Abstract
Superficially, the Earliest Task First (ETF) heuristic [1] is attractive because it models heterogeneous messages passing through a heterogeneous network. On closer inspection, however, this is precisely the set of circumstances that can cause ETF to produce seriously sub-optimal schedules. In this paper we analyze the scope of applicability of ETF. We show that ETF has a good performance if messages are short and the links are fast and a poor performance otherwise. For the first application we choose the Diamond DAG with unit execution time for each task and the multiprocessor system in the form of the fully connected network. We show that ETF partitions the DAG into lines each of which is scheduled on the same processor. The analysis reveals that if the communication times between pairs of adjacent tasks in a precedence relation are all less than or equal to unit then the schedule is optimal. If the communication time is equal to the processing time needed to evaluate a row then the completion time is O(√n) times more than the optimal one for an n×n Diamond DAG. For the second application, we choose the join DAG evaluated by two connected processors.
Preview
Unable to display preview. Download preview PDF.
References
J-J. Hwang, Y-C. Chow, F.D. Anger, and C-Y. Lee. Scheduling precedence graphs in systems with interprocessor communication times. SIAM J. Comput., 18(2):244–257, 1989.
A.A. Khan, C.L. McCreary, and M.S. Jones A comparison of multiprocessor scheduling heuristics. Technical Report comparison-ICPP-94, Dept. of Computer Science and Engineering, Auburn University, 1994. Published in the Proceeding of the 8th Int. Parallel Processing Sym. — April, 1994.
S. Manoharan and P. Thanisch. Assigning dependency graphs onto processor networks. Parallel Computing, 17(1):63–73, 1991.
S. Manoharan and N.P. Topham. An assessment of assignment schemes for dependency graphs. Parallel Computing, 21(1):85–107, 1995.
M.G. Norman, G. Chochia, P. Thanisch, and E. Issman. Predicting the performance of the diamond dag computation. Technical Report EPCC-TR-92-07, Edinburgh Parallel Computing Centre, 1992.
M. Norman, P. Thanisch, and G. Chang. Partitioning DAG Computations. In W. Joosen and E. Milgrom, editors, Parallel Computing: From Theory to Sound Practice, pages 360–364, Amsterdam, 1992. IOS Press.
M.G. Norman and P. Thanisch. Models of machines and computations for mapping in multicomputers. Computing Surveys, 25(3):263–302, 1993.
C.H. Papadimitriou and J.D. Ullman. A communication-time tradeoff. SIAM J. Comput., 16(4):639–646, 1987.
C.H. Papadimitriou and M. Yannakakis. Towards an architecture-independent analysis of parallel algorithms. SIAM J. Comput., 19:322–328, 1990.
R. Thurimella and Y. Yesha. A scheduling principle for precedence graphs with communication delay. J. of Computer and Software Engineering, 2(2):165–176, 1994.
B. Veltman, B.J. Lageweg, and J.K. Lenstra. Multiprocessor scheduling with communication delays. Parallel Computing, 16(2–3):173–182, 1990.
T. Yang and A. Gerasoulis. DSC: Scheduling parallel tasks on an unbounded number of processors. IEEE Trans. Paral. Distr. Systems, 5(9):951–967, Sep 1994.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Boeres, C., Chochia, G., Thanisch, P. (1995). On the scope of applicability of the ETF algorithm. In: Ferreira, A., Rolim, J. (eds) Parallel Algorithms for Irregularly Structured Problems. IRREGULAR 1995. Lecture Notes in Computer Science, vol 980. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60321-2_13
Download citation
DOI: https://doi.org/10.1007/3-540-60321-2_13
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60321-4
Online ISBN: 978-3-540-44915-7
eBook Packages: Springer Book Archive