E2ESlack: An End-to-End Graph-Based Framework for Pre-Routing Slack Prediction

2025-01-13

AI Summary

Existing EDA placement-stage timing closure lacks accurate pre-placement slack prediction, hindering early optimization. Method: This paper proposes the first end-to-end framework that directly ingests raw circuit files (DEF/SDF/LIB) and outputs path-level slack, total negative slack (TNS), and worst negative slack (WNS). It introduces a graph neural network coupled with TimingParser—a novel multi-format parser—to enable the first end-to-end learning of required arrival times (RATs), complemented by a lightweight RAT estimation algorithm. Contributions/Results: The RAT prediction accuracy surpasses state-of-the-art ML-based methods and pre-placement static timing analysis (STA) tools. TNS and WNS exhibit relative errors below 3%, closely approximating post-placement STA results. Inference speed improves up to 23× over conventional approaches, achieving both high accuracy and high efficiency.

Technology Category

• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Machine Learning: Hardware-aware ML
• Constraint Satisfaction and Optimization: Satisfiability

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Pre-routing slack prediction remains a critical area of research in Electronic Design Automation (EDA). Despite numerous machine learning-based approaches targeting this task, there is still a lack of a truly end-to-end framework that engineers can use to obtain TNS/WNS metrics from raw circuit data at the placement stage. Existing works have demonstrated effectiveness in Arrival Time (AT) prediction but lack a mechanism for Required Arrival Time (RAT) prediction, which is essential for slack prediction and obtaining TNS/WNS metrics. In this work, we propose E2ESlack, an end-to-end graph-based framework for pre-routing slack prediction. The framework includes a TimingParser that supports DEF, SDF and LIB files for feature extraction and graph construction, an arrival time prediction model and a fast RAT estimation module. To the best of our knowledge, this is the first work capable of predicting path-level slacks at the pre-routing stage. We perform extensive experiments and demonstrate that our proposed RAT estimation method outperforms the SOTA ML-based prediction method and also pre-routing STA tool. Additionally, the proposed E2ESlack framework achieves TNS/WNS values comparable to post-routing STA results while saving up to 23x runtime.

Problem

• Electronic Design Automation
• Timing Slack Prediction
• Required Arrival Time

Innovation

• E2ESlack
• Pre-routing Slack Prediction
• Machine Learning