Bridging RTL and Assertion Generation With Large Language Models
IEEE Design & Test · 2026-06 · 43 (3) · 5-13
DOI: 10.1109/mdat.2026.3670060 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Design & Test, 2026-06. Verfasst von Jayanth Thangellamudi und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 12 Literaturangaben. Gefördert von: National Science Foundation.
Abstract (Originalsprache)
Editor’s notes: This article presents a unified, resource-efficient framework that leverages large language models to jointly automate RTL generation and SystemVerilog assertion synthesis, overcoming long-standing fragmentation between design and verification. By fine-tuning LLaMA2-7B with LoRA/QLoRA and deriving assertions directly from generated RTL, the authors demonstrate substantial gains in correctness, consistency, and practicality for modern EDA workflows. –Arnab Raha, Intel, USA
Förderung
- National Science Foundation
Zitieren
APA
Thangellamudi, J., & Dinakarrao, S. M. P. (2026). Bridging RTL and Assertion Generation With Large Language Models. IEEE Design & Test, 43(3), 5-13. https://doi.org/10.1109/mdat.2026.3670060
Vancouver
Thangellamudi J, Dinakarrao SMP. Bridging RTL and Assertion Generation With Large Language Models. IEEE Design & Test. 2026;43(3):5-13. doi:10.1109/mdat.2026.3670060
BibTeX
@article{Thangellamudi2026,
author = {Thangellamudi, Jayanth and Dinakarrao, Sai Manoj Pudukotai},
title = {Bridging RTL and Assertion Generation With Large Language Models},
journal = {IEEE Design & Test},
year = {2026},
volume = {43},
number = {3},
pages = {5--13},
doi = {10.1109/mdat.2026.3670060}
}
EUVIMED