基于分布式对象的并行计算框架

在为工作站机群构造并行软件的过程中,计算特征和组成特征非常重要.但是,由于缺乏有效的支撑环境,当今的分布式并行计算软件系统效率低下,这在计算特征方面尤为明显.提出一个基于分布式对象的并行计算框架,目的在于保证高效的并行计算开发,提供封装和复用并行程序的机制,并保证系统的动态平衡和容错性.框架是4层模型,包括对象组层和移动对象层.实验结果证明了方案的有效性.

A Distributed Object Based Framework for Parallel Computations

The computational and compositional features are very important while constructing parallel software for the workstation clusters.However,lack of suitable supporting environment for parallel software development makes most existing distributed parallel software systems very weak in these two aspects,especially in the compositional feature.In this paper,a distributed object based framework for parallel computation is proposed.The goal of the framework is to achieve high efficiency for parallel computing,to construct a mechanism to encapsulate and reuse parallel programs,and to guarantee load balancing and fault tolerance.The framework is a four-layer model that includes an object-group layer and a mobile object layer.The experimental results verify the efficiency of the scheme.