用图神经网络和大模型优化芯片设计，预测更准、搜索更快。
Intelligent4DSE: Optimizing High-Level Synthesis Design Space Exploration with Graph Neural Networks and Large Language Models
- 结合图神经网络与大模型，自适应消息传递提升预测精度。
- 预测误差降低超一半，关键指标如功耗、延迟等改善显著。
- 适合芯片设计、自动化工具开发人员快速找到最优方案。
高层次综合（HLS）设计空间探索（DSE）对平衡性能、功耗和面积（PPA）至关重要。现有方法多采用消息传递神经网络（MPNN）预测设计质量（QoR），替代耗时的HLS工具估算。然而，传统MPNN存在过平滑和表达力不足问题。同时，元启发式算法虽广泛用于DSE，但需大量领域知识设计算子且调参耗时。为此，我们提出ECoGNNs-LLMMH框架，融合图神经网络与任务自适应消息传递，以及大语言模型增强的元启发式算法。相比最先进方法，ECoGNN在后高层次综合预测中误差降低57.27%；在后实现预测中，翻转寄存器使用减少17.6%，关键路径延迟降低33.7%，功耗下降26.3%，数字信号处理器利用率减少38.3%，块存储器使用减少40.8%。LLMMH变体生成的帕累托前沿优于传统元启发式算法，平均距离参考集改善87.47%；相较GNN-DSE和IRONMAN-PRO，ADRS分别降低68.17%和63.07%。
原文摘要 · Abstract (English)
High-Level Synthesis (HLS) Design Space Exploration (DSE) is essential for generating hardware designs that balance performance, power, and area (PPA). To optimize this process, existing works often employs message-passing neural networks (MPNNs) to predict quality of results (QoR). These predictors serve as evaluators in the DSE process, effectively bypassing the time-consuming estimations traditionally required by HLS tools. However, existing models based on MPNNs struggle with over-smoothing and limited expressiveness. Additionally, while meta-heuristic algorithms are widely used in DSE, they typically require extensive domain-specific knowledge to design operators and time-consuming tuning. To address these limitations, we propose ECoGNNs-LLMMHs, a framework that integrates graph neural networks with task-adaptive message passing and large language model-enhanced meta-heuristic algorithms. Compared with state-of-the-art works, ECoGNN exhibits lower prediction error in the post-HLS prediction task, with the error reduced by 57.27\%. For post-implementation prediction tasks, ECoGNN demonstrates the lowest prediction errors, with average reductions of 17.6\% for flip-flop (FF) usage, 33.7\% for critical path (CP) delay, 26.3\% for power consumption, 38.3\% for digital signal processor (DSP) utilization, and 40.8\% for BRAM usage. LLMMH variants can generate superior Pareto fronts compared to meta-heuristic algorithms in terms of average distance from the reference set (ADRS) with average improvements of 87.47\%, respectively. Compared with the SOTA DSE approaches GNN-DSE and IRONMAN-PRO, LLMMH can reduce the ADRS by 68.17\% and 63.07\% respectively.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。