Metraipolis › archive › dc_74d4bf6dbdf4
AutoC2V: Synthesis-Guided LLM Training for QoR-Optimized C++-to-Verilog Generation — arXiv:2611.10824
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.10824
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:46:12.648Z
- SHA-256 of the archived text
d913c0b61c1bd559c9f3f1e18184c922f9e56a91b86af6aae0b315c6f4ca2fed- Stable URL of this page
https://metraipolis.com/documento/dc_74d4bf6dbdf4
How to cite
AutoC2V: Synthesis-Guided LLM Training for QoR-Optimized C++-to-Verilog Generation — arXiv:2611.10824 — arXiv (en), https://arxiv.org/abs/2611.10824 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_74d4bf6dbdf4 (Metraipolis archive dc_74d4bf6dbdf4, sha256 d913c0b61c1bd559c9f3f1e18184c922f9e56a91b86af6aae0b315c6f4ca2fed)
BibTeX
@misc{dc74d4bf6dbdf4,
title = {AutoC2V: Synthesis-Guided LLM Training for QoR-Optimized C++-to-Verilog Generation — arXiv:2611.10824},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.10824},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_74d4bf6dbdf4; sha256 d913c0b61c1bd559c9f3f1e18184c922f9e56a91b86af6aae0b315c6f4ca2fed},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10824. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
High-level synthesis (HLS) can translate C/C++ kernels into register-transfer level (RTL) designs, yet generating high-quality hardware still relies heavily on manual pragma tuning and repeated synthesis evaluation. We propose AutoC2V, a C++-to-Verilog generation framework driven by real synthesis feedback that enables large language models (LLMs) to directly generate RTL with improved quality of results (QoR) from synthesizable C++ kernels. We construct training data from real synthesis results, including synthesizable C++ source code, the corresponding Verilog RTL, QoR metrics, and optimization objectives. Using this dataset, we align the model toward synthesis-aware RTL generation through Supervised Fine-Tuning (SFT) and Group Relative Policy Optimization (GRPO). To reduce the high cost of repeatedly invoking real synthesis during GRPO, we design the QoR Prediction Reward Model (QoR RM), which predicts latency and resource metrics by encoding RTL into long-context semantic representations, thereby providing low-cost and continuous QoR reward signals for policy optimization. Experimental results demonstrate that AutoC2V not only substantially improves RTL functional pass rates, but also achieves superior latency and resource optimization compared to the unfine-tuned base model, representative HLS optimization approaches (HLSPilot, LLM-DSE, and AutoDSE), and advanced general-purpose commercial models (Claude Opus 4.8, GPT-5.5, Gemini 3.1 Pro, DeepSeek v4 Pro, and GLM-5.2). These results indicate that combining real synthesis data with efficient QoR reward modeling can further improve the ability of LLMs to generate high-quality RTL. Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.AR, nuovi lavori del giorno). Categorie arXiv: Hardware Architecture (cs.AR) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.10824 — 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 2026-11-10T18:38:22.449Z dalla pagina https://arxiv.org/list/cs.AR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).