用图神经网络实现嵌入式平台实时调度，兼顾性能与温控。
GraphPerf-RT: A Graph-Driven Performance Model for Hardware-Aware Scheduling of OpenMP Codes
- 构建融合任务拓扑、代码语义和运行时状态的异构图模型。
- 在三款ARM设备上实现95%以上相关性与接近100%置信区间覆盖率。
- 适合需要低延迟、高可靠性的嵌入式AI系统调度优化场景。
嵌入式平台上的自主智能体需要在资源与热约束下实现实时、风险可控的调度。传统启发式方法难以应对工作负载不规则性，表格回归器丢失结构信息，无模型强化学习则存在过热风险。我们提出GraphPerf-RT，一种图神经网络代理模型，在保持启发式速度（2-7毫秒）的同时达到深度学习精度。该模型首次将任务有向无环图拓扑、基于控制流图的代码语义与运行时上下文（每核DVFS、热状态、利用率）统一建模于带类型边的异构图中，边类型编码依赖关系、放置关系与竞争关系。采用正态-逆伽马先验的证据回归提供校准的不确定性估计；我们在使完成时间预测上验证其风险感知调度能力。在Jetson TX2、Orin NX、RUBIK Pi三款ARM平台上的实验表明，对对数化完成时间的预测达到R² = 0.81，斯皮尔曼相关系数为0.95，且不确定性校准保守（95%置信度下预测区间覆盖概率PICP = 99.9%）。与四种强化学习方法集成后，基于GraphPerf-RT作为世界模型的多智能体模型驱动强化学习，相较无模型基线实现66%完成时间减少与82%能耗降低，且零热违规。
原文摘要 · Abstract (English)
Autonomous AI agents on embedded platforms require real-time, risk-aware scheduling under resource and thermal constraints. Classical heuristics struggle with workload irregularity, tabular regressors discard structural information, and model-free reinforcement learning (RL) risks overheating. We introduce GraphPerf-RT, a graph neural network surrogate achieving deep learning accuracy at heuristic speeds (2-7ms). GraphPerf-RT is, to our knowledge, the first to unify task DAG topology, CFG-derived code semantics, and runtime context (per-core DVFS, thermal state, utilization) in a heterogeneous graph with typed edges encoding precedence, placement, and contention. Evidential regression with Normal-Inverse-Gamma priors provides calibrated uncertainty; we validate on makespan prediction for risk-aware scheduling. Experiments on three ARM platforms (Jetson TX2, Orin NX, RUBIK Pi) achieve R^2 = 0.81 on log-transformed makespan with Spearman rho = 0.95 and conservative uncertainty calibration (PICP = 99.9% at 95% confidence). Integration with four RL methods demonstrates that multi-agent model-based RL with GraphPerf-RT as the world model achieves 66% makespan reduction and 82% energy reduction versus model-free baselines, with zero thermal violations.
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。