RTLocating:面向硬件设计迭代的意图感知RTL定位
RTLocating: Intent-aware RTL Localization for Hardware Design Iteration
AI总结:
RTLocating通过意图感知的RTL定位框架,实现了工业级硬件设计迭代中意图驱动的高效定位,显著提升了变更请求与RTL代码的匹配精度。
摘要:
工业芯片开发本质上是迭代的,更倾向于进行局部化的、以意图驱动的更新,而不是从头开始重写RTL。然而,大多数基于大语言模型的硬件设计(LAD)工作都集中在一次性合成上,忽略了这一工作流程。为弥补这一差距,我们首次正式化了ΔSpec到RTL的定位,这是一个多正问题,将自然语言变更请求(ΔSpec)映射到受影响的寄存器传输级(RTL)语法块。我们提出了RTLocating,一个意图感知的RTL定位框架,其特征是动态路由器,能够自适应地融合来自文本语义编码器、局部结构编码器和全局交互与依赖编码器(GLIDE)的互补视图。为了实现可扩展的监督,我们引入了EvoRTL-Bench,这是首个工业级基准,来源于OpenTitan的Git历史,包含1905个经过验证的请求和13583个ΔSpec-RTL块对。在EvoRTL-Bench上,RTLocating实现了0.568 MRR和15.08%的R@1,比最强基线分别高出22.9%和67.0%,在演进硬件设计的意图驱动定位中建立了新的最先进的水平。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。