Abstract
The main objective of this paper is to describe a realistic framework to understand parallel performance of high-dimensional image processing algorithms in the context of heterogeneous networks of workstations (NOWs). As a case study, this paper explores techniques for mapping hyperspectral image analysis techniques onto fully heterogeneous NOWs. Hyperspectral imaging is a new technique in remote sensing that has gained tremendous popularity in many research areas, including satellite imaging and aerial reconnaissance. The automation of techniques able to transform massive amounts of hyperspectral data into scientific understanding in valid response times is critical for space-based Earth science and planetary exploration. Using an evaluation strategy which is based on comparing the efficiency achieved by an heterogeneous algorithm on a fully heterogeneous NOW with that evidenced by its homogeneous version on a homogeneous NOW with the same aggregate performance as the heterogeneous one, we develop a detailed analysis of parallel algorithms that integrate the spatial and spectral information in the image data through mathematical morphology concepts. For comparative purposes, performance data for the tested algorithms on Thunderhead (a large-scale Beowulf cluster at NASA’s Goddard Space Flight Center) are also provided. Our detailed investigation of the parallel properties of the proposed morphological algorithms provides several intriguing findings that may help image analysts in selection of parallel techniques and strategies for specific applications.
Similar content being viewed by others
References
Lastovetsky A (2003) Parallel computing on heterogeneous networks. Wiley-Interscience, Hoboken
Casanova H, Thomason M, Dongarra J (1999) Stochastic performance prediction for iterative algorithms in distributed environments. J Parallel Distrib Comput 58:68–91
Braun TD, Siegel HJ, Beck N, Bölöni L, Maheswaran M, Reuther AI, Robertson JP, Theys MD, Yao B, Hensgen DA, Freund RF (2001) A comparison of eleven static heuristics for mapping a class of independent tasks onto heterogeneous distributed computing systems. J Parallel Distrib Comput 61:810–837
Beaumont O, Boudet V, Rastello F, Robert Y (2001) Matrix multiplication on heterogeneous platforms. IEEE Trans Parallel Distrib Syst 12:1033–1051
Lin C (2004) Heuristic contention-free broadcast in heterogeneous networks of workstations with multiple send and receive speeds. J Supercomput 30:37–64
Lastovetsky A, Reddy R (2004) On performance analysis of heterogeneous parallel algorithms. Parallel Comput 30:1195–1216
Hawick KA, Coddington PD, James HA (2003) Distributed frameworks and parallel algorithms for processing large-scale geographic data. Parallel Comput 29:1297–1333
Aloisio G, Cafaro M (2003) A dynamic earth observation system. Parallel Comput 29:1357–1362
Veeravalli B, Ranganath S (2003) Theoretical and experimental study on large size image processing applications using divisible load paradigm on distributed bus networks. Image Vis Comput 20:917–935
Chang C-I (2003) Hyperspectral imaging: techniques for spectral detection and classification. Kluwer Academic, New York
Green RO et al (1998) Imaging spectroscopy and the airborne visible/infrared imaging spectrometer AVIRIS. Remote Sens Environ 65:227–248
Dorband J, Palencia J, Ranawake U (2003) Commodity computing clusters at Goddard Space Flight Center. J Space Commun 1:1–12
Available online: http://satjournal.tcom.ohiou.edu/pdf/Dorband.pdf
Brightwell R, Fisk LA, Greenberg DS, Hudson T, Levenhagen M, Maccabe AB, Riesen R (2000) Massively parallel computing using commodity components. Parallel Comput 26:243–266
Culler DE, Singh JP (1999) Parallel computer architecture: a hardware/software approach. Morgan Kaufmann, San Francisco
Seinstra FJ, Koelma D, Geusebroek JM (2002) A software architecture for user transparent parallel image processing. Parallel Comput 28:967–993
Darbha S, Agrawal DP (1998) Optimal scheduling algorithm for distributed memory systems. IEEE Trans Parallel Distrib Syst 9:87–95
Soille P (2003) Morphological image analysis: principles and applications, 2nd edn. Springer, Berlin
Plaza A, Martínez P, Pérez RM, Plaza J (2002) Spatial/spectral endmember extraction by multidimensional morphological operations. IEEE Trans Geosci Remote Sens 40:2025–2041
Plaza A, Martínez P, Pérez RM, Plaza J (2004) A new approach to mixed pixel classification of hyperspectral imagery based on extended morphological profiles. Pattern Recognit 37:1097–1116
Plaza A, Valencia D, Plaza J, Chang C-I (2006) Parallel implementation of endmember extraction algorithms from hyperspectral data. IEEE Geosci Remote Sens Lett 3:334–338
Prieto M, Llorente IM, Tirado F (2000) Data locality exploitation in the decomposition of regular domain problems. IEEE Trans Parallel Distrib Syst 11:1141–1149
Plaza A, Valencia D, Plaza J, Martínez P (2006) Commodity cluster-based parallel processing of hyperspectral imagery. J Parallel Distrib Comput 66:345–358
Garey MR, Johnson DS (1991) Computers and intractability: a guide to the theory of NP-completedness. Freeman, New York
Banino C, Beaumont O, Carter L, Ferrante J, Legrand A, Robert Y (2004) Scheduling strategies for master-slave tasking on heterogeneous processor platforms. IEEE Trans Parallel Distrib Syst 15:319–330
Bazterra VE, Cuma M, Ferraro MB, Facelli JC (2005) A general framework to understand parallel performance in heterogeneous clusters: analysis of a new adaptive parallel genetic algorithm. J Parallel Distrib Comput 65:48–57
Seinstra FJ, Koelma D (2002) P-3PC: A point-to-point communication model for automatic and optimal decomposition of regular domain problems. IEEE Trans Parallel Distrib Syst 13:758–768
Renard H, Robert Y, Vivien F (2003) Static load-balancing techniques for iterative computations on heterogeneous clusters. Technical Report RR-2003-12. Laboratoire de l’Informatique du Parall(c)lisme (LIP), Ecole Normale Sup(c)rieure de Lyon, France. Available online: http://www.ens-lyon.fr/LIP/Pub/Rapports/RR/RR2003/RR2003-12.ps.gz
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Plaza, A., Plaza, J. & Valencia, D. Impact of platform heterogeneity on the design of parallel algorithms for morphological processing of high-dimensional image data. J Supercomput 40, 81–107 (2007). https://doi.org/10.1007/s11227-006-0015-2
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-006-0015-2