Evaluation of static and dynamic task mapping algorithms in NoC-based MPSoCs

Task mapping is an important issue in MPSoC design. Most recent mapping algorithms perform them at design time, an approach known as static mapping. Nonetheless, applications running in MPSoCs may execute a varying number of simultaneous tasks. In some cases, applications may be defined only after system design, enforcing a scenario that requires the use of dynamic task mapping. Static mappings have as main advantage the global view of the system, while dynamic mappings normally provide a local view, which considers only the neighborhood of the mapping task. This work aims to evaluate the pros and cons of static and dynamic mapping solutions. Due to the global system view, it is expected that static mapping algorithms achieve superior performance (w.r.t. latency, congestion, energy consumption). As dynamic scenarios are a trend in present MPSoC designs, the cost of dynamic mapping algorithms must be known, and directions to improve the quality of such algorithms should be provided without increasing execution time. This quantitative comparison between static and dynamic mapping algorithms is the main contribution of this work.

[1]  G.J.M. Smit,et al.  Run-time Mapping of Applications to a Heterogeneous SoC , 2005, 2005 International Symposium on System-on-Chip.

[2]  Ewerson Carvalho,et al.  Investigating runtime task mapping for NoC-based multiprocessor SoCs , 2009, 2009 17th IFIP International Conference on Very Large Scale Integration (VLSI-SoC).

[3]  E. Carvalho,et al.  Congestion-aware task mapping in heterogeneous MPSoCs , 2008, 2008 International Symposium on System-on-Chip.

[4]  Radu Marculescu,et al.  User-Aware Dynamic Task Allocation in Networks-on-Chip , 2008, 2008 Design, Automation and Test in Europe.

[5]  Petru Eles,et al.  Scheduling and mapping of conditional task graphs for the synthesis of low power embedded systems , 2003, 2003 Design, Automation and Test in Europe Conference and Exhibition.

[6]  Timo Hämäläinen,et al.  Automated memory-aware application distribution for Multi-processor System-on-Chips , 2007, J. Syst. Archit..

[7]  Petru Eles,et al.  Fault and energy-aware communication mapping with guaranteed latency for applications implemented on NoC , 2005, Proceedings. 42nd Design Automation Conference, 2005..

[8]  Jörg Henkel,et al.  ADAM: Run-time agent-based distributed application mapping for on-chip communication , 2008, 2008 45th ACM/IEEE Design Automation Conference.

[9]  Ahmad Khademzadeh,et al.  DSM: A Heuristic Dynamic Spiral Mapping algorithm for network on chip , 2008, IEICE Electron. Express.

[10]  Fernando Gehm Moraes,et al.  HERMES: an infrastructure for low area overhead packet-switching networks on chip , 2004, Integr..

[11]  Altamiro Amadeu Susin,et al.  A contextual resources use: a proof of concept through the APACHES' platform , 2006, 2006 IEEE Design and Diagnostics of Electronic Circuits and systems.

[12]  Shashi Kumar,et al.  Algorithms and tools for network on chip based system design , 2003, 16th Symposium on Integrated Circuits and Systems Design, 2003. SBCCI 2003. Proceedings..

[13]  Radu Marculescu,et al.  Energy- and performance-aware mapping for regular NoC architectures , 2005, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[14]  Srinivasan Murali,et al.  A Methodology for Mapping Multiple Use-Cases onto Networks on Chips , 2006, Proceedings of the Design Automation & Test in Europe Conference.

[15]  Fernando Gehm Moraes,et al.  Comparison of network-on-chip mapping algorithms targeting low energy consumption , 2008, IET Comput. Digit. Tech..