Parallel Algorithm in Hotspot Detection Based on Machine Learning

LI Zhong; WU Yu-ping; CHEN Lan; ZHANG Xue-lian

Chinese

您当前的位置：

首页 >

文章列表页 >

Parallel Algorithm in Hotspot Detection Based on Machine Learning

更新时间：2026-09-04

- Parallel Algorithm in Hotspot Detection Based on Machine Learning
- Vol. 36, Issue 1, Pages: 27-31(2019)
- 作者机构：
  
  1. 中国科学院机构微电子研究所,北京,100029
  2. 三维及纳米集成电路设计自动化技术北京市重点实验室,北京,100029
  3. 中国科学院大学机构,北京,101408
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2019
- 稿件说明：
移动端阅览
李仲, 吴玉平, 陈岚, 张学连. 基于机器学习的版图热点检测并行算法[J]. 微电子学与计算机, 2019, 36(1): 27-31.

LI Zhong, WU Yu-ping, CHEN Lan, et al. Parallel Algorithm in Hotspot Detection Based on Machine Learning[J]. 2019, 36(1): 27-31.
李仲, 吴玉平, 陈岚, 张学连. 基于机器学习的版图热点检测并行算法[J]. 微电子学与计算机, 2019, 36(1): 27-31. DOI：

LI Zhong, WU Yu-ping, CHEN Lan, et al. Parallel Algorithm in Hotspot Detection Based on Machine Learning[J]. 2019, 36(1): 27-31. DOI：

摘要

针对基于机器学习的版图热点训练过程中降维算法耗时长和大多数训练算法没有利用多核资源的问题

分别提出了基于MPI的PCA并行降维算法和基于OpenMP的AdaBoost并行训练算法.首先采用QR分解优化奇异值求解特征矩阵

再结合MPI实现PCA的并行降维计算

最后将降维后的数据利用多核CPU进行训练

达到减小训练时间的目的.实验结果表明

PCA并行降维算法加速比达4.7倍

AdaBoost并行训练算法加速比达4.9倍

验证了并行化的可行性.

Abstract

The training phase of hotspot detection based on Machine Learning is time-consuming. In this paper

a parallel PCA algorithm based on MPI and a parallel AdaBoost algorithm based on OpenMP are proposed to reduce the training time. Firstly

the QR decomposition is used to optimize SVD

and then the MPI is used to implement the PCA parallel algorithm. Finally

the reduced dimension data is trained using multi-core CPU parallel algorithm. The experimental results show that the PCA parallel algorithm could achieve a 4.7 times speed-up ratio

and the AdaBoost parallel algorithm could achieve a 4.9 times speed-up ratio

which verifies the feasibility of parallelization.

关键词

Keywords

references

Quinn M J. MPI与OpenMP并行程序设计:C语言版[M].陈文光, 武永卫, 译.北京:清华大学出版社, 2004.

Drmac Z. A posteriori computation of the singular vectors in a preconditioned Jacobi SVD algorithm[J]. Ima Journal of Numerical Analysis, 1999, 19(2):191-213. DOI: 191

Matsunawa T, Gao J R, Yu B, et al. A new lithography hotspot detection framework based on AdaBoost classifier and simplified feature extraction[J]. Spie Advanced Lithography, 2015 :94270S-94270S-11. DOI: 94270S

Yu Y T. Machine-learning-based hotspot detection usingtopological classification and critical feature extraction[J]. IEEE/ACM Design Automation Conference(DAC), 2013, 34 (3) :1-6. DOI: 1

Wuu J, Pikus Y. Detecting context sensitive hotspots in standard cell libraries[J]. Proc. of SPIE, 2009, (7275):265-271. DOI: 265

Yoav F Schapire, Robert E. A decision-theoretic generalization of on-line learning and an application to boosting[J]. Journal of Computer and System Sciences, 1997, 55(1): 119-139. DOI: 119

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Human Detection Based on Multi-classifiers in Static Image

The Support Vector Pre-extracting Method Based on Error Samples AdaBoost Algorithm

Real-time Gesture Recognition Based on AdaBoost Algorithm and Optical Flow Matching

Object Localization of Nonlinear Active Shape Model Based on Kernel PCA

Simulation on the DC characteristics of double heterojunction p-GaN HEMT with AlN/GaN hybrid buffer layer

Related Author

HU Xing-fu

PENG Xian-rong

WU Ming-jun

YE Fei

LUO Jun

WANG Kai

YU Hong-yang

ZHANG Ping

Related Institution

Institute of Optics and Electronics, Chinese Academy of Sciences

Graduate School of the Chinese Academy of Sciences

Army Officer Academy,,Hefei

1 Research Institute of Electronic Science and Technology, University of Electronic Science and Technology of China

2 School of Electronic Engineering, University of Electronic Science and Technology of China

AI问答

Postal code：100079
Tel：（010）53879206 Email：tmw@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09082226号-64 京公网安备11010602201714号
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰