A hybrid heuristic algorithm for HW-SW partitioning within timed automata

被引：0

作者：

Pu, Geguang ^{[1
]}

Chong, Zhang

Qiu, Zongyan

Lin, Zuoquan

He Jifeng

机构：

[1] E China Normal Univ, Software Engn Inst, Shanghai 200062, Peoples R China

[2] Peking Univ, LMAM, Dept Informat, Sch Math, Beijing 100871, Peoples R China

来源：

KNOWLEDGE-BASED INTELLIGENT INFORMATION AND ENGINEERING SYSTEMS, PT 1, PROCEEDINGS | 2006年 / 4251卷

关键词：

hardware/software partitioning; timed automata; GRASP; tabu search; scheduling algorithm;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Hardware/Software (HW-SW) partitioning is a critical problem in co-design of embedded systems. This paper focuses on the synchronous system model, and formalizes the partitioning problem using timed automata (TA), which captures the key elements of the partitioning problem. Based on the TA model, we propose a hybrid heuristic algorithm to obtain near-optimal solutions effectively and efficiently. The experiments conducted show that our approach can deal with large applications with hundreds of nodes in task graph.

引用

页码：459 / 466

页数：8