TY - GEN
T1 - AI-Assisted Electro-Thermal Co-Design for Hybrid Bonded Packages
AU - Konduru, Juhitha
AU - Rangarajan, Srikanth
AU - Schutt-Aine, Jose E.
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025
Y1 - 2025
N2 - As electronic components become more complex and power-dense, thermal effects significantly impact their performance. Therefore, electro-thermal co-simulation tools are necessary for accurately modeling the devices. By integrating thermal analysis with electrical simulations, we can optimize designs for efficiency without overheating issues. This paper discusses a method to perform electro-thermal co-simulation using machine learning. The proposed method shows a 220X speedup when compared to the two-way coupling process for electrothermal simulations.
AB - As electronic components become more complex and power-dense, thermal effects significantly impact their performance. Therefore, electro-thermal co-simulation tools are necessary for accurately modeling the devices. By integrating thermal analysis with electrical simulations, we can optimize designs for efficiency without overheating issues. This paper discusses a method to perform electro-thermal co-simulation using machine learning. The proposed method shows a 220X speedup when compared to the two-way coupling process for electrothermal simulations.
KW - electro-thermal analysis
KW - machine learning
KW - neural networks
KW - two-way coupling
UR - https://www.scopus.com/pages/publications/105010648533
UR - https://www.scopus.com/pages/publications/105010648533#tab=citedBy
U2 - 10.1109/ECTC51687.2025.00165
DO - 10.1109/ECTC51687.2025.00165
M3 - Conference contribution
AN - SCOPUS:105010648533
T3 - Proceedings - Electronic Components and Technology Conference
SP - 947
EP - 952
BT - Proceedings - IEEE 75th Electronic Components and Technology Conference, ECTC 2025
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 75th IEEE Electronic Components and Technology Conference, ECTC 2025
Y2 - 27 May 2025 through 30 May 2025
ER -