UVMarvel: an Automated LLM-aided UVM Machine for Subsystem-level RTL Verification

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ye, Junhao, Pan, Dingrong, Liu, Hanyuan, Hu, Yuchen, Zhou, Jie, Xu, Ke, Fang, Xinwei, Wang, Xi, Guan, Nan, Jiang, Zhe
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910195134758912
author Ye, Junhao
Pan, Dingrong
Liu, Hanyuan
Hu, Yuchen
Zhou, Jie
Xu, Ke
Fang, Xinwei
Wang, Xi
Guan, Nan
Jiang, Zhe
author_facet Ye, Junhao
Pan, Dingrong
Liu, Hanyuan
Hu, Yuchen
Zhou, Jie
Xu, Ke
Fang, Xinwei
Wang, Xi
Guan, Nan
Jiang, Zhe
contents Verification presents a major bottleneck in Integrated Circuit (IC) development, consuming nearly 70% of total effort. While the Universal Verification Methodology (UVM) improves reuse through structured verification environments, constructing subsystem-level UVM testbenches and generating high-quality stimuli still require extensive manual coding, repeated EDA tool runs, and deep protocol and micro-architectural expertise. We present UVMarvel, an automated verification framework that leverages Large Language Models (LLMs) to build UVM testbenches for subsystem-level RTL. UVMarvel introduces an Intermediate Representation (IR) and a Bus Protocol Library to translate heterogeneous specifications into protocol-correct subsystem-level UVM testbenches, and employs a Signal Tracker and a Verilog Patching Library to guide LLM-based stimuli refinement. UVMarvel is the first framework capable of automatically constructing subsystem-level UVM testbenches across mainstream bus protocols, and it achieves an average code coverage of 95.65%, while reducing verification time from several human working days to a 4.5-hour automated execution.
format Preprint
id arxiv_https___arxiv_org_abs_2605_04704
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle UVMarvel: an Automated LLM-aided UVM Machine for Subsystem-level RTL Verification
Ye, Junhao
Pan, Dingrong
Liu, Hanyuan
Hu, Yuchen
Zhou, Jie
Xu, Ke
Fang, Xinwei
Wang, Xi
Guan, Nan
Jiang, Zhe
Hardware Architecture
Software Engineering
Verification presents a major bottleneck in Integrated Circuit (IC) development, consuming nearly 70% of total effort. While the Universal Verification Methodology (UVM) improves reuse through structured verification environments, constructing subsystem-level UVM testbenches and generating high-quality stimuli still require extensive manual coding, repeated EDA tool runs, and deep protocol and micro-architectural expertise. We present UVMarvel, an automated verification framework that leverages Large Language Models (LLMs) to build UVM testbenches for subsystem-level RTL. UVMarvel introduces an Intermediate Representation (IR) and a Bus Protocol Library to translate heterogeneous specifications into protocol-correct subsystem-level UVM testbenches, and employs a Signal Tracker and a Verilog Patching Library to guide LLM-based stimuli refinement. UVMarvel is the first framework capable of automatically constructing subsystem-level UVM testbenches across mainstream bus protocols, and it achieves an average code coverage of 95.65%, while reducing verification time from several human working days to a 4.5-hour automated execution.
title UVMarvel: an Automated LLM-aided UVM Machine for Subsystem-level RTL Verification
topic Hardware Architecture
Software Engineering
url https://arxiv.org/abs/2605.04704