Industrial chip development is inherently iterative, favoring localized, intent-driven updates over rewriting RTL from scratch. Yet most LLM-Aided Hardware Design (LAD) work focuses on one-shot synthesis, leaving this workflow underexplored. To bridge this gap, we for the first time formalize $Δ$Spec-to-RTL localization, a multi-positive problem mapping natural language change requests ($Δ$Spec) to the affected Register Transfer Level (RTL) syntactic blocks. We propose RTLocating, an intent-aware RTL localization framework, featuring a dynamic router that adaptively fuses complementary views from a textual semantic encoder, a local structural encoder, and a global interaction and dependency encoder (GLIDE). To enable scalable supervision, we introduce EvoRTL-Bench, the first industrial-scale benchmark for intent-code alignment derived from OpenTitan's Git history, comprising 1,905 validated requests and 13,583 $Δ$Spec-RTL block pairs. On EvoRTL-Bench, RTLocating achieves 0.568 MRR and 15.08% R@1, outperforming the strongest baseline by +22.9% and +67.0%, respectively, establishing a new state-of-the-art for intent-driven localization in evolving hardware designs.

翻译：工业芯片开发本质上是迭代式的，更倾向于基于意图的局部化更新而非从头重写RTL。然而，现有的大多数LLM辅助硬件设计研究都聚焦于一次性综合，对此工作流程探索不足。为填补这一空白，我们首次形式化了$Δ$Spec-to-RTL定位问题——这是一个将自然语言变更请求映射到受影响的寄存器传输级语法块的多正例匹配问题。我们提出了RTLocating，一个意图感知的RTL定位框架，其核心是一个动态路由器，能够自适应地融合来自文本语义编码器、局部结构编码器以及全局交互与依赖编码器的互补视图。为实现可扩展的监督，我们构建了EvoRTL-Bench，这是首个基于OpenTitan项目Git历史衍生的、用于意图-代码对齐的工业规模基准数据集，包含1,905个已验证的变更请求和13,583个$Δ$Spec-RTL块对。在EvoRTL-Bench上，RTLocating取得了0.568的MRR值和15.08%的R@1值，分别比最强基线提升了+22.9%和+67.0%，为演化式硬件设计中的意图驱动定位确立了新的技术标杆。