Cedar is presented, which extends equality saturation to RTL an order of magnitude beyond prior e-graph work through an LLM-driven optimization loop that accumulates formally verified rewrite rules across designs : rules discovered while optimizing one circuit are reused on future, unseen ones.
In the agentic flow, the PRISM codegen outperforms other baselines when optimizing complex code and drives the average normalized improvement across the HLS-Eval suite to 26.4\%.
Hao-Cheng Xu, Ye Qiao, Phyo Pyae Moe Aung et al.· 0 citations
A metamorphic testing based evaluation method and a companion benchmark to measure the effectiveness of LLM-aided RTL code optimization show that LLM-aided methods effectively optimize logic operations and data paths, achieving lower or stable wire counts and area with delays near baseline.
Zhi-Hao Xu, Bi-Xin Li, Ran Yan et al.· ACM Transactions on Reconfig...· 0 citations
Large language models (LLMs) can generate register-transfer-level (RTL) code from natural-language specifications, but compilation alone does not establish structural completeness, functional correctness, or implementation efficiency. This paper presents a framework for evaluating LLM-generated RTL beyond compilation,...
Hepziba Susan, R. ShivaranjaniG, Malik Imran et al.· arXiv.org· 1 citation
A novel empirical study targeting three domain- specific languages for transformation rules, namely Comby, GritQL, and Ast-Grep, which shows great potential for LLMs to generate sound, correct, generalizable, and reusable rules.
Axel Allain, Aymeric Blot, D. Khelladi et al.· Proceedings of the 41st IEEE...· 1 citation
This work fine-tune a code-centric LLM on transformations produced by Wyvern and embed Alive2 into a feedback loop that enforces semantic preservation for every generated rewrite, demonstrating that generative AI components can be safely integrated into compiler pipelines through deterministic validation and structured...
LLM-based language services (e.g., summarization, translation, and question answering) require low-latency and cost-effective inference, yet GPU resources may be costly, unavailable, or difficult to integrate in many deployments. Many-core CPUs provide a flexible alternative, but achieving efficient inference requires...