一种MPI并行程序设计中的动态负载平衡策略

介绍了MPI并行编程环境和MPI并行程序设计的特点,讨论了在MPI并行程序设计中实现动态负载平衡的方法,提出一种根据计算节点的计算能力和实时负载情况进行任务迁移的动态负载平衡策略。     

一种支持容错的任务并行程序设计模型

任务并行程序设计模型已成为并行程序设计的主流,其通过发掘任务并行性来提高并行计算机的系统性能.提出一种支持容错的任务并行程序设计模型,将容错技术融入到任务并行程序设计模型中,在保证性能的同时提高系统可靠性.该模型以任务为调度、执行、错误检测与恢复的基本单位,在应用级实现容错支持.采用一种Buffer-Commit计算模型支持瞬时错误的检测与恢复;采用应用级无盘检查点实现节点故障类型永久错误的恢复;采用一种支持容错的工作窃取任务调度策略获得动态负载均衡.实验结果表明,该模型以较低的性能开销提供了对硬件错误的容错支持.     

A Parallel Interval Computation Model for Global Optimization with Automatic Load Balancing

In this paper,we propose a decentralized parallel computation model for global optimization using interval analysis.The model is adaptive to any number of processors and the workload is automatically and evenly distributed among all processors by alternative message passing.The problems received by each processor are processed based on their local dominance properties,which avoids unnecessary interval evaluations.Further,the problem is treated as a whole at the beginning of computation so that no initial decomposition scheme is required.Numerical experiments indicate that the model works well and is stable with different number of parallel processors,distributes the load evenly among the processors,and provides an impressive speedup,especially when the problem is time-consuming to solve.     

基于模式的并行编程环境中任务队列模式的研究与实现

并行程序的设计是并行计算的难点之一。本文在基于模式的并行编程方法的基础上,对一种典型的并行计算与通信模式-任务队列模式进行了深入的研究,并在基于模式的并行编程环境中对该模式进行了实现。本文将通过两个典型的应用实例说明在基于模式的并行编程环境中使用任务队列模式进行问题的并行求解与并行程序开发的过程,并从实现效率和可编程性方面对使用任务队列模式的并行程序和传统的MPI/PVM实现的并行程序进行了分析与比较。     

基于并行约束规划的最大团识别研究

为提高大数据平台下大规模图例的最大团问题求解效率,提出一种基于并行约束规划的最大团识别算法.通过BMT图划分策略将一个复杂图例分割为若干个可独立计算的子图,并将其分配给Spark集群中的计算节点,每个计算节点采用约束规划方法对分割产生的子问题分别进行建模和求解,实现最大团问题的并行化处理.引入时间预测模型,设计基于任务运行时间预测模型的并行图划分方法,从而有效解决计算节点的负载均衡问题.实验结果表明,与基于BMC图划分策略的最大团并行识别算法相比,该算法具有更高的求解效率,可取得近似线性的加速比.     

Functional programming languages for verification tools: a comparison of Standard ML and Haskell

We compare Haskell with Standard ML as programming languages for verification tools based on our experience developing the verification platform Truth in Haskell and the Edinburgh Concurrency Workbench (CWB) in Standard ML. We review not only technical language features but also the worlds of the languages, for example, the availability of compilers, tools, and libraries. We also discuss the merits and difficulties of comparing programming languages in this wide sense and support our view that Truth and the CWB are similar enough to justify the conclusions drawn in this paper.     

高性能并行入侵检测算法与框架

基于单引擎检测的网络入侵检测系统(network intrusion detection system,NIDS)靠辅助硬件和改进检测算法来提高处理性能,但已无法适应10Gb/s以上流量的线速处理要求。利用多检测引擎进行并行处理是实现高性能入侵检测的重要技术手段,并行检测系统通过多检测引擎进行并行协同检测,具有高性能和可扩展的优点。归纳了进行流量划分时遇到的保持检测攻击所需证据和负载均衡这两方面的挑战及其解决策略。综合现有并行入侵检测框架的优点,提出了一个统一的支持多检测引擎并行检测的体系结构UPDA(uniformed parallel detection architecture)。利用NetMagic平台,基于UPDA框架,设计和实现了一个高性能并行入侵检测原型系统,并通过实验验证了系统的高性能和有效性。     

Windows环境下CRNG多核并行算法的设计实现

多核技术的出现给人们带来了一种大幅提升计算机运行速度的方法,大量的并行算法也被设计并应用到各个场合中。文中目的在于设计一种新的用于组合随机数发生器CRNG（Combined Random Number Generator）的并行算法,以提高传统算法的运算速率。文中采用并行编程方法中的任务级的并行模式,对传统组合随机数发生器的运算过程进行任务分解,将其分配到四个执行核上并行执行,以产生最终的随机数序列。最后在Windows环境下,使用常用的并行编程工具-OpenMP对新算法进行了编程验证,结果证实该算法可充分利用现有计算机所能提供的多核计算资源,其加速比高于3。     

Self-Organized Load Balancing in Proxy Servers: Algorithms and Performance

Proxy servers are common solutions to relieve organizational networks from heavy traffic by storing the most frequently referenced web objects in their local cache. These proxies are commonly known as cooperative proxy systems and are usually organized in such a way as to optimize the utilization of their storage capacity. However, the design of the organizational structure of such proxy system depends heavily on the designer's knowledge of the network's performance. This article describes three methods to tackle this load balancing problem. They allow the self-organization of proxy servers by modeling each server as an autonomous entity that can make local decisions based on the traffic pattern it has served.     

Parallel Bayesian inference of range and reflectance from LaDAR profiles

Bayesian analysis using reversible jump Markov chain Monte Carlo (RJMCMC) algorithms improves the measurement accuracy, resolution and sensitivity of full waveform laser detection and ranging (LaDAR), but at a significant computational cost. Parallel processing has the potential to significantly reduce the processing time, but although there have been several strategies for Markov chain Monte Carlo (MCMC) parallelization, adaptation of these strategies to RJMCMC may degrade parallel performance.     

EPS: An ‘elementary’ programming system for the Delft Parallel Processor

A programming system for synchronous parallel processors, like the DPP-84 working in synchronous mode, is proposed. In EPS a program consists of a collection of well-defined and separate units, described in a conventional procedure-oriented language like PASCAL or MODULA-2. The connection between the ‘elementary’ program units is laid in a supervisory ‘configuration’ program, which defines both the spatial and time relations between the units. The concept of ‘virtual’ parallel processing is introduced, which enables the construction of logical parallel programs, independent of the number of processing elements actually available.     

Parallel Computing with the Sisal Applicative Language: Programmability and Performance Issues

The traditional argument for applicative languages has been programmability. Indeed, due to high-level abstractions and the implicit parallelism provided by applicative languages, programmers are free to concentrate on the implementation of the algorithm at hand without being burdened with low-level machine execution details. However, it has long been believed that the implementation and raw performance of applicative languages would be their downfall. We report here that it is easy to deliver both programmability and performance through applicative programming. To demonstrate the viability of applicative programming in the context of parallel computing, quantitative results from an experiment which consists of developing a multigrid elliptic Partial Differential Equation (PDE) solver are presented.