在此論文中，我們改進一個系統行為層級模擬環境，使之得以快速評估應用 程式在不同系統結構上的效能以及記憶體系統功率資訊。模擬速度上，比起精確 的週期指令集模擬器 ARM SoC Designer，抽象化應用程式行為與硬體結構作系統 層級的模擬有速度上的優勢，平均約有 15 至 25 倍的提升；但是誤差也會隨著硬 體架構的複雜化提升，雙核心架構的誤差約達 8.16%，四核心則為 11.78%，雖有 些微提升，但仍在可作為參考的範圍之內，這是未來可以探討改進的空間。
另外在功率方面，我們提供函數層級的記憶體系統功率模型與能量相關資訊，
並將應用程式裡各函數對記憶體系統的功率值建成功率函數資料庫，在效能模擬 的同時，估量應用程式對記憶體系統的功率與耗能，並且評估其誤差，測試的應 用程式誤差大約皆低於 6%，可見功率函數資料庫的可用性，
未來，隨著硬體結構的複雜化，軟體程式的多樣化，系統層級的行為模擬挑 戰性也日趨上升。例如雙核心與四核心甚至更多核心的行為比起單核心的結構，
必定多出許多溝通以及資源分享，包括之前提過的仲裁方針、資料一致性的協議 等。因此，後續研究的重點是將這些複雜的資訊抽象化，設計出更多的軟體及硬 體模組加入目前的模擬環境，改善其誤差率，提高可伸縮性（Scalability），提供更 穩定且可信的模擬環境將是未來展望之一。
其次，功率的部份在本文中討論了記憶體系統部分，尚未提供處理器以及匯 流排等相關資訊，未來可將系統其他元件考量入模擬環境中，提供設計者更全面 的參考，做更多研究的應用，例如根據 SoC 中各元件所需的功率做最合適的區塊 劃分，達到節省成本及能耗的作用等。此外，將函數功率資料庫擴充至微作業系 統（Micro-OS）或是更多的應用程式也是未來展望之ㄧ，上述實驗可以得知函數 功率資料庫的可用性，若應用至嵌入式系統中的作業系統，提供核心中系統呼叫 及標準函式庫等的功率資訊，可以進而了解作業系統對於功率及能耗的需求，對
軟體層面所帶來的功耗影響做更近一步的分析及研究。
參考文獻
[1] Kunle, O., Basem, A.N., Lance, H., Ken, W., and Kunyung, C., "The Case for a Single-Chip Multiprocessor", Proc. 7th International Symposium on
Architectural Supportfor Programming Languages and Operating Systems,
vol. 31, no. 9, 1996.[2] Jose, R., Karin, S., Luis, C., Wei, L., Smruti, S., James, T., and Josep, T.,
"Thread-Level Speculation on a Cmp Can Be Energy Efficient", in
Proceedings of the 19th annual international conference on Supercomputing,
2005[3] Sungjoo, Y., Iuliana, B., Aimen, B., Yanick, P., and Ahmed, A.J., "Building Fast and Accurate Sw Simulation Models Based on Hardware Abstraction Layer and Simulation Environment Abstraction Layer", in Proceedings of the
conference on Design, Automation and Test in Europe - Volume 1, 2003
[4] In-Cheol, P., Sehyeon, K., and Yongseok, Y., "Fast Cycle-Accurate Behavioral Simulation for Pipelined Processors Using Early Pipeline Evaluation", in
Proceedings of the 2003 IEEE/ACM international conference on
Computer-aided design, 2003
[5] A.Snavely, L.Carrington, and Wolter, N., "Modeling Application Performance by Convolving Machine Signatures with Application Profiles", Proc. IEEE
Workshop on Workload Characterization, 2001.
[6] M.Mahoney, and T.Elrad, "Modeling Platform Specific Attributes of a System as Crosscutting Concerns Using Aspect-Oriented Statecharts and Virtual Finite State Machines", the 6th International Workshop on Aspect-Oriented
Modeling as part of AOSD05 Chicago,USA, 2005.
[7] "Simplescalar"
http://www.simplescalar.com/
[8] "Rsim"
http://rsim.cs.uiuc.edu/rsim/dist.html
[9] Magnusson, P.S., Christensson, M., Eskilson, J., Forsgren, D., Hallberg, G., Hogberg, J., Larsson, F., Moestedt, A., and Werner, B., "Simics: A Full System Simulation Platform", Computer, vol. 35, no. 2, 2002.
[10] "SystemC"
http://www.systemc.org/home
[11] Chang, H.W., A Rapid Simulation Environment for Application Performance
Estimation on Parameterized Multi-Core/Multi-Threading Architecture Models(2007)
[12] Enrico, M., Massoud, P., and Fabio, S., "High-Level Power Modeling, Estimation, and Optimization", in Proceedings of the 34th annual conference
on Design automation, 1997
[13] Paul, L., "High-Level Power Estimation", in Proceedings of the 1996
international symposium on Low power electronics and design, 1996
[14] Tony, D.G., Frank, V., J, and rg, H., "Instruction-Based System-Level Power Evaluation of System-on-a-Chip Peripheral Cores", in Proceedings of the 13th
international symposium on System synthesis, 2000
[15] C. Talarico, J. W. Rozenblit, V. Malhotra, and Stritter, A., "A New Framework for Power Estimation of Embedded Systems", Computer, vol. 38, no. 2, 2005.
[16] David, B., Vivek, T., and Margaret, M., "Wattch: A Framework for
Architectural-Level Power Analysis and Optimizations", in Proceedings of the
27th annual international symposium on Computer architecture, 2000
[17] Ye, W., Vijaykrishnan, N., Kandemir, M., and Irwin, M.J., "The Design and
Use of Simplepower: A Cycle-Accurate Energy Estimation Tool", in
Proceedings of the 37th conference on Design automation, 2000
[18] "Sim-Panalyzer Project"
http://www.eecs.umich.edu/~panalyzer/
[19] Tan, T.K., Raghunathan, A.K., Lakishminarayana, G., and Jha, N.K.,
"High-Level Software Energy Macro-Modeling", in Proceedings of the 38th
conference on Design automation, 2001
[20] Tan, T.K., Raghunathan, A., and Jha, N.K., "Energy Macromodeling of Embedded Operating Systems", Trans. on Embedded Computing Sys., vol. 4, no. 1, 2005.
[21] Jinwen, X., Zhaohui, H., and Peixin, Z., "Energy Macro-Modeling of Embedded Microprocessor Using Systemc", in Electro Information
Technology, 2005 IEEE International Conference on, 2005, pp. 6 pp.
[22] "Intel Vtune Performance Analyzer"
http://www.intel.com/software/products/vtune.
[23] "Sun Dtrace"
http://www.sun.com/bigadmin/content/dtrace/
[24] "GNU gprof"
http://www.cs.utah.edu/dept/old/texinfo/as/gprof_toc.html
[25] "Valgrind"http://valgrind.org/
[26] "ARM SoC Designer"
http://www.arm.com/products/DevTools/RealViewSystemDevelopment.html
[27] "Mibench"
http://www.eecs.umich.edu/mibench/
[28] Kiran, P., Kyu-Won, C., Jun Cheol, P., Vincent J. Mooney, III, Abhijit, C., and Peeter, E., "System Level Power-Performance Trade-Offs in Embedded Systems Using Voltage and Frequency Scaling of Off-Chip Buses and
Memory", in Proceedings of the 15th international symposium on System
Synthesis, 2002
[29] David, W., Brinda, G., Nuengwong, T., Kathleen, B., Aamer, J., and Bruce, J.,
"Dramsim: A Memory System Simulator", SIGARCH Comput. Archit. News, vol. 33, no. 4, 2005.
[30] "Micron Technology, Inc"
http://www.micron.com/
[31] Gang, Q., Naoyuki, K., Kimiyoshi, U., and Miodrag, P., "Function-Level Power Estimation Methodology for Microprocessors", in Proceedings of the