Evaluation of a Practical Parallel Optimization Algorithm for the Minimum Execution-Time Multiprocessor Scheduling Problem

10 References
  • TOBITA TAKAO
    Dept. of Electrical, Electronics and Computer Engineering, Waseda University
  • KASAHARA HIRONORI
    Dept. of Electrical, Electronics and Computer Engineering, Waseda University

Bibliographic Information

Other Title
  • 実行時間最小マルチプロセッサスケジューリング問題に対する実用的並列最適化アルゴリズムの性能評価

Search this article

Description

This paper describes application of a practical parallel optimization algorithm PDF/IHS to very large scale problems with more than one thousand tasks. We imprement PDF/IHS on Sun Microsystems Ultra Enterprise 3000 and apply to 50-1100 tasks problems. Within 600 second wall-clock time, it was confirmed that optimal schedules were found for 69.3% of problems on 1 processor, 80.8% on 3 processors and 82.8% on 6 processors. An average search time which could get optimal schedule is 5.8 [s] with 6 processors ; 18.5 times faster than sequential DF/IHS 107.5[s].

Journal

References(10)*help

See more

Keywords

Details 詳細情報について

  • CRID
    1573950402189168256
  • NII Article ID
    110003179840
  • NII Book ID
    AN10013141
  • Text Lang
    ja
  • Data Source
    • CiNii Articles

Report a problem

Back to top