2022 · 19 citations · 7 references
EngineeringComputational EngineeringComputer ScienceHeat TransferMachine LearningThermal AnalysisHeat Transfer AnalysisHeat Transfer ModelingThermal DesignThermal ManagementThermal SimulationThermal ValidationAccuracyComputational Design ExplorationElectro-thermal ModelingTemperature SimulationThermal Device SimulationThermal Resistance ModelingThermal-aware DesignThermal-aware Physical Design
Thermal analysis provides deeper insights into electronic chips’ behavior under different temperature scenarios and enables faster design exploration. However, obtaining detailed and accurate thermal profile on chip is very time-consuming using FEM or CFD. Therefore, there is an urgent need for speeding up the on-chip thermal solution to address various system scenarios. In this paper, we propose a thermal machine-learning (ML) solver to speed-up thermal simulations of chips. The thermal ML-Solver is an extension of the recent novel approach, CoAEMLSim (Composable Autoencoder Machine Learning Simulator) with modifications to the solution algorithm to handle constant and distributed HTC. The proposed method is validated against commercial solvers, such as Ansys MAPDL, as well as a latest ML baseline, UNet, under different scenarios to demonstrate its enhanced accuracy, scalability, and generalizability.
7
Physics-Informed Neural Networks for Heat Transfer Problems
Shengze Cai, Zhicheng Wang, Sifan Wang et al. · Journal of Heat Transfer · 2021 · 1.2K citations
DNN-based Fast Static On-chip Thermal Solver
Jimin Wen, Stephen H. Pan, Norman Chang et al. · 2020 · 36 citations
Engineering, Computational Engineering, Computer Engineering +17