Amdahl's law in the multicore era

被引:595
|
作者
Hill, Mark D. [1 ,2 ]
Marty, Michael R.
机构
[1] Univ Wisconsin, Dept Comp Sci, Madison, WI 53706 USA
[2] Univ Wisconsin, Dept Elect & Comp Engn, Madison, WI 53706 USA
基金
美国国家科学基金会;
关键词
Amdahl's law; Chip multiprocessors (CMPs); Multicore chips;
D O I
10.1109/MC.2008.209
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Computing vendors' road maps promise multiple processor cores that will double the number of cores per chip repeatedly. Yet designers must subdue more degrees of freedom for multicore chips than for single-core designs. Amdahl's law shows that this model has important consequences for the multicore era. Sources as varied as Intel and the University of California, Berkeley, predict designs of a hundred, if not a thousand, cores. The authors offer a corollary of a simple model of multicore hardware resources. Their results should encourage multicore designers to view the entire chip's performance rather than focusing on core efficiencies. They also describe several important limitations of their models to stimulate discussion and future work.
引用
收藏
页码:33 / +
页数:7
相关论文
共 50 条
  • [31] Reversed Amdahl's Law for Hybrid Parallel Computing
    Rudy, Jaroslaw
    Bozejko, Wojciech
    COMPUTER AIDED SYSTEMS THEORY - EUROCAST 2017, PT I, 2018, 10671 : 101 - 108
  • [32] Extending Amdahl's Law for Multicores with Turbo Boost
    Verner, Uri
    Mendelson, Avi
    Schuster, Assaf
    IEEE COMPUTER ARCHITECTURE LETTERS, 2017, 16 (01) : 30 - 33
  • [33] Applying Amdahl's Other Law to the data center
    Cohen, D.
    Petrini, F.
    Day, M. D.
    Ben-Yehuda, M.
    Hunter, S. W.
    Cummings, U.
    IBM JOURNAL OF RESEARCH AND DEVELOPMENT, 2009, 53 (05)
  • [34] Overcoming Amdahl's Law by Distributing Workload Asymmetrically
    Kim, Heegon
    Lee, Sungju
    Chung, Yongwha
    CONVERGENCE AND HYBRID INFORMATION TECHNOLOGY, 2012, 310 : 465 - 471
  • [35] Mitigating Amdahl's Law through EPI throttling
    Annavaram, M
    Grochowski, E
    Shen, J
    32ND INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE, PROCEEDINGS, 2005, : 298 - 309
  • [36] ONCE AGAIN, AMDAHL LAW
    HEATH, M
    WORLEY, P
    COMMUNICATIONS OF THE ACM, 1989, 32 (02) : 262 - 263
  • [37] Performance Characterization of Hadoop and DataMPI Based on Amdahl's Second Law
    Liang, Fan
    Feng, Chen
    Lu, Xiaoyi
    Xu, Zhiwei
    2014 9TH IEEE INTERNATIONAL CONFERENCE ON NETWORKING, ARCHITECTURE, AND STORAGE (NAS), 2014, : 207 - 215
  • [38] Extending Amdahl’s law and Gustafson’s law by evaluating interconnections on multi-core processors
    Tian Huang
    Yongxin Zhu
    Meikang Qiu
    Xiaojing Yin
    Xu Wang
    The Journal of Supercomputing, 2013, 66 : 305 - 319
  • [39] Extending Amdahl's law and Gustafson's law by evaluating interconnections on multi-core processors
    Huang, Tian
    Zhu, Yongxin
    Qiu, Meikang
    Yin, Xiaojing
    Wang, Xu
    JOURNAL OF SUPERCOMPUTING, 2013, 66 (01): : 305 - 319
  • [40] Amdahl's law and parallelization of the FMLSQ program on the Intel Nehalem architecture
    Strokopytov, Boris V.
    Dorovatovsky, Pavel V.
    Trofimov, Anton A.
    Polyakov, Konstantin M.
    JOURNAL OF APPLIED CRYSTALLOGRAPHY, 2011, 44 : 672 - 680