首页 | 本学科首页   官方微博 | 高级检索  
     


Power- and performance-efficient cluster-based network-on-chip with reconfigurable topology
Affiliation:1. School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Tehran, Iran;2. School of Electrical and Computer Engineering, College of engineering, University of Tehran, Theran, Iran;3. Department of Computer engineering, Sharif University of Technology, Tehran, Iran;1. Department of Neurology, University Hospital, Zagreb, Croatia;2. Departamento de Psiquiatría, Universidad Maimónides, Buenos Aires, Argentina;3. Department of Anatomy and Neurobiology, Washington University, St. Louis, MO, USA;4. Department of Neurology, Washington University, St. Louis, MO, USA;5. Department of Psychiatry, Washington University, St. Louis, MO, USA;6. Department of Radiology, Washington University, St. Louis, MO, USA;7. Department of Neurology, Penn State University, Hershey, PA, USA;1. Dept. of Computer Science, University of California, Los Angeles, United States;2. School of Medicine, Yale University, United States;3. Dept. of Preventative Medicine, Northwestern University, United States;1. Department of Computer Science, Shahid Beheshti University, GC, Tehran, Iran;2. Australian National University, Canberra, ACT 0200, Australia;1. DIEE, University of Cagliari, 09123 Cagliari, Italy;2. PolComIng, University of Sassari, 07100 Sassari, Italy;3. Micrel Lab - DEI, University of Bologna, 40136 Bologna, Italy
Abstract:Topology is widely known as the most important characteristic of networks-on-chip (NoC), since it highly affects overall network performance, cost, and power consumption. In this paper, we propose a reconfigurable architecture and design flow for NoCs on which a customized topology for any target application can be implemented. In this structure, the nodes are grouped into some clusters interconnected by a reconfigurable communication infrastructure. The nodes inside a cluster are connected by a mesh to benefit from the interesting characteristics of the mesh topology, i.e. regular structure and efficient handling of local traffic. A reconfigurable inter-cluster topology then eliminates the major shortcoming of the mesh by providing short paths between remotely located nodes. We then present a design flow that maps the frequently communicating tasks of a given application onto the same cluster and exploits the reconfigurable infrastructure to set up appropriate inter-cluster connections. The experimental results show that by efficiently handling local and long-distance traffic flows, this structure is scalable, and power- and performance-efficient.
Keywords:
本文献已被 ScienceDirect 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号