Version 1
: Received: 24 April 2024 / Approved: 25 April 2024 / Online: 26 April 2024 (11:07:08 CEST)
How to cite:
Kasprowicz, D.; Kasprowicz, G. Generative Modeling of Semiconductor Devices for Statistical Circuit Simulation. Preprints2024, 2024041675. https://doi.org/10.20944/preprints202404.1675.v1
Kasprowicz, D.; Kasprowicz, G. Generative Modeling of Semiconductor Devices for Statistical Circuit Simulation. Preprints 2024, 2024041675. https://doi.org/10.20944/preprints202404.1675.v1
Kasprowicz, D.; Kasprowicz, G. Generative Modeling of Semiconductor Devices for Statistical Circuit Simulation. Preprints2024, 2024041675. https://doi.org/10.20944/preprints202404.1675.v1
APA Style
Kasprowicz, D., & Kasprowicz, G. (2024). Generative Modeling of Semiconductor Devices for Statistical Circuit Simulation. Preprints. https://doi.org/10.20944/preprints202404.1675.v1
Chicago/Turabian Style
Kasprowicz, D. and Grzegorz Kasprowicz. 2024 "Generative Modeling of Semiconductor Devices for Statistical Circuit Simulation" Preprints. https://doi.org/10.20944/preprints202404.1675.v1
Abstract
Emerging semiconductor devices often lack accurate analytical models. The same is usually true of any devices working under extreme conditions like cryogenic temperatures. The usual workaround involves the use of approximation models, usually based on lookup tables or neural networks individually fitted to measurement data. In the case of experimental devices or ones working under extreme conditions, the number of units available for measurement is limited. As a result, the number of approximation-model instances is too small to enable a statistical simulation of even middle-sized circuits, which is a necessary step in integrated-circuit design since it provides the realistic picture of the circuit’s behavior in the presence of manufacturing process variations. Approximation models using structure parameters as inputs do exist in the literature, but are only useful if the end user knows the statistical distributions of those parameters, which is not usually the case. We propose a technique based on generative machine learning, namely the variational autoencoder, that uses only a small sample of devices to capture the essential features of their I–V curves under process variations and subsequently generates an arbitrary number of similarly disturbed curves. The model trained on as few as 20 instances per device type is shown to precisely reproduce the distributions of period and power consumption of a ring oscillator.
Keywords
generative model; machine learning; variational autoencoder; VAE; semiconductor device modeling; process variability; MOSFET; Monte Carlo
Subject
Engineering, Electrical and Electronic Engineering
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
