Abstract
In this work we investigate how Distributed Shared Memory (DSM) architectures affect performance of or-parallel logic programming systems and how this performance approaches that of conventional C systems. Our work concentrates on basic performance, scalability, and programmability. We use execution-driven simulation of a hardware DSM (DASH) to investigate the access patterns and caching behaviour exhibited by parallel C programs and by Aurora, a parallel logic programming system capable of exploiting implicit parallelism in Prolog programs. Aurora was originally written to run on bus-based shared-memory platforms. © Springer-Verlag Berlin Heidelberg 1999.

Abstract
One of the challenges in grid computing research is to provide means to automatically submit, manage, and monitor applications which spread a large number of tasks. The usual way of managing these tasks is to represent each one as an explicit node in a graph, and this is the approach taken by many grid systems up to date. This approach can quickly saturate the machine where the application is launched, as we increase the number of tasks. In this work we present and validate a novel architectural model, GRAND (Grid Robust ApplicatioN Deployment), whose main objective is to deal with the problem of memory and load saturation of the submission machine. GRAND is implemented at a middleware level, aiming at providing a distributed task submission through a hierarchical organization. This paper provides an overview of the GRAND submission model as well our implementation. Initial results show that our approach can be much more effective than other approaches in the literature. Copyright 2005 ACM.

Abstract
Speedup in distributed executions of Constraint Logic Programming (CLP) applications are directed related to a good constraint partitioning algorithm. In this work we study different mechanisms to distribute constraints to processors based on straightforward mechanisms such as Round-Robin and Block distribution, and on a more sophisticated automatic distribution method, Grouping-Sink, that takes into account the connectivity of the constraint network graph. This aims at reducing the communication overhead in distributed environments. Our results show that Grouping-Sink is, in general, the best alternative for partitioning constraints as it produces results as good or better than Round-Robin or Blocks with low communication rate.

Abstract

Abstract
Grid environments are dynamic and heterogeneous by nature, therefore requiring adaptive scheduling strategies. Reinforcement learning is an interesting and simple adaptive approach that may work well in actual grid environments. In this work, we employ reinforcement learning to classify available resources in a grid environment, giving support to two scheduling algorithms, AG and MQD. We study the makespan optimisation and load balancing. An algorithm known as RR is used for normalising purposes. Copyright © 2009 Inderscience Enterprises Ltd.

Abstract
Several works on grid computing have been proposed in the last years. However, most of them, including available software, can not deal properly with some issues related to control of applications that spread a very large number of tasks across the grid network. This work presents a step toward solving the problem of controlling such applications. We propose and discuss an architectural model called GRAND (Grid Robust ApplicatioN Deployment) based on partitioning and hierarchical submission and control of such applications. The main contribution of our model is to be able to control the execution of a huge number of distributed tasks while preserving data locality and reducing the load of the submit machines. We propose a taxonomy to classify application models to run in grid environments and partitioning methods. We also present our application description language GRID-ADL. Copyright 2004 ACM.