An Implementation of a Directory Protocol for a Cache Coherent System on FPGAs

被引:0
|
作者
Mirian, Vincent [1 ]
Chow, Paul [1 ]
机构
[1] Univ Toronto, Toronto, ON, Canada
关键词
cache coherence; directory protocol; FPGA;
D O I
暂无
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
As FPGA-based systems evolve towards using networks of heterogeneous processing systems, it is important to develop suitable memory systems. This paper presents a cache coherent system that uses a directory protocol. The Directory component of our system has a pipeline design, where a message, which represents a memory request, is serviced every three cycles. Such a design works well for an FPGA, which is an ideal platform for parallel and streaming-type designs. Our system performs 25% more barriers per second than a previous system by Mirian et al. [1], which uses a snoopy protocol, by making minor changes to the Interconnect and the cache coherence protocol.
引用
收藏
页数:6
相关论文
共 50 条
  • [41] Design and Implementation of a Cache System in Web Search Engines
    Ma, Hongyuan
    PROGRESS IN MECHATRONICS AND INFORMATION TECHNOLOGY, PTS 1 AND 2, 2014, 462-463 : 1106 - 1109
  • [42] Design and Implementation of Configurable Cache Coherence Protocol for Multi- Core Processor
    Chen Z.
    Zhou H.
    Feng Q.
    Deng R.
    Zhou, Hongwei (forrestszhw@sohu.com), 1600, Science Press (58): : 1166 - 1175
  • [43] Software DSM system based on a new cache coherence protocol
    Hu, Weiwu
    Shi, Weisong
    Tang, Zhimin
    Jisuanji Xuebao/Chinese Journal of Computers, 1999, 22 (05): : 467 - 475
  • [44] FPGAs bridge the protocol gap
    Anon
    Electronic Product Design, 2001, 22 (07):
  • [45] Seclusive Cache Hierarchy for Mitigating Cross-Core Cache and Coherence Directory Attacks
    Gupta, Vishal
    Ganesan, Vinod
    Panda, Biswabandan
    PROCEEDINGS OF THE 2021 DESIGN, AUTOMATION & TEST IN EUROPE CONFERENCE & EXHIBITION (DATE 2021), 2021, : 637 - 640
  • [46] A Directory Cache with Dynamic Private-Shared Partitioning
    Valls, Joan J.
    Gomez, Maria E.
    Ros, Alberto
    Sahuquillo, Julio
    PROCEEDINGS OF 2016 IEEE 23RD INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING (HIPC), 2016, : 382 - 391
  • [47] Directory cache design for multi-core processor
    State Key Laboratory of High-End Server & Storage Technology , Beijing
    100085, China
    Jisuanji Yanjiu yu Fazhan, 6 (1242-1253):
  • [48] Implementation of ITER Fast Plant Interlock System Using FPGAs with cRIO
    Barrera, Eduardo
    Ruiz, Mariano
    Bustos, Alvaro
    Afif, Mehdi
    Radle, Byron
    Fernandez-Hernando, Juan Luis
    Prieto, Ignacio
    Pedica, Riccardo
    Barcala, Miguel
    Carlos Oller, Juan
    Castro, Rodrigo
    2016 IEEE-NPSS REAL TIME CONFERENCE (RT), 2016,
  • [49] The arrow distributed directory protocol
    Demmer, MJ
    Herlihy, MP
    DISTRIBUTED COMPUTING, 1998, 1499 : 119 - 133
  • [50] The Arvy Distributed Directory Protocol
    Khanchandani, Pankaj
    Wattenhofer, Roger
    SPAA'19: PROCEEDINGS OF THE 31ST ACM SYMPOSIUM ON PARALLELISM IN ALGORITHMS AND ARCHITECTURESS, 2019, 2019, : 225 - 235