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

TL;DR

UVMarvel is an automated framework that uses Large Language Models to generate subsystem-level UVM testbenches, significantly reducing verification time and achieving high code coverage.

Contribution

It introduces a novel IR and Bus Protocol Library for automatic UVM testbench construction across protocols, leveraging LLMs for stimuli refinement.

Findings

Achieves an average code coverage of 95.65%.

Reduces verification time from several days to 4.5 hours.

First framework to automate subsystem-level UVM testbench generation across mainstream protocols.

Abstract

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.