跳到主要內容

臺灣博碩士論文加值系統

(18.97.14.87) 您好!臺灣時間:2025/02/09 10:28
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:黃昱雄
研究生(外文):Yu-Hsiung Huang
論文名稱:以多階層式力導向演算法為基礎之低功率導向的標準元件擺置
論文名稱(外文):Low Power Driven Standard-Cell Placement Based on a Multilevel Force-Directed Algorithm
指導教授:陳美麗陳美麗引用關係
指導教授(外文):Mely chen chi
學位類別:碩士
校院名稱:中原大學
系所名稱:資訊工程研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2002
畢業學年度:90
語文別:中文
論文頁數:40
中文關鍵詞:多階層式力導向演算法功率消耗最小化以切換頻率為導向的擺置
外文關鍵詞:power consumption minimizationmulti-level force-directed algorithmswitching rate driven placement
相關次數:
  • 被引用被引用:0
  • 點閱點閱:178
  • 評分評分:
  • 下載下載:10
  • 收藏至我的研究室書目清單書目收藏:0
隨著製程技術進入深次微米,功率消耗變得越來越重要。在考量電路的功率消耗之外,功率均勻分佈也將是另一個必須注意的問題。本論文中,我們提出一個以多階層式力導向演算法為基礎之低功率導向的標準元件擺置。此方法包含了四個階段,分別為切割、群組、擺置、以及元件交換。在第一階段,我們切割晶片成數個區塊(bin)。第二階段則是將標準元件(standard cell)群組形成模組(module),並形成多階層式架構。第三階段,我們分配群組後的每一個模組到每一個區塊,此區塊的中心點即為模組的初始位置。接著,使用力導向演算法搬動每一個模組到力平衡的位置,並將模組反群組(uncoarsen)。重複此動作直到反群組成最初的標準元件。開始擺置標準元件在最上方的列(row)及最下方的列(row),並且再將未擺置的標準元件使用力導向演算法更新其位置。直到所有列都被標準元件擺置。前三個階段在使得導線切換功率最小化。最後一階段,則是交換標準元件達到功率均勻分佈。
本程式以整合入商業設計流程。從實驗結果可以顯示出在權重函式中加入導線切換功率能有效降低導線切換功率。我們也研究加入群組階段對於功率消耗的影響,並且考量交換標準元件後所必需付出的成本。詳細結果請參照第五章。

As the process technology enters the deep sub-micron era, power consumption of a circuit becomes more important. Besides considering power consumption, uniform power distribution is also very important for longer life time of a chip. A low-power driven placement method based on multi-level force-directed algorithm is proposed. This approach includes four phases that are partitioning, coarsening, placement, and standard cell exchange. In the first phase, we partition a chip into several bins. In the second phase, we coarsen standard cells to form one module and build multi-level structure. In the third phase, we assign every coarsened module to one bin and the center position of bin is the initial position of module. Then, we move every coarsened module to its force-balanced location and uncoarsen every coarsened module. This action is repeated until all the coarsened module are uncarsened to the original standard cells. We start to place standard cells to the top row and the bottom row and the position of all non-placed standard cells are updated by using force-directed algorithm. Repeating this process until all rows are formed, the third phase is completed. The first three phases tries to minimize the switching power of wires. In the final phase, we exchange standard cells in order to balance power distribution of standard cells.
We have integrated this approach into commercial design flow. The experimental result shows that adding switching rate to cost function can effectively reduce total switching power of wire. We also study the effect due to the coarsen phase and analyze the trade off between minimum power consumption and uniform power distribution. Experimental results are shown in chapter 5.

目 錄
中文摘要
Abstract
誌謝
第一章 前言
第二章 低功率擺置問題
第三章 問題描述與方法
第四章 演算法、資料結構與程式流程
第五章 結果與實驗數據
第六章 結論與未來方向
參考文獻

[1] Chingwei Yeh; Yin-Shuin Kang; Shan-Jih Shieh; Jinn-Shyan Wang , “Layout techniques supporting the use of dual supply voltages for cell-based designs” , in Porc. of 36th Design Automation Conference, pages 62-67, 1999.[2] Chunhong Chen; Sarrafzadeh, M. , “Provably good algorithm for low power consumption with dual supply voltages”, Computer-Aided Design , pages 76-79 ,1999.[3] Chingwei Yeh; Yin-Shuin Kang , “A simulated annealing based method supporting dual supply voltages in standard cell placement” , Proceedings of the 1999 IEEE International Symposium on , Volume: 1 , pages 310-313 , 1999.[4] Vaishnav, H.; Pedram, M. , “PCUBE: A performance driven placement algorithm for low power designs” , Design Automation Conference, pages 72-77, 1993.[5] Holt, G.; Tyagi, A. , “GEEP: a low power genetic algorithm layout system” , IEEE 39th Midwest symposium on , Volume: 3 , pages 1337-1340 , 1996.[6] Sait, S.M.; Youssef, H.; Khan, J.A.; El-Maleh, A. , “Fuzzy simulated evolution for power and performance optimization of VLSI placement” , Proceedings. IJCNN '01. International Joint Conference on , Volume: 1, pages 738 -743 , 2001.[7]Dennis J.-H. Huang and Andrew B. Kahng , “Partitioning-Based Standard-Cell Global Placement with An exact Objective” , ISPD’97 , pages 18-25,1997.[8]Xiaojian Yang , Maogang Wang , Kenneth Eguro , and Majid Sarrafzadeh , “A Snap-On Placement Tool” , Proceeding of the international symposium on Physical design , page 153-158, 2000.[9] Maogang Wang , Xiaojian Yang , and Majid Sarrafzadeh , “Dragon2000:Fast Standard-Cell Placement for Large Circuits ,” in Proc. International Conference on Computer-Aided Design , pages260-263, 2000.[10] G.Karypis , R.Aggarwal , V.Kumar , and S.Shekhar , “Multilevel Hypergraph Partitioning:Applications in VLSI Domain ,” in Proc. IEEE Very Large Scale Integration Systems , pages69-79 , 1999.[11] Tony F. Chan , Jason cong , Tianming Kong , and Joseph R. Shinnerl , “Multilevel Optimization for Large-Scale Circuit Placement , ” IEEE Computer-Aided Design , pages171-176 , 2000.[12] Charles J. Alpert , Jen-Hsin Huang , and A. B. Kahng , “Multilevel Circuit Partitioning , “ IEEE Trans. Computer-Aided Design of Integrated Circuits and Systems , pages655-667 , 1998.[13] George Karypis and Vipin Kumar , “Multilevel k-way Hypergraph Partitioning” , Design Automation Conference , pages 343-348 , 1999.[14] P.Agrawal , B.Narendran , and N.Shivakumar , “Multi-Way Partitioning of VLSI Circuits ,” in Proc. 9th International Conference on VLSI Design , pages 393-399 ,1995.[15] C. M. Fiduccia and R. M. Mattheyses , “A linear time heuristic for improving network partitions ,” in Proc. 19th IEEE Design Automation Conference , pages175-181 , 1982.[16]N. R. Quinn. “The placement problem as viewed from the physics of classical mechanics , “ Proceedings of the 12th Design Automation Conference , pages 173-178 , 1975.[17] Yih-Chih Chou , and Youn-Long Lin , “A Performance-Driven Standard-Cell Based on a Modified Force-Directed Algorithm ,” in Proc. of ISPD’01, pages24-29 , 2001.[18] S.H. Huang and J.Y. Lai , “A High-Speed VLSI Fuzzy Logic Controller with Pipeline Architecture “ , in the Proc. of IEEE International Conference on Fuzzy Systems , Vol. 3 , pp. 8-11 , 2001.

電子全文 電子全文(本篇電子全文限研究生所屬學校校內系統及IP範圍內開放)
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top