Industry Paper: Surrogate Models for Testing Analog Designs under Limited Budget - a Bandgap Case Study

Testing analog integrated circuit (IC) designs is notoriously hard. Simulating tens of milliseconds from an accurate transistor level model of a complex analog design can take up to two weeks of computation. Therefore, the number of tests that can be executed during the late development stage of an...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International Conference on Hardware/Software Codesign and System Synthesis (Online) S. 21 - 24
Hauptverfasser: Bloem, Roderick, Larrauri, Alberto, Lengfeldner, Roland, Mateis, Cristinel, Nickovic, Dejan, Ziegler, Bjorn
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.10.2022
Schlagworte:
analog design
Artificial neural networks
Bayes methods
Computational modeling
Integrated circuit modeling
machine learning
Photonic band gap
surrogate model
testing
Transistors
Voltage
ISSN:2832-6474
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Testing analog integrated circuit (IC) designs is notoriously hard. Simulating tens of milliseconds from an accurate transistor level model of a complex analog design can take up to two weeks of computation. Therefore, the number of tests that can be executed during the late development stage of an analog IC can be very limited. We leverage the recent advancements in machine learning (ML) and propose two techniques, artificial neural networks (ANN) and Gaussian processes, to learn a surrogate model from an existing test suite. We then explore the surrogate model with Bayesian optimization to guide the generation of additional tests. We use an industrial bandgap case study to evaluate the two approaches and demonstrate the virtue of Bayesian optimization in efficiently generating complementary tests with constrained effort.
ISSN:2832-6474
DOI:10.1109/CODES-ISSS55005.2022.00016