A Partial Evaluator for A Parallel Lambda Language

This paper describes theoretical and practical aspects of a partial evaluator that treats a parallel lambda language.The parallel language presented is a combination of lambda calculus and message passing communication mechanism.This parallel language can be used to write a programming language‘s denotational semantics which extracts the paallelism in the program.From this denotational definition of the programming language,the partial evaluator can generate parallel compiler of the language by self-application. The key technique of partial evaluation is binding time analysis that determines in advance which parts of the source program can be evaluated during partial evaluation,and which parts cannot,A binding time analysis is described based upon type inference.A new type chcode in introduced into the type system,which denotes the type of those expressions containing residual channel operations.A well-formedness criterion is given which ensures that partial evaluation not only doesn‘t commit type errors but also doesn‘t change the sequence of channel operations.Before binding time analysis,channel analysis is used to analyze the communication relationship between send and receive processes.     

Study on Parallel Computing

In this paper, we present a general survey on parallel computing. The main contents include parallel computer system which is the hardware platform of parallel computing, parallel algorithm which is the theoretical base of parallel computing, parallel programming which is the software support of parallel computing. After that, we also introduce some parallel applications and enabling technologies. We argue that parallel computing research should form an integrated methodology of ＂architecture algorithm programming application＂. Only in this way, parallel computing research becomes continuous development and more realistic.     

构造类型论与计算机程序设计

Recent years,in the area of computer programming language theories,automated deduction,and more generalized area of logic and computing,a lot of systems based on constructive type theory are used widely to design type system for computer programming languages,to do formal system develpment and verification,and to be used as foundation of mathematics and computing.constructive type theory provides computer scientists with a framework to combine logic and computer program design in an elegant and flexible way.In this paper,the evolvement of constructive type theory is first introduced.The several foundations of type theory are then discussed,together with analysis of the relationships between them.The relation between constructive type theory and computer programming is explored in-depth.In the last,Martin Lof‘‘‘‘s intuitionistic type theory is used as an example to demonstrate how to do program development and verification in the same formal system.     

Timing-sequence testing of parallel programs

Testing of parallel programs involves two parts-testing of control flow within the processes and testing of timing-sequence.This paper focuses on the latter,particularly on the timing-sequence of message-passing paradigms.Firstly the coarse-grained SYN-sequence model is built up to describe the execution of distributed programs.All of the topics discussed in this paper are based on it .The most direct way to test a program is to run it.A fault-free parallel program should be of both correct computing results and propoer SYN-sequence.In order to analyze the validity of observed SYN-sequence,this paper presents the formal specification (Backus Normal Form) of the valid SYN-sequence.Till now there is little work about the testing coverage for distributed programs.Calculating the number of the valid SYN-sequences is the key to coverage problem,while the number of the valid SYN-sequences is terribly large and it is very hard to obtain the combination law among SYN-events.In order to resolve this problem,this paper proposes an efficient testing strategy-atomic SYN-event testing,which is to linearize the SYN-sequence (making it only consist of serial atomic SYN-events)first and then test each atomic SYN-event independently.This paper particularly provides the calculating formula about the number of the valid SYN-sequences for tree-topology atomic SYN-event(broadcast and combine),Furthermore,the number of valid SYN-sequences also,to some degree,mirrors the testability of parallel programs.Taking tree-topology atomic SYN-event as an example,this paper demonstrates the testability and communication speed of the tree-topology atomic SYN-event under different numbers of branches in order to achieve a more satisfactory tradeoff between testability and communication efficiency.     

基于LogP简化模型的矩阵求逆并行算法研究

LogP is becoming a practical parallel computation model that meets the demanding of parallel computers and parallel algorithms. So it is important to re-design parallel algorithms on the LogP model. This paper studies the parallel algorithm of computing converse matrix on the simplified LogP model, and gets the simulating results.     

A self-routing load balancing algorithm in parallel computing: comparison to the central algorithm

Load balancing is an important stage of a system using parallel computing where the aim is the balance of workload among all processors of the system. In this paper, we introduce a new load balancing algorithm with new capabilities for parallel systems, among which is the independence of a separate route-finder algorithm between the load receiver and sender nodes. In addition to simulation of the new algorithm, due to similarity in behavior to the proposed algorithm, the central algorithm is simulated. Simulation results show that, the system performance increases with the increase of the degree of neighborhood between the processors. These results also indicate the algorithm’s high compatibility with environment changes.     

Hierarchical bulk synchronous parallel model and performance optimization

Based on the framework of BSP,a Hierarchical Bulk Synchronous Parallel(HBSP)performance model is introduced in this paper to capture the performance optimization problem for various stages in parallel program development and to accurately predict the performance of a parallel program by considering factors causing variance at local computation and global communication.The related methodology has been applied to several real applications and the results show that HBSP is a suitable model for optimizing parallel programs.     

On dependability of computing systems

With the rapid development and wide applications of computing systems on which more reliance has been put,a dependable system will be much more important than ever.This paper is first aimed at giving informal but precise definitions characterizing the various attributes o dependability of computing systems an then th importance of (and the relationships among)all te the attributes are explained.Dependability is first introduced as a blobal concept which subsumes the usual atributes of reliability,availability,maintainability,safety and sevurity.The basic definitions given here are then commended and supplemented by detailed material and additional explanations in the subsequent sections. The presentation has been structured as follows so as to attract the reader‘s attention to the important attributions of dependability.Search for a few number of concise concepts enabling the dependability attributes to be expressed as clearly as possible.Use of terms which are identical or as close as possible to those commonly used nowadays.This paper is also intended to provoke people‘s interest in designing a dependable computing system.     

Performance evaluation of a parallel cascade semijoin algorithm for computing path expressions in object database systems

With the emerging of new applications,especially in Web,Such as E-Commerce,Digital Library and DNA Bank,object database systems show their stronger funcitons than other kinds of database systems due to their powerful representation ability on complex semantics and relationshiop.One distinguished feature of object database systems is path expression,and most queries on an object database ar based on path expression because it is the most natural and convenient way to access the object databse,for example,to navigate the hyper-links in a web-based database,The execution of path expression is usually extremely expensive on a very large database.Therefore,the improvement of path expression eecution efficiency is critical for the performance ofobject databases.As an importan approach realizing high-performance query processing ,the parallel processing of path expression on distributed object databases is explored in this paper.Up to now,some algorithms about how to compute path expressions and how to optimize path expression processing have been proposed for centralizedenvironments.But,few approaches have been presented for computing path expressions in parallel.In this paper,a new paralle algorithm for computing path expression named Parallel Cascade Semijoin(PCSJ)is proposed.Moreover,a new scheduling strategy called right-deep zigzag tree is designed to further improve the performance of the PCSJ algorithm.The exper-iments have been implemented in an NOW distributed and parallel environment.The results show that the PCSJ algorithm outperforms the other two parallel algorithms(the parallel version of forward pointer chasing algorithm(PFPC)and the index splitting parallel algorithm(IndexSplit) when computing path expressions with restrictive predicates and that the right-deep zigzage tree scheduling strategy has better performance than the right-deep tree scheduling strategy.     

Parallel Processing of FIRST and FOLLOW Sets in Multiprocessors Environments

This paper describes a new method of computing FIRST and FOLLOW sets on multiprocessors environments in parallel, and it also discusses the design thoughts and tactics. For a given grammar G,when the LL（R） analysis table is constructed and the grammar is judged whether it is a LL （1） grammar or not, it needs to construct FIRST and FOLLOW sets of the grammar, because of large quantities of terminals and non-terminals in the grammar and this is of theoretical and operation significance in considering the parallel processing method of computing FIRST and FOLLOW sets.     

云计算研究

云计算模式是在基础设施即服务（IaaS）、平台即服务（PaaS）、软件即服务（SaaS）、分布式计算、并行计算和网格计算等概念演进并产生的结果。云计算模式是一种全新的计算应用模式,将会成为人们获取服务的主导方式。本文首先介绍云计算在业界中的概念,接着分析云计算和相关计算,最后关于云计算发展的前景进行展望。     

网络并行计算在图象处理中的应用

当前随着计算要求的不断提高,并行计算发展方法未艾,网络并行计算更成为新的潮流,在并行处理中,图象处理是一个重要的应用领域。提出一种动态并行方法,以此实现Ｍａｎｄｅｌｂｒｏｔ图形。通过对实验数据的分析,对于任务规模和并行计算的加速比进行了研究。     

用于并行计算的PC机群

随着计算机技术的高速发展，使用机群进行并行计算也越来越流行，尤其是利用工作站机群进行并行计算已经十分普遍。但使用ＰＣ机群进行并行计算的系统还很少，这种ＰＣ机群由一组ＰＣ机（４８６，５８６）通过网络互连组成。本文介绍现有的几个ＰＣ机群和我们研制的一个ＰＣ机群计算环境     

异构计算——求解超级问题的新途径

异构计算是近年来并行处理领域中新的研究热点。它的思想是充分利用一组汪同结构的高性能计算机求解含有不同并行性的超级问题。文中分析了异构计算的背景及特点，讨论了当前存在的问题。     

基于网格的并行算法研究

分析了传统分布式并行计算和网格基础上并行计算技术应用中存在的问题。然后将LogP并行计算模型拓展到网格上,给出双层LogP模型和设计策略。针对网格特点对CG并行算法进行了改进,并有很好的效果。     

网格并行计算模型研究

分析了传统分布式并行计算和网格基础上并行计算技术应用中存在的问题,将Log P并行计算模型拓展到网格上,给出双层Log P模型和设计策略,针对网格特点对CG并行算法进行了改进,取得了很好的效果.     

TDCE:基于Tspaces的分布并行计算系统

Tspaces是一种新型的网络中间件。它为网络环境中各进程提供一种强大的共享存储机制来处理相互之间通信和同步。在Tspaces的基础上，构造了一个用于群机环境的并行计算系统TDCE。TDCE支持SPMD模式的并行程序，实验结果表明TDCE能以较小的系统配置和管理开销构建分布式计算平台，为并行程序的开发运行提供有效的支持，给出了系统MPI的对比测试结果并作了分析。     

非规则、核外并行计算研究综述

非规则、核外计算既是大规模并行应用普遍存在的问题,也是影响大规模并行应用效率的关键问题.本文从并行处理模型、运行支持库实现和并行优化三个方面对非规则、核外计算技术进行了全面综述,并对典型研究成果的特点和不足进行了分析.如何充分利用系统结构的特点和应用数据本身的特点,寻求非规则、核外计算处理的优化是现有技术发展的共同思想.在此基础上,指出了处理两类问题的技术相关性以及在SMP集群系统结构和网络存储环境下,解决非规则、核外计算的新思路:一是从问题描述、编译优化、运行支持等多层次协同研究充分利用系统结构特点的优化技术,二是从应用问题出发,在并行粒度确定、并行范例选择等方面统一非规则、核外计算的处理,三是研究新的支持非规则通信的优化技术和动态负载均衡方法.     

基于移动代理的分布式并行计算中间件设计与实现

文中提出了一个基于移动代理(Mobile Agent)的分布式并行计算中间件，用于将Internet用户闲置的计算资源与其他成员共享。针对分布式并行计算中存在的问题，利用移动代理技术的特点，将中间件的体系结构分为两层，为分布式并行计算提供各种基础服务，尤其是任务迁移和容错机制。着重介绍了分布式并行计算中间件的主要实现技术，实现了一个分布式并行计算原型系统并给出实验结果。     

Windows环境下的Matlab并行机群计算配置及应用

介绍了两种Windows环境下Matlab并行计算的机群搭建方案,并对这两种方案进行比较,较详细地讨论了Matlab并行计算工具箱中各部件的关系,对并行计算环境中的关键参数设置进行了介绍。通过一个实例在机群上的并行实现进一步说明Madab并行程序设计的方法。本文内容对在Matlab环境下进行并行计算具有一定参考价值。