发表机构
University of California, Santa Barbara; Cadence Design Systems（加利福尼亚大学圣巴巴拉分校; 楷登电子科技公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
DeepOHeat-v2通过改进物理损失与自改进框架，解决高对比度3D-IC热优化问题，使热预测误差大幅降低，速度提升56倍且性能匹配逐步求解优化器。
AI 中文摘要
面向多裸片3D集成电路的热感知优化需评估大量设计，每个设计都需进行成本高昂的热方程求解。算子学习代理可将该求解替换为快速前向传播，理想情况下仅从物理数据训练，无需标注数据。DeepOHeat-v1已实现此类代理的快速性与可靠性，但仅适用于低对比度几何结构。高对比度多裸片堆叠会从两方面破坏其性能：不连续电导率使连续物理损失在材料界面处定义不明确；病态条件（κ₂(Aₕ)≈6×10⁴）使离散强形式损失超出一阶优化范围。我们提出DeepOHeat-v2以克服上述问题：首先，我们采用天然处理不连续性的离散物理损失进行训练，其能量形式将预测空间损失-海森矩阵条件数从κ²降至κ，结合矩阵预条件优化器，将平均峰值温度误差从30K以上降至0.55K；其次，由于优化会偏离训练分布，我们提出自改进框架：热点信任门将标记的布局发送至参考求解器，代理基于精炼解进行增量再训练，仅当验证集泛化误差提升时保留更新。在多裸片基准测试中，返回设计的代理-真实峰值误差从1.12K降至0.11K，与每步求解的优化器性能相当，运行速度快56倍。
英文摘要
Thermal-aware optimization of multi-die 3D integrated circuits evaluates many designs, each a costly heat-equation solve. Operator-learning surrogates replace this solve with a fast forward pass, ideally trained from physics alone, without labeled data. DeepOHeat-v1 made such surrogates fast and trustworthy, but only on low-contrast geometries. High-contrast multi-die stacks break it in two ways: discontinuous conductivities make the continuous physics loss ill-defined at material interfaces, and ill-conditioning ($κ_2(A_h) \approx 6 \times 10^4$) puts the discretized strong-form loss beyond first-order optimization. We propose DeepOHeat-v2 to overcome both. First, we train on a discretized physics loss that handles the discontinuities natively; its energy form reduces the prediction-space loss-Hessian conditioning from $κ^2$ to $κ$, and a matrix-preconditioned optimizer cuts the mean peak temperature error from over 30 K to 0.55 K. Second, because optimization leaves the training distribution, we propose a self-improving framework: a hotspot trust gate sends flagged placements to a reference solver, and the surrogate incrementally retrains on the refined solutions, keeping an update only when it improves held-out validation error. On a multi-die benchmark, the surrogate-true peak gap on the returned design falls from 1.12 K to 0.11 K, matching a solve-at-every-step optimizer while running $56\times$ faster.
