arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1804.04773cs.DCcs.DMcs.DS
收藏

论局部工作窃取的效率

On the Efficiency of Localized Work Stealing

Warut Suksompong, Charles E. Leiserson, Tao B. Schardl

摘要:

本文研究了工作窃取算法的一个变种,我们称之为本地化的工作窃取算法。这种变体背后的直觉是,由于局部性,处理器可以从自己的工作中受益。因此,当一个处理器空闲时,它会尝试窃取自己的工作。我们把这种偷叫偷回。我们证明了算法的期望运行时间为$T_1/P+O(T_\infty P)$,在"自由代理均匀分布假设"下,算法的期望运行时间为$T_1/P+O(T_\infty\lg P)$.此外,我们得到了另一个运行时间界的基础上的计算串行任务的大小之间的比率。如果$M$表示在从考虑中去除所有处理器上的$O(P)$串行任务总数之后处理器的最大串行任务与最小串行任务之间的最大比率,则算法的预期运行时间为$T_1/P+O(T_\infty M)$。

英文摘要:

This paper investigates a variant of the work-stealing algorithm that we call the localized work-stealing algorithm. The intuition behind this variant is that because of locality, processors can benefit from working on their own work. Consequently, when a processor is free, it makes a steal attempt to get back its own work. We call this type of steal a steal-back. We show that the expected running time of the algorithm is $T_1/P+O(T_\infty P)$, and that under the "even distribution of free agents assumption", the expected running time of the algorithm is $T_1/P+O(T_\infty\lg P)$. In addition, we obtain another running-time bound based on ratios between the sizes of serial tasks in the computation. If $M$ denotes the maximum ratio between the largest and the smallest serial tasks of a processor after removing a total of $O(P)$ serial tasks across all processors from consideration, then the expected running time of the algorithm is $T_1/P+O(T_\infty M)$.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑