利用功率模式分析及功能性權值計算法估測暫存器轉換層次功率消耗

簡易檢索 / 詳目顯示

回結果列表

研究生：	蘇明毅 Ming-Yi Sum
論文名稱：	利用功率模式分析及功能性權值計算法估測暫存器轉換層次功率消耗 RTL Power Estimation Using Power Mode Classification and Functional Weighting
指導教授：	黃錫瑜 Shi-Yu Huang
口試委員:
學位類別：	碩士 Master
系所名稱：	電機資訊學院 - 電機工程學系 Department of Electrical Engineering
論文出版年：	2004
畢業學年度：	92
語文別：	中文
論文頁數：	71
中文關鍵詞：	功率評估、暫存器轉移階層
外文關鍵詞：	Power Estimation, RTL
相關次數：	點閱：4 下載：0
分享至:	分享至facebook 分享至twitter

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

近年來，功率消耗成為了IC設計中非常重要的一個課題。這主要是因為過大的功率消耗，會導致電路過熱，使得電路的效能大打折扣。為了處理今日越來越複雜的晶片密度，電路在設計的階段中，能夠越早知道電路的消耗，越能夠在早期幫助設計者做功率上的最佳化設計。如此的最佳化設計，能夠在越高的層次執行，所節省的功率消耗更顯著。
基於上述種種，電路的功率評估工具對於設計者而言，是非常重要的。但不幸地，一般的功率評估工具在評估功率時，都需要在比較低階的層次，例如邏輯閘階層，如此一來會消耗蠻多的時間來做評估，對於設計者而言，功率最佳化的工作，也變得只有較少的選擇。因此，我們發展了一個建立在暫存器轉移階層，並且能夠快速評估功率兼具準確度的方法。主要我們分為兩個階段，第一個階段為功率模型的建立，第二個階段則為功率評估階段。首先我們將電路的行為模式細分出來，根據這些行為模式以及我們拿來使用建立模型的功能性樣本，建立起預測電路的模型。一旦在模型建立好後，進入了功率評估的階段，我們將功能性樣本依其操作的行為模式以及型態，帶入我們的功率模型，最後可以求得最終的功率消耗。
實驗的結果發現，我們所建立的暫存器轉移階層的功率模型，能夠得到準確的功率消耗，在我們測試的十一個電路中，得到的平均誤差為3.82%.

RT-level power estimation is to quickly predict the total switching activity in a logic design without resorting to the time-consuming gate-level simulation. This thesis investigates an RTL power estimation methodology suitable for large designs. In order to retain high accuracy, a number of features are proposed, including a power mode classification method and a functional-weighting scheme for linear approximation. Furthermore, in order to take into account the temporal and spatial correlations among the input patterns, we use a cycle-by-cycle modeling scheme. On top of it, each primary input is further encoded into two binary variables to faithfully reflect its switching behavior. The proposed method has been realized as a practical tool that can fit into the commercial design flow and tested by a number of real designs. Experimental results show that the average estimation error as compared to full gate-level simulation is only 3.82%.

Introductions                                                     7
1 Motivation……...…………….……………………………………………......8
2 Organization……………………………………………...…………………...12

Preliminary                                                      13
1 RT-level power estimation techniques…………………………………….…..13
1.1 Analytical power models……………………………………….......….13
1.2 Characterization-based macro-model……………………….………....14
1.3 Control logic analysis techniques………………………….…………..15
2 Power consumption components…………………………………….………..15
2.1 Static power consumption…………………………………….....………16
2.2 Dynamic power consumption…………………………....…….………..18

Improved Linear Approximation                                    20
1 Statement of the problem………………………………….…………...……...20
1.1 Power model format…………………………………………………..…21  3.2 Up-down encoding…………………………………………………………….22
3 The main restrictions on up-down encoding scheme………………………….27

Overall Flow                                                     29
1 Power mode identification………………………………………….………....29
1.1 Build hierarchical module tree of the circuit………………….………...29
1.2 Build power mode tree of every module……………………….…….…31
1.3 Analyze the VCD file………………………………………….………..33
2 Power model using functional weighting…………………………….……….35
2.1 Constructing fan-out cones of each input……………………….………36
2.2 Calculating functional weights………………………………….………37

Implementation                                                  43
1 System overview………………………………………………………….…..44
1.1 Data preparation……………………………………………….………..44
1.2 Modeling phase………………………………………………....………45
1.3 Extrapolation phase………………………………………………….….47

Experimental Results                                              49
1 Usage of our tool………………………………………………………………49
2 Experiments………………………………………………………….………..51
2.1 Circuits elaborated from DesignWare………………………….……….51
2.2 Greatest-common-divisor circuit……………………………….……….55
2.3 Montgomery inverse circuit…………………………………….……….57
2.4 Finite impulse response filter…………………………………….…..….60
2.5 Arithmetic encoder………………………………………………...…….62
2.6 A symmetric crypto processor (AES)…...………………………….……65

Conclusion                                                       67

Bibliography                                                     68

                                

[1] S. Gupta and F. N. Najm, “Power Macro modeling For High-Level Power Estimation,” Proc. of Design Automation Conf., pp. 365-370, 1997.
[2] E. Macii, M. Pedram, and F. Somenzi, “High-Level Power Modeling, Estimation, and Optimization,” in IEEE Transactions on CAD, Vol. 17, No. 11, pp. 1061-1079, 1998.
[3] P. Landman, “High-Level Power Estimation,” in IEEE Proc. of ISLPED, Monterey, CA, pp. 29-35, June 1996.
[4] D. Marculescu, R. Marculescu, and M. Pedram, “Information Theoretic Measures For Power Analysis,” in Trans. on CAD, Vol. 15, No. 6, pp. 599-610, 1996.
[5] A. Bogliolo, R. Corgnati, E. Macii, and M. Poncino, ”Parameterized RTL Power Models For Soft Macros,” IEEE Trans. On VLSI Systems, Vol. 9, No.6, pp. 880-887, 2001.
[6] R. Corgnati, E. Macii, and M. Poncino, “Clustered Table-Based Macromodels For RTL Power Estimation,” Greak Lake Symposium on VLSI, pp. 354-357, 1999.
[7] M. Eiermann and W. Stechele, “Novel Modeling Techniques For RTL Power Estimation,” Proc. of Low-Power Electronics and Design (ISLPED), pp. 323-328, 2002.
[8] P. Landman, and J. Rabaey, “Architectural Power Analysis: The Dual-Bit Type Method,” IEEE Trans. On VLSI Systems, Vol. 3, No. 2, pp. 173-187, 1995.
[9] A. Bogliolo, L Benini, and G. DeMicheli, “Regression-Based RTL Power Modeling,” ACM Trans. on Design Automation of Electronics Systems, Vol. 5, No. 3, pp. 337-372, 2000.
[10] S. Gupta and F. N. Najm, “Power Macromodeling For High-Level Power Estimation,” Proc. of Design Automation Conf., pp. 365-370, 1997.
[11] A. Bogliolo and L. Benini, “Node Sampling: A Robust RTL Power Modeling Approach,” Prof. of Int’l Conf. on Computer-Aided Design, pp. 8-12, 1998.
[12] S. Gupta, and F. N. Najm, “Energy-per-cycle Estimation at RTL,” in Proc. ISLPED, Monterey, CA, pp. 121-126, 1999.
[13] Q. Wu, Q. Qiu, and M. Pedram, C. S. Ding, “Cycle-Accurate Macro-Models for RT-Level Power Analysis,” in Trans. On VLSI 1998, Vol. 6, No. 4, pp. 520-528, 1998.
[14] K. D. Muller-Glaser, K. Kirsch, and K. Neusinger, “Estimating Essential Design Characteristics to Support Project Planning for ASIC Design Management,” in Proc. Int. Conf. Computer-Aided Design, pp. 148-151, Nov. 1991.
[15] D. Marculescu, R. Marculescu, and M. Pedram, “Information Theoretic Measures for Energy Consumption at the Register-Transfer Level,” in Proc. Int. Symp. Low-Power Design, pp. 81-86, Apr. 1995.
[16] F. N. Najm, “Toward a High-Level Power Estimation Capability,” in Proc. Int. Symp. Low-Power Design, pp. 87-92, Apr. 1995.
[17] M. Nemani and F. N. Najm, “High Level Power Estimation And the Area Complexity of Boolean Functions,” in Proc. Int. Symp. Low-Power Electronics and Design, pp. 329-334, Aug. 1996.
[18] C. H. Chen and C. Y. Tsui, “Toward the Capability of Providing Power-Area-Delay Tradeoff at the Register Transfer Level,” in Proc. Int. Symp. Low-Power Electronics and Design, pp. 24-29, Aug. 1998.
[19] M. Nemani and F. Najm, “High-Level Area and Power Estimation for VLSI Circuits,” IEEE Trans. Computer-Aided Design, Vol. 18, pp.697-713, June 1999.
[20] D. D. Gajski, N. D. Dutt, A. C.-H. Wu, and S. Y.-L. Lin, “High-level Synthesis: Introduction to Chip and System Design.” Norwell, MA: Kluwer, 1992
[21] S. R. Powell and P. M. Chau, “Estimating Power Dissipation of VLSI Signal Processing Chips: The PFA Technique,” in Proc. VLSI Signal Processing IV, pp. 250-259, Sept. 1990.
[22] P. Landman and J. M. Rabaey, “Architectural Power analysis: The Dual Bit Type Method,” IEEE Trans. VLSI Syst., Vol.3, pp. 173-187, June 1995.
[23] P. Landman and J. M. Rabaey, ”Activity-Sensitive Architectural Power Analysis for the Control Path,” in Proc. Int. Symp. Low-Power Design, pp. 93-98, Apr. 1995.
[24] R. P. Llopis and F. Goossens, “The Petrol Approach to High-Level Power Estimation,” in Proc. Int. Symp. Low-Power Electronic and Design, pp.130-132, Aug. 1998.
[25] D. I. Cheng, K.-T. Cheng, D. C. Wang, and M. Marek-Sadowska, “A New Hybrid Methodology for Power Estimation,” in Proc. Design Automation Conf., pp. 439-444, June 1996.
[26] A. Bogliolo and L. Benini, “Node Sampling: A Robust RTL Power Modeling Approach,” Prof. of Inte’l Conf. on Computer-Aided Design, pp. 8-12, 1998.

全文公開日期本全文未授權公開 (校內網路)
全文公開日期本全文未授權公開 (校外網路)

簡易檢索 / 詳目顯示

相關論文