GANNoC: A Framework for Automatic Generation of NoC Topologies Using Generative Adversarial Networks

Maxime Mirka, Maxime France France Pillois, Gilles Sassatelli, Abdoulaye Gamatié

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We propose GANNoC, a framework for automatic generation of customized Network-on-Chip (NoC) topologies, which exploits generative adversarial networks (GANs) learning capabilities. We define the problem of NoC generation as a graph generation problem, and train a GAN to produce such graphs. We further present a Reward-WGAN (RWGAN) architecture, based on the Wasserstein GAN (WGAN). It is coupled to a reward network enabling to steer the resulting generative system towards topologies having desired properties. We illustrate this capability through a case study aimed at producing topologies with a specific number of physical connections. After training, the generative network produces unique topologies with a 36% improvement regarding the number of connections, when compared to those found in the training dataset. NoCs’ performance assessment is carried out using the Ratatoskr 3D-NoC simulator with state-of-the-art characteristics. Results suggest interesting opportunities in learning correlations between intrinsic NoC features and resulting performance.
Original languageEnglish
Title of host publicationProceedings of the 2021 Drone Systems Engineering and Rapid Simulation and Performance Evaluation: Methods and Tools Proceedings
Place of PublicationNew York, NY, USA
PublisherAssociation for Computing Machinery, Inc
Pages51–58
Number of pages8
ISBN (Electronic)9781450389525
DOIs
Publication statusPublished - 24 Feb 2021
Event13th Workshop Rapid Simulation and Performance Evaluation: Methods and Tools 2021 - Budapest, Hungary
Duration: 20 Jan 202120 Jan 2021
Conference number: 13
https://rapidoworkshop.github.io/2021/index.html

Publication series

NameDroneSE and RAPIDO '21
PublisherAssociation for Computing Machinery

Workshop

Workshop13th Workshop Rapid Simulation and Performance Evaluation: Methods and Tools 2021
Abbreviated titleRAPIDO 2021
Country/TerritoryHungary
CityBudapest
Period20/01/2120/01/21
Internet address

Keywords

  • Network-on-Chip
  • Generative Adversarial Network
  • Neural Networks
  • NoC Topology

Fingerprint

Dive into the research topics of 'GANNoC: A Framework for Automatic Generation of NoC Topologies Using Generative Adversarial Networks'. Together they form a unique fingerprint.

Cite this