Fast thermal simulation of 2D/3D integrated circuits exploiting neural networks and GPUs
Embedded Systems Laboratory (ESL), Ecole Polytechnique Federale de Lausanne (EPFL), Switzerland
International Symposium on Low Power Electronics and Design (ISLPED) 2011
@inproceedings{vincenzi2011fast,
title={Fast thermal simulation of 2D/3D integrated circuits exploiting neural networks and GPUs},
author={Vincenzi, A. and Sridhar, A. and Ruggiero, M. and Atienza, D.},
booktitle={Low Power Electronics and Design (ISLPED) 2011 International Symposium on},
pages={151–156},
year={2011},
organization={IEEE}
}
Heat removal is one of the major challenges faced in developing the new generation of high density integrated circuits. Future design technologies strongly depend on the availability of efficient means for thermal modeling and analysis. These thermal models must be also accurate and provide the most efficient level of abstraction enabling fast execution. We propose an innovative thermal simulation method based on Neural Networks that is able to solve the scalability problem of transient heat flow simulation in large 2D/3D multi-processor ICs by exploiting the computational power of massively parallel graphics processing units (GPUs).
December 14, 2011 by hgpu
