Reinforcement Learning based Interconnection Routing for Adaptive Traffic Optimization

TL;DR

This paper explores reinforcement learning techniques to develop adaptive routing algorithms for Network-on-Chip architectures, aiming to improve runtime performance through continuous learning.

Contribution

It introduces three RL-based routing methods that learn near-optimal solutions, demonstrating their effectiveness in optimizing NoC performance.

Findings

RL algorithms successfully learn near-optimal routing solutions

The methods adapt to different environment states effectively

Code is made available for reproducibility

Abstract

Applying Machine Learning (ML) techniques to design and optimize computer architectures is a promising research direction. Optimizing the runtime performance of a Network-on-Chip (NoC) necessitates a continuous learning framework. In this work, we demonstrate the promise of applying reinforcement learning (RL) to optimize NoC runtime performance. We present three RL-based methods for learning optimal routing algorithms. The experimental results show the algorithms can successfully learn a near-optimal solution across different environment states. Reproducible Code: github.com/huckiyang/interconnect-routing-gym