证据引导的仓库级RTL修复

中文摘要 AI 辅助

仓库级RTL修复必须定位跨越文件、模块和时钟周期的故障，然后一致地传播修复。现有方法在源代码上进行推理，这揭示了可能的行为而非失败的执行，并且无法判断局部修复是否被一致地传播。因此，我们提出了一个包含三个模块的证据引导框架。故障定位将问题陈述转化为可复现的失败运行和故障锚点。波形引导的定位使用定位工具箱将观察到的违规缩小为候选机制和证据链。一致性感知的修复与验证随后将该种子扩展为协调的补丁，并重放相同场景以检查违规是否消失。我们在HWE-Bench上进行了实验，取得了优于基线的性能。

英文摘要

Repository-level RTL repair must localize a failure that spans files, modules, and clock cycles, then propagate the fix consistently. Existing methods reason over source code, which reveals possible behaviors but not the failed execution, and cannot tell whether a local fix was propagated consistently. We therefore present an evidence-guided framework with three modules. Failure grounding converts a problem statement into a reproduced failing run and a failure anchor. Waveform-guided localization uses a localization toolbox to narrow the observed violation into a candidate mechanism and an evidence trail. Consistency-aware repair and validation then expand that seed into a coordinated patch and replay the same scenario to check that the violation disappears. We conducted experiments on HWE-Bench and achieved better performance than the baseline.

发表机构

• City University of Hong Kong（香港城市大学）
• Southeast University（东南大学）
• National Center of Technology Innovation for EDA（EDA国家技术创新中心）

机构由 AI 辅助整理，请以论文原文为准。