中国邮电高校学报(英文) ›› 2009, Vol. 16 ›› Issue (5): 86-91.doi: 10.1016/S1005-8885(08)60273-3

• Others • 上一篇    下一篇

S-Mesh: a Mesh-based on-chip network with
separation of control and transmission

刘浩; 邹雪城; 蔡梦;吉立新;张科峰   

  1. Department of Electronic Science and Technology, Huazhong University of Science and Technology, Wuhan 430074, China
  • 收稿日期:2009-02-04 修回日期:1900-01-01 出版日期:2009-10-30
  • 通讯作者: 邹雪城

S-Mesh: a Mesh-based on-chip network with
separation of control and transmission

LIU Hao, ZOU Xue-cheng, JI Li-xin, CAI Meng, ZHANG Ke-feng   

  1. Department of Electronic Science and Technology, Huazhong University of Science and Technology, Wuhan 430074, China
  • Received:2009-02-04 Revised:1900-01-01 Online:2009-10-30
  • Contact: ZOU Xue-cheng

摘要:

The current network-on-chip (NoC) topology cannot pre¬dict subsequent switch node status promptly. Switch nodes have to perform various functions such as routing decision, data forwarding, packet buffering, congestion control and properties of an NoC system. Therefore, these make switch architecture far more complex. This article puts forward a separating on-chip network architecture based on Mesh (S-Mesh). S-Mesh is an on-chip network that separates routing decision flow from the switches. It consists of two types of networks: datapath network (DN) and control network (CN). The CN establishes data paths for data transferring in DN. Meanwhile, the CN also transfers instructions between different resources. This property makes switch architecture simple, and eliminates conflicts in network interface units between the resource and switch. Compared with 2D-Mesh, Torus Mesh, Fat-tree and Butterfly, the average packet latency in S-Mesh is the shortest when the packet length is more than 53 B. Compared with 2D-Mesh, the areas savings of S-Mesh is about 3%–7%, and the power dissipation is decreased by approximate 2%.

关键词:

network;on-chip,;Mesh;architecture,;separation;system,;congestion;avoidance,;lower;latency

Abstract:

The current network-on-chip (NoC) topology cannot pre¬dict subsequent switch node status promptly. Switch nodes have to perform various functions such as routing decision, data forwarding, packet buffering, congestion control and properties of an NoC system. Therefore, these make switch architecture far more complex. This article puts forward a separating on-chip network architecture based on Mesh (S-Mesh). S-Mesh is an on-chip network that separates routing decision flow from the switches. It consists of two types of networks: datapath network (DN) and control network (CN). The CN establishes data paths for data transferring in DN. Meanwhile, the CN also transfers instructions between different resources. This property makes switch architecture simple, and eliminates conflicts in network interface units between the resource and switch. Compared with 2D-Mesh, Torus Mesh, Fat-tree and Butterfly, the average packet latency in S-Mesh is the shortest when the packet length is more than 53 B. Compared with 2D-Mesh, the areas savings of S-Mesh is about 3%–7%, and the power dissipation is decreased by approximate 2%.

Key words:

network on-chip;Mesh architecture;separation system;congestion avoidance;lower latency