Shift-Left High-Level Synthesis Verification via Knowledge-Augmented LLM Agent

2026-06-15

AI Summary

This work addresses the challenge of verifying functional equivalence between golden C specifications and HLS-C implementations in high-level synthesis (HLS), a task traditionally hindered by heavy reliance on manual effort. To overcome this, the authors propose a left-shift verification framework driven by a knowledge-enhanced large language model (LLM) agent. The framework integrates static structural alignment with dynamic behavioral equivalence checking through a dual-layer consistency verification mechanism, a heterogeneous HLS knowledge graph, and autonomous agents capable of topology-aware testbench generation and cross-toolchain iterative diagnosis. By combining symbolic execution with coverage-driven strategies, the approach achieves an average coverage of 98.26% and dynamic consistency of 95.33% across 107 HLS benchmarks, significantly outperforming baseline methods such as AST comparison, retrieval-augmented generation, and iterative agent-based approaches.

Abstract

High-Level Synthesis (HLS) enables rapid hardware development by translating C/C++ programs into hardware implementations. Functional consistency verification between golden C specifications and HLS-oriented C implementations is a critical yet labor-intensive task in HLS design flows. While Large Language Models (LLMs) have recently shown promise in automated testbench generation, their stochastic nature often leads to insufficient coverage, inconsistent verification environments, and unreliable equivalence checking results. To address these limitations, we propose a knowledge-augmented, agent-driven shift-left verification framework for automated functional consistency checking between golden C and HLS-C implementations before synthesis. The framework introduces a Dual-Tier Consistency Checking mechanism that jointly enforces static structural alignment and dynamic behavioral equivalence between paired testbenches, while integrating symbolic execution and coverage-driven refinement to improve verification completeness. Furthermore, we construct a heterogeneous HLS Verification Knowledge Graph to provide topology-aware reasoning priors for testbench generation, and design an autonomous verification agent to orchestrate iterative refinement and failure diagnosis across heterogeneous toolchains. Experimental results on 107 HLS benchmark pairs demonstrate that the proposed framework achieves 98.26\% average coverage and 95.33\% dynamic consistency, outperforming representative AST-based, retrieval-augmented, and iterative agent-based baselines. https://github.com/cz-5f/HLS-LeVeri.git

Problem

• High-Level Synthesis
• Functional Consistency Verification
• Testbench Generation
• Equivalence Checking
• Verification Coverage

Innovation

• Shift-Left Verification
• Knowledge-Augmented LLM Agent
• Dual-Tier Consistency Checking
• HLS Verification Knowledge Graph
• Coverage-Driven Refinement