Analysis of Peer-to-Peer Protocols Performance for Establishing a Decentralized Desktop Grid Middleware

Proceedings of the 28th Annual ACM Symposium on Applied Computing

et al. 2013

Self Cite

This paper proposes a Publish-Subscribe framework for the design of Desktop Grid (DG) middleware.This work focuses on a modeling and a verification of a DG protocol based on the Publish-Subscribe paradigm and introduces a prototype that we are currently developing. Our prototype implementation is based on Redis, a key-value no-SQL Web 2.0 tool with Publish-Subscribe functionality. Whereas most previous approaches required to build a number of layers before the layer of the DG middleware, we have only one layer in our system. In addition, our system is characterized to be light in terms of coding lines and used resources. It is therefore very convenient to implement DGs on resource constrained systems, e.g. tablets and smartphones.

Section: The Publish-subscribe Paradigmmentioning

confidence: 99%

A publication-subscription interaction schema for desktop grid computing

Abidi

Dubacq

Proceedings of the 28th Annual ACM Symposium on Applied Computing

et al. 2013

Self Cite

“…To summarize, the objective of this experiment was to present a use case of BonjourGrid using a real application and from the user point of view. Abbes, Cérin and Jemni have already done experiments to analyze the performance of BonjourGrid in [7,8] and [5] but the scope of this work is to demonstrate how BonjourGrid can help users to construct, dynamically and without any intervention of a system administrator, their own environments to deploy and perform out a parallel application.…”

Section: Experiments and Validation Of Bonjourgridmentioning

confidence: 99%

“…Computation time with respect to the dilatation coefficient. The partitions are λ =(5,3,2,2,1), μ = (4,3,2,2,1) and ν =(7,5,4,4,3,2).…”

mentioning

confidence: 99%

Parallelization of Littlewood-Richardson Coefficients Computation and its Integration into the BonjourGrid Meta-Desktop Grid Middleware

Abbes

Butelle

International Journal of Grid and High Performance Computing

2011

Self Cite

International audienceThe aim of this paper is to show how to parallelize a compute intensive application in mathematics (Group Theory) for an institutional Desktop Grid platform coordinated by a meta-grid middleware named BonjourGrid. The paper is twofold: first of all, it shows how to parallelize a sequential program for a multicore CPU which participates in the computation and second it demonstrates the effort for launching multiple instances of the solutions for the mathematical problem with the BonjourGrid middleware. BonjourGrid is a fully decentralized Desktop Grid middleware. The main results of the paper are: a) an efficient multi-threaded version of a sequential program to compute Littlewood- Richardson coefficients, namely the Multi-LR program and b) a proof of concept, centered around the user needs, for the BonjourGrid middleware dedicated to coordinate multiple instances of programsfor Desktop Grids and with the help of Multi-LR. In this paper, the scientific work consists in starting from a model for the solution of a compute intensive problem in mathematics, to incorporate the concrete model into a middleware and running it on commodity PCs platform managed by an innovative meta Desktop Grid middleware

“…The architectural context of the RedisDG system that we are designing is very important to understand because it underlines the specific difficulties of the allocation problem and strategies we are designing. RedisDG is based on the Publish/Subscribe paradigm which is an asynchronous mode for communicating between entities [1], [4]. This communication mode is multipoint, anonymous and implicit which increases the scalability by eliminating many sorts of explicit dependencies between participating entities.…”

Section: Introductionmentioning

confidence: 99%

Data Management for the RedisDG Scientific Workflow Engine

Abidi

Bejaoui

2016 IEEE International Conference on Computer and Information Technology (CIT)

et al. 2016

International audience—In this paper we investigate the general problem of controlling a scientific workflow service in terms of data management. We focus on the data management problem for the RedisDG scientific workflow engine. RedisDG is based on the Publish/Subscribe paradigm for the interaction between the different components of the system, hence new issues appear for scheduling. Indeed, the Publish/Subscribe paradigm utilization introduces different challenging problems, among them the design of effective solutions for managing data, on the fly, when tasks are published. Our contributions are twofold. First we add new functionalities to the RedisDG workflow engine with scheduling decisions related to the allocation of data intensive jobs to compute units and according to an efficient management of data and second we introduce a large set of experiments to validate our approaches. We analyze our results and we also sketch perspectives and insights. Experiments are conducted on the Grid'5000 testbed and the paper is a step forward to implement a 'Workflow engine as a Service' (WaaS)