臺灣博碩士論文加值系統

隨著目前行動多媒體系統越來越普及 , 在行動多媒體系統中電池壽命
成為相當重要的因素。 由於MPEG 影片對於效能需求的變動性 , 我們可以
有效的來利用閒置的處理時間以達到能量的節省。 本論文提出了一個針對
即時的影像解碼的極平順控制的機制。 我們利用極平順演算法來找出一個
合理並且越平順越好的排程來達到大量能量的節省。 我們也利用預測錯誤
累加器來減低output buffer overflow 與 underflow 的機會。 另外, 我們利
用兩級最接近的電壓/頻率等級來最佳化最佳平順控制在影像解碼中的效
能。 實驗結果顯示這個機制可以大量減少在影像解碼的能源消耗並且提供
即時特性保證與減少 output buffer overflow 與 underflow 的機會。

As mobile multimedia systems become more and more popular, battery life become critical factor in mobile multimedia system. Because of the variability of MPEG stream, we can achieve energy saving by fully utilizing the idle processing time. This paper introduces an aggressively smoothing control mechanism for on-line video decoding. We use the aggressively smoothing algorithm to find a flexible schedule that is as smooth as possible so as to achieve significant energy savings. We also use prediction error counter to decrease the opportunity of the output buffer overflow and underflow that is caused by prediction accuracy. We also exploit two closed discrete voltage/frequency level to maximize the performance of aggressively smoothing control in video decoding. Simulation results show that this mechanism significantly reduces energy for video decoding and also provides strong real-time guarantees
and prevents output buffer overflow.

1 Introduction 1
1.1 Motivation
1.2 Problems Definition
1.3 Thesis Organization
2 Background and Related Work
2.1 MPEG Decoding
2.2 Dynamic Voltage Scaling (DVS)
2.3 Related Work
2.3.1 Prediction-based DVS Approaches
2.3.2 Control Theorem Approaches
2.3.3 Miscellaneous DVS Approaches
3 Video Decoding with Aggressively Smoothing Control
3.1 System Architecture
3.1.1 The Original Architecture
3.1.2 Our System Architecture
3.2 Key Ideas of Aggressively Smoothing Control for MPEG Decoding
3.3 Frame Decoding Cycle Prediction
3.4 Aggressively Smoothing Control for MPEG Decoding
3.4.1 Problems Definition
3.4.2 The Aggressively Smoothing Algorithm
3.4.3 Problems of On-line Aggressively Smoothing Control and Solutions
4 Experiments
4.1 Experiment Environment
4.1.1 Simulation tool sets
4.1.2 Workload Video Streams
4.1.3 Power Model and DVS Overhead
4.2 Experiment Results
4.2.1 Comparison of various DVS schemes
4.2.2 Experiment results and discussions
5 Conclusion

[1] LongRun Technology from Transmeta. http://www.transmeta.com/crusoe/lowpower/longrun.html.
[2] Xvid Encoder and Decoder. http://www.xvid.org.
[3] T. D. Burd, T. A. Perimg, A. J. Stratakos, and R.W. Brodersen. A Dynamic Voltage Scaled Microprocessor System. In IEEE Journal of Solid-State Circuits, November 2000.
[4] Andy C.Bavier, A. Brady Montz, and Larry L. Peterson. Predicting MPEG Execution Times. In Proceedings of the 1998 ACM SIGMETRICS joint international conference on Measurement and Modeling of Computer Systems, pages 131–140, 1998.
[5] W. Chedid and C. Yu. Survey on Power Management Techniques for Energy Efficient Computer Systems. Laboratory Report, 2002.
[6] Kihwan Choi, Karthik Dantu, Wei-Chung Cheng, and Massoud Pedram. Frame-based dynamic voltage and frequency scaling for a MPEG decoder. In Proceedings of International Conference on Computer Aided Design, pages 32–37, November 2002.
[7] E. Chung, L. Benini, and G. D. Micheli. Contents providerassisted dynamic voltage scaling for low energy multimedia applications. In International Symposium on Low Power Electronics and Design, pages 42–47, August 2002.
[8] D.Burger and T. Austin. The Simplescalar Tool Set, Verison 2.0. Technical Report CS-TR-97-1342, University of Wisconsin, June 1997.
[9] James D.Salehi, Zhi-Li Zhang, James F. Kurose, and Don Towsley. Supporting Stored Video: Reducing Rate Variability and End-to-End Resource Requirements through Optimal Smoothing. In Proceedings of ACM SIGMETRICS joint international conference on Measurement and Modeling of Computer Systems, pages 222–231, May 1996.
[10] C. Im, H. Kim, and S. Ha. Dynamic voltage scheduling technique for low-power multimedia applications using buffers. In International Symposium on Low Power Electronics and Design, August 2001.
[11] CHAESEOK IM, SOONHOI HA, and HUISEOK KIM. Dynamic Voltage Scheduling
with Buffers in Low-Power Multimedia Applications. In ACM Transactions on Embedded Computing Systems, pages 686–705, November 2004.
[12] Chistopher J.Hughes, Jayanth Srinivasan, and Sarita V.Adve. Saving energy with architectural and frequency adaptations for multimedia applications. In Proceedings of the 34th International Symposium on Microarchitecture, December 2001.
[13] J.Mitchell and W. Pennebaker. MPEG Video Compression Standard. Chapman and
Hall, 1996.
[14] Y. Lu, L. Benini, and G. D. Micheli. Dynamic frequency scaling with buffer insertion for mixed workloads. In IEEE Transactions on computer-aided design of integrated circuits and systems, page 1284V1305, November 2002.
[15] Z. Lu, J. Hein, M. Humphrey, M. Stan, J. Lach, and K. Skadron. Control-theoretic dynamic frequency and voltage scaling for multimedia workloads. In Proceedings of the 2002 International Conferences on Compilers, Architecture, and Synthesis for Embedded Systems, page 156V163, October 2002.
[16] Zhijian Lu, John Lach, Mircea Stan, and Kevin Skadron. Reducing Multimedia Decode Power using Feedback Control. In Proceedings of the 2003 International Conference on Computer Design (ICCD), October 2003.
[17] Malena Mesarina and Yoshio Turner. A Comparative Study of Dynamic Voltage Scaling Techniques for Low-Power Video Decoding. In Proceedings of the International Conference on Embedded Systems and Applications, June 2003.
[18] Trevor Pering, Thomas Burd, and Robert Brodersen. Voltage Scheduling in the lpARM Microprocessor System. In International Symposium on Low Power Electronics and Design, 2000.
[19] J. Pouwelse, K. Langendoen, R. Lagendijk, and H. Sips. Power-Aware Video Decoding. In Picture Coding Symposium (PCS’01),, April 2001.
[20] Johan Pouwelse, Koen Langendoen, Inald Lagendijk, and Henk Sips. Power-Aware Video Decoding. In Picture Coding Symposium (PCS’01),, April 2001.
[21] Johan Pouwelse, Koen Langendoen, and Henk Sips. Dynamic Voltage Scaling on a Low-Power Microprocessor. In 7th ACM Int. Conf. on Mobile Computing and Networking(Mobicom), pages 251–259, July 2001.
[22] Donghwan Son, Chansu Yu, and Heung-Nam Kim. Dynamic Voltage Scaling on MPEG Decoding. In Proceedings of the 7th International Conference on Parallel and Distrubuted Systems, page 633, June 2001.
[23] Y.Lu and G.De Micheli. Comparing System-Level Power Management Policies. In IEEE Design and Test of Computers, pages 62–74, March 2001.