Encoder-Decoder Networks for Analyzing Thermal and Power Delivery Networks
ACM Transactions on Design Automation of Electronic Systems · 31.01.2023 · 28 (1) · 1-27
DOI: 10.1145/3526115 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Design Automation of Electronic Systems, online erschienen am 10.12.2022. Verfasst von Vidya A. Chhabria und 5 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: University of Minnesota Doctoral Dissertation Fellowship, Louise Dosdall Fellowship.
Abstract (Originalsprache)
Power delivery network (PDN) analysis and thermal analysis are computationally expensive tasks that are essential for successful integrated circuit (IC) design. Algorithmically, both these analyses have similar computational structure and complexity as they involve the solution to a partial differential equation of the same form. This article converts these analyses into image-to-image and sequence-to-sequence translation tasks, which allows leveraging a class of machine learning models with an encoder-decoder–based generative (EDGe) architecture to address the time-intensive nature of these tasks. For PDN analysis, we propose two networks: (i) IREDGe: a full-chip static and dynamic IR drop predictor and (ii) EMEDGe: electromigration (EM) hotspot classifier based on input power, power grid distribution, and power pad distribution patterns. For thermal analysis, we propose ThermEDGe, a full-chip static and dynamic temperature estimator based on input power distribution patterns for thermal analysis. These networks are transferable across designs synthesized within the same technology and packing solution. The networks predict on-chip IR drop, EM hotspot locations, and temperature in milliseconds with negligibly small errors against commercial tools requiring several hours.
Förderung
- University of Minnesota Doctoral Dissertation Fellowship
- Louise Dosdall Fellowship
Zitieren
APA
Chhabria, V. A., Ahuja, V., Prabhu, A., Patil, N., Jain, P., & Sapatnekar, S. S. (2023). Encoder-Decoder Networks for Analyzing Thermal and Power Delivery Networks. ACM Transactions on Design Automation of Electronic Systems, 28(1), 1-27. https://doi.org/10.1145/3526115
Vancouver
Chhabria VA, Ahuja V, Prabhu A, Patil N, Jain P, Sapatnekar SS. Encoder-Decoder Networks for Analyzing Thermal and Power Delivery Networks. ACM Transactions on Design Automation of Electronic Systems. 2023;28(1):1-27. doi:10.1145/3526115
BibTeX
@article{Chhabria2023,
author = {Chhabria, Vidya A. and Ahuja, Vipul and Prabhu, Ashwath and Patil, Nikhil and Jain, Palkesh and Sapatnekar, Sachin S.},
title = {Encoder-Decoder Networks for Analyzing Thermal and Power Delivery Networks},
journal = {ACM Transactions on Design Automation of Electronic Systems},
year = {2023},
volume = {28},
number = {1},
pages = {1--27},
doi = {10.1145/3526115}
}
EUVIMED