NVCell: Standard Cell Layout in Advanced Technology Nodes with Reinforcement Learning

TL;DR

This paper presents NVCell, an automated standard cell layout generator using reinforcement learning, capable of producing efficient, compliant layouts with smaller or equal area for most cells in advanced technology nodes.

Contribution

NVCell introduces a reinforcement learning-based approach for automating standard cell layout generation, addressing complex design rules in advanced nodes.

Findings

Achieves over 90% success rate in generating compliant layouts

Produces layouts with equal or smaller area compared to existing methods

Demonstrates effectiveness of RL in standard cell placement and routing

Abstract

High quality standard cell layout automation in advanced technology nodes is still challenging in the industry today because of complex design rules. In this paper we introduce an automatic standard cell layout generator called NVCell that can generate layouts with equal or smaller area for over 90% of single row cells in an industry standard cell library on an advanced technology node. NVCell leverages reinforcement learning (RL) to fix design rule violations during routing and to generate efficient placements.