CktEvo: 用于设计演化的仓库级RTL代码基准
CktEvo: Repository-Level RTL Code Benchmark for Design Evolution
AI总结:
CktEvo提出一个用于仓库级RTL代码演化的基准和框架,通过闭环框架实现PPA改进,无需人工干预。
摘要:
寄存器传输级(RTL)编码是一种迭代的、仓库级的过程,在其中功率、性能和面积(PPA)从许多文件之间的相互作用以及下游工具链中涌现。尽管大型语言模型(LLMs)最近已被应用于硬件设计,但大多数努力集中在从自然语言提示生成或调试,其中模糊性和幻觉需要专家审查。另一条工作线从正式输入开始,但通常优化高层次综合或孤立模块,并且通常与跨文件依赖性脱节。在本工作中,我们提出了CktEvo,这是一个用于仓库级RTL演化的基准和参考框架。与之前的基准由孤立片段组成不同,我们的基准针对完整的IP核心,其中PPA从跨文件依赖性中涌现。我们的基准包了几个多质量的Verilog仓库来自真实设计。我们将任务正式化为:给定一个初始仓库,产生编辑以保持功能行为同时改进PPA。我们还提供了一个闭环框架,将LLM提出的编辑与工具链反馈结合,以实现跨文件修改和在仓库规模上的迭代修复。我们的实验表明,参考框架在没有任何人类互动的情况下实现了PPA的改进。CktEvo建立了严格且可执行的基础,用于研究对工程实践至关重要的LLM辅助RTL优化:仓库级、功能保持和PPA驱动。
英文摘要:
Register-Transfer Level (RTL) coding is an iterative, repository-scale process in which Power, Performance, and Area (PPA) emerge from interactions across many files and the downstream toolchain. While large language models (LLMs) have recently been applied to hardware design, most efforts focus on generation or debugging from natural-language prompts, where ambiguity and hallucinations necessitate expert review. A separate line of work begins from formal inputs, yet typically optimizes high-level synthesis or isolated modules and remains decoupled from cross-file dependencies. In this work, we present CktEvo, a benchmark and reference framework for repo-level RTL evolution. Unlike prior benchmarks consisting of isolated snippets, our benchmark targets complete IP cores where PPA emerges from cross-file dependencies. Our benchmark packages several high-quality Verilog repositories from real-world designs. We formalize the task as: given an initial repository, produce edits that preserve functional behavior while improving PPA. We also provide a closed-loop framework that couples LLM-proposed edits with toolchain feedback to enable cross-file modifications and iterative repair at repository scale. Our experiments demonstrate that the reference framework realizes PPA improvements without any human interactions. CktEvo establishes a rigorous and executable foundation for studying LLM-assisted RTL optimization that matters for engineering practice: repository-level, function-preserving, and PPA-driven.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。