RTLocating: Intent-aware RTL Localization for Hardware Design Iteration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xing, Changwen, Lu, Yanfeng, Qi, Lei, Niu, Chenxu, Li, Jie, Wang, Xi, Chen, Yong, Yang, Jun
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917300634910720
author Xing, Changwen
Lu, Yanfeng
Qi, Lei
Niu, Chenxu
Li, Jie
Wang, Xi
Chen, Yong
Yang, Jun
author_facet Xing, Changwen
Lu, Yanfeng
Qi, Lei
Niu, Chenxu
Li, Jie
Wang, Xi
Chen, Yong
Yang, Jun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_00434
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RTLocating: Intent-aware RTL Localization for Hardware Design Iteration
Xing, Changwen
Lu, Yanfeng
Qi, Lei
Niu, Chenxu
Li, Jie
Wang, Xi
Chen, Yong
Yang, Jun
Emerging Technologies
Computation and Language
Information Retrieval
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.
title RTLocating: Intent-aware RTL Localization for Hardware Design Iteration
topic Emerging Technologies
Computation and Language
Information Retrieval
url https://arxiv.org/abs/2603.00434