A Comparative Evaluation of Techniques for Studying Parallel SystemsReportar como inadecuado

A Comparative Evaluation of Techniques for Studying Parallel Systems

A Comparative Evaluation of Techniques for Studying Parallel Systems - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

This paper presents a comparative and qualitative survey of techniques for evaluating parallel systems. We also survey metrics that have been proposed for capturing and quantifying the details of complex parallel system interactions. Experimentation, theoretical-analytical modeling and simulationare three frequently used techniques in performance evaluation. Experimentationuses real or synthetic workloads, usually called benchmarks, to measure and analyze their performance on actual hardware. Theoretical and analytical models are used to abstract details of a parallel system, providing the view of a simplified system parameterized by a limited number of degrees of freedomthat are kept tractable. Simulation and related performance monitoring-visualization tools have become extremely popular because of their ability to capture the dynamic nature of the interaction between applications and architectures.We first present the figures of merit that are important for any performance evaluation technique. With respect to these figures of merit, we survey the three techniques and make a qualitative comparison of their pros and cons.In particular, for each of the above techniques we discuss: representative casestudies; the underlying models that are used for the workload and thearchitecture; the feasibility and ease of quantifying standard performancemetrics from the available statistics; the accuracy-validity of the outputstatistics; and the cost-effort that is expended in each evaluationstrategy.

College of Computing Technical Reports -

Autor: Sivasubramaniam, Anand - Ramachandran, Umakishore - Venkateswaran, H. - -

Fuente: https://smartech.gatech.edu/

Documentos relacionados