View in EDS

The Use of Java in High Performance Computing: A Data Mining Example

Saved in:
Bibliographic Details
Title: The Use of Java in High Performance Computing: A Data Mining Example
Authors: David Walker, Omer Rana
Contributors: The Pennsylvania State University CiteSeerX Archives
Source: http://www.csm.ornl.gov/~walker/JAVA/./papers/hpcn99.ps.
Collection: CiteSeerX
Subject Terms: Java Grande, High Performance Java, Parallel Computing, Neural Networks, Distributed Objects
Description: The role of Java in high performance computing is discussed with particular reference to the efforts of the Java Grande Forum to develop Java into the environment of choice for large-scale, resourcehungry applications. The support provided in HPJava for the design of parallel Java programmes is outlined, and its use demonstrated with a data mining application based on a neural network. Keywords: Java Grande, High Performance Java, Parallel Computing, Neural Networks, Distributed Objects 1 Introduction High performance computing (HPC) refers to any application that is sufficiently large-scale to require more computing resources than are typically directly available on a desk-top computer. This includes, but is by no means limited to, (1) numerical computing applications in the physical sciences, engineering, and mathematics; (2) commercial applications such as data mining and financial modelling; (3) immersive virtual environments for training, simulation, and the exploration .
Document Type: text
File Description: application/postscript
Language: English
Relation: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.41.8973; http://www.csm.ornl.gov/~walker/JAVA/./papers/hpcn99.ps
Availability: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.41.8973
http://www.csm.ornl.gov/~walker/JAVA/./papers/hpcn99.ps
Rights: Metadata may be used without restrictions as long as the oai identifier remains attached to it.
Accession Number: edsbas.DB1F05B
Database: BASE
Description
Abstract:The role of Java in high performance computing is discussed with particular reference to the efforts of the Java Grande Forum to develop Java into the environment of choice for large-scale, resourcehungry applications. The support provided in HPJava for the design of parallel Java programmes is outlined, and its use demonstrated with a data mining application based on a neural network. Keywords: Java Grande, High Performance Java, Parallel Computing, Neural Networks, Distributed Objects 1 Introduction High performance computing (HPC) refers to any application that is sufficiently large-scale to require more computing resources than are typically directly available on a desk-top computer. This includes, but is by no means limited to, (1) numerical computing applications in the physical sciences, engineering, and mathematics; (2) commercial applications such as data mining and financial modelling; (3) immersive virtual environments for training, simulation, and the exploration .