臺灣博碩士論文加值系統

隨著科技的發展，硬體工作可以在動態被更改設定。具有可重組邏輯裝置的系統裡面包含著複雜的軟硬體工作。為了其他硬體工作的使用，在可重組邏輯中閒置的硬體工作應當透過一個工作切換的機制被取代掉。對於緊急工作效率的加強，較低優先權的硬體工作必須被切換。所以，有限的系統資源的有效使用在可組邏輯裝置是一個重要的目的。再者，一個在運算中從可重組邏輯被切換的工作可以透過一個工作重新配置機制被允釵b處理器上去繼續它未完成的工作。為了系統資源的有效使用，工作切換以及重新配置的機制在這個著作中被提出。在工作切換和重新配置的過程中，包含可切換點的選擇、正確溝通的維護以及內容資料的傳送等三個議題必須要解決。為了達到工作的搶先，工作的可切換點必須決定出來。一個可切換點指出何時一個工作準備好要切換或者重新配置。當一個工作到達切換點的時候，它的內容資料包含資料以及狀態必須被存到記憶體中或是傳送給要取代原有工作的新工作。設計硬體工作和軟體工作的方法被提出來以便允釣洏峈怚h整合他們的設計到一個具有工作切換以及重新配置機制的系統上。樣板函式實作被提出和實作以便允酗u作去儲存/回復他們的資料內容。為了正確的執行，工作切換以及重新配置的控制流程也保證在切換或重新配置後工作溝通關係的正確性和一貫性。最後，一些實作的例子被提出來證明這個機制的正確性。以一個不在作業系統上跑的求最大公因數的例子而言，軟體工作切換佔據軟體總執行時間的2%，然而硬體工作切換佔據硬體總執行時間的23%。考量到工作重新配置，軟體到硬體的重新配置佔據總執行時間的3%，而硬體到軟體的重新配置佔據總執行時間的5%。軟體工作切換和硬體工作切換時間上的大差異是因為內容資料的傳送和硬體驅動程序的執行時間。

With technology development, hardware tasks can be configured at run-time. Systems with a reconfigurable logic device include complex hardware and software tasks. Idle hardware tasks in a reconfigurable logic should be replaced by other hardware tasks through a task switching mechanism. Hardware tasks with lower priority should be switched for urgent hardware tasks to enhance performance. Hence, the efficient use of limited system resources in reconfigurable logic devices is an important goal. Furthermore, a task switched from a reconfigurable logic in the middle of computation could be allowed to continue its unfinished work on a processor through a task relocation mechanism. For the efficient use of system resources, task switching and relocation mechanism are proposed in this work. During task switching and relocation, three issues including the choice of switchable points, the maintenance of correct transparent communication, and the transfer of context data need to be solved. For task preemption, switchable points in a task have to be determined. A switchable point indicates when a task is ready for task switching or relocation. When a task reaches a switchable point, the context data including data and state information need to be stored in the memory or transferred to a new task replacing the original one. The methods for designing both hardware tasks and software tasks are proposed so as to allow users to integrate their designs into a system with task switching and relocation. Template functions are proposed and implemented to allow tasks to save/restore their context data. The control flows of task switching and relocation also guarantee the correctness and consistency of task communication relations after switching or relocation. Finally, several implementation examples are provided to prove the correctness of the proposed mechanism. For the GCD example without an operating system, software task switching takes 2% of the total software execution time, while hardware task switching takes 23% of the total hardware execution time. As far as task relocation is concerned, the software to hardware relocation takes 3% of the total execution time, while the hardware to software relocation takes 5% of the total execution time. The high difference in software and hardware task switching time is due to the latency incurred by the context data transfer and the execution of the hardware driver process.

1 Introduction
1.1 Target
1.2 Motivation
1.3 Thesis Organization
2 PreviousWork
2.1 Software-to-Software Task Relocation
2.2 Hardware-to-Hardware Task Relocation
2.3 Software-to-Hardware Task Relocation
3 System Architecture and Issues
3.1 System Architecture
3.2 Task Allocation Flow
3.3 Hardware Configuration Time
3.4 Issues
4 Task Switching and Relocation Mechanism
4.1 Modifying User Designs
4.1.1 Switchable Hardware
4.1.2 Switchable Software
4.1.3 Context Data Transfer
4.2 Task Switching and Relocation
4.3 Task Design Flows
5 Implementation Examples
5.1 Example: Greatest Common Divisor
6 Conclusion and FutureWork

[1] A. Baumann, J. Appavoo, D. Silva, O. Krieger, and R. Wisniewski. Improving operating system availability with dynamic update. In Proceedings of the 1st Workshop on Operating System and Architectural Support for the On-Demand IT Infrastructure, pages 21–27. Operating System and Architectural Support for the on demand IT InfraStructure (OASIS), October 2004.
[2] A. Baumann, G. Heiser, J. Appavoo, D. Da Silva, O. Krieger, R. W. Wisniewski, and J. Kerr. Providing Dynamic Update in an Operating System. In Proceedings of the 2005 USENIX Technical Conference, pages 279–291. USENIX Association, April 2005.
[3] A. Baumann, J. Kerr, J. Appavoo, D. D. Silva, O. Krieger, and R. W. Wisniewski. Module hot-swapping for dynamic update and reconfiguration in K42. In Proceedings of the 6th Linux.Conf.Au, April 2005.
[4] C.-H. Huang, S.-S. Chang, and P.-A. Hsiung. Generic Wrapper Design for Dynamic Swappable Hardware IP in Partially Reconfigurable Systems. International Journal of Electrical Engineering, 14(3):229–238, June 2007.
[5] K. Hui, J. Appavoo, R. W. Wisniewski, M. A. Auslander, D. Edelsohn, B. Gamsa, O. Krieger, B. S. Rosenburg, and M. Stumm. Supporting Hot-Swappable Components for System Software. In HOTOS ’01: Proceedings of the Eighth Workshop on Hot Topics in Operating Systems, page 170, May 2001.
[6] H. Kalte and M. Porrmann. Context Saving and Restoring for Multitasking in Reconfigurable Systems. In Proceedings of the 2005 International Conference on Field Programmable Logic and Applications (FPL), pages 223–228, August 2005.
[7] O. Krieger, M. Auslander, B. Rosenburg, R. W. Wisniewski, J. Xenidis, D. D. Silva, M. Ostrowski, J. Appavoo, M. Butrico, M. Mergen, A.Waterland, and V. Uhlig. K42: building a complete operating system. SIGOPS Oper. Syst. Rev., 40(4):133–145, April 2006.
[8] L. Levinson, R. M¨anner, M. Sessler, and H. Simmler. Preemptive Multitasking on FPGAs. In Proceedings of the IEEE Symposium on Field-Programmable Custom Computing Machines, pages 301–302. IEEE Computer Society, April 2000.
[9] J-Y. Mignolet, V. Nollet, P. Coene, D. Verkest, S. Vernalde, and R. Lauwereins. Infrastructure for Design and Management of Relocatable Tasks in a Heterogeneous Reconfigurable System-on-Chip. In Proceedings of the Conference on Design, Automation and Test in Europe, pages 10986–10993. IEEE Computer Society, 2003.
[10] R. Pellizzoni and M. Caccamo. Adaptive Allocation of Software and Hardware Real-Time Tasks for FPGA-based Embedded Systems. In Proceedings of the 12th IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS’06), pages 208–220. IEEE Computer Society, April 2006.
[11] J. Resano and D. Mozos. Specific scheduling support to minimize the reconfiguration overhead of dynamically reconfigurable hardware. In Proceedings of the 41st Design Automation Conference (DAC), pages 119–124. ACM Press, June 2004.
[12] D. D. Silva, O. Krieger, R. W. Wisniewski, A. Waterland, D. Tam, and A. Baumann. K42: an infrastructure for operating system research. SIGOPS Oper. Syst. Rev., 40(2):34–42, April 2006.
[13] H. Simmler, L. Levinson, and R. M¨anner. Multitasking on FPGA Coprocessors. In FPL ’00: Proceedings of the The Roadmap to Reconfigurable Computing, 10th International Workshop on Field-Programmable Logic and Applications, pages 121–130, London, UK, August 2000. Springer-Verlag.
[14] C. A. N. Soules, J. Appavoo, K. Hui, R. W. Wisniewski, D. D. Silva, G. R. Ganger, O. Krieger, M. Stumm, M. Auslander, M. Ostrowski, B. Rosenburg, and J. Xenidis. System Support for Online Reconfiguration. In Proceedings of the Usenix Technical Conference, pages 141–154, June 2003.
[15] M. Ullmann, M. H¨ubner, B. Grimm, and J. Becker. An FPGA Run-Time System for Dynamical On-Demand Reconfiguration. In Proceedings of the 18th International Parallel and Distributed Processing Symposium, page 135a. IEEE Computer Society, April 2004.
[16] G. Vanmeerbeeck, P. Schaumont, S. Vernalde, M. Engels, and I. Bolsens. Hardware/software partitioning of embedded system in OCAPI-xl. In Proceedings of the Ninth International Symposium on Hardware/software Codesign, pages 30–35. ACM Press, April 2001.
[17] P. J. Waldeck and N. W. Bergmann. Hardware support for real-time reconfigurable system-on-chip. In Proceedings of the Society of Photo-Optical Instrumentation Engineers (SPIE), volume 5274, pages 464–469. Society of Photo-Optical Instrumentation Engineers, March 2004.