{"title":"Usage of Global States-Based Application Control","authors":"J. Borkowski, D. Kopanski, M. Tudruj","doi":"10.1109/ISPDC.2006.53","DOIUrl":null,"url":null,"abstract":"The novel parallel/distributed application control method, discussed in this paper, is based on the use of global states monitoring. Application processes report their local states to monitors. The monitors construct global states, analyze them and send control signals to processes to stimulate necessary actions. A number of application areas of this control method are examined. Tests results and gained experience are presented for irregular computation, load balancing and dynamic workflow implementations. It is shown, that the new control method can lead to a better performance than message passing and that it provides a useful and convenient framework, facilitating program development and maintenance","PeriodicalId":196790,"journal":{"name":"2006 Fifth International Symposium on Parallel and Distributed Computing","volume":"238 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2006-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2006 Fifth International Symposium on Parallel and Distributed Computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISPDC.2006.53","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
The novel parallel/distributed application control method, discussed in this paper, is based on the use of global states monitoring. Application processes report their local states to monitors. The monitors construct global states, analyze them and send control signals to processes to stimulate necessary actions. A number of application areas of this control method are examined. Tests results and gained experience are presented for irregular computation, load balancing and dynamic workflow implementations. It is shown, that the new control method can lead to a better performance than message passing and that it provides a useful and convenient framework, facilitating program development and maintenance