@conference {17838, title = {Efficient Manipulation of Large Datasets on Heterogeneous Storage Systems}, booktitle = {Parallel and Distributed Processing Symposium, International}, volume = {2}, year = {2002}, month = {2002///}, pages = {0084 - 0084}, publisher = {IEEE Computer Society}, organization = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, abstract = {In this paper we are concerned with the efficient use of a collection of disk-based storage systems and computing platforms in a heterogeneous setting for retrieving and processing large scientific datasets. We demonstrate, in the context of a data-intensive visualization application, how heterogeneity affects performance and show a set of optimization techniques that can be used to improve performance in a component-based framework. In particular, we examine the application of parallelism via transparent copies of application components in the pipelined processing of data.}, keywords = {component-based frameworks, data-intensive computing, load balancing}, isbn = {0-7695-1573-8}, doi = {http://doi.ieeecomputersociety.org/10.1109/IPDPS.2002.1015655}, author = {Beynon,Michael D. and Sussman, Alan and Kurc,Tahsin and Catalyurek,Umit and Saltz,Joel} }