Machine Learning and Intelligent Communications. Second International Conference, MLICOM 2017, Weihai, China, August 5-6, 2017, Proceedings, Part II

Research Article

A Virtual Channel Allocation Algorithm for NoC

Download
304 downloads
  • @INPROCEEDINGS{10.1007/978-3-319-73447-7_37,
        author={Dongxing Bao and Xiaoming Li and Yizong Xin and Jiuru Yang and Xiangshi Ren and Fangfa Fu and Cheng Liu},
        title={A Virtual Channel Allocation Algorithm for NoC},
        proceedings={Machine Learning and Intelligent Communications. Second International Conference, MLICOM 2017, Weihai, China, August 5-6, 2017, Proceedings, Part II},
        proceedings_a={MLICOM},
        year={2018},
        month={2},
        keywords={VC allocation Block probability Network-on-chip},
        doi={10.1007/978-3-319-73447-7_37}
    }
    
  • Dongxing Bao
    Xiaoming Li
    Yizong Xin
    Jiuru Yang
    Xiangshi Ren
    Fangfa Fu
    Cheng Liu
    Year: 2018
    A Virtual Channel Allocation Algorithm for NoC
    MLICOM
    Springer
    DOI: 10.1007/978-3-319-73447-7_37
Dongxing Bao1, Xiaoming Li2,*, Yizong Xin3, Jiuru Yang1, Xiangshi Ren4,*, Fangfa Fu2, Cheng Liu2
  • 1: Heilongjiang University
  • 2: Harbin Institute of Technology
  • 3: Shenyang University of Technology
  • 4: Kochi University of Technology
*Contact email: lixiaoming@hit.edu.cn, eastarbox@163.com

Abstract

Virtual channel (VC) flow control proves to be an alternative way to promote network performance, but uniform VC allocation in the network may be at the cost of chip area and power consumption. We propose a novel VC number allocation algorithm customizing the VCs in network based on the characteristic of the target application. Given the characteristic of target application and total VC number budget, the block probability for each port of nodes in the network can be obtained with an analytical model. Then VCs are added to the port with the highest block probability one by one. The simulation results indicate that the proposed algorithm reduces buffer consumption by 14.58%–51.04% under diverse traffic patterns and VC depth, while keeping similar network performance.