{"title":"A Method for Synthesis of Specialized Processors to Support On-board Scheduling of Periodic Tasks","authors":"V. Khachumov, M. Khachumov","doi":"10.1109/ET.2019.8878619","DOIUrl":null,"url":null,"abstract":"We consider the actual problem of synthesizing specialized computing devices (SCDs) for periodic task scheduling to support autonomous functioning of a small UAV having limited computing resources. A specialized processor implements a given system of concurrent local algorithms. The problems of minimizing the number of processing units (PUs) in SCDs and minimizing the number of inter-processor connections are solved. We consider the issues of designing a control unit for switching PUs to optimize periodic computational process. The solution to the problem of partitioning a connection graph of PUs into weakly coupled fragments is proposed. To determine the expediency of partitioning optimization we propose an efficiency function.","PeriodicalId":306452,"journal":{"name":"2019 IEEE XXVIII International Scientific Conference Electronics (ET)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE XXVIII International Scientific Conference Electronics (ET)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ET.2019.8878619","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
We consider the actual problem of synthesizing specialized computing devices (SCDs) for periodic task scheduling to support autonomous functioning of a small UAV having limited computing resources. A specialized processor implements a given system of concurrent local algorithms. The problems of minimizing the number of processing units (PUs) in SCDs and minimizing the number of inter-processor connections are solved. We consider the issues of designing a control unit for switching PUs to optimize periodic computational process. The solution to the problem of partitioning a connection graph of PUs into weakly coupled fragments is proposed. To determine the expediency of partitioning optimization we propose an efficiency function.