Design of a High-Performance CDMA-Based Broadcast-Free Photonic Multi-Core Network on Chip

被引:3
|
作者
Poddar, Soumyajit [1 ,2 ]
Ghosal, Prasun [1 ,2 ]
Rahaman, Hafizur [1 ,2 ]
机构
[1] Indian Inst Engn Sci & Technol, Sibpur, India
[2] Indian Inst Engn Sci & Technol, PO Bot Garden, Howrah 711103, WB, India
关键词
Photonic networks on chip; optical interconnect; code division multiple access; multicore architecture; ON-CHIP;
D O I
10.1145/2839301
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Present-day focus on multicore research has not only increased computing power but also power- and bandwidth-efficient communication among cores. On-chip communication networks have become popular today because of their low energy use and modular structure compared to bus-based interconnects. Silicon photonics has further boosted the performance of on-chip interconnection networks with its low energy-delay product and high reliability. In current multicore Network-on-Chip (NoC) architectures, photonics is playing an important role in transferring large volumes of data both on- and off-chip. The problem addressed in this work is the issue of broadcast traffic arising due to invalidation requests from on-chip cache memories. Although such traffic is typically less than 1% of total traffic, it can easily present a high load on network resources, creating congestion and degrading performance. In this article, we propose a CDMA-based, secure, scalable, and energy-efficient technique to eliminate broadcast invalidations and increase overall performance. Experimental results indicate a performance boost up to 22.2% over a competing Photonic NoC and up to 57.4% over Electrical Mesh-based NoC when the proposed technique is used. Additional hardware deployed has an area overhead of less than 1%, whereas total energy consumed is at par with other state-of-the-art techniques.
引用
收藏
页数:30
相关论文
共 50 条
  • [1] Design of high performance firewall based on multi-core network development platform
    Zhang, Wei-wei
    Dong, Ming-gang
    PROCEEDINGS OF THE 2016 3RD INTERNATIONAL CONFERENCE ON MATERIALS ENGINEERING, MANUFACTURING TECHNOLOGY AND CONTROL, 2016, 67 : 447 - 450
  • [2] Performance explorations of multi-core network on chip router
    Saravanakumar, U.
    Rangarajan, R.
    International Journal of Simulation: Systems, Science and Technology, 2012, 13 (01): : 36 - 42
  • [3] High-Performance Packet Classification on Multi-Core Network Processing Platforms
    亓亚烜
    薛一波
    李军
    TsinghuaScienceandTechnology, 2011, 16 (04) : 432 - 439
  • [4] StackPool: A High-Performance Scalable Network Architecture on Multi-core Servers
    Gu, Qiang
    Wen, Liufei
    Dai, Fen
    Gong, Hao
    Yang, Yongqiang
    Xu, Xiangyang
    Feng, Zexi
    2013 IEEE 15TH INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING AND COMMUNICATIONS & 2013 IEEE INTERNATIONAL CONFERENCE ON EMBEDDED AND UBIQUITOUS COMPUTING (HPCC_EUC), 2013, : 17 - 28
  • [5] Wireless Network-on-Chip: A New Era in Multi-Core Chip Design
    Deb, Sujay
    Mondal, Hemanta Kumar
    PROCEEDINGS OF THE 2014 25TH IEEE INTERNATIONAL SYMPOSIUM ON RAPID SYSTEM PROTOTYPING (RSP): SHORTENING THE PATH FROM SPECIFICATION TO PROTOTYPE, 2014, : 59 - 64
  • [6] Reliable network-on-chip design for multi-core system-on-chip
    Kuei-Chung Chang
    The Journal of Supercomputing, 2011, 55 : 86 - 102
  • [7] Reliable network-on-chip design for multi-core system-on-chip
    Chang, Kuei-Chung
    JOURNAL OF SUPERCOMPUTING, 2011, 55 (01): : 86 - 102
  • [8] Towards High-performance Pattern Matching on Multi-core Network Processing Platforms
    Qi, Yaxuan
    Zhou, Zongwei
    Wu, Yiyao
    Xue, Yibo
    Li, Jun
    2010 IEEE GLOBAL TELECOMMUNICATIONS CONFERENCE GLOBECOM 2010, 2010,
  • [9] A high-performance and scalable multi-core aware software solution for network monitoring
    Dashtbozorgi, Mahdi
    Azgomi, Mohammad Abdollahi
    JOURNAL OF SUPERCOMPUTING, 2012, 59 (02): : 720 - 743
  • [10] A high-performance and scalable multi-core aware software solution for network monitoring
    Mahdi Dashtbozorgi
    Mohammad Abdollahi Azgomi
    The Journal of Supercomputing, 2012, 59 : 720 - 743