Filters








233 Hits in 6.2 sec

Adaptive deadlock- and livelock-free routing with all minimal paths in Torus networks

Pablo E. Berman, Luis Gravano, Gustavo D. Pifarré, Jorge L. C. Sanz
1992 Proceedings of the fourth annual ACM symposium on Parallel algorithms and architectures - SPAA '92  
In the first part, a new algorithm for deadlock-and livelock-free routing for the  ...  In this Section, a fully-adaptive, minimal, deadlock-free, worm-hole routing algorithm for the n-dimensional ktorus will be presented.  ...  In [DA90], a method for deadlock-free adaptive routing in k-ary n-dimensional cubes is pre- sented, which can be used for worm-hole routing.  ... 
doi:10.1145/140901.140902 dblp:conf/spaa/BermanGPS92 fatcat:difwphwsp5dcpmv2mxwaqpjqsu

The Alpha 21364 network architecture

S.S. Mukherjee, P. Bannon, S. Lang, A. Spink, D. Webb
2002 IEEE Micro  
The Alpha 21364 processor provides a high-performance, highly scalable, and highly reliable network urchitecture. The router runs at I.2GHz and routes packets at a peak bandwidth of 22.4 GB/s.  ...  The network architecture scales up to a 128-processor configuration, which can support up to f o u r terabytes of distributed Rambus memory and hundreds of terabytes of disk storage.  ...  ACKNOWLEDGMENTS The Alpha 21364 network architecture has been made possible many engineers.  ... 
doi:10.1109/40.988687 fatcat:ocsxabo4snhmfd6wiiipk4xfhy

Descending layers routing: a deadlock-free deterministic routing using virtual channels in system area networks with irregular topologies

M. Koibuchi, A. Jouraku, K. Watanabe, H. Amano
2003 2003 International Conference on Parallel Processing, 2003. Proceedings.  
In this paper, we propose a novel deadlock-free deterministic routing called descending layers (DL) routing for SANs.  ...  Since wormhole or virtual cut-through transfer is used for low latency communication, deadlock-free routings are essential in SANs.  ...  Avoiding Deadlocks First, restrictions of routing in each sub-network are decided enough to satisfy deadlock-free as long as every packet is routed inside the sub-network.  ... 
doi:10.1109/icpp.2003.1240620 dblp:conf/icpp/KoibuchiJWA03 fatcat:ij7u6k74nfgyfnbxonpipvpj3a

OutFlank Routing: Increasing Throughput in Toroidal Interconnection Networks

Francesco Versaci
2013 2013 International Conference on Parallel and Distributed Systems  
We present a new, deadlock-free, routing scheme for toroidal interconnection networks, called OutFlank Routing (OFR).  ...  OFR is an adaptive strategy which exploits non-minimal links, both in the source and in the destination nodes.  ...  Acknowledgment We wish to express our gratitude to Fabio Schifano, for providing useful insights on the routing hardware and helping to discriminate implementable ideas from unimplementable ones.  ... 
doi:10.1109/icpads.2013.40 dblp:conf/icpads/Versaci13 fatcat:5goipm6fhvdjjlti7qxqkr32si

Wormhole routing techniques for directly connected multicomputer systems

Prasant Mohapatra
1998 ACM Computing Surveys  
Next, the characteristics of the wormhole routing mechanism are described in detail along with the theory behind deadlock-free routing.  ...  The main difference among various adaptive routing schemes is the technique used to avoid deadlocks. We also discuss a few algorithms based on deadlock recovery techniques.  ...  ACKNOWLEDGMENTS The author is grateful to Jatin Upadhyay and Vara Varavithya for their help in preparing this article: the comments and suggestions by Professor Lionel Ni have also improved its quality  ... 
doi:10.1145/292469.292472 fatcat:awgtqfbqvjfmvfibgxf3aeqlay

An Empirical Investigation of Mesh and Torus NoC Topologies Under Different Routing Algorithms and Traffic Models

M. Mirza-Aghatabar, S. Koohi, S. Hessabi, M. Pedram
2007 10th Euromicro Conference on Digital System Design Architectures, Methods and Tools (DSD 2007)  
To the best of our knowledge, this is the first effort in comparing mesh and torus topologies under different routing algorithms and traffic models with respect to their performance and power consumption  ...  In this paper, we compare two popular NoC topologies, i.e., mesh and torus, in terms of different figures of merit e.g., latency, power consumption, and power/throughput ratio under different routing algorithms  ...  routing algorithms [9] These examples were chosen because they are all deadlock-free and incur minimal hardware cost.  ... 
doi:10.1109/dsd.2007.4341445 dblp:conf/dsd/Mirza-AghatabarKHP07 fatcat:pwtopbf7kne5nmkaicdtiim7xa

Deadlock-free adaptive routing in multicomputer networks using virtual channels

W.J. Dally, H. Aoki
1993 IEEE Transactions on Parallel and Distributed Systems  
This paper describes two deadlock-free adaptive routing algorithms.  ...  Abstmct-The use of adaptive routing in a multicomputer interconnection network improves network performance by making use of all available paths and provides fault tolerance by allowing messages to be  ...  Wallach for assistance with the network simulations, and to R. Lethin for suggesting the use of hierarchical routing tables. H. Aoki thanks his wife Kuniko for her support during this work.  ... 
doi:10.1109/71.219761 fatcat:ppbyz5gbqvh2pdgb2vsbrmxvyq

Centralized buffer router: A low latency, low power router for high radix NOCs

Syed Minhaj Hassan, Sudhakar Yalamanchili
2013 2013 Seventh IEEE/ACM International Symposium on Networks-on-Chip (NoCS)  
A novel extension to bubble flow control enables routing deadlock and message dependent deadlock to be avoided with the same mechanism having constant buffer size per router independent of the number of  ...  While router buffers have been used as performance multipliers, they are also major consumers of area and power in on-chip networks.  ...  ACKNOWLEDGEMENTS This research was supported in part by the National Science Foundation under grant CNS 0855110 and Sandia National Laboratories.  ... 
doi:10.1109/nocs.2013.6558397 dblp:conf/nocs/HassanY13 fatcat:agndczl4tjcr3kj2puaai5n2iu

On the design of a high-performance adaptive router for CC-NUMA multiprocessors

V. Puente, J. Gregorio, R. Beivide, C. Izu
2003 IEEE Transactions on Parallel and Distributed Systems  
We exploit a simple and efficient packet injection mechanism to avoid deadlock, which leads to a fully adaptive routing by employing only three virtual channels.  ...  The outcome of this research is a High-Performance Adaptive Router (HPAR), which adequately balances the needs of parallel applications: minimal network latency at low loads and high throughput at heavy  ...  One of the best known methods to design deadlock-free adaptive networks is to add fully adaptive virtual channels to a given deadlock-free network, the latter constituting an escape subnet for any packet  ... 
doi:10.1109/tpds.2003.1199066 fatcat:52wjmnt6hjemxpp64xwpqy5dje

Performance evalulation of different routing algorithms in Network on Chip

Jayant Kumar Singh, Ayas Kanta Swain, Tetala Neel Kamal Reddy, Kamala Kanta Mahapatra
2013 2013 IEEE Asia Pacific Conference on Postgraduate Research in Microelectronics and Electronics (PrimeAsia)  
CERTIFICATE This is to certify that the Thesis entitled, " Performance Evaluation of Different Routing Algorithms in Network on Chip" submitted by " Jayant Kumar Singh" bearing Roll No. 212ec2147 to the  ...  " in Electronics and Communication Engineering specializing in " VLSI Design and Embedded System " from this institute.  ...  Valiant's routing algorithm and minimal oblivious routing are deadlock free when used in conjunction with Figure 3 3 adaptivity to only two dimensions at a time.  ... 
doi:10.1109/primeasia.2013.6731201 fatcat:26k7svm2tjehhf2kpppdawmmtu

A Necessary and Sufficient Condition for Deadlock-Free Wormhole Routing

Loren Schwiebert, D.N. Jayasimha
1996 Journal of Parallel and Distributed Computing  
An important open problem in wormhole routing has been to find a necessary and sufficient condition for deadlock-free adaptive routing.  ...  This is illustrated by proving deadlock freedom for a partially adaptive nonminimal mesh routing algorithm that does not require virtual channels and a fully adaptive minimal hypercube routing algorithm  ...  A packet wait-for graph is defined dynamically by the packets in the network and contains an edge from packet ing algorithm is deadlock-free if none of the channels in the network can be held forever.  ... 
doi:10.1006/jpdc.1996.0008 fatcat:zr24oyqmzjhdpnworwnx2q6ul4

Enabling Parallel Simulation of Large-Scale HPC Network Systems

Misbah Mubarak, Christopher D. Carothers, Robert B. Ross, Philip Carns
2017 IEEE Transactions on Parallel and Distributed Systems  
in parallel with high-fidelity network simulations.  ...  In this work, we present a simulation framework for modeling two important classes of networks used in today's IBM and Cray supercomputers: torus and dragonfly networks.  ...  We are thankful to Nikhil Jain (UIUC) for his contributions to CODES network models.  ... 
doi:10.1109/tpds.2016.2543725 fatcat:4fmce73wyvdsrlkhfdqrldfhva

A framework for designing deadlock-free wormhole routing algorithms

R.V. Boppana, S. Chalasani
1996 IEEE Transactions on Parallel and Distributed Systems  
This paper presents a framework to design fully-adaptive, deadlock-free wormhole algorithms for a variety of network topologies.  ...  The hop-based wormhole algorithms can be applied to a variety of networks including torus, mesh, de Brujin, and a class of Cayley networks, with the best known bounds on virtual channels for minimal routing  ...  Chalsani's research has been supported in part by a grant from the graduate school of the University of Wisconsin-Madison, and by NSF Grants CCR-9308966 and ECS-9216308.  ... 
doi:10.1109/71.485506 fatcat:hedproogcrhizm6cmhh3zdq4oa

Performance evaluation of deterministic routings, multicasts, and topologies on RHiNET-2 cluster

M. Koibuchi, K. Watanabe, T. Otsuka, H. Amano
2005 IEEE Transactions on Parallel and Distributed Systems  
In this paper, we implement and evaluate deadlock-free routings and unicast-based multicasts under various topologies and channel buffer sizes on a PC cluster called RHiNET-2 with 64 hosts.  ...  System Area Networks (SANs), which usually accept arbitrary topologies, have been used to connect nodes in PC/WS clusters or high-performance storage systems.  ...  In structured channel pools (SBP), a packet stored in the virtual network i is transferred to the virtual network (i + 1) in order to guarantee both minimal paths and deadlock-free routing.  ... 
doi:10.1109/tpds.2005.97 fatcat:e3yyeh7fzbh5rcvq2hqeydzqci

Optimal fully adaptive wormhole routing for meshes

L. Schwiebert, D. N. Jayasimha
1993 Proceedings of the 1993 ACM/IEEE conference on Supercomputing - Supercomputing '93  
A deadlock-free fully adaptive routing algorithm for 2D meshes which is optimal in the number of virtual channels required and in the number of restrictions placed on the use of these virtual channels  ...  The routing algorithm imposes less than half as many routing restrictions as any previous fully adaptive routing algorithm.  ...  The header flits of a packet contain the routing information and the data flits of the packet follow the header flits through the network in a pipelined fashion.  ... 
doi:10.1145/169627.169835 dblp:conf/sc/SchwiebertJ93 fatcat:6ycv7y4ocrai3pxlmvmgx2mdri
« Previous Showing results 1 — 15 out of 233 results