期刊文献+

环网中的维度气泡流控与自适应路由算法 被引量:3

Dimensional Bubble Flow Control and Adaptive Routing Algorithm in Torus Networks
下载PDF
导出
摘要 介绍了一个称为环网维度气泡流控(TDBFC)的新型流控策略和称为环网维度气泡路由(TAD-BR)算法的新型自适应路由算法.在Bubble流控和DBFC流控的基础上设计了适合于环网的维度气泡流控.在环网中,如果采用TDBFC流控策略,设计的TADBR自适应路由算法可实现无死锁的最短距离的路由.对于以上结论,提供了详细的证明.最后,介绍了自行设计的模拟工具RingNetSim,该模拟器实现了TDBFC流控策略和TADBR算法.在RingNetSim上分析了TADBR算法的性能,结果显示环网维度气泡路由算法拥有较好的性能. One novel flow control strategy called torus' dimensional bubble flow control (TDBFC) is presented. At the same time, a novel adaptive routing algorithm called torus' dimensional bubble routing algorithm (TADBR) is also presented. The flow control strategy of TDBFC is designed for torus networks and based on bubble flow control and DBFC flow control. Since there are similar things between bubble flow control and DBFC flow control such as virtual cut-through switching and credit-based flow control mechanism etc, the flow control strategy of TDBFC is realized by integration of bubble and DBFC flow control. In torus networks, when the flow control strategy of TDBFC is accepted, the routing algorithm of TADBR can get the goals including deadlock-free and minimal distance even if the cyclic dependencies exist. The detailed proof is provided for these conclusions by analysis of the situation of all kinds of packet. Finally, the 2-D torus simulator called RingNetSim is presented. The simulator realizes the flow control of TDBFC and routing algorithm of TADBR. The performance of routing algorithms is evaluated by adjusting buffering space, communication models and arbitration algorithms. The performance results of TADBR algorithm are compared with the dimension-order routing algorithm. The results show that the TADBR algorithm owns preferable performance.
出处 《计算机研究与发展》 EI CSCD 北大核心 2007年第9期1510-1517,共8页 Journal of Computer Research and Development
基金 国家自然科学基金项目(90307001 60633050)
关键词 Bubble流控 DBFC流控 死锁 自适应路由算法 环网 bubble flow control DBFC flow control deadlock adaptive routing algorithm torus networks
  • 相关文献

参考文献9

  • 1S L Scott,G Thorson.Optimized routing in the Cray T3D[C].In:Proc of the Parallel Computer Routing and Communications Workshop (PCRCW).Berlin:Springer-Verlag,1994.281-294
  • 2S L Scott,G Thorson.The Cray T3E network:Adaptive routing in a high performance 3-D torus[C].Hot Interconnects Symposium IV,Standford,1996
  • 3N R Adga,et al.An overview of the BlueGene/L supercomputer[C].Supercomputing 2002 Conf,Baltimore,USA,2002
  • 4金怡濂,黄永勤,陈左宁,桂亚东,漆锋滨.高性能计算机的关键技术和发展趋势[J].中国工程科学,2001,3(6):1-8. 被引量:9
  • 5V Puente,Gregorio.On the design of a high-performance adaptive router for CC-NUMA multiprocessors[J].IEEE Trans on Parallel and Distributed Systems,2003,14(5):487-501
  • 6J Duato.A necessary and sufficient condition for deadlock-free routing in cut-through and store-and-forward networks[J].IEEE Trans on Parallel Distributed Systems,1996,7(8):841-854
  • 7肖灿文,张民选,过锋.K-ary N-cube网络中的维度气泡流控与无死锁完全自适应路由[J].计算机学报,2006,29(5):801-807. 被引量:1
  • 8Rajeev Sivaram,Craig B Stunkel,Dhabaleswar K Panda.HIPIQS:A high-performance switch architecture using input queuing[J].IEEE Trans on Parallel and Distributed Systems,2002,13(3):275-289
  • 9James Laudon,Daniel Lenoski.The SGI origin:A ccNUMA highly scalable server[C].The 24th Int'l Symp on Computer Architecture (ISCA'97),Denver,Colorado,1997

二级参考文献19

  • 1[1]Anderson E, Brooks J, Grassl C, et al. Performance of the CRAY T3E multiprocessor [A]. Proceedings of SC97 [C], Nov 1997
  • 2[2]Laudon J, Lenoski D. The SGI Origin: A cc-NUMA highly scalable server [A]. 24th Annual International Symposium on Computer Architecture [C], June 1997.241~251
  • 3[3]Dongarra J J, Meuer H W, Strohmaier E, et al. TOP500supercomputer sites [DB/OL] . http: //www. netlib.org/benchmark/top500. html, 2000- 11- 03
  • 4[4]DOE. Accelerated strategic computing initiative (ASCI)program plan [DB/OL]. http: //www. llnl. gov/ascialliances/pp/001toc. html, 2000 - 09
  • 5[5]DOE. ASCI pathforward project description [DB/OL].http: //www. llnl. gov/asci-pathforward/pf-overview.html, 1997 - 04 - 25
  • 6[6]Papadopoulo J. Evolution in high-end parallel computing: SMP, Clusters and MPP Revisited [DB/OL] .http://www. frec. bull. fr/OSBU2.0/WP. hep. html,1998 - 04 - 03
  • 7[7]Garg S, et al. Achieving large scale parallelism through operating system resource management on the Intel TFLOPS supercomputer [ DB/OL ]. http://developer.intel. com/technology/itj/ql1998/articles/art-3a ( b, c,……). html, Mar. 1998 - 03 - 20
  • 8[8]LLNL. Parallel code support for ASCI blue-pacific [ DB/OL]. http://www. llnl. gov/asci/platforrms/bluepac/parallel. html, 2000- 10 - 13
  • 9Borkar S.et al.Iwarp:An integrated solution to high-speed parallel computing.In:Proceedings of the Supercomputing'88,Florida,1988,330~339
  • 10Agarwal A..Limits on interconnection network performance.IEEE Transactions on Parallel Distributed Systems,1991,2(4):398~412

共引文献8

同被引文献27

  • 1顾华玺,刘增基,王琨,谢启明.Torus网络中分布式自适应路由算法[J].西安电子科技大学学报,2006,33(3):352-358. 被引量:11
  • 2Petrini F, Kerbyson D J, Pakin S. The case of the missing supercomputer performance: Achieving optimal performance on the 8, 192 processors of ASCI Q [C] //Proc of SC2003. New York: ACM, 2003.
  • 3McKinley P K, Xu H, Esfahanian A, et al. Unieast-based multicast communication in wormhole-routed direct networks [J]. IEEE Trans on Parallel and Distributed Systems, 1994, 5(12) : 1252-1265.
  • 4Malumbres M P, Duato J, Torrellas J. An efficient implementation of tree-based muhicast routing in distributed shared-memory multiproeessors [C] //Proc of the 8th IEEE Syrup on Parallel and Distributed Processing. Piscataway, NJ: IEEE, 1996.
  • 5Scott S L, Thorson G. Optimized routing in the Cray T3D [C] //Proc of the Parallel Computer Routing and Communications Workshop (PCRCW). Berlin: Springer, 1994: 281-294.
  • 6Adga N R, et al. An overview of the BlueGene/L supercomputer [C] //Proc of Supercomputing 2002 Conf. Piseataway, NJ: IEEE, 2002:1-22.
  • 7Lin X, McKinley P K, Ni L M. Performance evaluation of multicast wormhole routing in 2D-mesh multicomputers [C] //Proc of the Int Conf on Parallel Processing. Piscataway, NJ: IEEE, 1992:173-178.
  • 8Panda D K, Singal S, Kesavan R. Multidestination message passing in wormhole k-ary n-cube networks with base routing conformed paths [J]. IEEE Trans on Parallel and Distributed Systems, 1999, 10(1): 76-96.
  • 9高惠 吴静溪.Cray XT4-新一代大规模并行处理系统[J].高性能计算发展与应用,2007,21(4):12-15.
  • 10Steve Scott, Dennis Abts, John Kim, et al. The blackwidow high-radix clos network [C]//Proc of the 33rd Int Syrup on Computer Architecture. Piscataway, NJ: IEEE, 2006: 16- 28.

引证文献3

二级引证文献4

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部