HLSmith: An Expert-Guided Agentic Framework for C/C++-to-HLS Translation

📄 arXiv: 2608.06791v1 📥 PDF

作者: Yuebo Luo, Ahmad Sedigh Baroughi, Philip Stachura, Le Chen, Venkatram Vishwanath, Zhenman Fang, Caiwen Ding

分类: cs.AR, cs.AI

发布日期: 2026-08-07

💡 一句话要点

提出HLSmith框架以解决C/C++到HLS转换的专家知识缺乏问题

🎯 匹配领域: 支柱九：具身大模型 (Embodied Foundation Models)

关键词: FPGA加速器 高层次综合 专家指导 性能优化 机器学习 硬件设计 模型适应

📋 核心要点

  1. 现有的HLS加速器开发方法缺乏硬件直觉和程序知识，导致性能优化困难。
  2. HLSmith通过结合优化知识库和反馈驱动的开发流程，提供了专家指导的转换框架。
  3. HLSmith在PolyBench上实现了4.24倍的加速，且功能正确率显著高于ChatHLS。

📝 摘要（中文）

应用特定的FPGA加速器在多个应用领域提供了显著的性能和能效提升，但开发过程成本高昂，通常需要数月的专业努力。即使使用高层次综合（HLS），设计者仍需具备广泛的硬件专业知识。本文提出HLSmith，一个专家指导的框架，用于将C/C++程序转换为优化的HLS加速器。HLSmith结合了HLS优化知识库、反馈驱动的分阶段流程和模型适应管道，显著提高了设计的有效性和性能。实验表明，HLSmith在PolyBench上相较于ChatHLS实现了4.24倍的几何平均加速，并在每个基准测试中生成了功能正确的设计。

🔬 方法详解

问题定义：本文旨在解决现有C/C++到HLS转换方法中缺乏硬件直觉和优化过程知识的问题。现有方法在识别有效架构和应用硬件变换时存在困难，导致性能不足。

核心思路：HLSmith框架通过专家知识指导，结合优化知识库和反馈机制，帮助设计者更有效地进行HLS加速器的开发。这样的设计旨在减少对硬件专业知识的依赖，提高设计的效率和准确性。

技术框架：HLSmith的整体架构包括三个主要模块：HLS优化知识库、反馈驱动的分阶段流程和模型适应管道。优化知识库编码了变换配方及其适用条件，分阶段流程则模拟了专家的开发实践，模型适应管道将优化轨迹转化为训练数据。

关键创新：HLSmith的主要创新在于将专家知识系统化，并通过反馈机制优化设计流程。这与现有方法的根本区别在于，HLSmith能够在缺乏硬件直觉的情况下，依然生成高性能的HLS设计。

关键设计：HLSmith的设计中，优化知识库包含了安全和不安全的变换案例，反馈流程通过分析瓶颈来指导优化，模型适应管道则利用商业模型的优化轨迹进行微调，确保了设计的有效性和准确性。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

HLSmith在PolyBench基准测试中实现了4.24倍的几何平均加速，相较于ChatHLS的57%有效设计率，HLSmith在每个基准测试中均生成了功能正确的设计。此外，HLSmith在使用商业前沿模型和开放权重模型时，分别达到了252倍和138倍的加速效果。

🎯 应用场景

HLSmith框架具有广泛的应用潜力，尤其是在需要高性能计算的领域，如图像处理、机器学习和科学计算等。通过降低FPGA加速器开发的门槛，HLSmith能够帮助更多的开发者快速实现高效的硬件加速，推动相关技术的普及和发展。

📄 摘要（原文）

Application-specific FPGA accelerators offer substantial performance and energy-efficiency gains across many application domains, but developing them is costly, often requiring months of specialized effort. Even with high-level synthesis (HLS), designers still need extensive hardware expertise to build high-performance accelerators. Although large language models (LLMs) have demonstrated strong software-generation capabilities, even frontier models lack the hardware intuition and procedural knowledge needed to reliably translate baseline C/C++ programs into high-performance HLS designs: they struggle to identify effective architectures, follow the optimization processes used by HLS experts, and apply hardware transformations consistently across diverse kernels. We present HLSmith, an expert-guided framework for translating C/C++ programs into optimized HLS accelerators. HLSmith combines three components: an HLS optimization expertise library that encodes guarded transformation recipes, their applicability and prerequisite conditions, and unsafe cases to avoid; a staged, feedback-driven orchestration flow modeled on expert HLS development practice that guides agents through synthesis, bottleneck analysis, and optimization; and a tool-grounded model-adaptation pipeline that converts optimization trajectories from commercial frontier models into training data for fine-tuning open-weight LLMs. We evaluate HLSmith on PolyBench against ChatHLS, a leading prior agent-orchestration framework for HLS accelerator development. HLSmith achieves a geometric mean speedup of 4.24x over ChatHLS while producing functionally correct designs, in both software and RTL simulation, for every benchmark, compared with ChatHLS's 57% valid-design rate. It further reaches speedups of up to 252x and 138x with commercial frontier models and open-weight models, respectively.