面向异构信号处理平台的量子调度算法  

Quantum Scheduling Algorithm for Heterogeneous Signal Processing Platform

作　　者：沈小龙 马金全[1] 胡泽明[1] 李娜 李宇东 SHEN Xiaolong;MA Jinquan;HU Zeming;LI Na;LI Yudong(School of Information Systems Engineering,Information Engineering University,Zhengzhou 450000,China;Henan Branch,Bank of Communications,Zhengzhou 450000,China)

机构地区：[1]战略支援部队信息工程大学信息系统工程学院,河南郑州450000 [2]交通银行河南省分行,河南郑州450000

出　　处：《电子科技》2024年第3期84-90,共7页Electronic Science and Technology

基　　金：国家科技支撑项目(2013BAH56F00)。

摘　　要：针对异构信号处理平台中已有调度算法的调度长度较大导致信号处理应用实时性下降问题,文中提出一种面向异构信号处理平台的量子调度算法。该算法采用任务优先级分流排序策略,得到更加准确的任务调度顺序。使用量子比特对任务分配方案进行编码,增加任务分配方案的多样性,且编码规则有助于跳出局部最优找到全局最优解。按照最小计算开销原则和任务复制思想进行处理器分配,减少任务间通信开销,并通过量子旋转门对量子编码方案进行更新,不断逼近最优解。仿真结果表明,所提算法能够减少调度长度,提升信号处理应用的实时性,进而提高平台的工作效率。In order to solve the problem that the scheduling length of existing scheduling algorithms in heterogeneous signal processing platforms is large,which leads to the decline of real-time performance of signal processing applications,a quantum scheduling algorithm for heterogeneous signal processing platforms is proposed.The algorithm adopts task priority diffluence sorting strategy to obtain more accurate task scheduling order.Quantum bits are used to encode the task allocation scheme,which increases the diversity of the task allocation scheme,and the coding rules help to find the global optimal solution out of the local optimal.According to the principle of minimum computing cost and the idea of task replication,the processor is allocated to reduce the communication cost between tasks,and the quantum coding scheme is updated through the quantum turnstile to constantly approximate the optimal solution.Simulation results show that the proposed algorithm can reduce the scheduling length,improve the real-time performance of signal processing applications,and improve the working efficiency of the platform.

关 键 词：任务调度 异构信号处理平台 DAG 量子算法 量子比特 量子旋转门 调度长度 信号处理 

分 类 号：TN911[电子电信—通信与信息系统]