LLM4PQC - 通过反馈驱动的LLM实现准确且高效的PQC核心合成
LLM4PQC - Accurate and Efficient Synthesis of PQC Cores by Feedback-Driven LLMs
AI总结:
LLM4PQC通过反馈驱动的LLM实现PQC核心的高效准确合成,减少手动工作量并加速设计探索。
摘要:
后量子密码(PQC)硬件设计是一个复杂且分层的过程,面临诸多挑战。主要瓶颈之一是将PQC参考代码从C语言转换为高层次综合(HLS)规范,这需要大量的手动重构。另一个瓶颈是复杂PQC原语的综合可扩展性,包括数论变换(NTT)加速器和宽内存接口。尽管大语言模型(LLM)在一般用途语言如Python中的编码任务中表现出色,但硬件设计的编码更具挑战性;反馈驱动和代理集成是成功最新方法的关键原则。本文提出LLM4PQC,一个基于LLM的框架,将高层次PQC规范和参考C代码重构为HLS-ready且可综合的C代码。我们的框架生成并验证所得到的RTL代码。在正确性方面,我们利用多级检查,涵盖快速C编译和仿真以及RTL仿真。针对NIST PQC参考设计的案例研究显示,与传统流程相比,减少了手动工作量并加快了设计空间探索。总体而言,LLM4PQC为合成复杂硬件加速器提供了一种强大而高效的途径。
英文摘要:
The design of post-quantum cryptography (PQC) hardware is a complex and hierarchical process with many challenges. A primary bottleneck is the conversion of PQC reference codes from C to high-level synthesis (HLS) specifications, which requires extensive manual refactoring. Another bottleneck is the scalability of synthesis for complex PQC primitives, including number theoretic transform (NTT) accelerators and wide memory interfaces. While large language models (LLMs) have shown remarkable results for coding in general-purpose languages like Python, coding for hardware design is more challenging; feedback-driven and agentic integration are key principles of successful state-of-the-art approaches. Here, we propose LLM4PQC, an LLM-based framework that refactors high-level PQC specifications and reference C codes into HLS-ready and synthesizable C code. Our framework generates and verifies the resulting RTL code. For correctness, we leverage a hierarchy of checks, covering fast C compilation and simulation as well as RTL simulation. Case studies on NIST PQC reference designs demonstrate a reduction in manual effort and accelerated design-space exploration compared to traditional flows. Overall, LLM4PQC provides a powerful and efficient pathway for synthesizing complex hardware accelerators.
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。