期刊名称：International Journal of Computer Science and Security (IJCSS)
电子版ISSN：1985-1553
出版年度：2007
卷号：1
期号：1
页码：1-10
出版社：Computer Science Journals
摘要：Parallel computing has emerged as an environment for computing inherently parallel and computation intensive applications. Performance is always a key factor in determining the success of any system. So parallel computing systems are no exception. Evaluating and analyzing the performance of parallel systems is an important aspect of parallel computing research. Evaluating and analyzing parallel system is difficult due to the complex interaction between application characteristics and architectural features. Experimental measurement, Theoretical/Analytical modeling and Simulation are the most widely used techniques in the performance evaluation of parallel systems. Experimental measurement uses real or synthetic workloads, usually known as benchmarks, to evaluate and analyze their performance on actual hardware. Theoretical/Analytical models try to abstract details of a parallel system. Simulation and other performance monitoring/visualization tools are extremely popular because they can capture the dynamic nature of the interaction between applications and architectures. Each of them has several types. For example, Experimental measurement has software, hardware, and hybrid. Theoretical/Analytical modeling has queueing network, Petri net, etc. and simulation has discrete event, trace/execution driven, Monte Carlo. Each of these three techniques has their own pros and cons. The purpose of this paper is firstly to present a qualitative parametric comparative analysis of these techniques based on parameters like stage, output statistics, accuracy, cost, resource consumption, time consumption, flexibility, scalability, tools required, trustability and secondly to justify the need for an integrated model combining the advantages of all these techniques to evaluate the performance of parallel systems and thirdly to present a new integrated model for performance evaluation . This paper also discusses certain issues like selecting an appropriate metric for evaluating parallel systems.
