{"title":"可重构计算系统的资源管理","authors":"A. Azibi, Ramzi Ayadi, M. L. Kaddachi","doi":"10.1109/ICEEE2019.2019.00031","DOIUrl":null,"url":null,"abstract":"Task placement problem is one of the most significant and time-consuming parts in reconfigurable computing system. Many investigators have explored on the subject, and most of the traditional studies are focused on free space management in the device. The aim of the free space management algorithm is to find all available free spaces to place a new module. Moreover, the algorithms proposed in the literature are heuristic algorithms, and does not offer a good compromise between the placement quality and the execution time. In order to remedy these problems and to obtain satisfactory results, in this paper we propose a module placement algorithm based on mathematical model that aims to minimize the total communication costs between modules. The results show a significant improvement in communication costs compared to other approaches.","PeriodicalId":407725,"journal":{"name":"2019 6th International Conference on Electrical and Electronics Engineering (ICEEE)","volume":"51 6","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Resource Management for Reconfigurable Computing Systems\",\"authors\":\"A. Azibi, Ramzi Ayadi, M. L. Kaddachi\",\"doi\":\"10.1109/ICEEE2019.2019.00031\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Task placement problem is one of the most significant and time-consuming parts in reconfigurable computing system. Many investigators have explored on the subject, and most of the traditional studies are focused on free space management in the device. The aim of the free space management algorithm is to find all available free spaces to place a new module. Moreover, the algorithms proposed in the literature are heuristic algorithms, and does not offer a good compromise between the placement quality and the execution time. In order to remedy these problems and to obtain satisfactory results, in this paper we propose a module placement algorithm based on mathematical model that aims to minimize the total communication costs between modules. The results show a significant improvement in communication costs compared to other approaches.\",\"PeriodicalId\":407725,\"journal\":{\"name\":\"2019 6th International Conference on Electrical and Electronics Engineering (ICEEE)\",\"volume\":\"51 6\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-04-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 6th International Conference on Electrical and Electronics Engineering (ICEEE)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICEEE2019.2019.00031\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 6th International Conference on Electrical and Electronics Engineering (ICEEE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICEEE2019.2019.00031","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Resource Management for Reconfigurable Computing Systems
Task placement problem is one of the most significant and time-consuming parts in reconfigurable computing system. Many investigators have explored on the subject, and most of the traditional studies are focused on free space management in the device. The aim of the free space management algorithm is to find all available free spaces to place a new module. Moreover, the algorithms proposed in the literature are heuristic algorithms, and does not offer a good compromise between the placement quality and the execution time. In order to remedy these problems and to obtain satisfactory results, in this paper we propose a module placement algorithm based on mathematical model that aims to minimize the total communication costs between modules. The results show a significant improvement in communication costs compared to other approaches.