首页|基于GSLF-SSA的异构多核处理器任务调度

基于GSLF-SSA的异构多核处理器任务调度

扫码查看
原文链接
  • 国家科技期刊平台
  • NETL
  • NSTL
  • 万方数据
为了提高异构多核处理器平台的计算性能，从任务调度的角度出发，提出了一种使用黄金正弦和莱维飞行机制改进的麻雀搜索算法(Fusion of Golden Sinusoidal and Levy Flight in Sparrow Search Algorithm，GSLF-SSA)来优化异构多核处理器的任务调度。通过对异构任务调度的分析，将异构任务建模为DAG(Directed Acyclic Graph)任务模型，通过对其优先级进行随机编码分配，实现了GSLF-SSA算法求解域从连续到离散的映射，使该算法更能适用于异构多核任务调度之中。将DAG任务的最优调度长度作为算法的适应度值进行迭代寻优，通过与目前应用广泛的麻雀搜索算法(SSA)、混合式任务调度算法(IHSSA)、人工蜂群算法(ABC)等多种启发式算法在异构任务调度环境下的实验对比表明，GSLF-SSA能获得更优的调度长度与更短的调度执行时间。
Task Scheduling for Heterogeneous Multi-core Processors Based on GSLF-SSA
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.

heterogeneous multi-core processorssparrow search algorithmdirected acyclic graphtask schedulinggolden sinusoidalLevy Fligh

刘齐坚、王韦刚、高鹏程

展开 >

南京邮电大学 电子与光学工程学院、柔性电子(未来技术)学院,江苏 南京 210023

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

国家自然科学基金项目国家自然科学基金项目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南京邮电大学研究生教改项目

6187123261571233KFJJ20200103JGKT22_XYB03

2024

10.20165/j.cnki.ISSN1673-629X.2024.0121

计算机技术与发展
陕西省计算机学会

计算机技术与发展

CSTPCD
影响因子：0.621
ISSN：1673-629X
年,卷(期)：2024.34(7)