簡易檢索 / 詳目顯示

回結果列表
研究生： 方晟軒
Fung, Chen-Xuan
論文名稱： 基於匹配演算之電腦輔助元件挑選最佳化
Matching-Based Component Selection for Computer-Aided Optimization of Embedded Systems
指導教授： 周百祥
Chou, Pai H.
口試委員: 韓永楷
Hon, Wing-Kai
周志遠
Chou, Jerry
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 資訊工程學系
Computer Science
論文出版年： 2020
畢業學年度： 108
語文別： 英文
論文頁數： 42
中文關鍵詞： 匹配 、元件選擇 、嵌入式系統 、電腦輔助設計 、電子設計自動化
外文關鍵詞： Matching, Component selection, Embedded system, Computer-aided design, electronic design automation
相關次數： 點閱：2  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 嵌入式系統設計最佳化的關鍵之一，在於挑選出最能符合應用需求的一組元件，而非皆由韌體或客製化電路來實作所有功能。 近年來物聯網的蓬勃發展，帶動了廠商大筆投入開發新型元件，以前所未見的速度推出功能豐富、高效能又廉價的產品。即使經驗豐富的設計師也難以對如此大量的元件有深入的認識，導致無法將它們套用於最新的設計專案中。 如此採用過時的元件設計出來的次級系統，往往浪費人力在重複自行實作一些新一代元件已提供 且已最佳化的功能。
    為了解決上述問題，我們提出一套電腦輔助元件挑選最佳化的演算法，基於匹配方式先篩選出功能符合需求的元件，再針對每個元件存取介面上的限制，找出相容的匹配方式，結合設計目標、規格與偏好，向設計師推薦多種可行的方案。實驗結果顯示，我們的匹配方法可以找到一些設計師不易察覺的組合，讓系統可以更創新、有效率且順暢的運作。

    A key approach to optimization of embedded systems is the selection of off-the-shelf components that best match the required features, rather than implementing such features as firmware or custom logic. The explosive growth in the Internet of Things (IoT) has driven the development of many new feature-rich, highly optimized components to market at unprecedented rates, faster than many designers can learn about them. Moreover, due to the increasing complexity of these highly integrated components, it is nearly impossible for most designers to fully understand and take advantage of the available features in them. As a result, they choose components that achieve suboptimal designs at best, and often designers unnecessarily reimplement many features already available in existing components. To address this problem, we propose an algorithm for identifying components that can fulfill the required functions by feature matching and estimating the communication cost. Experimental results show that our matching approach to be able to identify novel combinations of components to aid interactive optimization of embedded hardware designs.

    Acknowledgments v 1 Introduction 1 1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 Contributions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 1.3 Thesis Organization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 2 Related Work 5 2.1 Synthesis-Based Primitive Selection . . . . . . . . . . . . . . . . . . . . . . . . . . 5 2.2 Interface Selection . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 3 Methodology 8 3.1 Sysmaker Framework . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 3.1.1 Diagramming . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 3.1.2 Refinement and Abstraction . . . . . . . . . . . . . . . . . . . . . . . . . . 9 3.1.3 Design Space Exploration . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 3.1.4 Design Elaboration . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 3.1.5 Other Tools . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 3.2 Features . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 3.3 Interface Synthesis Procedure . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 3.4 Component Library . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 4 Formulation 14 4.1 Problem Statement . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 4.2 Bipartite Matching . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 4.3 Access Protocols . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 4.4 Flow Network . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 4.4.1 Vertices . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 4.4.2 OR . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 4.4.3 AND . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 4.4.4 Capacity Constraints . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 5 Technical Approach 21 5.1 Candidate Component Nomination . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 5.1.1 The Input of Candidate Component Nomination Algorithm . . . . . . . . . . 21 5.1.2 The Output of Candidate Component Nomination Algorithm . . . . . . . . . 22 5.1.3 Matching Algorithm . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23 5.1.4 Example of Algorithm . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24 5.2 Access Interface Resolution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24 5.2.1 Input of Access Interface Resolution . . . . . . . . . . . . . . . . . . . . . . 26 5.2.2 Output of Access Interface Resolution . . . . . . . . . . . . . . . . . . . . . 27 5.2.3 Enumerate all paths by Permutation . . . . . . . . . . . . . . . . . . . . . . 28 5.2.4 Enumerate All Maximum Flows . . . . . . . . . . . . . . . . . . . . . . . . 31 6 Evaluation 35 6.1 Case Study . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35 6.1.1 Separate 9-axis sensor . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35 6.1.2 Add Analog-to-digital converter . . . . . . . . . . . . . . . . . . . . . . . . 37 7 Conclusions and Future Work 39 7.1 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39 7.2 Future Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40 Acronyms 42

    [1]H. Chen, S. Meenakshi, A. HeydatiGorji, S. M. Safavi, P. H. Chou, C.-T. Lee, and R.-K. Chang, “Bluebox: A complete recorder for code-blue events in hospitals,” in 2019 International Sym-posium on VLSI Design, Automation and Test (VLSI-DAT), pp. 1–4, IEEE, IEEE, 2019.
    [2]F. P. Armin Ronacher, “Twig.” https://twig.symfony.com/, 2009.
    [3]R. A. Bergamaschi, “Behavioral network graph unifying the domains of high-level and logic synthesis,” 1999.
    [4]R. Namballa, N. Ranganathan, and A. Ejnioui, “Control and data flow graph extraction for high-level synthesis,” 2004.
    [5]Q. Wu, Y. Wang, J. Bian, W. Wu, and H. Xue, “A hierarchical cdfg as intermediate representation for hardware/software codesign,” 2002.
    [6]J. Shu, T. C. Wilson, and D. K. Banerji, “Instruction-set matching and ga-based selection for embedded-processor code generation,” 1996.
    [7]P. J. Hatcher and J. Tuller, “Efficient retargetable compiler code generation,” 1988.
    [8]T. Ziermann, N. Mühleis, S. Wildermann, and J. Teich, “A self-organizing distributed reinforce-ment learning algorithm to achieve fair bandwidth allocation for priority-based bus communi-cation,” in 2010 13th IEEE International Symposium on Object/Component/Service-Oriented Real-Time Distributed Computing Workshops, pp. 11–20, IEEE, 2010.
    [9]S. Sugimoto, T. Hattori, T. Izumi, and H. Kawano, “Fast kansei matching method as an algorithm for the solution of extended stable marriage problem,” 2009.
    [10]J. Edmonds and R. M. Karp, “Theoretical improvements in algorithmic efficiency for network flow problems,” 1972.

    QR CODE