A performance evaluation study of pipeline TMR systems

A distributed system in which a job can be broken into a number of subjobs which are processed sequentially at various processors is considered. The performance of such a system is then compared to the replicated (triple modular redundant, or TMR) version of the system in which each subjob will require concurrent replicated processing with majority voting. The effect of voting times and processor failure rates on the performance of the system is investigated with analytical approximations and computer simulations. The accuracy of the former is examined. The results indicate the possible existence of a threshold voting time, below which the TMR system performs better than the unreplicated one, and above which the situation is reversed. Such thresholds are observed, where possible, in systems with repairable servers, as well as in those with nonrepairable servers     

A trace-driven simulator for performance evaluation of cache-basedmultiprocessor systems

We describe a simulator which emulates the activity of a shared memory, common bus multiprocessor system with private caches. Both kernel and user program activities are considered, thus allowing an accurate analysis and evaluation of coherence protocol performance. The simulator can generate synthetic traces, based on a wide set of input parameters which specify processor, kernel and workload features. Other parameters allow us to detail the multiprocessor architecture for which the analysis has to be carried out. An actual-trace-driven simulation is possible, too, in order to evaluate the performance of a specific multiprocessor with respect to a given workload, if traces concerning this workload are available. In a separate section, we describe how actual traces can also be used to extract a set of input parameters for synthetic trace generation. Finally, we show how the simulator may be successfully employed to carry out a detailed performance analysis of a specific coherence protocol     

On performance evaluation of ERP systems with fuzzy mathematics

An enterprise resource planning (ERP) system is a complex network composed of various business processes. This paper proposes a method based on stochastic-flow network model to evaluate the performance of an ERP system depending upon the fuzzy linguistic results of the ERP examination of the users involved. The nodes in the network denote the persons responsible for the business tasks during the processes. The arcs between nodes denote the process precedence relationships in the ERP system. When the process starts, the documents are initiated from the source node to its succeeding nodes. Finally, the documents are released in the destination node. Thus, the performance of an ERP system is related to the document flow under the network. The failure of an ERP system is therefore described as in the condition that the flow of the system is under the acceptable level d. By using the fuzzy linguistic results of the ERP examination of the users, we propose a fuzzy linguistic performance index, defuzzified from the probability of maximal flow not less than d, to evaluate the performance of an ERP system. An algorithm is subsequently proposed to generate the performance index, which can be used to assess the system performance either before or after the system going live.     

Assessing performance and uncertainty in developing carpet reverse logistics systems

The US carpet industry is striving to reach a 40% diversion rate from landfills by 2012, according to a memorandum of understanding signed by industry and government officials in 2002. As a result, they are interested in methods of setting up a reverse logistics (RL) system which will allow them to manage the highly variable return flows. In this paper, we simulate such a carpet RL supply chain and use a designed experiment to analyze the impact of the system design factors as well as environmental factors impacting the operational performance of the RL system. First, we identify the relative importance of various network design parameters. We then show that even with the design of an efficient RL system, the use of better recycling technologies, and optimistic growth in recycling rates, the return flows cannot meet demand for nearly a decade. We conclude by discussing possible management options for the carpet industry to address this problem, including legal responses to require return flows and the use of market incentives for recycling.     

Empirical performance evaluation of graphics recognition systems

Presents a methodology for evaluating graphics recognition systems operating on images that contain straight lines, circles, circular arcs, and text blocks. It enables an empirical comparison of vectorization software packages and uses practical performance evaluation methods that can be applied to complete vectorization systems. The methodology includes a set of matching criteria for pairs of graphical entities, a set of performance evaluation metrics, and a benchmark for the evaluation of graphics recognition systems. The benchmark was tested on three systems. The results are reported and analyzed in the paper     

Analysis of manufacturing blocking systems with Network Calculus

In this paper, the manufacturing blocking system (MBS) is studied from the Network Calculus (NetCal) perspective. By dominating an MBS by a window flow controller (WFC), we obtain service curves for systems with instantaneous and non-instantaneous acknowledgements. The explicit expression for the system service curve leads to the optimal allocation of the buffer sizes, which guarantees the ideal system service curve: that is, the service curve for the system with no restrictions on the sizes of in-between buffers. This allocation is more efficient than one based on guarantees of individual service curves. In addition, a method of simulation of NetCal systems is developed exploiting the duality between arrival curves and strict service curves. Simulation experiments are conducted to show the tightness of the theoretical bounds obtained using NetCal.     

Approximate analysis of exponential queueing systems with blocking

Summary A network of service stations Q ₀ Q ₁,...,Q_M is studied. Requests arrive at the centers according to independent Poisson processes; they travel through (part of) the network demanding amounts of service, with independent and negative exponentially distributed lengths, from those centers which they enter, and finally depart from the network. The waiting rooms or buffers at each service station in this exponential service system are finite. When the capacity at Q _i is reached, service at all nodes which are currently processing a request destined next for Q _i is instantaneously interrupted. The interruption lasts until the service of the request in the saturated node Q _i is. completed. This blocking phenomenon makes an exact analysis intractable and a numerical solution computationally infeasible for most exponential systems. We introduce an approximation procedure for a class of exponential systems with blocking and show that it leads to accurate approximations for the marginal equilibrium queue length distributions. The applicability of the approximation method may not be limited to blocking systems.Mathematical Sciences Department Postdoctoral Fellow 1978–79.     

A group Undo/Redo method in 3D collaborative modeling systems with performance evaluation

Undo/Redo is an indispensable function in 3D collaborative modeling systems where a single mistake conducted by one user is propagated to all participants. Both intention preservation and consistency maintenance should be satisfied when applying group Undo/Redo. Besides, fast local responsiveness and timely group awareness are accepted performance metrics in interactive systems. In this paper, we contribute a novel group Undo/Redo mechanism for 3D collaborative modeling systems to support the “any time, any where” Undo/Redo. Response time will be shortened noticeably with a Model State Stream kept on each collaborative site. In the case of concurrent Undo/Redo, an Undo State Vector is proposed to ensure the Undo/Redo intention preservation and model consistency maintenance. Furthermore, the paper studies the performance of the algorithm including the worst, best and average cases with theoretical analyses. Our experiments show that responsive time is actually depending on a number of factors such as size of the history buffer, execution time for a single modeling operation.     

A queueing theoretic approach for performance evaluation of low-power multi-core embedded systems

With Moore’s law supplying billions of transistors on-chip, embedded systems are undergoing a transition from single-core to multi-core to exploit this high transistor density for high performance. However, the optimal layout of these multiple cores along with the memory subsystem (caches and main memory) to satisfy power, area, and stringent real-time constraints is a challenging design endeavor. The short time-to-market constraint of embedded systems exacerbates this design challenge and necessitates the architectural modeling of embedded systems to reduce the time-to-market by expediting target applications to device/architecture mapping. In this paper, we present a queueing theoretic approach for modeling multi-core embedded systems that provides a quick and inexpensive performance evaluation both in terms of time and resources as compared to the development of multi-core simulators and running benchmarks on these simulators. We verify our queueing theoretic modeling approach by running SPLASH-2 benchmarks on the SuperESCalar simulator (SESC). Results reveal that our queueing theoretic model qualitatively evaluates multi-core architectures accurately with an average difference of 5.6% as compared to the architectures’ evaluations from the SESC simulator. Our modeling approach can be used for performance per watt and performance per unit area characterizations of multi-core embedded architectures, with varying number of processor cores and cache configurations, to provide a comparative analysis.     

An approach to evaluation of hierarchical systems performance

An approach to assessment of performance of hierarchical systems with simple subordination is developed with regard to moment characteristics of sequences of random sums. Translated from Kibernetika i Sistemnyi Analiz, No. 4, pp. 70–79, July–August, 2000.     

A novel disassembly tool with screwnail endeffectors

One of the most intriguing aspects of disassembly is that of dealing with the products not designed for disassembly. This paper presents a novel disassembly tool, wherein a screwnail is used as an endeffector. It is shown that the screwnail indentation process can well overcome the geometrical uncertainties of the products to be dismantled. A self-connection resulted from the screwnail indentation provides a reliable closure to transmit forces and torques required for various dismantling operations. Some differences between the self-connection and the assembly connection are analyzed in detail. With the screwnail endeffector integrated, a disassembly task is decomposed into a screwnail indentation process, a task execution process, and a separating process. A vivid example is given to illustrate these concepts.     

面向过程的测试方法在大规模数据密集型系统中的应用

针对数据密集型的大规模系统提出了一种面向过程的测试方法,它根据测试节点的不同角色,综合负载特征和资源利用情况,对大规模系统进行综合全面的分析,这不仅简化了大规模系统测试的复杂性,而且较好的屏蔽了上层应用的多样性。该方法已在一些大规模系统测试中得到了应用,及时发现了系统设计和系统设备的问题,取得了很好的效果。     

Automatic performance evaluation of printed Chinese character recognition systems

Performance evaluation is crucial for improving the performance of OCR systems. However, this is trivial and sophisticated work to do by hand. Therefore, we have developed an automatic performance evaluation system for a printed Chinese character recognition (PCCR) system. Our system is characterized by using real-world data as test data and automatically obtaining the performance of the PCCR system by comparing the correct text and the recognition result of the document image. In addition, our performance evaluation system also provides some evaluation of performance for the segmentation module, the classification module, and the post-processing module of the PCCR system. For this purpose, a segmentation error-tolerant character-string matching algorithm is proposed to obtain the correspondence between the correct text and the recognition result. The experiments show that our performance evaluation system is an accurate and powerful tool for studying deficiencies in the PCCR system. Although our approach is aimed at the PCCR system, the idea also can be applied to other OCR systems.     

Variants of P systems with activation and blocking of rules

Natural Computing - We introduce new possibilities to control the application of rules based on the preceding applications, which can be defined in a general way for (hierarchical) P systems and...     

Checkpointing strategies in database systems and their performance evaluation

A transaction-oriented database system is investigated, where checkpointing is carried out after a certain number of transactions are processed. The design objective is to maximize the system availability given the failure rate, checkpointing time, error recovery time, and other system parameters. Several checkpointing strategies have been proposed and analysed. The effect of error latency is also considered.     

A testbed for performance evaluation of load‐balancing strategies for Web server systems

To improve response time of a Web site, one replicates the site on multiple servers. The effectiveness of a replicated server system will depend on how the incoming requests are distributed among replicas. A large number of load‐balancing strategies for Web server systems have been proposed. In this paper we describe a testbed that can be used to evaluate the performance of different load‐balancing strategies. The testbed uses a general architecture which allows different load‐balancing approaches to be supported easily. It emulates a typical World Wide Web scenario and allows variable load generation and performance measurement. We have performed some preliminary experiments to measure the performance of a few policies for load balancing using this testbed. Copyright © 2003 John Wiley & Sons, Ltd.