实时分布式计算机系统的容错技术研究

本文提出了一种具有容错功能的实时分布式计算机系统的体系结构，同时对实时分布式计算机系统中的容错技术进行了研究，特别对实时分布式计算机系统中的节点机容错技术及实时性的实现方面做了较深入的讨论，并提出了实现方案。     

STD容错计算机系统

本文介绍了ＳＴＤ双模容错计算机系统的结构，对其中几个关键电路作了详细叙述，并在双模容错系统的基础上构成了ＳＴＤ四模容错计算机系统，最后对这两个系统的可靠性进行了评价。     

基于分布式架构的星载并行计算机容错技术

星载计算机需要容错技术来满足在外太空运行的可靠性要求。目前的星载计算机多机系统通常设计为主从结构,集中于一个主节点上进行容错策略控制,这种结构存在着一点失效即瘫痪的隐患。为此,本文提出一种分布式架构下的星载并行容错计算机系统,将集中控制的容错部件分布化于各个节点之上,提高了系统的容错可靠性,在此架构上提出了计算节点、容错部件和I/O等容错策略,并给出了相应的模型及模拟测试结果,为进行类似项目的开发研究提供了有价值的指导和参考。     

计算机控制系统的容错技术

计算机控制系统的可靠性设计是实现柔性智能控制所面临的一个重要课题，而容错技术是系统可靠性设计的关键技术。本文在分析计算机系统可靠性设计的基础上，综述了容错技术的发展、研究的主要内容及实现的主要方法，对常用的几种容错结构进行了比较和评价。指出了对计算机系统进行容错设计必须解决的主要问题。     

两种容错方案的比较和可靠性分析

为了提高系统的性能和可靠性,文中描述了计算机控制系统的两种容错方案:系统级三模冗余(TMR)方案和部件级三模冗余(TTMR)方案,给出了两种容错系统的马尔可夫模型,并利用MATLAB工具对描述可靠性的重要参数指标———可靠度进行了比较和分析。得出部件级容错计算机系统的可靠度受故障覆盖率C的影响比系统级容错计算机系统的小,在C相同的情况下,部件级容错计算机系统的可靠度比系统级容错计算机系统的可靠度高,因此部件级容错计算机系统比较易于实现。     

两种容错方案的比较和可靠性分析

为了提高系统的性能和可靠性,文中描述了计算机控制系统的两种容错方案:系统级三模冗余(TMR)方案和部件级三模冗余(TTMR)方案,给出了两种容错系统的马尔可夫模型,并利用MATLAB工具对描述可靠性的重要参数指标--可靠度进行了比较和分析.得出部件级容错计算机系统的可靠度受故障覆盖率C的影响比系统级容错计算机系统的小,在C相同的情况下,部件级容错计算机系统的可靠度比系统级容错计算机系统的可靠度高,因此部件级容错计算机系统比较易于实现.     

一个采用表决技术的容错微型计算机系统

本文描述了实现低成本、高可靠性、容错的微型计算机系统的方法。使用了设备冗余、时间冗余的技术。详细讨论了表决器的结构及实现容错的策略。     

CROMEMCO XTM容错计算机系统

美国著名的计算机生产厂商Cromemco公司是基于UNIX的计算机系统的主要供应商之一.其Cromemco XTM机系第三代UNIX容错计算机系统,它把传统的容错技术与高性能的对称型多处理机结构结合在一起.     

容错星载计算机系统结构设计

容错技术是提高计算机系统可靠性的重要手段，本文介绍了某立体测绘小卫星星载计算机系统的容错设计。该系统具有功能强，灵活性和可靠性高等特点，满足了小卫星性能高，重量轻、体积小，功耗低的要求。     

软件冗余MIMD系统及其软件自修理

容错MIMD系统是目前国际国内重点研究的新型容错计算机体系结构之一，其典型结构（多处理机／多计算机系统）在复杂及高速实时领域已经得到了应用。本文着重讨论了分布式硬件冗余SISD系统和硬件冗余MIMD系统的硬件结构、软件环境及其软件自修理方面的问题。     

现代操作系统体系结构

给出了关于现代操作系统的４种观点，并用这观点对现代操作系统的界面，功能，结构进行了描述，同时讨论了硬件环境对操作系统体系结构的影响。关于现代操作系统的４种观点是了解现代操作系统体系结构的基础。     

Enabling simulation interoperability

Over the past years a series of architectures have addressed the need to link multiple simulations. These efforts have been driven primarily by the desire to reuse existing "best of breed" simulations in new combinations to avoid developing any single, monolithic architecture with the impossible goal of meeting all simulation needs. The US Department of Defense began developing the high level architecture (HLA) for distributed computer simulation systems. The high level architecture addresses the need to link multiple computer simulation systems. HLA separates the data model from the architecture's functions for exchanging information.     

计算机系统在自动化仪器仪表中的应用

随着各领域技术的迅速发展和不断进步,计算机技术逐渐渗透到自动化控制技术中,其中,嵌入式计算机系统已经在仪器仪表领域获得了越来越多的应用。如今,自动化仪器仪表已具备＂工业IT＂的特征。本文首先介绍了我国仪器仪表控制系统的发展历程,阐述了嵌入式计算机系统的定义、特征、基本构架以及嵌入式计算机系统中的软件技术,对嵌入式计算机系统在仪器仪表中的应用进行了研究与分析,并展望了高级嵌入式系统对未来新型仪器仪表技术的支持及其前景。     

Differential Mathematical Models to Investigate the Computer Network Architecture of an All-Mode System of Control over a Distance of Railways

The evolutionary development of railway power-supply systems and computer networks and technologies that control these systems are analyzed. It is shown that the optimization of electricity consumption is based on the intellectualization of electricity supply procedures. A graph is constructed whose topology adequately represents the typical architecture of a computer network of control at the layer of a distance of power supply of railways with a view to investigating the mutual integration of a power supply infrastructure and a computer network architecture of all-mode control. This article proposes a differential mathematical model for investigating the computer network architecture of an all-mode system of control over a distance of power supply and methods (in analytical form) for determining values of probabilities of states of system nodes, their capacities, and the number of failures of requests as the basis for the intellectualization of power supply procedures.     

Vega: A Computer Systems Approach to Grid Computing

In this paper, we contrast four approaches for Grid computing, and discuss a computer systems approach in detail. This approach views a Grid as a distributed computer system, and its main concerns are systems abstractions and constructs, such as the Grid equivalents of computer architecture, address space, process, device, file system, user/developers interface. Following this methodology, we identified several essential issues, developed a Vega Grid systems architecture, and proposed several systems techniques such as Grid routers, Grid address spaces, Grid process (grip), Grid community (agora), and a Grid Service Markup Language (GSML) software suite. We evaluated the computer systems approach and the associated techniques by discussing an OSGA-compliant Grid system software implementation and a travel agency example.     

基于CPCI热切换技术实现高可用适度并行系统

为了满足应用对性能、可靠性和成本的严格要求,适度并行计算机系统必须具有很高的系统可用度.CPCI总线热切换规范作为一个工业标准,为实现高可用的适度并行计算机系统提供了良好的基础.提出了一种基于热切换技术实现高可用适度并行计算机系统的体系结构.运用该结构设计的适度并行计算机系统能够实现高效的容错并行计算,系统的可用性服务机制具有标准结构,较好地满足了应用的要求.     

A new system architecture for crowd simulation

Crowd simulation requires both rendering visually plausible images and managing the behavior of autonomous agents. Therefore, these applications need an efficient design that allows them to simultaneously handle these two requirements. Although several proposals have focused on the software architectures for these systems, no proposals have focused on the computer systems supporting them.In this paper, we analyze the computer architectures used in the literature to support distributed virtual environments. Also, we propose a distributed computer architecture which is efficient enough to support simulations of thousand of autonomous agents. This proposal consists of a cluster of interconnected computers in order to improve flexibility and robustness, as well as a hierarchical software architecture that efficiently provides consistency. Performance evaluation results show that the trade-off between flexibility and consistency allows to efficiently manage thousands of autonomous agents. Therefore, this network-based system architecture can provide the required scalability for large-scale crowd simulations.     

A Token Based Graphics System

This paper presents the design of a novel process oriented graphics systems architecture suitable for emulating many general purpose computer graphics systems. The systems architecture has been designed loosely on the actor model of computation, and consists of a number of functionally distinct modules or processes, which communicate solely by token (message) passing. The design addresses a specific requirement for configurability and adaptability of and between modules identified within interactive computer graphics systems.     

大规模并行系统中的Firmware结构及其实现研究

Firmware是IA64体系结构的一个重要组成部分。在系统启动时，首先运行Firmware，它对系统的各部件进行初始化、配置和测试，同时还对操作系统的引导进行管理。在大规模并行计算机系统中，节点问的Firmware结构是设计系统时要解决的重要问题。本文提出一种基于IA64的大规模并行系统的Firmware的结构，并对其作了简要分析。     

Critic Systems – Towards Human–Computer Collaborative Problem Solving

Human–computer collaboration is extremely necessary for solving ill-structured problems and critic systems can effectively facilitate human–computer collaborative problem solving. This paper conducts a systematic study on critic systems. First, the concepts of critic systems are presented. Then, a literature review is presented on critic systems. Afterwards, a generic architecture is put forward for critic systems, with its important aspects being analyzed. Finally, two case studies are given to illustrate critic systems.