Hierarchical cache coherency protocol in a multi-level multiprocessors system

被引:0
|
作者
Patel, P [1 ]
Razzaque, MM [1 ]
机构
[1] Univ Texas, Div Engn, San Antonio, TX 78249 USA
关键词
cache coherency; snoopy protocol; multi-level architecture; write invalidate; write update;
D O I
暂无
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Shared memory multiprocessors have recently become popular due to their cost effectiveness and simplicity in implementation. Building multiprocessor system with cheap commercially available chips and high speed cache memory is a viable alternative to attaining higher performance. Moreover, multiprocessor systems have a much better price/performance ratio than a single large centralized system. However, multiprocessor system's performance is directly related to cache performance. One of the key performance issues of such system is the solution to the cache coherence problem. The choice of the coherence mechanism is dependent on the design architecture of the intended multiprocessor system. This paper presents a new scalable multiprocessor architecture that implement hierarchy of caches on multi-level bus. A new hardware based cache coherency protocol to maintain coherency of data in the system is presented. The architecture defines private common bus in each cluster of processors where as communication between the clusters takes place through the shared cache and main bus. Types of necessary bus transactions are also presented.
引用
收藏
页码:110 / 114
页数:5
相关论文
共 50 条
  • [21] Reducing cache conflicts by multi-level cache partitioning and array elements mapping
    Chang, CY
    Sheu, JP
    Chen, HC
    [J]. SEVENTH INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED SYSTEMS, PROCEEDINGS, 2000, : 195 - 202
  • [22] PERFORMANCE ANALYSIS OF HIERARCHICAL CACHE-CONSISTENT MULTIPROCESSORS
    VERNON, MK
    JOG, R
    SOHI, GS
    [J]. PERFORMANCE EVALUATION, 1989, 9 (04) : 287 - 302
  • [23] SVCP: A cache coherency protocol with explicit update subscription
    Yamazaki, T
    Yonezawa, N
    Kulkasem, P
    Yamagiwa, S
    Ono, M
    Al-Khoury, A
    Wada, K
    [J]. INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED PROCESSING TECHNIQUES AND APPLICATIONS, VOLS I-IV, PROCEEDINGS, 1998, : 899 - 906
  • [24] High level cache simulation for heterogeneous multiprocessors
    Pieper, JJ
    Mellan, A
    Paul, JM
    Thomas, DE
    Karim, F
    [J]. 41ST DESIGN AUTOMATION CONFERENCE, PROCEEDINGS 2004, 2004, : 287 - 292
  • [25] 2-LEVEL CACHE PERFORMANCE FOR MULTIPROCESSORS
    ZIMMERMAN, SL
    ROBINSON, JP
    [J]. SIMULATION, 1993, 60 (04) : 222 - 231
  • [26] Multi-level hierarchical analogue fault simulation
    Straube, B
    Vermeiren, W
    Spenke, V
    [J]. MICROELECTRONICS JOURNAL, 2002, 33 (10) : 815 - 821
  • [27] Fabrication and characterization of multi-level hierarchical surfaces
    Bhushan, Bharat
    Lee, Hyungoo
    [J]. FARADAY DISCUSSIONS, 2012, 156 : 235 - 241
  • [28] ASA: An Adaptive Space Allocation algorithm for cache management in multi-level cache hierarchy
    Ou, Li
    Sankar, Karthik
    He, Xubin Ben
    [J]. PROCEEDINGS OF THE THIRTY-EIGHTH SOUTHEASTERN SYMPOSIUM ON SYSTEM THEORY, 2004, : 524 - 528
  • [29] Criticality Aware Tiered Cache Hierarchy: A Fundamental Relook at Multi-level Cache Hierarchies
    Nori, Anant Vithal
    Gaur, Jayesh
    Rai, Siddharth
    Subramoney, Sreenivas
    Wang, Hong
    [J]. 2018 ACM/IEEE 45TH ANNUAL INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE (ISCA), 2018, : 96 - 109
  • [30] Precise Multi-Level Inclusive Cache Analysis for WCET Estimation
    Zhang, Zhenkai
    Koutsoukos, Xenofon
    [J]. 2015 IEEE 36TH REAL-TIME SYSTEMS SYMPOSIUM (RTSS 2015), 2015, : 350 - 360