Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

UCAgent: An End-to-End Agent for Block-Level Functional Verification

Junyue Wang, Zhicheng Yao, Yan Pi, Xiaolong Li, Fangyuan Song, Jinru Wang, Yunlong Xie, Sa Wang, Yungang Bao

Abstract

Functional verification remains a critical bottleneck in modern IC development cycles, accounting for approximately 70% of total development time in many projects. However, traditional methods, including constrained-random and formal verification, struggle to keep pace with the growing complexity of modern semiconductor designs. While recent advances in Large Language Models (LLMs) have shown promise in code generation and task automation, significant challenges hinder the realization of end-to-end functional verification automation. These challenges include (i) limited accuracy in generating Verilog/SystemVerilog verification code, (ii) the fragility of LLMs when executing complex, multi-step verification workflows, and (iii) the difficulty of maintaining verification consistency across specifications, coverage models, and test cases throughout the workflow. To address these challenges, we propose UCAgent, an end-to-end agent that automates hardware block-level functional verification based on three core mechanisms. First, we establish a pure Python verification environment using Picker and Toffee to avoid relying on LLM-generated SystemVerilog verification code. Second, we introduce a configurable 31-stage fine-grained verification workflow to guide the LLM, where each stage is verified by an automated checker. Furthermore, we propose a Verification Consistency Labeling Mechanism (VCLM) that assigns hierarchical labels to LLM-generated artifacts, improving the reliability and traceability of verification. Experimental results show that UCAgent can complete end-to-end automated verification on multiple modules, including the UART, FPU, and integer divider modules, achieving up to 98.5% code coverage and up to 100% functional coverage. UCAgent also discovers previously unidentified design defects in realistic designs, demonstrating its practical potential.

UCAgent: An End-to-End Agent for Block-Level Functional Verification

Abstract

Functional verification remains a critical bottleneck in modern IC development cycles, accounting for approximately 70% of total development time in many projects. However, traditional methods, including constrained-random and formal verification, struggle to keep pace with the growing complexity of modern semiconductor designs. While recent advances in Large Language Models (LLMs) have shown promise in code generation and task automation, significant challenges hinder the realization of end-to-end functional verification automation. These challenges include (i) limited accuracy in generating Verilog/SystemVerilog verification code, (ii) the fragility of LLMs when executing complex, multi-step verification workflows, and (iii) the difficulty of maintaining verification consistency across specifications, coverage models, and test cases throughout the workflow. To address these challenges, we propose UCAgent, an end-to-end agent that automates hardware block-level functional verification based on three core mechanisms. First, we establish a pure Python verification environment using Picker and Toffee to avoid relying on LLM-generated SystemVerilog verification code. Second, we introduce a configurable 31-stage fine-grained verification workflow to guide the LLM, where each stage is verified by an automated checker. Furthermore, we propose a Verification Consistency Labeling Mechanism (VCLM) that assigns hierarchical labels to LLM-generated artifacts, improving the reliability and traceability of verification. Experimental results show that UCAgent can complete end-to-end automated verification on multiple modules, including the UART, FPU, and integer divider modules, achieving up to 98.5% code coverage and up to 100% functional coverage. UCAgent also discovers previously unidentified design defects in realistic designs, demonstrating its practical potential.

Paper Structure

This paper contains 22 sections, 8 figures, 1 table.

Table of Contents

  1. Introduction
  2. Design Overview
  3. Python Verification Environment
  4. The Verification Workflow
  5. Verification Consistency Labeling Mechanism
  6. UCAgent Implementation
  7. Agent Middleware
  8. Workflow Management Module
  9. Stage Validation Module
  10. Implementation of VCLM
  11. Python-Based Verification Execution Environment
  12. Evaluation
  13. Experimental Setup
  14. Overall Verification Effectiveness
  15. Stage-wise Execution Analysis
  16. ...and 7 more sections

Figures (8)

  • Figure 1: An example that violates verification consistency. The term overrun is replaced with the semantically similar overflow; additionally, an underrun scenario is incorrectly added. Such a scenario typically does not appear in UART designs and is more common in modules like SPI and USB host controllers intel_xhci_reqspec_2019_rev122.
  • Figure 2: Relationships among UCAgent's core mechanisms
  • Figure 3: The detailed verification workflow. Dotted stages indicate that they are skipped by default
  • Figure 4: UCAgent implementation overview
  • Figure 5: Workflow management module
  • ...and 3 more figures