arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.09240cs.LG
收藏

DiffHLS: 基于GNN和LLM代码嵌入的高阶综合QoR预测差分学习

DiffHLS: Differential Learning for High-Level Synthesis QoR Prediction with GNNs and LLM Code Embeddings

Shanghai Jiao Tong University(上海交通大学);The Chinese University of Hong Kong(香港中文大学)

Zedong Peng, Zeju Li, Qiang Xu, Jieru Zhao

AI总结:

DiffHLS通过GNN和LLM代码嵌入预测高阶综合QoR,利用核基线与pragma插入设计变体的差分学习,降低合成成本,实验显示在PolyBench上优于GNN基线,且在ForgeHLS数据集上验证了可扩展性。

摘要:

高阶综合(HLS)将C/C++编译为RTL,但探索由pragma驱动的优化选择成本高,因为每个设计点需要耗时的综合。我们提出DiffHLS,一种用于HLS质量-结果(QoR)预测的差分学习框架,通过学习核-设计对:核基线和插入pragma的设计变体。DiffHLS使用专用图神经网络(GNN)分支编码核和设计中间表示图,并通过预训练的代码大语言模型(LLM)代码嵌入增强delta路径。不同于直接回归绝对目标,我们联合预测核基线和设计诱导的delta,并将它们组合以获得设计预测。在PolyBench上,DiffHLS在四个GNN后端下均优于GNN基线,且LLM代码嵌入在GNN-only消融中表现更优。我们进一步在ForgeHLS数据集上验证了可扩展性。

英文摘要:

High-Level Synthesis (HLS) compiles C/C++ into RTL, but exploring pragma-driven optimization choices remains expensive because each design point requires time-consuming synthesis. We propose \textbf{\DiffHLS}, a differential learning framework for HLS Quality-of-Result (QoR) prediction that learns from kernel--design pairs: a kernel baseline and a pragma-inserted design variant. \DiffHLS~encodes kernel and design intermediate-representation graphs with dedicated graph neural network (GNN) branches, and augments the delta pathway with code embeddings from a pretrained code large language model (LLM). Instead of regressing absolute targets directly, we jointly predict the kernel baseline and the design-induced delta, and compose them to obtain the design prediction. On PolyBench, \DiffHLS~attains lower average MAPE than GNN baselines under four GNN backbones, and LLM code embeddings consistently improve over a GNN-only ablation. We further validate scalability on the ForgeHLS dataset.

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。

↑