ParaGate: Parasitic-Driven Domain Adaptation Transfer Learning for Netlist Performance Prediction

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Sun, Bin, Zhou, Jingyi, Mu, Jianan, Chao, Zhiteng, Yang, Tianmeng, Xu, Ziyue, Ye, Jing, Li, Huawei
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915644001222656
author Sun, Bin
Zhou, Jingyi
Mu, Jianan
Chao, Zhiteng
Yang, Tianmeng
Xu, Ziyue
Ye, Jing
Li, Huawei
author_facet Sun, Bin
Zhou, Jingyi
Mu, Jianan
Chao, Zhiteng
Yang, Tianmeng
Xu, Ziyue
Ye, Jing
Li, Huawei
contents In traditional EDA flows, layout-level performance metrics are only obtainable after placement and routing, hindering global optimization at earlier stages. Although some neural-network-based solutions predict layout-level performance directly from netlists, they often face generalization challenges due to the black-box heuristics of commercial placement-and-routing tools, which create disparate data across designs. To this end, we propose ParaGate, a three-step cross-stage prediction framework that infers layout-level timing and power from netlists. First, we propose a two-phase transfer-learning approach to predict parasitic parameters, pre-training on mid-scale circuits and fine-tuning on larger ones to capture extreme conditions. Next, we rely on EDA tools for timing analysis, offloading the long-path numerical reasoning. Finally, ParaGate performs global calibration using subgraph features. Experiments show that ParaGate achieves strong generalization with minimal fine-tuning data: on openE906, its arrival-time R2 from 0.119 to 0.897. These results demonstrate that ParaGate could provide guidance for global optimization in the synthesis and placement stages.
format Preprint
id arxiv_https___arxiv_org_abs_2511_23340
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ParaGate: Parasitic-Driven Domain Adaptation Transfer Learning for Netlist Performance Prediction
Sun, Bin
Zhou, Jingyi
Mu, Jianan
Chao, Zhiteng
Yang, Tianmeng
Xu, Ziyue
Ye, Jing
Li, Huawei
Machine Learning
Artificial Intelligence
In traditional EDA flows, layout-level performance metrics are only obtainable after placement and routing, hindering global optimization at earlier stages. Although some neural-network-based solutions predict layout-level performance directly from netlists, they often face generalization challenges due to the black-box heuristics of commercial placement-and-routing tools, which create disparate data across designs. To this end, we propose ParaGate, a three-step cross-stage prediction framework that infers layout-level timing and power from netlists. First, we propose a two-phase transfer-learning approach to predict parasitic parameters, pre-training on mid-scale circuits and fine-tuning on larger ones to capture extreme conditions. Next, we rely on EDA tools for timing analysis, offloading the long-path numerical reasoning. Finally, ParaGate performs global calibration using subgraph features. Experiments show that ParaGate achieves strong generalization with minimal fine-tuning data: on openE906, its arrival-time R2 from 0.119 to 0.897. These results demonstrate that ParaGate could provide guidance for global optimization in the synthesis and placement stages.
title ParaGate: Parasitic-Driven Domain Adaptation Transfer Learning for Netlist Performance Prediction
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2511.23340