Machine Learning-based feasibility estimation of digital blocks in BCD technology

TL;DR

This paper introduces a machine learning methodology to rapidly predict the feasibility of digital block implementation in BCD technology, reducing the need for time-consuming placement and routing trials in mixed-signal IC design.

Contribution

The paper presents a novel ML-based approach for feasibility estimation of digital blocks in BCD technology, facilitating faster design iterations and improved collaboration between digital and analog designers.

Findings

ML model accurately predicts feasibility with high precision.

Significant reduction in design iteration time.

Enhanced feedback loop between digital and analog design teams.

Abstract

Analog-on-Top Mixed Signal (AMS) Integrated Circuit (IC) design is a time-consuming process predominantly carried out by hand. Within this flow, usually, some area is reserved by the top-level integrator for the placement of digital blocks. Specific features of the area, such as size and shape, have a relevant impact on the possibility of implementing the digital logic with the required functionality. We present a Machine Learning (ML)-based evaluation methodology for predicting the feasibility of digital implementation using a set of high-level features. This approach aims to avoid time-consuming Place-and-Route trials, enabling rapid feedback between Digital and Analog Back-End designers during top-level placement.