30 Hits in 7.6 sec

A New Scalable and Cost-Effective Congestion Management Strategy for Lossless Multistage Interconnection Networks

J. Duato, I. Johnson, J. Flich, F. Naven, P. Garcia, T. Nachiondo
11th International Symposium on High-Performance Computer Architecture  
In this paper, we propose a new congestion management strategy for lossless multistage interconnection networks that scales as network size and/or link bandwidth increase.  ...  This is achieved in a scalable manner by using separate queues for congested flows. These are dynamically allocated only when congestion arises, and deallocated when congestion subsides.  ...  Conclusions In this paper we have proposed RECN, a new strategy for congestion management in lossless interconnection networks, also describing the most relevant implementation details for multistage interconnection  ... 
doi:10.1109/hpca.2005.1 dblp:conf/hpca/DuatoJFNGF05 fatcat:o6z5aehpqndwjnurlycjoen7qu

Cost / Performance Trade-Offs and Fairness Evaluation of Queue Mapping Policies [chapter]

Teresa Nachiondo, José Flich, José Duato, Mitchell Gusat
2005 Lecture Notes in Computer Science  
The new results show that DBBM with modulo-4/8 mapping performs very well for only a fraction of the VOQ cost.  ...  To improve VOQ's scalability we have proposed the Destination-Based Buffer Management (DBBM), a scheme that compares well with VOQ.  ...  Acknowledgments We are indebted to Ton Engbersen and Ronald Luijten for significant contributions and careful review.  ... 
doi:10.1007/11549468_112 fatcat:zdxzxskrmffmnl7urkbpivzmem

Decongestants for clogged networks

Pedro Garcia, Jose Flich, Jose Duato, Ian Johnson, Francisco Quiles, Finbar Naven
2007 IEEE potentials  
FACING CONGESTION AND HOL BLOCKING Managing congestion has been an open issue in lossless interconnection networks for the last 20 years.  ...  For instance, Fig. 2(a) shows what congestion does to network throughput for a bidirectional multistage interconnection network with 64 sending and 64 receiving end nodes (a 64 × 64 BMIN).  ... 
doi:10.1109/mpot.2007.906118 fatcat:psvf5jcf6ngz7bkzbrjlgd2i6i

FBICM: Efficient Congestion Management for High-Performance Networks Using Distributed Deterministic Routing [chapter]

Jesús Escudero-Sahuquillo, Pedro García, Francisco Quiles, Jose Flich, Jose Duato
2008 Lecture Notes in Computer Science  
We propose a novel congestion management technique for distributed tablebased routing. The mechanism relies on additional congestion information located at routing tables.  ...  One way to reduce both problems is using smaller networks with adequate congestion management mechanisms.  ...  However, none of them are suitable for modern interconnection networks due, respectively, to the high cost and consumption of current network components and to the lossless character of these networks.  ... 
doi:10.1007/978-3-540-89894-8_44 fatcat:ej4wgazg2vg6flnsiu7k7jgu6m

Progressive Congestion Management Based on Packet Marking and Validation Techniques

J. Ferrer, E. Baydal, A. Robles, Pedro López, J. Duato
2012 IEEE transactions on computers  
In this paper, we present an overview of the different strategies to detect and correct congestion in multistage interconnection networks, and propose a new mechanism referred to as Marking and Validation  ...  Congestion management in multistage interconnection networks is a serious problem, which is not solved completely.  ...  ACKNOWLEDGMENTS This work was supported by the Spanish MEC and MICINN, as well as European Commission FEDER funds, under Grants CSD2006-00046 and TIN2009-14475-C04-01, and by the European Commission in  ... 
doi:10.1109/tc.2011.146 fatcat:erckp7um4nguzkpzkvzb2i57la

Adaptive Routing Strategies for Modern High Performance Networks

Patrick Geoffray, Torsten Hoefler
2008 2008 16th IEEE Symposium on High Performance Interconnects  
Our best adaptive routing scheme is able to increase the effective bisection bandwidth to 77% for 512 nodes and 100% for smaller node counts.  ...  Our experiments show that the effective bisection bandwidth of a non-blocking 512-node Clos network is as low as 38% if the network is routed statically.  ...  Acknowledgments Computation for the work described in this paper was supported by the University of Southern California Center for High-Performance Computing and Communications (  ... 
doi:10.1109/hoti.2008.21 dblp:conf/hoti/GeoffrayH08 fatcat:l4nunhv5cbhd5j7v6ststh5bly

High-Performance Routing with Multipathing and Path Diversity in Ethernet and HPC Networks [article]

Maciej Besta, Jens Domke, Marcel Schneider, Marek Konieczny, Salvatore Di Girolamo, Timo Schneider, Ankit Singla, Torsten Hoefler
2020 arXiv   pre-print
We first develop a taxonomy of different forms of support for multipathing and overall path diversity. Then, we analyze how existing routing schemes support this diversity.  ...  Many low-diameter topologies such as Slim Fly or Jellyfish that substantially reduce cost, power consumption, and latency have been proposed.  ...  237] , general data center networking for clouds [226] , congestion management [120] , reconfigurable data center networks [81] , and transport protocols [207] , [182] .  ... 
arXiv:2007.03776v3 fatcat:zwex5rqaobdttnpduurzww6gze


Lee Luan Ling, Alberto José Centeno Filho
2001 Computer communication review  
This paper presents a new topology for multidimensional interconnection networks, namely D-ARM, which has the goal of simultaneously providing a high network transmission capacity and a low information  ...  The new D-ARM topology has a connection pattern arranged in alternated regular mesh fashions with toroidal boundaries.  ...  In addition, there are also embbeded/folded, multistages/hierachical, and scalable networks [19, 30, 15, 31, 4] .  ... 
doi:10.1145/382176.383019 fatcat:dmw5siad5rgc3eqywzxshsihqm

Ethernet as a Lossless Deadlock Free System Area Network [chapter]

Sven-Arne Reinemo, Tor Skeie
2005 Lecture Notes in Computer Science  
I would also like to thank my secondary supervisor Olav Lysne for valuable feedback and support during this period, and for granting me a Ph.D. scholarship at Simula Research Laboratory.  ...  Acknowledgement First and foremost I would like to thank my primary supervisor Tor Skeie for guidance and inspiration throughout the four years of thesis work.  ...  Clos networks have been used in Figure 2 . 2 : 22 Multistage interconnection network topologies.  ... 
doi:10.1007/11576235_90 fatcat:gcxhe22ol5gttm7wxzbm6yefxi

Towards Internet QoS Provisioning Based on Generic Distributed QoS Adaptive Routing Engine

Amira Y. Haikal, M. Badawy, Hesham A. Ali
2014 The Scientific World Journal  
introduce a QoS routing algorithm (QOPRA) based on dynamic programming technique, and (iii) propose QoS multipath forwarding (QMPF) model for paths diversity exploitation.  ...  The main objective of this paper is to (i) provide a general configuration guideline for service differentiation, (ii) formalize the theoretical properties of different QoS routing algorithms and then  ...  There is a crucial need for an effective MPF scheme that optimizes the network, with the joint goals of avoiding network congestion and ensuring QoS provisioning.  ... 
doi:10.1155/2014/694847 pmid:25309955 pmcid:PMC4182902 fatcat:spuobipqfnedbmz6amq6if74pq

Novel Network Architecture for Optical Burst Transport

Chr. M. Gauger
2009 PIK - Praxis der Informationsverarbeitung und Kommunikation  
The design objectives for the OBTN architecture are (i) an overall high quality of service, (ii) a network design allowing for cost-efficiency and scalability, and (iii) a network evolution perspective  ...  The architecture is motivated by the need for flexible, scalable, and cost-efficient transport in next generation networks.  ...  Also, thanks to Massimo Tornatore for the great time and fun we had and for introducing me to the Italian community of Davis.  ... 
doi:10.1515/piko.2009.0012 fatcat:hrxftshbwjgi7d4powfrj2jhee

Novel Network Architecture for Optical Burst Transport [chapter]

Christoph M. Gauger
2009 Kommunikation in Verteilten Systemen (KiVS)  
The design objectives for the OBTN architecture are (i) an overall high quality of service, (ii) a network design allowing for cost-efficiency and scalability, and (iii) a network evolution perspective  ...  The architecture is motivated by the need for flexible, scalable, and cost-efficient transport in next generation networks.  ...  Also, thanks to Massimo Tornatore for the great time and fun we had and for introducing me to the Italian community of Davis.  ... 
doi:10.1007/978-3-540-92666-5_33 dblp:conf/kivs/Gauger09 fatcat:x5ipyssnfrbexaiwql75tystwe

Building Upon NB-IoT Networks: A Roadmap Towards 5G New Radio Networks

Safiu A. Gbadamosi, Gerhard P. Hancke, Adnan M. Abu-Mahfouz
2020 IEEE Access  
Gbadamosi et al: Building Upon NB-IoT Networks: A Roadmap To 5G New Radio Networks (2020) 4 The first strategy optimizes the existing network and technologies to offer MTC services [26].  ...  The second strategy, termed a long-term strategy, provides support to the rising large-scale MTC services based on the introduced new air interface of NB-IoT, and for maintaining core competitiveness to  ...  My sincere appreciation also goes to Dr Adeiza J, Onumanyi for proofreading the text and the anonymous reviewers for helping me to improve on the article.  ... 
doi:10.1109/access.2020.3030653 fatcat:fih7dlvf2nefvmpb4n47jb7vii

Signal Processing, Management and Monitoring in Transmission Networks [chapter]

Carmen Vázquez, Julio Montalvo, Jawaad Ahmed, David Bolt, Christophe Caucheteur, Gerald Franzl, Philippe Gravey, David Larrabeiti, Jose A. Lazaro, Tatiana Loukina, Veronique Moeyaert, Josep Prat (+2 others)
2011 Signals and Communication Technology  
Thus, new techniques in both physical layer and network layer are necessary for mitigating impairments to accommodate high-speed traffic (Tomkos et al. 2002) .  ...  With the help of these tools, it is possible to predict the QoT (quality of transmission) attainable for a lightpath at a given time (i.e. the latest network-wide monitoring instant), and the control plane  ...  Cost-effective CD monitoring techniques have been developed in order to manage reconfigurable and scalable optical networks, in which the accumulated CD may change.  ... 
doi:10.1007/978-94-007-1767-1_2 fatcat:rfs3mozlqnh5bcvdn5yufxteee

Practical Strategies for Power-Efficient Computing Technologies

L. Chang, D.J. Frank, R.K. Montoye, S.J. Koester, B.L. Ji, P.W. Coteus, R.H. Dennard, W. Haensch
2010 Proceedings of the IEEE  
Solutions for the critical elements of a practical computing system are discussed, including the underlying logic device, associated cache memory, off-chip interconnect, and power delivery system.  ...  Going forward, further power reduction may demand radical changes in device technologies and computer architecture; hence, a few such promising methods are briefly considered.  ...  Nair for input on system-level parallelism effects, and G. Shahidi for management support. The authors would also like to thank E. Nowak and K.  ... 
doi:10.1109/jproc.2009.2035451 fatcat:hp3zqxde7vakvd7xzvu7l6wcga
« Previous Showing results 1 — 15 out of 30 results