Automated SVA Generation with LLMs

TL;DR

This paper introduces SVA Generator, a data-centric framework that translates natural-language SVA descriptions into executable SVAs, significantly improving semantic correctness over general LLMs through structured validation and benchmarking.

Contribution

It presents a novel, data-driven approach with a structured evaluation benchmark for reliable, semantics-preserving SVA generation using LLMs.

Findings

SVA Generator achieves higher semantic equivalence rates than general LLMs.

The framework maintains comparable syntax pass rates across difficulty tiers.

Depth-stratified benchmarking reveals the importance of high-fidelity data for semantic accuracy.

Abstract

Functional verification remains a dominant cost in modern IC development, and SystemVerilog Assertions (SVAs) are critical for simulation-based monitoring and formal property checking. However, writing SVAs by hand is time-consuming and error-prone. Directly prompting general-purpose large language models (LLMs) is also unreliable: the generated properties are often syntactically invalid or semantically incorrect, and the problem is exacerbated by scarce, high-quality domain training data. We present SVA Generator, a data-centric framework that translates natural-language SVA Descriptions (SVADs) into executable SVAs. It uses AST-grounded constraint injection and an automated supervision pipeline that enforces structural consistency and reduces hallucinations via de-duplication and constraint checks. To enable rigorous evaluation, we introduce a benchmark suite stratified by AST depth and use formal property equivalence checking to quantify semantic correctness separately from syntax validity, by checking mutual implication between the generated and reference properties under the same clocking and environment assumptions. Across all difficulty tiers, SVA Generator achieves comparable Syntax Pass Rate (SPR) to strong general LLM baselines, while delivering substantially higher Semantic Equivalence Rate (SER) on deeper tiers: +24.5 pp on D2, +26.0 pp on D3, and +17.5 pp on D4 relative to the best-performing general LLM, corresponding to a +22.7 pp SER improvement on average over D2--D4. These results highlight that high-fidelity data construction and depth-stratified benchmarking are key to reliable, semantics-preserving SVA generation.