Integrated Hardware/Software Codesign for Heterogeneous Computing Systems

This paper describes a strategy that integrates the task mapping and task scheduling steps for heuristic search techniques, with multiple neighbourhood functions to reduce search time and enchance solution quality in developing heterogeneous computing systems. For case studies involving 40 randomly generated task graphs and the fast Fourier transform, experimental results show that our approach outperfroms previous approaches in terms of search time by up to 93 times, and solution quality by up to 22.6% for a system with a microprocessor, a floating-point digital signal processor, and an FPGA.

[1]  Soonhoi Ha,et al.  Hardware-software cosynthesis of multi-mode multi-task embedded systems with real-time constraints , 2002, Proceedings of the Tenth International Symposium on Hardware/Software Codesign. CODES 2002 (IEEE Cat. No.02TH8627).

[2]  Mariangela L. Silva,et al.  An object-oriented approach to a parallel tabu search algorithm for the task scheduling problem , 1999, Proceedings. SCCC'99 XIX International Conference of the Chilean Computer Science Society.

[3]  C. Ribeiro,et al.  A Tabu Search Approach to Task Scheduling on Heterogeneous Processors under Precedence Constraints , 1995, Int. J. High Speed Comput..

[4]  Theerayod Wiangtong,et al.  Comparing Three Heuristic Search Methods for Functional Partitioning in Hardware–Software Codesign , 2002, Des. Autom. Embed. Syst..

[5]  T. Wiangtong,et al.  Hardware/software codesign: a systematic approach targeting data-intensive applications , 2005, IEEE Signal Processing Magazine.

[6]  José Ignacio Hidalgo,et al.  Functional partitioning for hardware-software codesign using genetic algorithms , 1997, EUROMICRO 97. Proceedings of the 23rd EUROMICRO Conference: New Frontiers of Information Technology (Cat. No.97TB100167).

[7]  Krishna R. Pattipati,et al.  On mapping a tracking algorithm onto parallel processors , 1990 .

[8]  Wayne Luk,et al.  Interleaving behavioral and cycle-accurate descriptions for reconfigurable hardware compilation , 2005, 13th Annual IEEE Symposium on Field-Programmable Custom Computing Machines (FCCM'05).