M. D. Beynon, T. Kurc, U. Catalyurek, C. Chang, A. Sussman, and J.Saltz. Distributed processing of very large datasets with datacutter. Parallel Computing, 27(11):1457--1478, 2001.  Home/Search   Document Not in Database   Summary   Related Articles   Check

No context found.

M. D. Beynon, T. Kurc, U. Catalyurek, C. Chang, A. Sussman, and J. Saltz. Distributed processing of very large datasets with DataCutter. Parallel Computing, 27(11):1457-- 1478, Oct. 2001.

No context found.

M. D. Beynon, T. Kurc, U. Catalyurek, C. Chang, A. Sussman, and J. Saltz. Distributed processing of very large datasets with DataCutter. Parallel Computing, 27(11):1457-- 1478, October 2001.

....the remote node may be more than the cost of recomputing it. Good system support is needed to balance the workload among processors and minimize the communication overheads due to cached pairwise alignments. We plan to look at the implementation of system support using a componentbased framework [4]. In this framework, data retrieval and data processing operations are implemented as a set of interacting components. Communication, computation, and I O overheads can be minimized by placing components efficiently across the system and by efficiently scheduling data flow between components. ....

M. D. Beynon, T. Kurc, U. Catalyurek, C. Chang, A. Sussman, and J. Saltz. Distributed processing of very large datasets with DataCutter. Parallel Computing, 27(11):1457-- 1478, Oct. 2001.

....the portion containing useful data, and the maximum size of the buffer. In the current prototype implementation we use TCP for stream communication, but any point to point communication library could be added. DataCutter provides several degrees of flexibility to improve application performance [7], 8] 9] The choice of placement represents an important degree of freedom in affecting application performance by placing filters with affinity to data sources near the sources, minimizing communication volume on slow links, and placing filters to deal with heterogeneity. Parallelism in ....

M. D. Beynon, T. Kurc, U. Catalyurek, C. Chang, A. Sussman, and J. Saltz. Distributed processing of very large datasets with DataCutter. Parallel Computing, 27(11):1457--1478, Oct. 2001.

....issues for data analysis applications. This paper differs from our previous work in that we look at the effect on data reuse of functional decomposition. There are a number of research projects that focus on component based models for developing applications in a distributed environment [1, 3, 13, 15, 24, 31, 32, 33, 38]. In these models, the application processing structure is decomposed into a set of interacting computation components. The earlier work on component based frameworks has focused on improving the performance of a single or a set of independent queries by effectively decomposing the application ....

M. D. Beynon, T. Kurc, U. Catalyurek, C. Chang, A. Sussman, and J. Saltz. Distributed processing of very large datasets with DataCutter. Parallel Computing, 27(11):1457--1478, October 2001.

....onto computational resources represents an important degree of flexibility in optimizing application performance. Network and computation overheads can be decreased by efficiently placing components to deal with computational heterogeneity in both the application and the available resources [7, 8]. Parallelism is another method for increasing performance, by executing multiple copies of a single component on a single host machine or across a set of hosts [10] In this paper we define the scheduling problem for effectively placing components in a pipelined data processing chain onto Grid ....

....111 111 111 111 000 000 000 111 111 111 w E D A B C G (a) b) Figure 1: a) A sample filter group with 7 filters. b) The filter group with three transparent copies of filter F. 2 Programming Model and Runtime Environment The programming model, called filter stream programming [8], is a component based model. Each component performs a portion of the application specific processing, and interactions between the components are realized by flow of data and control information. The interface for a component, referred to as a filter, consists of three functions: 1) an ....

[Article contains additional citation context not shown here]

M. D. Beynon, T. Kurc, U. Catalyurek, C. Chang, A. Sussman, and J. Saltz. Distributed processing of very large datasets with DataCutter. Parallel Computing, 27(11):1457--1478, Oct. 2001.

No context found.

M. D. Beynon, T. Kurc, U. Catalyurek, C. Chang, A. Sussman, and J.Saltz. Distributed processing of very large datasets with datacutter. Parallel Computing, 27(11):1457--1478, 2001.

No context found.

M. D. Beynon, T. Kurc, U. Catalyurek, C. Chang, A. Sussman, J.Saltz, Distributed processing of very large datasets with datacutter, Parallel Computing 27 (11) (2001) 1457--1478.

No context found.

M. D. Beynon et al. Distributed processing of very large datasets with DataCutter. Parallel Computing, 27(11):1457-- 1478, Oct. 2001.

No context found.

Beynon, M., Kurc, T., Catalyurek, U., Chang, C., Sussman, A., and Saltz, J., "Distributed Processing of Very Large Datasets with DataCutter," Parallel Computing, vol. 27, no. 11, pp. 1457-2478, 2001.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC