← 研踪 PaperTrailarXiv:2610.38489 · v1
GI-RTL-Fuzz: Grammar-Informed RTL Generation with LLMs for End-to-End Differential Simulator Fuzzing
首次提交 2026-10-28 17:03
版本更新 2026-10-28 17:03
雷达观测 2026-10-30 10:22
摘要
Register-Transfer Level (RTL) simulators are fundamental to modern IC design workflows, yet like any complex software, they frequently contain critical bugs that compromise simulation accuracy. To systematically stress-test these tools, we introduce GI-RTL-Fuzz, a grammar-informed fuzzing framework that leverages Large Language Models (LLMs) to generate high-quality RTL test cases. Our key innovation is guiding the LLM's generation process using Backus-Naur Form (BNF) grammar coverage information, enabling the exploration of complex and rarely-tested language features. By performing differential testing against different RTL simulators, our framework uncovered a significant number of previously unknown inconsistencies in both the linting process and simulation results of major Verilog simulators.
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-10-28 17:03 · 最新观测版本
GI-RTL-Fuzz: Grammar-Informed RTL Generation with LLMs for End-to-End Differential Simulator Fuzzing
Register-Transfer Level (RTL) simulators are fundamental to modern IC design workflows, yet like any complex software, they frequently contain critical bugs that compromise simulation accuracy. To systematically stress-test these tools, we introduce GI-RTL-Fuzz, a grammar-informed fuzzing framework that leverages Large Language Models (LLMs) to generate high-quality RTL test cases. Our key innovation is guiding the LLM's generation process using Backus-Naur Form (BNF) grammar coverage information, enabling the exploration of complex and rarely-tested language features. By performing differential testing against different RTL simulators, our framework uncovered a significant number of previously unknown inconsistencies in both the linting process and simulation results of major Verilog simulators.
查看此版本解读 →查看此版本原文 ↗