|
doi: 10.3850/978-3-9815370-4-8_0102
Fast Deployment of Alternate Analog Test Using
Bayesian Model Fusion
John Liaperdos1,5, Haralampos-G. Stratigopoulos2,3, Louay Abdallah2,3, Yiorgos Tsiatouhas4, Angela Arapoyanni5 and Xin Li6
1Technological Educational Institute of Peloponnese, Department of Computer Engineering, Sparta 23100, Greece
2Université Grenoble Alpes, TIMA, F-38000 Grenoble, France
3CNRS, TIMA, F-38000 Grenoble, France
4University of Ioannina, Department of Computer Science & Engineering, Ioannina 45110, Greece
5National and Kapodistrian University of Athens, Department of Informatics and Telecommunications, Athens 15784, Greece
6Carnegie Mellon University, ECE Department, Pittsburgh, PA 15213, USA
ABSTRACT
In this paper, we address the problem of limited training sets for learning the regression functions in alternate analog test. Typically, a large volume of real data needs to be collected from different wafers and lots over a long period of time to be able to train the regression functions with accuracy across the whole design space and apply alternate test with high confidence. To avoid this delay and achieve a fast deployment of alternate test, we propose to use the Bayesian model fusion technique that leverages prior knowledge from simulation data and fuses this information with data from few real circuits to draw accurate regression functions across the whole design space. The technique is demonstrated for an alternate test designed for RF low noise amplifiers.
Full Text (PDF)
|