{"title":"Parsim-message PAssing computeR SIMulator","authors":"A. Symons, V. Narasimhan","doi":"10.1109/ICAPP.1995.472249","DOIUrl":null,"url":null,"abstract":"The task of predicting the performance of an application on a new platform given its performance on a particular computer system is fairly difficult. Significant degree of exhaustive modeling of both algorithms and architectures is required before a reasonable prediction can be attempted. This paper describes a general purpose simulator for message passing multiprocessors (Parsim), which facilitates system modeling. Besides monitoring a number of system parameters, Parsim permits easy reconfiguration of topology and algorithm mappings. Parsim has been used to predict the performance of a number of different algorithms such as Fast Fourier Transform, Livermore loops and integer programming, on a variety of topologies such as transputer hypercubes, transputer meshes and a cluster of workstations on an ethernet backbone.<<ETX>>","PeriodicalId":448130,"journal":{"name":"Proceedings 1st International Conference on Algorithms and Architectures for Parallel Processing","volume":"55 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1995-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings 1st International Conference on Algorithms and Architectures for Parallel Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICAPP.1995.472249","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
The task of predicting the performance of an application on a new platform given its performance on a particular computer system is fairly difficult. Significant degree of exhaustive modeling of both algorithms and architectures is required before a reasonable prediction can be attempted. This paper describes a general purpose simulator for message passing multiprocessors (Parsim), which facilitates system modeling. Besides monitoring a number of system parameters, Parsim permits easy reconfiguration of topology and algorithm mappings. Parsim has been used to predict the performance of a number of different algorithms such as Fast Fourier Transform, Livermore loops and integer programming, on a variety of topologies such as transputer hypercubes, transputer meshes and a cluster of workstations on an ethernet backbone.<>