{"title":"动态运行时硬件/软件调度的3D可重构SoC","authors":"Quang-Hai Khuat, D. Chillet, M. Hübner","doi":"10.1109/ReConFig.2014.7032512","DOIUrl":null,"url":null,"abstract":"In this paper, we present a new online hardware/software (HW/SW) scheduling algorithm for a 3D Reconfigurable SoC platform comprising a multiprocessors layer and a heterogeneous reconfigurable layer. The proposed algorithm decides on the fly whether the tasks will run in SW or HW, at which time, on which processor or in which region of the reconfigurable layer in order to minimize the overall execution time of the application. It evaluates, during runtime, the interest to continue the SW execution of a task or to cancel it for starting a new HW execution of this task from the initial state. By using our algorithm called Hardware/Software algorithm with Software execution Prediction (HSSP), the overall execution time can be reduced by 26 % compared with other existing HW/SW scheduling methods.","PeriodicalId":137331,"journal":{"name":"2014 International Conference on ReConFigurable Computing and FPGAs (ReConFig14)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Dynamic run-time hardware/software scheduling for 3D reconfigurable SoC\",\"authors\":\"Quang-Hai Khuat, D. Chillet, M. Hübner\",\"doi\":\"10.1109/ReConFig.2014.7032512\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, we present a new online hardware/software (HW/SW) scheduling algorithm for a 3D Reconfigurable SoC platform comprising a multiprocessors layer and a heterogeneous reconfigurable layer. The proposed algorithm decides on the fly whether the tasks will run in SW or HW, at which time, on which processor or in which region of the reconfigurable layer in order to minimize the overall execution time of the application. It evaluates, during runtime, the interest to continue the SW execution of a task or to cancel it for starting a new HW execution of this task from the initial state. By using our algorithm called Hardware/Software algorithm with Software execution Prediction (HSSP), the overall execution time can be reduced by 26 % compared with other existing HW/SW scheduling methods.\",\"PeriodicalId\":137331,\"journal\":{\"name\":\"2014 International Conference on ReConFigurable Computing and FPGAs (ReConFig14)\",\"volume\":\"12 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2014-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2014 International Conference on ReConFigurable Computing and FPGAs (ReConFig14)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ReConFig.2014.7032512\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 International Conference on ReConFigurable Computing and FPGAs (ReConFig14)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ReConFig.2014.7032512","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3
摘要
在本文中,我们提出了一种新的在线硬件/软件(HW/SW)调度算法,该算法适用于由多处理器层和异构可重构层组成的3D可重构SoC平台。该算法动态地决定任务是在软件中运行还是在硬件中运行,在哪个时间,在哪个处理器上或在可重构层的哪个区域运行,以最小化应用程序的总体执行时间。它在运行时评估是否有兴趣继续任务的软件执行或取消它,以便从初始状态开始该任务的新硬件执行。采用HSSP (Hardware/Software algorithm with Software execution Prediction)算法,与现有的硬件/软件调度方法相比,总执行时间可减少26%。
Dynamic run-time hardware/software scheduling for 3D reconfigurable SoC
In this paper, we present a new online hardware/software (HW/SW) scheduling algorithm for a 3D Reconfigurable SoC platform comprising a multiprocessors layer and a heterogeneous reconfigurable layer. The proposed algorithm decides on the fly whether the tasks will run in SW or HW, at which time, on which processor or in which region of the reconfigurable layer in order to minimize the overall execution time of the application. It evaluates, during runtime, the interest to continue the SW execution of a task or to cancel it for starting a new HW execution of this task from the initial state. By using our algorithm called Hardware/Software algorithm with Software execution Prediction (HSSP), the overall execution time can be reduced by 26 % compared with other existing HW/SW scheduling methods.