发表机构
The Hong Kong University of Science and Technology; Huazhong Agricultural University（香港科技大学; 华中农业大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
X-OPM提出一种基于同步数字VLSI设计原则的可解释特征工程框架，结合树模型与线性模型，并引入人在回路工作流，在C906处理器上实现R²>0.93且面积开销低于0.1%，优于现有方法。
AI 中文摘要
主动功耗管理系统通过运行时功耗预测和功耗感知调度来降低处理器动态功耗。准确、稳定且低开销的数字片上功耗计（OPM）对于提高预测质量至关重要。近期研究探索了多种建模方法，包括使用线性模型、决策树和多层感知机（MLP）来构建OPM。然而，当前大多数方法端到端地训练模型，而未分析特征的物理可解释性，这影响了它们对未见工作负载的泛化能力。基于同步数字VLSI电路的设计原则，X-OPM引入了一个鲁棒的特征工程框架，该框架使用基于树的模型来捕获特征交互，并使用线性模型进行预测。它还整合了一个人在回路（human-in-the-loop）工作流程，以在模型准确性和建模工作量之间取得平衡。在商业C906向量处理器上评估时，X-OPM在所有工作负载下始终实现$R^2 > 0.93$，且采样窗口大小设置为低于$8$个周期。相比之下，包括APOLLO、COBIT和标准MLP在内的最先进方法无法在所有测试用例上泛化。使用商业EDA工具进行布局显示，X-OPM的面积开销低于$0.1\%$，这与轻量级基于树和线性模型相当，且显著小于基于MLP的模型。
英文摘要
Proactive power management systems reduce processor dynamic power through runtime power prediction and power-aware scheduling. Accurate, stable and low-overhead digital on-chip power meters (OPMs) are crucial for improving the prediction quality. Recent studies have explored various modeling methods, including using linear models, decision trees, and multi-layer perceptrons (MLPs) to construct OPMs. However, most current approaches train models end-to-end without analyzing the physical interpretability of features, affecting their ability to generalize to unseen workloads. Grounded in the design principles of synchronous digital VLSI circuits, X-OPM introduces a robust feature engineering framework that uses tree-based models to capture feature interactions and linear models for prediction. It also incorporates a human-in-the-loop workflow to balance model accuracy against modeling effort. Evaluated on a commercial C906 vector processor, X-OPM consistently achieves $R^2 > 0.93$ across all workloads with sampling window size set below $8$ cycles. In contrast, state-of-the-art methods including APOLLO, COBIT, and standard MLPs fail to generalize across all test cases. Layout with commercial EDA tools shows that X-OPM incurs an area overhead below $0.1\%$, which is on par with lightweight tree-based and linear models, and significantly smaller than MLP-based models.
