Venus: A Low-Latency, Low-Loss 3-D Hybrid Network-on-Chip for Kilocore Systems

被引:21
|
作者
Tan, Wei [1 ]
Gu, Huaxi [1 ]
Yang, Yintang [2 ]
Wang, Kun [3 ]
Wang, Xiaolu [1 ]
机构
[1] Xidian Univ, State Key Lab Integrated Serv Networks, Xian 710071, Shaanxi, Peoples R China
[2] Xidian Univ, Inst Microelect, Xian 710071, Shaanxi, Peoples R China
[3] Xidian Univ, Sch Comp Sci, Xian 710071, Shaanxi, Peoples R China
基金
中国国家自然科学基金;
关键词
3-D architecture; hybrid photonic-electronic; insertion loss; ONoC; WDM; POWER-EFFICIENT; BULK SILICON; INTERCONNECTION; CHALLENGES; PHOTONICS; PERFORMANCE; INTEGRATION; TOPOLOGIES; ANTENNAS; SWITCH;
D O I
10.1109/JLT.2017.2764956
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Network on chip (NoC) with more than 1000 cores is anticipated to meet the requirements of exascale computing in the foreseeable future. As latency is one of the most critical metrics to evaluate performance for kilocore-chip, researchers recently proposed optical networks on chip (ONoCs) with multiwavelength to achieve low latency. Nevertheless, with networks scaling to kilo-cores and too many wavelengths used, waveguide crossings loss and microring resonators (MRs) pass-by loss on the critical path are increased considerably. In this paper, we propose Venus, a three-dimensional NoC architecture with multiple photonic and electrical layers. By using space division multiplexing and hybrid wavelength assignments method, Venus possesses the following two features: 1) Each core can communicate with any other one in one hop and any two clusters in different subnets can communicate with each other without any blocking, thus reducing latency greatly; and 2) the number of waveguide crossings and also the MRs passed by on the critical path is reduced, thus saving energy consumption considerably. Architectures based on 64-core, 512-core, and 1024-core are simulated respectively. Evaluation results of different synthetic traffic patterns and real applications demonstrate that Venus significantly reduces the end-to-end latency and worst case loss compared to previous proposals.
引用
收藏
页码:5448 / 5455
页数:8
相关论文
共 50 条
  • [1] Low-latency Mapping Algorithm for Network-on-Chip
    Cao, Qinping
    Qin, Huabiao
    Chen, Wu
    Yi, Sijun
    2017 INTERNATIONAL CONFERENCE ON COMPUTER SYSTEMS, ELECTRONICS AND CONTROL (ICCSEC), 2017, : 1203 - 1206
  • [2] A Compression Router for Low-Latency Network-on-Chip
    Niwa, Naoya
    Shikama, Yoshiya
    Amano, Hideharu
    Koibuchi, Michihiro
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2023, E106D (02) : 170 - 180
  • [3] A Case for Low-Latency Network-on-Chip using Compression Routers
    Niwa, Naoya
    Shikama, Yoshiya
    Amano, Hideharu
    Koibuchi, Michihiro
    2021 29TH EUROMICRO INTERNATIONAL CONFERENCE ON PARALLEL, DISTRIBUTED AND NETWORK-BASED PROCESSING (PDP 2021), 2021, : 134 - 142
  • [4] WaveSync: A Low-Latency Source Synchronous Bypass Network-On-Chip Architecture
    Yang, Yoon Seok
    Kumar, Reeshav
    Choi, Gwan
    Gratz, Paul
    2012 IEEE 30TH INTERNATIONAL CONFERENCE ON COMPUTER DESIGN (ICCD), 2012, : 241 - 248
  • [5] A Low-Latency Fair-Arbiter Architecture for Network-on-Chip Switches
    Luo, Jifeng
    Wu, Wenqi
    Xing, Qianjian
    Xue, Meiting
    Yu, Feng
    Ma, Zhenguo
    APPLIED SCIENCES-BASEL, 2022, 12 (23):
  • [6] Low-Latency Power-Efficient Adaptive Router Design for Network-on-Chip
    Nasirian, Nasim
    Bayoumi, Magdy
    2015 28TH IEEE INTERNATIONAL SYSTEM-ON-CHIP CONFERENCE (SOCC), 2015, : 287 - 291
  • [7] WaveSync: Low-Latency Source-Synchronous Bypass Network-on-Chip Architecture
    Yang, Yoon Seok
    Kumar, Reeshav
    Choi, Gwan
    Gratz, Paul V.
    ACM TRANSACTIONS ON DESIGN AUTOMATION OF ELECTRONIC SYSTEMS, 2014, 19 (04)
  • [8] A LOW-AREA AND LOW-LATENCY NETWORK ON CHIP
    Wang, Xiaofang
    Bandi, Leeladhar
    2010 23RD CANADIAN CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING (CCECE), 2010,
  • [9] LumiNOC: A Low-latency, High-Bandwidth per Watt, Photonic Network-on-Chip
    Browning, Mark
    Li, Cheng
    Gratz, Paul V.
    Palermo, Samuel
    2013 ACM/IEEE INTERNATIONAL WORKSHOP ON SYSTEM LEVEL INTERCONNECT PREDICTION (SLIP), 2013,
  • [10] HyDMA: low-latency inter-core DMA based on a hybrid packet-circuit switching network-on-chip
    Wei, Zhenqi
    Liu, Peilin
    Sun, Rongdi
    Zhou, Zunquan
    Jin, Ke
    Zhou, Dajiang
    IEICE ELECTRONICS EXPRESS, 2016, 13 (14):