# Neural Network Surrogate Model for Junction Temperature and Hotspot Position in 3D Multi-Layer High Bandwidth Memory (HBM) Chiplets under Varying Thermal Conditions

arXiv: https://arxiv.org/abs/2503.04049 · HTML: https://mlsanity.com/paper/2503.04049/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 19 references that are in the map.
- First posted on arXiv 6 Mar 2025.

## Builds on (most cited first, 3 of 3)

- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [DeepOHeat: Operator Learning-based Ultra-fast Thermal Simulation in 3D-IC Design](https://mlsanity.com/paper/2302.12949/) (2023)
- [An Artificial Neural Networks based Temperature Prediction Framework for Network-on-Chip based Multicore Platform](https://mlsanity.com/paper/1612.04197/) (2016)

## Abstract (arXiv)

As the demand for computational power increases, high-bandwidth memory (HBM) has become a critical technology for next-generation computing systems. However, the widespread adoption of HBM presents significant thermal management challenges, particularly in multilayer through-silicon-via (TSV) stacked structures under varying thermal conditions, where accurate prediction of junction temperature and hotspot position is essential during the early design. This work develops a data-driven neural network model for the fast prediction of junction temperature and hotspot position in 3D HBM chiplets. The model, trained with a data set of 13,494 different combinations of thermal condition parameters, sampled from a vast parameter space characterized by high-dimensional combination (up to 327), can accurately and quickly infer the junction temperature and hotspot position for any thermal conditions in the parameter space. Moreover, it shows good generalizability for other thermal conditions not considered in the parameter space. The data set is constructed using accurate finite element solvers. This method not only minimizes the reliance on costly experimental tests and extensive computational resources for finite element analysis but also accelerates the design and optimization of complex HBM systems, making it a valuable tool for improving thermal management and performance in high-performance computing applications.