TY - JOUR
AB - 18 Packet classification is a computationally intensive, highly parallelizable task in many advanced 19 network systems like high-speed routers and firewalls that enable different functionalities 20 through discriminating incoming traffic. Recently, graphics processing units (GPUs) have been 21 exploited as efficient accelerators for parallel implementation of software classifiers. The 22 Aggregated bit vector (ABV) is a highly parallelizable packet classification algorithm. In this 23 work, first we present a parallel kernel for running this algorithm on GPUs. Next we adapt an 24 asymptotic analysis method which predicts any empirical result of the proposed kernel. 25 Experimental results not only confirm the efficiency of the proposed parallel kernel but also 26 reveal the accuracy of the analysis method in predicting important trends in experimental results. PeerJ Comput. Sci. reviewing PDF | (CS-2018:12:33318:1:1:NEW 7 Feb 2019) Manuscript to be reviewed Computer Science 38 Introduction 39 The considerable evolution in the speed of internet communications makes the gap between 40 communication speed and processing speed ever wider. To resolve this problem, recent network 41 systems have deployed flow-based traffic processing instead of packet-based processing. For this 42 purpose, the packet classification technology is used as a fundamental process in their 43 architecture. 
TI - Peer Review #1 of "Enhancing the performance of the aggregated bit vector algorithm in network packet classification using GPU (v0.1)"
DO - 10.7287/peerj-cs.185v0.1/reviews/1
DA - 2019-04-15
UR - https://www.deepdyve.com/lp/unpaywall/peer-review-1-of-enhancing-the-performance-of-the-aggregated-bit-vqUM3iyIpM
DP - DeepDyve
ER -