ScaleRTL: Scaling LLMs with Reasoning Data and Test-Time Compute for Accurate RTL Code Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908451320365056 |
|---|---|
| author | Deng, Chenhui Tsai, Yun-Da Liu, Guan-Ting Yu, Zhongzhi Ren, Haoxing |
| author_facet | Deng, Chenhui Tsai, Yun-Da Liu, Guan-Ting Yu, Zhongzhi Ren, Haoxing |
| contents | Recent advances in large language models (LLMs) have enabled near-human performance on software coding benchmarks, but their effectiveness in RTL code generation remains limited due to the scarcity of high-quality training data. While prior efforts have fine-tuned LLMs for RTL tasks, they do not fundamentally overcome the data bottleneck and lack support for test-time scaling due to their non-reasoning nature. In this work, we introduce ScaleRTL, the first reasoning LLM for RTL coding that scales up both high-quality reasoning data and test-time compute. Specifically, we curate a diverse set of long chain-of-thought reasoning traces averaging 56K tokens each, resulting in a dataset of 3.5B tokens that captures rich RTL knowledge. Fine-tuning a general-purpose reasoning model on this corpus yields ScaleRTL that is capable of deep RTL reasoning. Subsequently, we further enhance the performance of ScaleRTL through a novel test-time scaling strategy that extends the reasoning process via iteratively reflecting on and self-correcting previous reasoning steps. Experimental results show that ScaleRTL achieves state-of-the-art performance on VerilogEval and RTLLM, outperforming 18 competitive baselines by up to 18.4% on VerilogEval and 12.7% on RTLLM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_05566 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ScaleRTL: Scaling LLMs with Reasoning Data and Test-Time Compute for Accurate RTL Code Generation Deng, Chenhui Tsai, Yun-Da Liu, Guan-Ting Yu, Zhongzhi Ren, Haoxing Hardware Architecture Artificial Intelligence Recent advances in large language models (LLMs) have enabled near-human performance on software coding benchmarks, but their effectiveness in RTL code generation remains limited due to the scarcity of high-quality training data. While prior efforts have fine-tuned LLMs for RTL tasks, they do not fundamentally overcome the data bottleneck and lack support for test-time scaling due to their non-reasoning nature. In this work, we introduce ScaleRTL, the first reasoning LLM for RTL coding that scales up both high-quality reasoning data and test-time compute. Specifically, we curate a diverse set of long chain-of-thought reasoning traces averaging 56K tokens each, resulting in a dataset of 3.5B tokens that captures rich RTL knowledge. Fine-tuning a general-purpose reasoning model on this corpus yields ScaleRTL that is capable of deep RTL reasoning. Subsequently, we further enhance the performance of ScaleRTL through a novel test-time scaling strategy that extends the reasoning process via iteratively reflecting on and self-correcting previous reasoning steps. Experimental results show that ScaleRTL achieves state-of-the-art performance on VerilogEval and RTLLM, outperforming 18 competitive baselines by up to 18.4% on VerilogEval and 12.7% on RTLLM. |
| title | ScaleRTL: Scaling LLMs with Reasoning Data and Test-Time Compute for Accurate RTL Code Generation |
| topic | Hardware Architecture Artificial Intelligence |
| url | https://arxiv.org/abs/2506.05566 |