Performance Evaluation of Parallel Systems

In this paper performance evaluation methodologies that have been applied in the analysis of parallel systems are reviewed together with the specific performance metrics. We concentrate on a few selected performance studies of parallel system components, i.e., processor, memory, interconnection network, input/output, and operating system. We demonstrate the utility of the performance evaluation methodologies for identification of system bottlenecks, performance forecasting, and future system design. 1 Introduction Parallel computing has emerged as an indispensable tool for problem solving in many scientific domains during the course of the past twenty years as parallelism is the only avenue to achieve the required performance, which is vastly 1 This work was partially supported by PQE2000 project and CNR CESTIA Center, Milano, Italy. 2 This work was partially supported by a William and Mary Summer Research grant. Preprint submitted to Elsevier Preprint 14 January higher than what..