Paper Info
Title
A Comparative Performance Evaluation of Network-on-Chip Architectures under Self-Similar Traffic
Abstract
The actual traffic data collected on various applications specific on-chip networks exposed that the network traffic is self-similar in nature. In this work, modeling of self-similar traffic by aggregation of a large number of on-off Pareto sources has been discussed. We have developed a cycle accurate network simulator for evaluating the performance of wormhole router based network by varying locality factor and offered load. The performance of a Mesh-of-Tree (MoT) based network has been compared with mesh and Butterfly Fat Tree (BFT) based networks all having 32 cores. We have shown that MoT based networks perform better than mesh and BFT under self-similar traffic.
Year
DOI
Venue
2009
10.1109/ARTCom.2009.164
Kottayam, Kerala
Keywords
Field
DocType
self-similar traffic,various application,specific on-chip network,actual traffic data,on-off pareto source,butterfly fat tree,network traffic,cycle accurate network simulator,large number,locality factor,comparative performance evaluation,network-on-chip architectures,computer architecture,network on chip,data collection,scalability,chip,network simulator,network topology,network analysis,network performance,throughput,system on a chip
Traffic generation model,Computer science,Network simulation,Network on a chip,Computer network,Offered load,Network topology,Network analysis,Network traffic simulation,Network traffic control,Distributed computing
Conference
ISBN
Citations 
PageRank 
978-0-7695-3845-7
7
0.49
References 
Authors
12
6
Name
Order
Citations
PageRank
Santanu Kundu1412.76
Kanchan Manna2445.53
Shobhit Gupta3595.29
Kundan Kumar4142.56
Ritesh Parikh5875.56
Santanu Chattopadhyay634344.89