BLOCK-BASED HARDWARE SCHEDULER DESIGN ON MANY-CORE ARCHITECTURE

被引:0
|
作者
Ju, Lihan [1 ]
Pan, Ping [1 ]
Quan, Baixing [1 ]
Chen, Tianzhou [1 ]
Wu, Minghui [1 ]
机构
[1] Zhejiang Univ, Coll Comp Sci, Hangzhou 310027, Zhejiang, Peoples R China
来源
2012 IEEE INTERNATIONAL SYMPOSIUM ON INDUSTRIAL ELECTRONICS (ISIE) | 2012年
关键词
Scheduler; parallel; many-core; hardware; thread; partition;
D O I
暂无
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
Because Moore's law is always still working and the requirement of energy-saving still exists, CPU architecture is becoming more and more complicated and developing to Many-core architecture. But many-core is incompatible with the current programming mode designed for single-core CPU. This paper proposed a Block level Hardware-based Scheduling on many-core architecture (BHS) by adding the program control information which combined with hard-ware design. With BHS, many-core can execute a variety of parallel styles for suiting parallel granularity. The two main features of BHS are: First, a block-based hardware scheduler was implemented to reduce the overhead of threads and get communication among cores faster; second, it is very applicable to small and scalable cores which were tightly coupled in the cores group, loosely coupled between groups in many-core architecture. And a variety of parallel techniques would be effectively exploited.
引用
收藏
页码:814 / 819
页数:6
相关论文
共 50 条
  • [31] Characterizing and optimizing Java']Java-based HPC applications on Intel many-core architecture
    Yu, Yang
    Lei, Tianyang
    Chen, Haibo
    Zang, Binyu
    SCIENCE CHINA-INFORMATION SCIENCES, 2017, 60 (12)
  • [32] Mapping Routing Lookup Algorithm on Many-Core Architecture based on SPM and Cache Mixed Method
    Yu, Lei
    Liu, Zhiyong
    Fan, Dongrui
    Ma, Yike
    Song, Fenglong
    Ye, Xiaochun
    Xu, Weizhi
    INFORMATION TECHNOLOGY FOR MANUFACTURING SYSTEMS II, PTS 1-3, 2011, 58-60 : 1226 - 1231
  • [33] Queuing Ports for Mesh Based Many-Core Processors
    Villaescusa D.G.
    Rivas M.A.
    Harbour M.G.
    Ada User Journal, 2021, 42 (3-4): : 189 - 192
  • [34] The power impact of hardware and software actuators on self-adaptable many-core systems
    del Mestre Martins, Andre Luis
    Garibotti, Rafael
    Dutt, Nikil
    Moraes, Fernando Gehm
    JOURNAL OF SYSTEMS ARCHITECTURE, 2019, 97 : 42 - 53
  • [35] Architecture and Evaluation of Low Power Many-Core SoC with Two 32-Core Clusters
    Miyamori, Takashi
    Xu, Hui
    Usui, Hiroyuki
    Hosoda, Soichiro
    Sano, Toru
    Yamamoto, Kazumasa
    Kodaka, Takeshi
    Nonogaki, Nobuhiro
    Ozaki, Nau
    Tanabe, Jun
    IEICE TRANSACTIONS ON ELECTRONICS, 2014, E97C (04): : 360 - 368
  • [36] An automatic mapping technique for OpenACC kernel code based on deeply fused and heterogeneous many-core architecture
    Zhang, Libo
    Mao, Xingquan
    You, Hongtao
    Gu, Long
    Jiang, Xiaocheng
    CCF TRANSACTIONS ON HIGH PERFORMANCE COMPUTING, 2020, 2 (04) : 323 - 331
  • [37] A Highly-Efficient and Tightly-Connected Many-Core Overlay Architecture
    Ben Abdelhamid, Riadh
    Yamaguchi, Yoshiki
    Boku, Taisuke
    IEEE ACCESS, 2021, 9 : 65277 - 65292
  • [38] Godson-T: An Efficient Many-Core Architecture for Parallel Program Executions
    Dong-Rui Fan
    Nan Yuan
    Jun-Chao Zhang
    Yong-Bin Zhou
    Wei Lin
    Feng-Long Song
    Xiao-Chun Ye
    He Huang
    Lei Yu
    Guo-Ping Long
    Hao Zhang
    Lei Liu
    Journal of Computer Science and Technology, 2009, 24 : 1061 - 1073
  • [39] Towards optimal scheduling policy for heterogeneous memory architecture in many-core system
    Park, Geunchul
    Rho, Seungwoo
    Kim, Jik-Soo
    Nam, Dukyun
    CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS, 2019, 22 (01): : 121 - 133
  • [40] Towards optimal scheduling policy for heterogeneous memory architecture in many-core system
    Geunchul Park
    Seungwoo Rho
    Jik-Soo Kim
    Dukyun Nam
    Cluster Computing, 2019, 22 : 121 - 133