Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/92588
Title: | 針對時序工程修改命令的快速準確動態電壓降預測 Fast and Accurate Dynamic IR-drop Prediction For Timing ECO |
Authors: | 謝兆和 Chao-Ho Hsieh |
Advisor: | 李建模 James Chien-Mo Li |
Keyword: | 電壓降預測,時序ECO,時脈樹,機器學習, IR-drop prediction,timing ECO,clock tree,machine learning, |
Publication Year : | 2024 |
Degree: | 碩士 |
Abstract: | 時序(timing)工程修改命令 (engineering change order, ECO)可能導致新的電壓降(IR-drop)熱點(hotspot),這些熱點需要在簽發(signoff)前通過額外的電壓降工程修改命令進行修復。在這篇論文中,我們提出了一種基於機器學習的做法,能預測時脈樹(clock tree)工程修改命令後,電路中每個單元(cell)的動態電壓降,以便讓我們找出時脈樹工程修改命令導致的新電壓降熱點。在機器學習模型訓練這方面,我們結合了時脈樹工程修改命令前後設計的特徵,並提出了四種新特徵:目標單元差異特徵、鄰近單元框形平均特徵、鄰近單元框形分佈特徵,和鄰近單元暫態功率特徵。我們的實驗結果顯示,相比於運用坊間軟體進行電壓降分析,我們的作法加速了至少九倍。預測結果的平均絕對百分比誤差也小於3%。我們的方法還可以在大多數情況下,有效找出時脈樹工程修改命令後的電壓降熱點。 Timing engineering change order (ECO) may result in new IR-drop hotspots, which are required to be fixed by additional efforts in IR-drop ECO before signoff. In this thesis, we proposed a machine-learning-based method to predict the dynamic IR-drop of every cell in a clock tree ECO revised design so that we can determine the new IR-drop hotspots resulting from the clock tree ECO. To train the machine learning model, we combine the features of a design before and after clock tree ECO, as well as propose four types of new features: target cell delta features, neighbor cell frame averaged features, neighbor cell frame distribution features, and neighbor cell transient power features. Our experimental results show that we achieved at least a 9x speed-up ratio compared to IR-drop analysis by commercial tools, with mean absolute percentage errors less than 3%. Our method can also improve the effectiveness of IR-drop hotspot identification after clock tree ECO in most cases. |
URI: | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/92588 |
DOI: | 10.6342/NTU202400880 |
Fulltext Rights: | 同意授權(全球公開) |
Appears in Collections: | 電子工程學研究所 |
Files in This Item:
File | Size | Format | |
---|---|---|---|
ntu-112-2.pdf | 4.87 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.