Scheduling algorithms for strict multithreaded computations
In this paper, two scheduling algorithms that solve the problem of efficient scheduling k-strict multithreaded computations are presented. Both of them use the work-stealing technique, in which a processor that doesn't have work to do, steals threads from other processors. Our results achieve linear speedup and linear expansion of memory, for constant k (that is k ∈ O(1)). However, they are general and hold for all values of k.
Unable to display preview. Download preview PDF.
- 1.Fatourou, P., Spirakis, P.: Scheduling Algorithms for Strict Multithreaded Computations. Computer Technology Institute, T.R. 96.5.13, (1996).Google Scholar
- 2.Blumofe, R., Leiserson, Ch.: Scheduling Multithreaded Computations by Work Stealing. Proc. of the 35th Ann. Symp. on Foundations of Computer Science (FOCS). (1994), 356–368.Google Scholar
- 3.Blumofe, R., Leiserson, Ch.: Space-Efficient Scheduling of Multithreaded Computation. Proc. of the 25th Ann. ACM Symposium on the Theory of Computing (STOC). San Diego, California, (May 1993), 362–371.Google Scholar
- 4.Liu, P., Aielo, W., Bhatt, S.: An atomic model for message passing. Proc. of the Fifth Annual ACM Symposium on Parallel Algorithms and Architectures (SPAA). Velen, Germany, (June 1993), 154–163.Google Scholar
- 5.Feller, W.: An Introduction to Probability Theory and its Application. Third Edition, vol.1, John Wiley & Sons, Inc., 1968.Google Scholar