ViTAD: Timing Violation-Aware Debugging of RTL Code using Large Language Models

TL;DR

ViTAD automates the debugging of timing violations in RTL code by combining graph analysis, large language models, and domain knowledge, significantly improving repair success rates over baseline methods.

Contribution

This paper introduces ViTAD, a novel approach that integrates signal dependency analysis, LLMs, and domain knowledge to automate timing violation debugging in RTL design.

Findings

Achieves a 73.68% success rate in repairing timing violations.

Outperforms baseline LLM-only approach by 19.30%.

Constructed a real-world dataset of 54 violation cases.

Abstract

In modern Very Large Scale Integrated (VLSI) circuit design flow, the Register-Transfer Level (RTL) stage presents a critical opportunity for timing optimization. Addressing timing violations at this early stage is essential, as modern systems demand higher speeds, where even minor timing violations can lead to functional failures or system crashes. However, traditional timing optimization heavily relies on manual expertise, requiring engineers to iteratively analyze timing reports and debug. To automate this process, this paper proposes ViTAD, a method that efficiently analyzes the root causes of timing violations and dynamically generates targeted repair strategies. Specifically, we first parse Verilog code and timing reports to construct a Signal Timing Dependency Graph (STDG). Based on the STDG, we perform violation path analysis and use large language models (LLMs) to infer the root causes of violations. Finally, by analyzing the causes of violations, we selectively retrieve relevant debugging knowledge from a domain-specific knowledge base to generate customized repair solutions. To evaluate the effectiveness of our method, we construct a timing violation dataset based on real-world open-source projects. This dataset contains 54 cases of violations. Experimental results show that our method achieves a 73.68% success rate in repairing timing violations, while the baseline using only LLM is 54.38%. Our method improves the success rate by 19.30%.