期刊文献+

灵活列选路模式下构造紧致逻辑阵列的高效算法

An Efficient Algorithm for Constructing Tightly-coupled Arrays Under Flexible Rerouting Schemes
下载PDF
导出
摘要 当前成百上千的处理器可以集成到同一个芯片上,而高密度处理器阵列在高速并行处理的时候经常发生故障.一种有效的解决方法是构造一个不包含故障单元的逻辑阵列,使得原始任务能够继续执行.我们研究在灵活列选路模式下构造逻辑阵列的高效算法,使得所构造的逻辑阵列不仅规模最大而且互连网络长度尽可能短.我们提出的算法TCA首先使用现存算法构造一个最大逻辑阵列,之后优化各个逻辑列来减少阵列的互连网络长度,我们把优化每个逻辑列的问题转化为带权图上的最短路径问题求解.实验结果表明我们的方法显著减少了逻辑阵列互连网络长度. Currently,hundreds to thousands of processing elements (PEs) are integrated in a single chip to process massive amounts of information in parallel, which increases the possibility of faults due to power overheating during massively parallel computing. An ef- fective way is to find a logical fault-free subarray such that the original application can still work on the subarray. In this paper,we propose an efficient algorithm, denoted as TCA, to construct maximum logical array( MLA ) with short interconnects under flexible re- routing schemes. TCA first producing a MLA using existing algorithm, then revise each logical column of the MLA to minimize the in- terconnection length. The problem of refining each logical column is solved by modeling it as a shortest path problem on a weighted graph. Experimental results show that our approach significantly reduces the interconnection length of the logical array.
出处 《小型微型计算机系统》 CSCD 北大核心 2015年第2期360-364,共5页 Journal of Chinese Computer Systems
基金 国家自然科学基金项目(61070136 61173032)资助
关键词 处理器阵列 容错重构 紧致逻辑阵列 互连网络 processor array fault-tolerant reconfiguration tightly-coupled array interconnection networks
  • 相关文献

参考文献14

  • 1Ajwani D, Ali S, Morrison J P. Graph partitioning for reconfigurable topology [ C ]. In : Proceedings of 2012 IEEE 26th International Par- allel & Distributed Processing Symposium ( IPDPS), Shanghai, Chi- na : IEEE Press, 2012 : 836 -847.
  • 2Modarressi M, Sarbazi-Azad H. Power-aware mapping for reconfig- urable NoC architectures[ C]. Proceedings of the 25th International Conference on Computer Design ( ICCD), Lake Tahoe, CA, USA: IEEE Press,2007:417-422.
  • 3Modarressi M, Sarbazi-Azad H, Tavakkol A. An efficient dynami- cally reconfigurable on-chip network architecture [ C ]. Proceedings of the 47 th Design Automation Conference ( DAC), Anaheim, CA, USA: ACM/IEEE Press ,2010:310-313.
  • 4Modarressi, Tavakkol M, Sarbazi-Azad A. Application-Aware topol- ogy reconfiguration for on-chip networks[ J ]. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2011,19 ( 11 ) : 2010-2022.
  • 5Takanami I, Horita T. A built-in circuit for self-repairing mesh-con- nected processor arrays by direct spare replacement [ C ]. IEEE Pa- cific Rim Intemationai Symposium on Dependable Computing (PRDC) ,IEEE Press,2012 :. 96-104.
  • 6Lin S Y, Shen W C ,Hsu C C, et al. Fault-tolerant router with built- in self-test/self-diagnosis and fault-isolation circuits for 2D-mesh based chip multiprocessor systems [ J ]. Journal of Electrical Engi- neering ,2009,16 ( 3 ) : 213 -222.
  • 7Chuang P J, Yao L C. An efficient reconfiguration scheme for fault- tolerant meshes [ J ]. Information Sciences, 2005,172 ( 3-4 ) : 309- 333.
  • 8Kuo S Y, Chen I Y. Efficient reconfiguration algorithms for degrad- able VLSI/WSI arrays[ J]. IEEE Transactions on Computer-Aided Design, 1992,11 (10) : 1289-1300.
  • 9Low C P. An efficient reconfiguration algorithm for degradable VL- SI/WSI arrays [ J ]. IEEE Transactions on Computers,2000,49 (6) : 553-559.
  • 10Jiang G, Wu J, Sun J. Efficiency of flexible rerouting scheme for maximizing logical arrays [ C ]. Proceedings of 10th IFIP Interna- tional Conference on Network and Parallel Computing, NPC 2013, Guiyang, China: Springer-Verlag, 2013,8147 : 194 -206.

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