Metraipolis › archive › dc_240024bce7cd

VSpector: Specification-Driven Bug Detection for RISC-V CPUs — arXiv:2609.23517

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.23517
License (as archived)
CC0-1.0
Archived
2026-10-09T06:55:57.603Z
SHA-256 of the archived text
b9e2827b5a7e90a29776bc2bf98e62f5e701bdfbf6c61ad1dda706720d7a461f
Stable URL of this page
https://metraipolis.com/documento/dc_240024bce7cd

How to cite

VSpector: Specification-Driven Bug Detection for RISC-V CPUs — arXiv:2609.23517 — arXiv (en), https://arxiv.org/abs/2609.23517 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_240024bce7cd (Metraipolis archive dc_240024bce7cd, sha256 b9e2827b5a7e90a29776bc2bf98e62f5e701bdfbf6c61ad1dda706720d7a461f)
BibTeX
@misc{dc240024bce7cd,
  title = {VSpector: Specification-Driven Bug Detection for RISC-V CPUs — arXiv:2609.23517},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.23517},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_240024bce7cd; sha256 b9e2827b5a7e90a29776bc2bf98e62f5e701bdfbf6c61ad1dda706720d7a461f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23517. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Detecting RTL design bugs in open-source RISC-V CPU implementations is critical for ensuring system reliability. Traditional detection approaches inherently rely on predefined artifacts. In this paper, we leverage the official,natural-language RISC-V specifications as an effective information source for bug detection. We present VSpector, a specification-driven bug detection pipeline that directly checks whether CPU register-transfer level (RTL) implementations adhere to official specification rules, without requiring specialized construction of reference models, formal properties, or custom bug patterns. To resolve the key technical trade-off between broad context scope and model reasoning accuracy when using Large Language Models (LLMs), VSpector employs a stepwise context refinement scheme across a four-stage pipeline: rule extraction, implementation localization, candidate identification, and sequential violation auditing. We evaluate VSpector on two industrial-strength RISC-V CPUs, CVA6 and XiangShan. Out of 217 reported candidates, manual inspection confirmed 148 true violations, representing a 68.2% precision. These violations correspond to 73 distinct bugs, including 42 previously unknown bugs. In our comparative experiments, DiveFuzz, a state-of-the-art CPU fuzzer, detected none of these new bugs during 24-hour runs per CPU. All 42 new bugs have been reported upstream, with developers already fixing 19 and confirming an additional 11 (30 in total), demonstrating that specification-driven auditing is a practical and complementary strategy for CPU bug detection.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-22 in cs.AR).
Categorie arXiv: Software Engineering (cs.SE) ; Hardware Architecture (cs.AR).
Pagina del lavoro: https://arxiv.org/abs/2609.23517 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T06:50:43.579Z dalla pagina https://arxiv.org/catchup/cs.AR/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).