Ygdrasil: aggregator network toolkit for large scale systems and the grid

Authors:
Susanne M. Balle;John Bishop;David LaFrance-Linden;Howard Rifkin
Affiliations:
Hewlett-Packard, Nashua, NH;Hewlett-Packard, Nashua, NH;Hewlett-Packard, Nashua, NH;Hewlett-Packard, Nashua, NH
Venue:
PARA'04 Proceedings of the 7th international conference on Applied Parallel Computing: state of the Art in Scientific Computing
Year:
2004

Citing 4
Cited 0

Modeling and Evaluating Design Alternatives for an On-Line Instrumentation System: A Case Study

IEEE Transactions on Software Engineering
The Globus Project: A Status Report

HCW '98 Proceedings of the Seventh Heterogeneous Computing Workshop
Extending a traditional debugger to debug massively parallel applications

Journal of Parallel and Distributed Computing
MRNet: A Software-Based Multicast/Reduction Network for Scalable Tools

Proceedings of the 2003 ACM/IEEE conference on Supercomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Many tools such as user programming tools, performance tools and system administration tools, which are targeted to be used on a very large number of processors (1,000+) have the same common problems. They need to deal with the large amount of data created by the large number of processes as well as be scalable. The data need to be condensed and reorganized into a useful set of information before it is presented to the user. We present an aggregating network toolkit, which due to its modularity can be tailored to almost any purpose involving reduction of data, from a large number of individual back-ends (connected to a tool or a user application), to a user portal. The latter allows the user to visualize as well as re-arrange the data to fit his need (integration with statistical packages, visualization, etc.). The user can write his own plug-ins and thereby tell the network what is getting aggregated, how to aggregate the data (identical data, discard data, etc.), as well as how to display the data in the user portal.