A Design Space Exploration methodology for allocating Task Precedence graphs to multi-core system architectures

In this paper, we propose a Design Space Exploration (DSE) methodology to produce multi-core system architectures with optimal scheduling, number of cores, number of buses and hardware-software partitioning from Task Precedence Graphs (TPGs). The viability and potential of the proposed methodology is demonstrated by extensive experimental results to conclude that it is an efficient scheme to obtain the optimality with hard and large task graph problems.

[1]  Jeffrey D. Ullman,et al.  NP-Complete Scheduling Problems , 1975, J. Comput. Syst. Sci..

[2]  Kemal Efe,et al.  Task scheduling with and without communication delays: A unified approach , 1996 .

[3]  Y.-K. Kwok,et al.  Static scheduling algorithms for allocating directed task graphs to multiprocessors , 1999, CSUR.

[4]  Dominique Lavenier,et al.  A Low Complex Scheduling Algorithm for Multi-processor System-on-Chip , 2005, Parallel and Distributed Computing and Networks.

[5]  Nikil D. Dutt,et al.  Physically-aware HW-SW partitioning for reconfigurable architectures with partial dynamic reconfiguration , 2005, Proceedings. 42nd Design Automation Conference, 2005..

[6]  Frode Eika Sandnes,et al.  Toward a realistic task scheduling model , 2006, IEEE Transactions on Parallel and Distributed Systems.

[7]  Oliver Sinnen,et al.  Task Scheduling for Parallel Systems , 2007, Wiley series on parallel and distributed computing.

[8]  Marco D. Santambrogio,et al.  Reconfigurable Computing and Hardware/Software Codesign , 2008, EURASIP J. Embed. Syst..

[9]  Ashraf Salem,et al.  Optimal Scheme for Search State Space and Scheduling on Multiprocessor Systems , 2009, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[10]  Marcello Mura,et al.  Semi-automated Hw/Sw Co-design for embedded systems: from MARTE models to SystemC simulators , 2009, 2009 Forum on Specification & Design Languages (FDL).