计算机技术与发展2024，Vol.34Issue(7)：48-54,7.DOI:10.20165/j.cnki.ISSN1673-629X.2024.0121
基于GSLF-SSA的异构多核处理器任务调度
Task Scheduling for Heterogeneous Multi-core Processors Based on GSLF-SSA
摘要
Abstract
To enhance the computational performance of heterogeneous multi-core processor platforms,we propose an improved Sparrow Search Algorithm called the Fusion of Golden Sinusoidal and Levy Flight in Sparrow Search Algorithm(GSLF-SSA)to optimize task scheduling on heterogeneous multi-core processors.Through an analysis of heterogeneous task scheduling,we model these tasks as a Directed Acyclic Graph(DAG)task model.By randomly encoding priorities for these DAG tasks,the GSLF-SSA algorithm achieves a mapping of the solution domain from continuous to discrete,making it more adaptable for heterogeneous multi-core task scheduling.The algorithm iteratively refines its fitness value using the optimal scheduling length of DAG tasks.Experimental comparisons with several widely used heuristic algorithms in the context of heterogeneous task scheduling,including Sparrow Search Algorithm(SSA),an improved task scheduling algorithm based on hybrid optimization strategy(IHSSA),and Artificial Bee Colony Algorithm(ABC),dem-onstrate that GSLF-SSA achieves superior scheduling lengths and shorter scheduling execution time.关键词
异构多核处理器/麻雀搜索算法/有向无环图/任务调度/黄金正弦/莱维飞行Key words
heterogeneous multi-core processors/sparrow search algorithm/directed acyclic graph/task scheduling/golden sinusoidal/Levy Fligh分类
信息技术与安全科学引用本文复制引用
刘齐坚,王韦刚,高鹏程..基于GSLF-SSA的异构多核处理器任务调度[J].计算机技术与发展,2024,34(7):48-54,7.基金项目
国家自然科学基金项目(61871232,61571233) （61871232,61571233）
射频集成与微组装技术国家地方联合工程实验室开放课题(KFJJ20200103) （KFJJ20200103）
南京邮电大学研究生教改项目(JGKT22_XYB03) （JGKT22_XYB03）
