Volume 7 Number 10 (Oct. 2012)
Home > Archive > 2012 > Volume 7 Number 10 (Oct. 2012) >
JCP 2012 Vol.7(10): 2518-2525 ISSN: 1796-203X
doi: 10.4304/jcp.7.10.2518-2525

A Novel Approach to Hardware/Software Partitioning for Reconfigurable Embedded Systems

Linhai Cui
School of Software, Harbin University of Science and Technology, Harbin, China
Abstract—Hardware/software partition is a crucial point in the design of a reconfigurable embedded system. Reconfigurable computing is a promising approach to overcome the traditional trade-off between flexibility and performance in the design of computer architectures which adapt their hardware to each application to achieve a high performance of dedicated hardware. In this paper, some hardware and software partitioning algorithms were analyzed and summarized first, then a innovative algorithm for task partition and scheduling is proposed based on new features of reconfigurable hardware such as dynamic reconfiguration and the delay of reconfiguration. In the proposed algorithm, a large-scale application is decomposed into multiple sub-tasks of suitable granularity and each sub-task has constraint relationship with each other. And a directed acyclic graph (DAG) which presents the relationship between tasks was drawn according to the execution order of tasks. Then the specific application presented in the DAG is mapped to the hardware and software platform by a strategy called GATS which combine the Genetic Algorithm and the Tabu Search algorithm together. The shortest time of assignment and task execution order can be found by the priority-based scheduling method. The experimental results show that the method is of high performance and can effectively mapping the application task to the reconfigurable system.

Index Terms—Reconfigurable embedded system, Task scheduling, Hardware/software partitioning, Genetic algorithm; Tabu search algorithm.

[PDF]

Cite: Linhai Cui, "A Novel Approach to Hardware/Software Partitioning for Reconfigurable Embedded Systems," Journal of Computers vol. 7, no. 10, pp. 2518-2525, 2012.

General Information

ISSN: 1796-203X
Abbreviated Title: J.Comput.
Frequency: Bimonthly
Editor-in-Chief: Prof. Liansheng Tan
Executive Editor: Ms. Nina Lee
Abstracting/ Indexing: DBLP, EBSCO,  ProQuest, INSPEC, ULRICH's Periodicals Directory, WorldCat,etc
E-mail: jcp@iap.org
  • Nov 14, 2019 News!

    Vol 14, No 11 has been published with online version   [Click]

  • Mar 20, 2020 News!

    Vol 15, No 2 has been published with online version   [Click]

  • Dec 16, 2019 News!

    Vol 14, No 12 has been published with online version   [Click]

  • Sep 16, 2019 News!

    Vol 14, No 9 has been published with online version   [Click]

  • Aug 16, 2019 News!

    Vol 14, No 8 has been published with online version   [Click]

  • Read more>>