Neste trabalho foi avaliada a utilização da grid computing em aspectos importantes para simulações em Física Computacional. Em particular, para aplicações de diagonalização de matrizes de grande porte. O projeto de código aberto Globus Toolkit foi utilizado para comparar o desempenho da biblioteca paralela de álgebra linear ScaLAPACK em duas versões baseadas na biblioteca de passagem de mensagens, a versão tradicional MPICH e a versão desenvolvida para um ambiente de grid computing MPICH-G2. Várias simulações com diagonalização de matrizes complexas de diversos tamanhos foram realizadas. Para um sistema com uma matriz de tamanho 8000 x 8000 distribuída em 8 processos, nos nós de 64 bits foi alcançado um speedup de 7,71 com o MPICH-G2. Este speedup é muito próximo do ideal que, neste caso, seria igual a 8. Foi constatado também que a arquitetura de 64 bits tem melhor desempenho que a de 32 bits nas simulações executadas para este tipo de aplicação / This work evaluates the use of grid computing in essential issues related to Computational Physics simulations. In particular, for applications with large scale matrix diagonalization. The Globus Toolkit open source project was used to compare the performance of the linear algebra parallel library ScaLAPACK in two different versions based on the message passing library, the traditional version MPICH and its version developed for a grid computing environment MPICH-G2. Several simulations within large scale diagonalization of complex matrix were performed. A 7.71 speedup was reached with the MPICH-G2 for a 8000 x 8000 size matrix distributed in 8 processes on 64 bits nodes. This was very close to the ideal speedup, that would be in this case, 8. It was also evidenced that the 64 bits architecture has better performance than the 32 bits on the performed simulations for this kind of application.

Neste trabalho foi avaliada a utilização da grid computing em aspectos importantes para simulações em Física Computacional. Em particular, para aplicações de diagonalização de matrizes de grande porte. O projeto de código aberto Globus Toolkit foi utilizado para comparar o desempenho da biblioteca paralela de álgebra linear ScaLAPACK em duas versões baseadas na biblioteca de passagem de mensagens, a versão tradicional MPICH e a versão desenvolvida para um ambiente de grid computing MPICH-G2. Várias simulações com diagonalização de matrizes complexas de diversos tamanhos foram realizadas. Para um sistema com uma matriz de tamanho 8000 x 8000 distribuída em 8 processos, nos nós de 64 bits foi alcançado um speedup de 7,71 com o MPICH-G2. Este speedup é muito próximo do ideal que, neste caso, seria igual a 8. Foi constatado também que a arquitetura de 64 bits tem melhor desempenho que a de 32 bits nas simulações executadas para este tipo de aplicação / This work evaluates the use of grid computing in essential issues related to Computational Physics simulations. In particular, for applications with large scale matrix diagonalization. The Globus Toolkit open source project was used to compare the performance of the linear algebra parallel library ScaLAPACK in two different versions based on the message passing library, the traditional version MPICH and its version developed for a grid computing environment MPICH-G2. Several simulations within large scale diagonalization of complex matrix were performed. A 7.71 speedup was reached with the MPICH-G2 for a 8000 x 8000 size matrix distributed in 8 processes on 64 bits nodes. This was very close to the ideal speedup, that would be in this case, 8. It was also evidenced that the 64 bits architecture has better performance than the 32 bits on the performed simulations for this kind of application.

The paper gives an overview on installation and usage of the Grid-enabled MPI implementation MPICH-G2. Performance results of MPICH-G2 in several environments are presented. / Die Arbeit gibt einen Überblick über die Installation und Nutzung der Grid-fähigen MPI-Implementation MPICH-G2. Performance-Ergebnisse von MPICH-G2 in verschiedenen Umgebungen werden gezeigt.

Grid computing is a field of research that combines many computers from distant locations to form one large computing resource. In order to be able to make use of the full potential of such a system there is a need to effectively manage resources on the Grid. There are numerous scheduling systems to perform this management for clusters of computers and a few scheduling systems for the Grid. These systems try for optimality (or close to optimality) with the goals of obtaining good throughput and minimizing job completion time. In this research, we examine issues that we believe have not been tackled in schedulers for the Grid. These issues revolve around the problem of coordinating resources belonging to separate administrative domains and scheduling in this context. In order for grid computing's vision of virtual organizations to be realized to its fullest extent, there is a need to implement and test schedulers that find resources and schedule tasks on them in a manner that is transparent to the user. These resources might be on a different administrative domain altogether and obtaining either resource or user account information on those resources might be difficult. Also, each organization might require their own policies and mechanisms to be enforced. Hence having a centralized scheduler is not feasible due to the pragmatics of the Grid. There are two basic aims to this thesis. The first aim is to design and implement a framework that takes administrative concerns into consideration during scheduling. The aim of the framework is to provide a lightweight, extensible, secure and scalable architecture under which multiple scheduling algorithms can be implemented. Second, we evaluate two prototypical of scheduling algorithms in the context of this framework. Scheduling algorithms are diverse and the applications are varied. Thus no single algorithm can obtain a good mapping for every application. We believe that different scheduling algorithms will be necessary to schedule different types of applications. In order to facilitate development of such algorithms, a framework in which it is easy to integrate other scheduling algorithms is necessary. The framework developed in this project is designed for such extensibility. / Master of Science

The paper gives an overview on installation and usage of the Grid-enabled MPI implementation MPICH-G2. Performance results of MPICH-G2 in several environments are presented. / Die Arbeit gibt einen Überblick über die Installation und Nutzung der Grid-fähigen MPI-Implementation MPICH-G2. Performance-Ergebnisse von MPICH-G2 in verschiedenen Umgebungen werden gezeigt.