A Generative AI for Heterogeneous Network-on-Chip Design Space Pruning

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

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

Abstract / Description of output

Often suffering from under-optimization, Networks-on-Chip (NoCs) heavily impact the efficiency of domain-specific Systems-on-Chip. To cope with this issue, heterogeneous NoCs are promising alternatives. Nevertheless, the design of optimized NoCs satisfying multiple performance objectives is extremely challenging and requires significant expertise. Prior works failed to combine many objectives or required an extended design space exploration time. In this paper, we propose an approach based on generative artificial intelligence to help pruning complex design spaces for heterogeneous NoCs, according to configurable performance objectives. This is made possible by the ability of Generative Adversarial Networks to learn and generate relevant design candidates for the target NoCs. The speed and flexibility of our solution enable a fast generation of optimized NoCs that fit users' expectations. Through some experiments, we show how to obtain competitive NoC designs reducing the power consumption with no communication performance or area penalty compared to a given conventional NoC design.
Original languageEnglish
Title of host publication2022 Design, Automation & Test in Europe Conference & Exhibition (DATE)
EditorsCristiana Bolchini, Ingrid Verbauwhede, Ioana Vatajelu
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages1135-1138
Number of pages4
ISBN (Electronic)978-3-9819263-6-1
ISBN (Print)978-1-6654-9637-7
DOIs
Publication statusPublished - 19 May 2022
EventDesign, Automation and Test in Europe Conference 2022 - Online
Duration: 14 Mar 202223 Mar 2022

Publication series

Name2022 Design, Automation & Test in Europe Conference & Exhibition
PublisherIEEE
ISSN (Print)1530-1591
ISSN (Electronic)1558-1101

Conference

ConferenceDesign, Automation and Test in Europe Conference 2022
Abbreviated titleDATE 2022
Period14/03/2223/03/22

Keywords / Materials (for Non-textual outputs)

  • Generative Adversarial Network
  • CAD
  • Network-on-Chip
  • DSSoC
  • Heterogeneous
  • Machine Learning

Fingerprint

Dive into the research topics of 'A Generative AI for Heterogeneous Network-on-Chip Design Space Pruning'. Together they form a unique fingerprint.

Cite this