E. Franke, M. Magee, Reducing data distribution bottlenecks by employing data visualization filters, in: Proceedings of the Eighth IEEE International Symposium on High Performance Distributed Computing, IEEE Computer Society Press, Redondo Beach, CA, 1999, pp. 255--262.  Home/Search   Document Not in Database   Summary   Related Articles   Check

.... For example, seismic data, used to extract images of the subsurface, requires a variety of processing steps to filter and transform data before computation [2] Data intensive applications also exist in climate modeling [3,4] physics and astronomy [5] biology and chemistry [6,7] visualization [8 10], and many others. 0167 739X 02 see front matter 2002 Elsevier Science B.V. All rights reserved. PII: S0167 739X(01)00076 0 In this paper, we present the armada framework for building I O access paths for data intensive grid applications. Armada s goal is to allow grid applications to ....

.... across disks is dependent on the value of the data, moving that function to the data server can halve network traffic [22] Processors near the data servers can filter data in an application specific way, passing only the necessary data on to the clients, saving network bandwidth and client memory [10,22 24]. Processors near the data servers can exchange blocks without passing the data through clients, e.g. to rearrange blocks between disks during a copy or permutation operation. Format conversion, compression, and decompression are also possible. In short, there are many ways to optimize memory and ....

E. Franke, M. Magee, Reducing data distribution bottlenecks by employing data visualization filters, in: Proceedings of the Eighth IEEE International Symposium on High Performance Distributed Computing, IEEE Computer Society Press, Redondo Beach, CA, 1999, pp. 255--262.

....I O Nodes Network Galley Armada Core System Core System Application Application Application Figure 1. Our proposed evolution of parallel file system structure allows applicationcontrol over the functionality on the compute nodes, the I O nodes, and intermediate network nodes. ory [3]. I O nodes can rearrange file blocks between disks without passing data through the client nodes. In short, there are many ways to optimize memory and disk activity on the data servers, and reduce disk and network traffic, by moving what is essentially application code closer to the data. 2 ....

E. Franke and M. Magee. Reducing data distribution bottlenecks by employing data visualization filters. In Proceedings of the Eigth IEEE International Symposium on High Performance Distributed Computing, pages 255--262, Redondo Beach, CA, Aug. 1999. IEEE Computer Society Press.

....allowing a user to selectively extract data from HDF files. An extractor can be thought of as supporting the database notion of views and allows computation on a view . Our work complements extractor capabilities; in fact we are exploring joint efforts. Franke presents a model of transformers [14] where a consumer explicitly controls the data generator and does a remote shell command to start up the generator. The transformer handles data events uniformly; that is, it performs the same transformation to every data event. The work is directed at satisfying the needs of a single ....

Ernest Franke and Michael Magee. Reducing data distribution bottlenecks by employing data visualization filters. In Proc. of High Performance Distributed Computing (HPDC8), 1999.

....our work, which is optimized to return full results of a query in a highly efficient manner. HDF5 allows a user to selectively extract data from HDF files. Selective extraction can be thought of as a database views ; HDF5 allows computation on the view . Our work complements HDF5. Franke s [7] model of data flow gives the client explicit control over the data generator and the intermediate transformation is applied to every data event. The approach is directed at a single visualization client and single event type. 7 7 Conclusions and Future Work In this paper we have introduced the ....

Ernest Franke and Michael Magee. Reducing data distribution bottlenecks by employing data visualization filters. In Proc. of High Performance Distributed Computing (HPDC8), 1999.

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