论文

GRODE-RTL:用源码映射依赖视图提升 LLM 修复 RTL 电路的准确率

GRODE-RTL: Source-Mapped Dependency Views for LLM-Based RTL Repair

精选理由

修硬件代码的朋友可以看看这篇:把网表扇入锥映射回源码行,LLM 修 RTL 的 pass@1 最多涨 26.7%。三个国产模型都测了,说明给模型喂“有结构的相关上下文”比塞整个综合图更管用,思路对调试其他硬件设计任务也有参考。

论文提出 GRODE-RTL,一种面向 LLM 自动修复 RTL(寄存器传输级)代码的锚点中心表示方法,用于解决根因与出错输出在源码中相距遥远的非局部故障难题。

正文

方法上,它从综合后的网表中提取可疑寄存器单时钟级的扇入锥,将网表节点映射回可编辑的源码行,并组织成按跳数分区的紧凑依赖视图,优先呈现直接驱动信号、折叠远距离跳数。这样标准工具调用型 Agent 无需接触完整综合图或任何真实答案提示即可定位故障。

评估覆盖 30 个经形式化验证的非局部故障,测试 DeepSeek-V4-Flash、GLM-5.2、MiniMax-M3 三个模型,pass@1 相比源码级探索分别提升 16.7%、26.7% 和 20.0%,远距离与间接锚点子集上均有稳定收益。六配置消融实验证明,收益来自选择性依赖组织而非单纯扩大上下文。

原文 · arXiv: DeepSeek

GRODE-RTL: Source-Mapped Dependency Views for LLM-Based RTL Repair

Large Language Models show great potential for automated Register-Transfer Level repair, yet they struggle with non-local faults where root causes and failing outputs reside far apart in source code. Treating RTL as a flat token sequence obscures hardware dataflows, whereas exposing complete synthesized graphs overwhelms the model with fine-grained metadata. To resolve this representation dilemma, we propose GRODE-RTL, an anchor-centric representation that extracts the single-clock-stage fan-in cone of a suspect register from the netlist, maps netlist nodes back to editable source lines, and organizes them into a compact hop-partitioned dependency view. By prioritizing direct drivers and folding distant hops, GRODE-RTL guides standard tool-using agents without exposing ground-truth hints or oracle feedback. We evaluate GRODE-RTL across 30 formally validated non-local faults using three LLMs (DeepSeek-V4-Flash, GLM-5.2, and MiniMax-M3) alongside a controlled six-configuration ablation study. GRODE-RTL improves pass@1 over source-level exploration by 16.7% on DeepSeek, by 26.7% on GLM-5.2, and by 20.0% on MiniMax-M3, with consistent gains on the hard-to-retrieve far-distance and indirect-anchor subsets of all three models. Our controls isolate structural relevance from generic context expansion, proving that selective dependency organization rather than full graph exposure is key to effective RTL repair.

产业坐标与信源核验

本条情报归属 AITOP「论文」核心栏目,重点聚焦中国 AI 产业与国产大模型生态。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:DeepSeek、GLM-5.2、MiniMax-M3、RTL修复,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明:本文原始信息发布自一手权威信源「arXiv: DeepSeek」(Tier-1 一手发布),具备高确定性参考价值。