面向SCA的DPR软件架构设计与调度技术  

DPR Software Architecture Design and Scheduling Technology for SCA

作　　者：郭彪 唐麒 文智敏 傅娟 王玲[1] 魏急波[2] GUO Biao;TANG Qi;WEN Zhimin;FU Juan;WANG Ling;WEI Jibo(College of Electrical and Information Engineering,Hunan University,Changsha 410082,China;College of Electronic Science and Technology,National University of Defense Technology,Changsha 410073,China;Changsha Rail Transit Operation Co.,Ltd,Changsha 410000,China;Academy of System Engineering,Academy of Military Science,Beijing 100101,China)

机构地区：[1]湖南大学电气与信息工程学院,长沙410082 [2]国防科技大学电子科学学院,长沙410073 [3]长沙轨道交通运营有限公司,长沙410000 [4]军事科学院系统工程研究院,北京100101

出　　处：《计算机工程》2021年第12期221-229,共9页Computer Engineering

基　　金：国家自然科学基金(62001483,U19B2024);湖南省科技创新计划(2020RC2045)。

摘　　要：为提高软件无线电(SDR)系统波形应用部署的灵活性和FPGA资源利用率,基于SDR系统的软件通信体系架构(SCA),设计一种支持FPGA的动态部分可重构(DPR)软件架构。针对DPR FPGA与CPU组成的异构计算平台,提出一种蚁群优化调度算法,以提高波形应用部署效率。实验结果表明,与MILP算法和ILP算法相比,所提算法的求解性能平均提升了约30%,且随着任务规模的增大,优势更加明显。In order to improve the flexibility of waveform application deployment and FPGA resource utilization in Software Defined Radio(SDR)systems,a software architecture that supports Dynamic Partial Reconfiguration(DPR)of FPGA is designed based on the Software Communication Architecture(SCA)in SDR systems.At the same time,in order to improve the efficiency of waveform application deployment,an Ant Colony Optimization(ACO)scheduling algorithm is designed for the heterogeneous computing platform composed of DPR FPGA and CPU.Experimental results show that compared with the MILP algorithm and the ILP algorithm,the proposed algorithm improves the solution performance by about 30%on average,and the solution performance grows along with the task size.

关 键 词：软件通信体系架构 动态部分可重构 可扩展标记语言 有向无环图 蚁群优化 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]