan, IranPacket classification is a computationally intensive, highly parallelizable task in many advanced network systems like high-speed routers and firewalls that enable different functionalities through discriminating incoming traffic. Recently, graphics processing units (GPUs) have been exploited as efficient accelerators for parallel implementation of software classifiers. The aggregated bit vector is a highly parallelizable packet classification algorithm. In this work, first we present a parallel kernel for running this algorithm on GPUs. Next, we adapt an asymptotic analysis method which predicts any empirical result of the proposed kernel. Experimental results not only confirm the efficiency of the proposed parallel kernel but also reveal the accuracy of the analysis method in predicting important trends in experimental results.https://peerj.com/articles/cs-185.pdfParallel processingAggregated bit vectorGPUPerformanceAnalysis
collection DOAJ
language English
format Article
sources DOAJ
author Mahdi Abbasi
Razieh Tahouri
Milad Rafiee
spellingShingle Mahdi Abbasi
Razieh Tahouri
Milad Rafiee
Enhancing the performance of the aggregated bit vector algorithm in network packet classification using GPU
PeerJ Computer Science
Parallel processing
Aggregated bit vector
GPU
Performance
Analysis
author_facet Mahdi Abbasi
Razieh Tahouri
Milad Rafiee
author_sort Mahdi Abbasi
title Enhancing the performance of the aggregated bit vector algorithm in network packet classification using GPU
title_short Enhancing the performance of the aggregated bit vector algorithm in network packet classification using GPU
title_full Enhancing the performance of the aggregated bit vector algorithm in network packet classification using GPU
title_fullStr Enhancing the performance of the aggregated bit vector algorithm in network packet classification using GPU
title_full_unstemmed Enhancing the performance of the aggregated bit vector algorithm in network packet classification using GPU
title_sort enhancing the performance of the aggregated bit vector algorithm in network packet classification using gpu
publisher PeerJ Inc.
series PeerJ Computer Science
issn 2376-5992
publishDate 2019-04-01
description Packet classification is a computationally intensive, highly parallelizable task in many advanced network systems like high-speed routers and firewalls that enable different functionalities through discriminating incoming traffic. Recently, graphics processing units (GPUs) have been exploited as efficient accelerators for parallel implementation of software classifiers. The aggregated bit vector is a highly parallelizable packet classification algorithm. In this work, first we present a parallel kernel for running this algorithm on GPUs. Next, we adapt an asymptotic analysis method which predicts any empirical result of the proposed kernel. Experimental results not only confirm the efficiency of the proposed parallel kernel but also reveal the accuracy of the analysis method in predicting important trends in experimental results.
topic Parallel processing
Aggregated bit vector
GPU
Performance
Analysis
url https://peerj.com/articles/cs-185.pdf
work_keys_str_mv AT mahdiabbasi enhancingtheperformanceoftheaggregatedbitvectoralgorithminnetworkpacketclassificationusinggpu
AT raziehtahouri enhancingtheperformanceoftheaggregatedbitvectoralgorithminnetworkpacketclassificationusinggpu
AT miladrafiee enhancingtheperformanceoftheaggregatedbitvectoralgorithminnetworkpacketclassificationusinggpu
_version_ 1725202885343444992

Similar Items