A new relaxed memory consistency model for shared-memory multiprocessors with parallel-multithreaded processing elements

被引:0
|
作者
Wu, CC [1 ]
Chen, C [1 ]
机构
[1] Natl Chiao Tung Univ, Dept Comp Sci & Informat Engn, Hsinchu 300, Taiwan
关键词
memory consistency model; multithread; multiprocessor; write cache; synchronization; PSC model; barrier; performance evaluation;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The release consistency model is the generally accepted hardware-centric relaxed memory consistency model because of its performance and implementation complexity. By extending the release consistency model, in this paper. we propose a hardware-centric memory consistency model particularly for shared-memory multiprocessor systems with parallel-multithreaded processing elements. The new model uses a new categorization for memory references and utilizes the feature of parallel multithreaded processors (PMPs). We further partition acquire and release references into three sub-categories: one for lock-unlock pairs, one for barrier synchronization, and the last for others. According to the semantic of each synchronization primitive, each sub-category has its own relaxed restrictions. On the other hand, the feature of a PMP is that it is capable of executing more than one thread at the same time, where all parallel threads share only one cache hierarchy. Under the new model, we can use dual write-caches to reduce write traffic and synchronization time. We have used five benchmarks in the SPLASH suite to evaluate the performance gain for the new model. According to the simulation results, the new model is superior to the release consistency model at best by about 11%.
引用
收藏
页码:785 / 808
页数:24
相关论文
共 50 条
  • [31] Parallel-vector algorithms for particle simulations on shared-memory multiprocessors
    Nishiura, Daisuke
    Sakaguchi, Hide
    JOURNAL OF COMPUTATIONAL PHYSICS, 2011, 230 (05) : 1923 - 1938
  • [32] The memory performance of DSS commercial workloads in shared-memory multiprocessors
    Trancoso, P
    LarribaPey, JL
    Zhang, Z
    Torrellas, J
    THIRD INTERNATIONAL SYMPOSIUM ON HIGH-PERFORMANCE COMPUTER ARCHITECTURE - PROCEEDINGS, 1997, : 250 - 260
  • [33] Processing graphs with barrierless asynchronous parallel model on shared-memory systems
    Luo, Le
    Liu, Yi
    FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2020, 106 : 641 - 652
  • [34] Parallelization of benchmarks for scalable shared-memory multiprocessors
    Paek, Y
    Navarro, A
    Zapata, E
    Padua, D
    1998 INTERNATIONAL CONFERENCE ON PARALLEL ARCHITECTURES AND COMPILATION TECHNIQUES, PROCEEDINGS, 1998, : 401 - 408
  • [35] A compiler optimization algorithm for shared-memory multiprocessors
    McKinley, KS
    IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 1998, 9 (08) : 769 - 787
  • [36] SEQUENTIAL HARDWARE PREFETCHING IN SHARED-MEMORY MULTIPROCESSORS
    DAHLGREN, F
    DUBOIS, M
    STENSTROM, P
    IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 1995, 6 (07) : 733 - 746
  • [37] CACHE INVALIDATION PATTERNS IN SHARED-MEMORY MULTIPROCESSORS
    GUPTA, A
    WEBER, WD
    IEEE TRANSACTIONS ON COMPUTERS, 1992, 41 (07) : 794 - 810
  • [38] Conservative circuit simulation on shared-memory multiprocessors
    Keller, J
    Rauber, T
    Rederlechner, B
    TENTH WORKSHOP ON PARALLEL AND DISTRIBUTED SIMULATION - PADS 96, PROCEEDINGS, 1996, : 126 - 134
  • [39] FILTERED BACK PROJECTION ON SHARED-MEMORY MULTIPROCESSORS
    ZAPATA, EL
    CARAZO, JM
    BENAVIDES, JI
    WALTHER, S
    PESKIN, R
    ULTRAMICROSCOPY, 1990, 34 (04) : 271 - 282
  • [40] SCALABLE CACHE COHERENCE FOR SHARED-MEMORY MULTIPROCESSORS
    THAPAR, M
    DELAGI, BA
    FLYNN, MJ
    LECTURE NOTES IN COMPUTER SCIENCE, 1992, 591 : 1 - 12