隨著行動運算時代來臨，越來越多複雜的應用程式需要被使用，因此嵌入式系統效能的提升已經變成現代科技產業最重要的問題。處理器和嵌入式作業系統是兩個影響嵌入式系統效能的最主要的原因，由於半導體製程技術的進步，提升處理器的速度是目前提升嵌入式系統效能最普遍的方式，但是當時脈達到一定程度時會衍生出能量消耗以及散熱等問題，基本上單顆處理器的效能已經達到極致，因此單晶片多核心處理器已經成為新一代設計主流趨勢，然而嵌入式作業系統也會對嵌入式系統的效能造成巨大影響，傳統的嵌入式作業系統是用軟體方式實現，傳統提升嵌入式作業系統的效能都是透過更快速的演算法和更有效率的資料結構，但是透過軟體的方式去提升效能始終還是會有極限，或一昧的提升處理器速度但卻忽略處理器和作業系統間密不可分的關係也很難得到最佳的效能，因此我們認為要有效提升整體嵌入式系統的效能勢必要將處理器和作業系統共同設計。我們提出多核心嵌入式運算平台，此平台透過處理器和硬體作業相互配合，達成硬體內文切換、硬體排程、硬體信號機制、硬體系統呼叫來提升整體嵌入式系統的效能。最後實驗的結果顯示多核心嵌入式運算平台確實可以有效提升嵌入式系統的效能。

With the mobile computing coming, application is becoming more and more complex. Improving embedded system performance is critical issue in modern technology industry. Because of advanced semiconductor manufacturing technology, the common way to improve the embedded system performance is improving the performance of processor. However the performance of embedded operating system has strong influence on embedded system performance. To get more performance of embedded system it is necessary that operating system CPU co-design. We propose a Multi-core Embedded Computation Platform (MECP). MECP improve the performance of embedded system through hardware context switch, hardware scheduling, hardware semaphore and hardware system call. The experimental show that MECP cad substantially improve embedded system performance.

[1] Raffaello D'Andrea, “The astounding athletic power of quadcopters”, https://www.ted.com/talks/raffaello_d_andrea_the_astounding_athletic_power_of_quadcopters 2013
[2] STMicroelectronics, “STM32F4DISCOVERY Datasheet”, http://www.st.com/stonline/stappl/resourceSelector/app?page=fullResourceSelector&doctype=datasheet&LineID=1806
[3] FreeRTOS Labs, “Free Real-Time Operating System”, http://www.freertos.org/index.html
[4] Intel, “MCS-51 MICROCONTROLLER FAMILY USER’S MANUAL”, http://datasheets.chipdb.org/Intel/MCS51/MANUALS/27238302.PDF
[5] ARM, “Cortex-A Series”, http://www.arm.com/products/processors/cortex-a/
[6] Qing Li Caroline Yao, “Real-Time Concepts for Embedded Systems”, CMP Books 2003
[7] JEAN J. LABROSSE, “MicroC/OS-II: Thre Real-Time Kernel Second Edition”, CMP Books 2002
[8] Hammond, L., Hubbert, B., Siu, M., Prabhu, M. K., Chen, M., & Olukolun, K. "The Stanford hydra cmp". Micro, IEEE, 20(2), 71-84, 2000.
[9] David A. Patterson, John L. Henness, “Computer Organization and Design: The Hardware/Software Interface 5th”, MORGAN KAUFMANN PUBLISHERS
[10] David A. Patterson, John L. Henness, “Computer Architecture A Quantitative Approach 5th”, MORGAN KAUFMANN PUBLISHERS
[11] Sanggyu Park, Do-sun Hong and Soo-Ik chae, “A hardware operating system kernel for multi-processor systems”, IEICE Electronics Express Vol. 5 (2008) No. 9 P 296-302
[12] Panit Watcharawitch, “MulTEP: A MultiThreaded Embedded Processor”, Doctoral Dissertation 2010 University of Cambridge
[13] Jason M. Agron, “Hardware Microkernels - A Novel Method for Constructing Operating Systems for Heterogeneous Multi-Core Platforms”, Doctoral Dissertation 2010 University of Arkansas
[14] Xilinx, “MicroBlaze Processor Reference Guide”, http://www.xilinx.com/support/documentation/sw_manuals/mb_ref_guide.pdf
[15] Soon Ee Ong, Siaw Chen Lee, “SEOS: Hardware Implementation of Real-Time Operating System for Adaptability”, Computing and Networking (CANDAR), 2013 First International Symposium
[16] L. SaWALHA, m. p. Tull and R. D. Barnes, “Hardware theread-context switching”, ELECTRONICS LETTERS 14th March 2013 Vol. 49 No. 6
[17] Terasic, “DE2i-150 FPGA Development Kit ”, http://www.terasic.com.tw/cgi-bin/page/archive.pl?Language=English&CategoryNo=11&No=529
[18] Intel, “Intel® Atom™ Processor N270”, http://ark.intel.com/products/36331/Intel-Atom-Processor-N270-512K-Cache-1_60-GHz-533-MHz-FSB
[19] Atera, “Cyclone IV Device Handbook”, Altrea Corporation November 2011
[20] STMicroelectronics, “STM32F429 Datasheet”, http://www.st.com/stonline/stappl/resourceSelector/app?page=fullResourceSelector&doctype=datasheet&LineID=1806
[21] ARM, “Cortex-M Series”, http://www.arm.com/products/processors/cortex-m/
[22] 藍楓葉, “自己動手寫嵌入式操作系統”, 文魁資訊 電子工業出版社