Scheduling Multithreaded Computations by Work Stealing

This paper studies the problem of e ciently scheduling fully strict (i.e., wellstructured) multithreaded computations on parallel computers. A popular and practical method of scheduling this kind of dynamic MIMD-style computation is \work stealing," in which processors needing work steal computational threads from other processors. In this paper, we give the rst provably good work-stealing scheduler for multithreaded computations with dependencies. Speci cally, our analysis shows that the expected time to execute a fully strict computation on P processors using our work-stealing scheduler is T1=P +O(T1), where T1 is the minimum serial execution time of the multithreaded computation and T1 is the minimum execution time with an in nite number of processors. Moreover, the space required by the execution is at most S1P , where S1 is the minimum serial space requirement. We also show that the expected total communication of the algorithm is at most O(P T1(1+nd)Smax), where Smax is the...

• Type: Conference
• Year: 1994
• Where: FOCS
• Authors: Robert D. Blumofe
• Keywords: Execution Time, FOCS 1994, Multithreaded Computation, Theoretical Computer Science, Work-stealing Schedulers