在現代系統越來越強調大量運算、多媒體的整合和穩固的通訊功能，單核心處理器已不敷需求。目前普遍的解決方法是透過多顆核心處理器來滿足大量運算的需求，而多顆核心處理器的使用也越來越普遍。在多核心中，尤其是異質型的多核心處理器更為熱門，因為把不同的工作適當分配給異質型處理器中不同類型的處理器可以達到更好的處理器利用度。不只是在個人電腦，在嵌入式系統中，多顆核心處理器也越來越受歡迎，其低功率、低耗能和高效能更為符合嵌入式系統的需求。所以在目前多核心的研究中，如何有效的利用每顆處理器變成一個熱門的議題。在此篇論文中，我們在多核心中搭載了多個核心 (MicroC/OS-II)，並且實作了核心間的行程搬移機制(migration mechanism)，打破了MicroC/OS-II常有的在不同核心中應用程式之不可分享性，使得各個核心中的應用程式可以互相分享執行。並在最後，我們實作了一套排程的政策(scheduling policy)來驗證我們的行程搬移機制的有效性並且評估了此政策對整個系統效能的提升。並且在實驗中我們評估的結果可以使系統效率提升19%。

Today, computer systems need high computing power, multimedia integration and reliable communication functionality. Single processor may not satisfy these requirements. In general, the solution is using multi-processors to overcome these requirements. Especially, heterogeneous processors are more popular on multi-core, because system can dispatch suitable process to suitable processor for high processor utilization. Not only to personal computers but also the requirements of embedded system multi-processors provide low power consumption and high performance. Now, how to increase processors utilization becomes an important issue. In this paper, we implement a multi-kernel system on a multiprocessors environment, and in order to alleviate the system load we ported kernels (MicroC/OS-II) in our system. We implement process migration mechanism, based on this mechanism we can perform process migration between kernels, so we break the constraint of applications sharing between kernels. Finally, we implement a global scheduling policy to verify the process migration mechanism. Basing the policy, we also evaluate the system performance, and in our experiment the system performance can almost be raised up to 19%.

[1] E. Carvalho, et al., "Heuristics for Dynamic Task Mapping in NoC-based Heterogeneous MPSoCs," in Rapid System Prototyping, 2007. RSP 2007. 18th IEEE/IFIP International Workshop on, 2007, pp. 34-40.
[2] E. Carvalho and F. Moraes, "Congestion-aware task mapping in heterogeneous MPSoCs," in System-on-Chip, 2008. SOC 2008. International Symposium on, 2008, pp. 1-4.
[3] M. Kim, et al., "Energy-aware cosynthesis of real-time multimedia applications on MPSoCs using heterogeneous scheduling policies," ACM Trans. Embed. Comput. Syst., vol. 7, pp. 1-19, 2008.
[4] V. Nollet, et al., "Low Cost Task Migration Initiation in a Heterogeneous MP-SoC," presented at the Proceedings of the conference on Design, Automation and Test in Europe - Volume 1, 2005.
[5] P. K. F. H, et al., "Run-time spatial mapping of streaming applications to a heterogeneous multi-processor system-on-chip (MPSoC)," presented at the Proceedings of the conference on Design, automation and test in Europe, Munich, Germany, 2008.
[6] S. Bertozzi, et al., "Supporting task migration in multi-processor systems-on-chip: a feasibility study," presented at the Proceedings of the conference on Design, automation and test in Europe: Proceedings, Munich, Germany, 2006.
[7] A. Jerraya, et al., "Guest Editors' Introduction: Multiprocessor Systems-on-Chips," Computer, vol. 38, pp. 36-40, 2005.
[8] C.-L. Chou and R. Marculescu, "Incremental run-time application mapping for homogeneous NoCs with multiple voltage levels," presented at the Proceedings of the 5th IEEE/ACM international conference on Hardware/software codesign and system synthesis, Salzburg, Austria, 2007.
[9] G. Koren, et al., "The power of migration in multi-processor scheduling of real-time systems," presented at the Proceedings of the ninth annual ACM-SIAM symposium on Discrete algorithms, San Francisco, California, United States, 1998.
[10] A. A. Andrea Acquaviva, Salvatore Carta, andMichele Pittau, "Assessing task migration impact on embedded soft real-time streaming multimedia applications," EURASIP J. Embedded Syst., vol. 2008, pp. 1-15, 2008.
[11] J. Castrillon, et al., "Task management in MPSoCs: an ASIP approach," presented at the Proceedings of the 2009 International Conference on Computer-Aided Design, San Jose, California, 2009.
[12] T. D. Braak ter, et al., "Run-time Spatial Resource Management for Real-Time Applications on Heterogeneous MPSoCs," presented at the Conference on Design, Automation and Test in Europe, DATE 2010, Dresden, Germany, 2010.
[13] A. K. Coskun, et al., "Temperature-aware MPSoC scheduling for reducing hot spots and gradients," presented at the Proceedings of the 2008 Asia and South Pacific Design Automation Conference, Seoul, Korea, 2008.
[14] T. Chantem, et al., "Temperature-aware scheduling and assignment for hard real-time applications on MPSoCs," presented at the Proceedings of the conference on Design, automation and test in Europe, Munich, Germany, 2008.
[15] N. Saint-Jean, et al., "MPI-Based Adaptive Task Migration Support on the HS-Scale System," in Symposium on VLSI, 2008. ISVLSI '08. IEEE Computer Society Annual, 2008, pp. 105-110.
[16] P. Bergheaud, et al., "Fault Tolerance in Multiprocessor Systems Via Application Cloning," presented at the Proceedings of the 27th International Conference on Distributed Computing Systems, 2007.
[17] M. S. Squillante and R. D. Nelson, "Analysis of task migration in shared-memory multiprocessor scheduling," SIGMETRICS Perform. Eval. Rev., vol. 19, pp. 143-155, 1991.
[18] D. Barcelos, et al., "A hybrid memory organization to enhance task migration and dynamic task allocation in NoC-based MPSoCs," presented at the Proceedings of the 20th annual conference on Integrated circuits and systems design, Copacabana, Rio de Janeiro, 2007.
[19] L. Friebe, et al., "HiBRID-SoC: a system-on-chip architecture with two multimedia DSPs and a RISC core," in SOC Conference, 2003. Proceedings. IEEE International [Systems-on-Chip], 2003, pp. 85-88.
[20] P. van der Wolf, et al., "Design and programming of embedded multiprocessors: an interface-centric approach," in Hardware/Software Codesign and System Synthesis, 2004. CODES + ISSS 2004. International Conference on, 2004, pp. 206-217.
[21] B. Andersson, et al., "Partitioned aperiodic scheduling on multiprocessors," in Parallel and Distributed Processing Symposium, 2003. Proceedings. International, 2003, p. 16 pp.
[22] G. Nan, et al., "Schedulability Analysis of Global Fixed-Priority or EDF Multiprocessor Scheduling with Symbolic Model-Checking," in Object Oriented Real-Time Distributed Computing (ISORC), 2008 11th IEEE International Symposium on, 2008, pp. 556-560.
[23] M. Bertogna, et al., "Schedulability Analysis of Global Scheduling Algorithms on Multiprocessor Platforms," Parallel and Distributed Systems, IEEE Transactions on, vol. 20, pp. 553-566, 2009.
[24] F. COTTET, DELACROIX,J.,KAISERC.,andMAMMERI,Z., "Scheduling in Real-Time Systems: A course with exercises and solutions.," 2002.
[25] J. W. S. Liu, "Real-Time Systems," 2000.
[26] Q. Li and C. Yao, Real-Time Concepts for Embedded Systems: CMP Books, 2003.
[27] J. Labrosse., " MicroC/OS-II: The Real-Time Kernel.," 1999.
[28] M. J. Flynn, "Some Computer Organizations and Their Effectiveness," Computers, IEEE Transactions on, vol. C-21, pp. 948-960, 1972.
[29] http://en.wikipedia.org/wiki/MIMD.
[30] http://en.wikipedia.org/wiki/Heterogeneous_computing.