Abstract
This paper presents the application scheduling algorithms on a class of multiprocessor architectures that exploit temporal and spatial parallelism simultaneously. The hardware platform is a multi-level or partitionable architecture. Spatial parallelism is exploited with MIMD type processor clusters (or layers) and temporal parallelism is exploited by pipelining operations on those independent clusters. In order to fully exploit system’s capacity, multi processor tasks (MPTs) that are executed on such system should be scheduled appropriately. In our earlier study, we have proposed scheduling algorithms based on well known local search heuristic algorithms such as simulated annealing, tabu search and genetic algorithm and their performances were tested computationally by using a set of randomly generated test data. In this paper, we present application of these scheduling algorithms on a multilayer architecture which is designed as a visual perception unit of an autonomous robot and evaluate performance improvement achieved.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Błażewicz, J., Drozdowski, M.: Scheduling Divisible Jobs on Hypercubes. Parallel Computing 21, 1945–1956 (1995)
Błażewicz, J., Ecker, K.H., Pesch, E., Schmidt, G., Węglarz, J.: Scheduling Computer and Manufacturing Processes. Springer, Berlin (1996)
Bokhari, S.H.: Assignment Problems in Parallel and Distributed Computing. Kluwer Academic, Boston (1987)
Choudhary, A.N., Patel, J.H., Ahuja, N.: NETRA: A Hierarchical and Partitionable Architecture for Computer Vision Systems. IEEE Transactions on Parallel and Distributed Systems 4, 1092–1104 (1993)
El-Revini, H.: Partitioning and Scheduling. In: Zomaya, A.D. (ed.) Parallel and Distributed Computing Handbook, pp. 239–273. McGraw-Hill, New York (1996)
Ercan, M.F., Fung, Y.F.: Real-time Image Interpretation on a Multi-layer Architecture. In: IEEE TENCON 1999, vol. 2, pp. 303–1306 (1999)
Ercan, M.F., Oğuz, C., Fung, Y.F.: Performance Evaluation of Heuristics for Scheduling Pipelined Multiprocessor Tasks. In: Alexandrov, V.N., Dongarra, J., Juliano, B.A., Renner, R.S., Tan, C.J.K. (eds.) ICCS-ComputSci 2001. LNCS, vol. 2073, pp. 61–70. Springer, Heidelberg (2001)
Ercan, M.F., Fung, Y.F.: Tabu Search and Simulated Annealing on the Scheduling of Pipelined Multiprocessor Tasks. In: Proceedings of ICSEC 2002, pp. 785–788 (2002)
Oğuz, C., Fung, Y.F., Ercan, M.F., Qi, X.T.: Parallel Genetic Algorithm for a Flow-Shop Problem with Multiprocessor Tasks. In: Kumar, V., Gavrilova, M.L., Tan, C.J.K., L’Ecuyer, P. (eds.) ICCSA 2003. LNCS, vol. 2667, pp. 987–997. Springer, Heidelberg (2003)
Oğuz, C.: (2002) http://www.acad.polyu.edu.hk/~msceyda/Research/data_set_EJOR.htm
Oğuz, C., Ercan, M.F., Cheng, T.C.E., Fung, Y.F.: Multiprocessor Task Scheduling in Multi Layer Computer Systems. European Journal of Operations Research 149, 390–403 (2003)
Scala, M.L., Bose, A., Tylavsky, J., Chai, J.S.: A Highly Parallel Method for Transient Stability Analysis. IEEE Transactions on Power Systems 5, 1439–1446 (1990)
TigerSharc DSP Hardware Specifications. Analog Devices (2002)
Weems, C.C., Riseman, E.M., Hanson, A.R.: Image Understanding Architecture: Exploiting Potential Parallelism in Machine Vision. IEEE Computer 25, 65–68 (1992)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ercan, M.F. (2005). Scheduling Pipelined Multiprocessor Tasks: An Experimental Study with Vision Architecture. In: Gervasi, O., et al. Computational Science and Its Applications – ICCSA 2005. ICCSA 2005. Lecture Notes in Computer Science, vol 3482. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11424857_47
Download citation
DOI: https://doi.org/10.1007/11424857_47
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-25862-9
Online ISBN: 978-3-540-32045-6
eBook Packages: Computer ScienceComputer Science (R0)