直接从性能指标预测芯片温度分布，速度快精度高。
TherMapNet Attention-Guided Runtime Full-Chip Thermal Map Prediction from Performance Metrics
- 用Transformer+CNN结构，从性能数据直接推算温度图
- 实测误差低于0.26℃，推理时间不足2.4毫秒
- 适合多核处理器实时温控，尤其适配现代高性能芯片
高性能芯片的运行时热管理依赖于快速准确的全芯片温度图。传统仿真器通常先从性能指标估算功耗，带来额外开销。本文提出TherMapNet，一种基于注意力机制的热仿真模型，可直接从性能指标预测全芯片温度分布。通过Transformer编码器将各指标的时间序列视为令牌，捕捉动态负载的时序演化；再由CNN提取精细空间特征，其中采用双分支通道-空间注意力卷积模块（DACM）和三元组损失函数，提升空间学习与重建精度。在多核CPU（AMD Ryzen 7 4800U）和多核GPU（NVIDIA GeForce RTX 4060）上测试，结果表明其优于现有热仿真方法，均方根误差低于0.26℃，在NVIDIA GeForce RTX 3090 GPU上推理时间小于2.4毫秒，具备支持现代多核芯片高质量运行时热管理的能力。
原文摘要 · Abstract (English)
Runtime thermal management of high-performance chips depends on fast and accurate full-chip thermal maps. Conventional simulators typically estimate power traces from performance metrics first, which adds overhead. This work proposes TherMapNet, an attention-guided thermal simulator that predicts full-chip thermal maps directly from performance metrics. A Transformer encoder captures temporal evolution by treating the time series of each metric as a token, improving modeling of dynamic workloads. A CNN then extracts fine-grained spatial features. For the CNN, a dual-branch channel-spatial attention convolution module (DACM) and a triplet loss are used to improve spatial learning and reconstruction accuracy. TherMapNet is applied to a multi-core CPU (AMD Ryzen 7 4800U) and a many-core GPU (NVIDIA GeForce RTX 4060). Experiments show that it outperforms prior thermal simulators, with RMSE below 0.26 C and inference under 2.4 ms on an NVIDIA GeForce RTX 3090 GPU. These results indicate that TherMapNet can support high-quality runtime thermal management of modern multi-core chips.
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。