# Transfer Learning for Minimum Operating Voltage Prediction in Advanced Technology Nodes: Leveraging Legacy Data and Silicon Odometer Sensing

## TL;DR

This paper introduces a transfer learning framework that uses legacy data and silicon odometer sensing to accurately predict minimum operating voltage at advanced technology nodes, addressing data scarcity and process variation challenges.

## Contribution

The paper presents a novel transfer learning approach that incorporates silicon odometer data to improve $V_{min}$ prediction accuracy at 5nm nodes using legacy 16nm data.

## Key findings

- Significantly improved $V_{min}$ prediction accuracy at 5nm.
- Effective leveraging of legacy 16nm data for advanced nodes.
- Enhanced process variation characterization through silicon odometer features.

## Abstract

Accurate prediction of chip performance is critical for ensuring energy efficiency and reliability in semiconductor manufacturing. However, developing minimum operating voltage ($V_{min}$) prediction models at advanced technology nodes is challenging due to limited training data and the complex relationship between process variations and $V_{min}$. To address these issues, we propose a novel transfer learning framework that leverages abundant legacy data from the 16nm technology node to enable accurate $V_{min}$ prediction at the advanced 5nm node. A key innovation of our approach is the integration of input features derived from on-chip silicon odometer sensor data, which provide fine-grained characterization of localized process variations -- an essential factor at the 5nm node -- resulting in significantly improved prediction accuracy.