Saved in:
Bibliographic Details
Main Authors: Xing, Wei W., Fan, Weijian, Liu, Zhuohua, Yao, Yuan, Hu, Yuanqi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.14433
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917647673720832
author Xing, Wei W.
Fan, Weijian
Liu, Zhuohua
Yao, Yuan
Hu, Yuanqi
author_facet Xing, Wei W.
Fan, Weijian
Liu, Zhuohua
Yao, Yuan
Hu, Yuanqi
contents Automatic transistor sizing in circuit design continues to be a formidable challenge. Despite that Bayesian optimization (BO) has achieved significant success, it is circuit-specific, limiting the accumulation and transfer of design knowledge for broader applications. This paper proposes (1) efficient automatic kernel construction, (2) the first transfer learning across different circuits and technology nodes for BO, and (3) a selective transfer learning scheme to ensure only useful knowledge is utilized. These three novel components are integrated into BO with Multi-objective Acquisition Ensemble (MACE) to form Knowledge Alignment and Transfer Optimization (KATO) to deliver state-of-the-art performance: up to 2x simulation reduction and 1.2x design improvement over the baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2404_14433
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle KATO: Knowledge Alignment and Transfer for Transistor Sizing of Different Design and Technology
Xing, Wei W.
Fan, Weijian
Liu, Zhuohua
Yao, Yuan
Hu, Yuanqi
Machine Learning
Computational Engineering, Finance, and Science
Automatic transistor sizing in circuit design continues to be a formidable challenge. Despite that Bayesian optimization (BO) has achieved significant success, it is circuit-specific, limiting the accumulation and transfer of design knowledge for broader applications. This paper proposes (1) efficient automatic kernel construction, (2) the first transfer learning across different circuits and technology nodes for BO, and (3) a selective transfer learning scheme to ensure only useful knowledge is utilized. These three novel components are integrated into BO with Multi-objective Acquisition Ensemble (MACE) to form Knowledge Alignment and Transfer Optimization (KATO) to deliver state-of-the-art performance: up to 2x simulation reduction and 1.2x design improvement over the baselines.
title KATO: Knowledge Alignment and Transfer for Transistor Sizing of Different Design and Technology
topic Machine Learning
Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2404.14433