A Multi-object GA Based Physical Placement Algorithm for Heterogeneous Dynamicaly Reconfigurable Arrays

Author

Nousias, Ioannis ; Khawam, Sami ; Milward, Mark ; Muir, Mark ; Arslan, Tughrul

Author_Institution

Univ. of Edinburgh, Edinburgh

fYear

2007

fDate

5-8 Aug. 2007

Firstpage

504

Lastpage

510

Abstract

This paper presents a physical placement algorithm, for Dynamically Reconfigurable Arrays (DRA), based on a multi-objective, multi-threaded GA implementation. The algorithm deals with the spatial and temporal nature of the configurations used in DRAs, in an attempt to find a suitable layout for a wide range of applications, since general applicability is a key criteria for DRAs. The results show that the proposed algorithm significantly improves the routability and total wire-length of the mapped configuration sets, with results ranging from 21% to 55% for various quality metrics.

Keywords

field programmable gate arrays; genetic algorithms; reconfigurable architectures; heterogeneous dynamically reconfigurable arrays; multithreaded GA implementation; physical placement algorithm; quality metrics; Biological system modeling; Circuits; Delta modulation; Field programmable gate arrays; Heuristic algorithms; Logic programming; Minimization; Routing; Silicon; Very large scale integration;

fLanguage

English

Publisher

ieee

Conference_Titel

Adaptive Hardware and Systems, 2007. AHS 2007. Second NASA/ESA Conference on

Conference_Location

Edinburgh

Print_ISBN

978-0-7695-2866-3

Type

conf

DOI

10.1109/AHS.2007.8

Filename

4291960