ML-based AIG Timing Prediction to Enhance Logic Optimization

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jiang, Wenjing, Yan, Jin, Sapatnekar, Sachin S.
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915045985746944
author Jiang, Wenjing
Yan, Jin
Sapatnekar, Sachin S.
author_facet Jiang, Wenjing
Yan, Jin
Sapatnekar, Sachin S.
contents As circuit designs become more intricate, obtaining accurate performance estimation in early stages, for effective design space exploration, becomes more time-consuming. Traditional logic optimization approaches often rely on proxy metrics to approximate post-mapping performance and area. However, these proxies do not always correlate well with actual post-mapping delay and area, resulting in suboptimal designs. To address this issue, we explore a ground-truth-based optimization flow that directly incorporates the exact post-mapping delay and area during optimization. While this approach improves design quality, it also significantly increases computational costs, particularly for large-scale designs. To overcome the runtime challenge, we apply machine learning models to predict post-mapping delay and area using the features extracted from AIGs. Our experimental results show that the model has high prediction accuracy with good generalization to unseen designs. Furthermore, the ML-enhanced logic optimization flow significantly reduces runtime while maintaining comparable performance and area outcomes.
format Preprint
id arxiv_https___arxiv_org_abs_2412_02268
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ML-based AIG Timing Prediction to Enhance Logic Optimization
Jiang, Wenjing
Yan, Jin
Sapatnekar, Sachin S.
Hardware Architecture
As circuit designs become more intricate, obtaining accurate performance estimation in early stages, for effective design space exploration, becomes more time-consuming. Traditional logic optimization approaches often rely on proxy metrics to approximate post-mapping performance and area. However, these proxies do not always correlate well with actual post-mapping delay and area, resulting in suboptimal designs. To address this issue, we explore a ground-truth-based optimization flow that directly incorporates the exact post-mapping delay and area during optimization. While this approach improves design quality, it also significantly increases computational costs, particularly for large-scale designs. To overcome the runtime challenge, we apply machine learning models to predict post-mapping delay and area using the features extracted from AIGs. Our experimental results show that the model has high prediction accuracy with good generalization to unseen designs. Furthermore, the ML-enhanced logic optimization flow significantly reduces runtime while maintaining comparable performance and area outcomes.
title ML-based AIG Timing Prediction to Enhance Logic Optimization
topic Hardware Architecture
url https://arxiv.org/abs/2412.02268