A rectilinear-monotone polygonal fault block model for fault-tolerant minimal routing in mesh

被引:27
作者
Wang, DJ [1 ]
机构
[1] Nanjing Univ, State Key Lab Novel Software Technol, Nanjing 210093, Peoples R China
[2] Montclair State Univ, Dept Comp Sci, Montclair, NJ 07043 USA
关键词
adaptive routing; fault model; fault tolerance; interconnection network; mesh;
D O I
10.1109/TC.2003.1183946
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
We propose a new fault block model, Minimal-Connected-Component (MCC), for fault-tolerant adaptive routing in mesh-connected multiprocessor systems. This model refines the widely used rectangular model by including fewer nonfaulty nodes in fault blocks. The positions of source/destination nodes relative to faulty nodes are taken into consideration when constructing fault blocks. The main idea behind it is that a node will be included in a fault block only if using it in a routing will definitely make the route nonminimal. The resulting fault blocks are of the rectilinear-monotone polygonal shapes. A sufficient and necessary condition is proposed for the existence of the minimal "Manhattan" routes in the presence of such fault blocks. Based on the condition, an algorithm is proposed to determine the existence of Manhattan routes. Since MCC is designed to facilitate minimal route finding, if there exists no minimal route under MCC fault model, then there will be absolutely no minimal route whatsoever. We will also present two adaptive routing algorithms that construct a Manhattan route avoiding all fault blocks, should such routes exist.
引用
收藏
页码:310 / 320
页数:11
相关论文
共 17 条
[1]   FAULT-TOLERANT WORMHOLE ROUTING ALGORITHMS FOR MESH NETWORKS [J].
BOPPANA, RV ;
CHALASANI, S .
IEEE TRANSACTIONS ON COMPUTERS, 1995, 44 (07) :848-864
[2]  
Boura Y. M., 1995, Proceedings of the 1995 International Conference on Parallel Processing, pI/106
[3]  
CHIEN AA, 1992, P 19 ANN INT S COMP, P268
[4]   A fault-tolerant routing strategy in hypercube multicomputers [J].
Chiu, GM ;
Wu, SP .
IEEE TRANSACTIONS ON COMPUTERS, 1996, 45 (02) :143-155
[5]  
DALLY WJ, 1989, ACTORS KNOWLEDGE BAS
[6]  
Estrin D., 1999, P MOBICOM, DOI DOI 10.1145/313451.313556
[7]   Distributed, deadlock-free routing in faulty, pipelined, direct interconnection networks [J].
Gaughan, PT ;
Dao, BV ;
Yalamanchili, S ;
Schimmel, DE .
IEEE TRANSACTIONS ON COMPUTERS, 1996, 45 (06) :651-665
[8]  
Glass G.J., 1996, IEEE T PARALL DISTR, V7, P6201
[9]   A FAULT-TOLERANT COMMUNICATION SCHEME FOR HYPERCUBE COMPUTERS [J].
LEE, TC ;
HAYES, JP .
IEEE TRANSACTIONS ON COMPUTERS, 1992, 41 (10) :1242-1256
[10]   FAULT-TOLERANT MULTICASTING ON HYPERCUBES [J].
LIANG, AC ;
BHATTACHARYA, S ;
TSAI, WT .
JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING, 1994, 23 (03) :418-428