PVM and other distributed computing systems have enabled the use of networks of workstations for parallel computation, but their approach of treating a network as a collection of point-to-point connections does not promote efficient communication--- particularly collective communication. ECO is a package which solves this problem with programs which analyze the network and establish efficient communication patterns which are used by a library of collective operations. The analysis is done off-line, so that after paying the one-time cost of analyzing the network, the execution of application programs is not delayed. This paper gives performance results from using ECO to implement the collective communication in CHARMM, a widely used macromolecular dynamics package. ECO facilitates the development of data parallel applications by providing a simple interface to routines which use the available heterogeneous networks efficiently. This approach gives a naive programmer the abili...

The aim of this paper is to present an original model of dynamic load balancing inside groups using queueing theory. Communication speed is greater inside a group than from one group to another. An analytical formula of the average queue length is obtained if we take two groups each with two processors. Beyond two groups, we can compute the numeric values as a function of the processes' arrival rates, execution times and communication speeds. The values of these parameters can be used to define the conditions requiring migration. Keywords : Dynamic load balancing, modeling, queueing theory models, groups decomposition, performance evaluation. 1 Introduction 1.1 Load balancing The arrival of workstations networks and multicomputers has resulted in a considerable increase in available computing power, however it also results in wasted performance, due to unbalanced CPU loading. Resource allocation is an answer to this major problem, which must be solved if systems are to become even ...

USAF, under agreement number F30602-96-1-0287. The U.S. Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of the Advanced Research

Type the abstract (100 to 150 words) using Italic font with point size 10. The abstract is an essential part of the paper. Use short, direct, and complete sentences. It should be as brief as possible and concise. It should be complete, selfexplanatory, and not require reference to the paper itself. The abstract should be informative giving the scope and emphasize the main conclusions, results, or signi cance of the work described. Do not use the rst person; do not include mathematical expressions; do not refer to the references.

In pervasive computing, software applications vanish into the user’s environment spreading their functionality to computers integrated into everyday devices. With the current state-of-the-art software tools, these characteristics put a great burden on programmers who have to enable the applications to dynamically partition across multiple devices, and to adapt such partitioning to frequent context changes such as network failures. This paper explores service partitioning techniques for development of pervasive computing applications. We propose a resilient actor model to structurally add service partitioning property to the pervasive applications. The service partitioning realised using resilient actor model happens at runtime, is user guided and the resulting partitioned application is retractable, and resilient to network failures.

Load balancing allows to increase system throughput and to reduce application response time. However, when the computing system increases in scale, load balancing becomes very complex to manage and is time consuming. Moreover, actual load balancing mechanisms are not able to manage heterogeneity both in system architectures and application behaviors. To deal with such systems we propose to split load balancing between environment oriented and application oriented managers. Negotiation between managers allows to manage heterogeneous and large systems, while internal management allows to use the most suitable policy. Then, hybrid applications, using simultaneously different programming models can be executed efficiently.