ZuSE-KI-Mobil AI Chip Design Platform: An Overview

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

  • Shaown Mojumder
  • Simon Friedrich
  • Emil Matus
  • Gerhard Fettweis
  • Matthias Lueders
  • Martin Friedrich
  • Oliver Renke
  • Holger Blume
  • Julian Hoefer
  • Patrick Schmidt
  • Juergen Becker
  • Darius Grantz
  • Markus Kock
  • Jens Benndorf
  • Nael Fasfous
  • Pierpaolo Mori
  • Hans Joerg Voegel
  • Samira Ahmadifarsani
  • Leonidas Kontopoulos
  • Ulf Schlichtmann
  • Kay Bierzynski

Research Organisations

External Research Organisations

  • Technische Universität Dresden
  • Karlsruhe Institute of Technology (KIT)
  • Dream Chip Technologies GmbH
  • Bayerische Motoren Werke AG
  • Technical University of Munich (TUM)
  • Infineon Technologies AG
View graph of relations

Details

Original languageEnglish
Title of host publication2024 IEEE Nordic Circuits and Systems Conference, NORCAS 2024 - Proceedings
EditorsJari Nurmi, Joachim Rodrigues, Luca Pezzarossa, Viktor Aberg, Baktash Behmanesh
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (electronic)9798331517663
ISBN (print)979-8-3315-1767-0
Publication statusPublished - 29 Oct 2024
Event10th IEEE Nordic Circuits and Systems Conference, NORCAS 2024 - Lund, Sweden
Duration: 29 Oct 202430 Oct 2024

Abstract

The ZuSE-KI-Mobil (ZuKIMo) project, a nationally funded initiative, focuses on creating an advanced ecosystem optimized for AI-driven applications in automotive, drone, and industrial domains. At the heart of this effort is a state-of-the-art System-on-Chip (SoC), successfully taped out using 22 nm FDX technology, integrating a novel AI accelerator tailored to specific use case requirements, along with proof-of-concept demonstrators that validate the platform's real-world application potential. Key aspects include the customized compiler flow, the hardware generation process of the novel AI accelerator, and the acceleration of different applications using the ZuKIMo platform. Examples of these applications are 3D object detection and disengagement prediction in autonomous driving. The paper provides an overview of the ZuKIMo ecosystem, highlighting its contributions to AI performance, energy efficiency, and safety in heterogeneous AI hardware platforms.

Keywords

    AI Accelerator, Compiler, System-on-Chip

ASJC Scopus subject areas

Sustainable Development Goals

Cite this

ZuSE-KI-Mobil AI Chip Design Platform: An Overview. / Mojumder, Shaown; Friedrich, Simon; Matus, Emil et al.
2024 IEEE Nordic Circuits and Systems Conference, NORCAS 2024 - Proceedings. ed. / Jari Nurmi; Joachim Rodrigues; Luca Pezzarossa; Viktor Aberg; Baktash Behmanesh. Institute of Electrical and Electronics Engineers Inc., 2024.

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Mojumder, S, Friedrich, S, Matus, E, Fettweis, G, Lueders, M, Friedrich, M, Renke, O, Blume, H, Hoefer, J, Schmidt, P, Becker, J, Grantz, D, Kock, M, Benndorf, J, Fasfous, N, Mori, P, Voegel, HJ, Ahmadifarsani, S, Kontopoulos, L, Schlichtmann, U & Bierzynski, K 2024, ZuSE-KI-Mobil AI Chip Design Platform: An Overview. in J Nurmi, J Rodrigues, L Pezzarossa, V Aberg & B Behmanesh (eds), 2024 IEEE Nordic Circuits and Systems Conference, NORCAS 2024 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 10th IEEE Nordic Circuits and Systems Conference, NORCAS 2024, Lund, Sweden, 29 Oct 2024. https://doi.org/10.1109/NorCAS64408.2024.10752454
Mojumder, S., Friedrich, S., Matus, E., Fettweis, G., Lueders, M., Friedrich, M., Renke, O., Blume, H., Hoefer, J., Schmidt, P., Becker, J., Grantz, D., Kock, M., Benndorf, J., Fasfous, N., Mori, P., Voegel, H. J., Ahmadifarsani, S., Kontopoulos, L., ... Bierzynski, K. (2024). ZuSE-KI-Mobil AI Chip Design Platform: An Overview. In J. Nurmi, J. Rodrigues, L. Pezzarossa, V. Aberg, & B. Behmanesh (Eds.), 2024 IEEE Nordic Circuits and Systems Conference, NORCAS 2024 - Proceedings Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/NorCAS64408.2024.10752454
Mojumder S, Friedrich S, Matus E, Fettweis G, Lueders M, Friedrich M et al. ZuSE-KI-Mobil AI Chip Design Platform: An Overview. In Nurmi J, Rodrigues J, Pezzarossa L, Aberg V, Behmanesh B, editors, 2024 IEEE Nordic Circuits and Systems Conference, NORCAS 2024 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2024 doi: 10.1109/NorCAS64408.2024.10752454
Mojumder, Shaown ; Friedrich, Simon ; Matus, Emil et al. / ZuSE-KI-Mobil AI Chip Design Platform : An Overview. 2024 IEEE Nordic Circuits and Systems Conference, NORCAS 2024 - Proceedings. editor / Jari Nurmi ; Joachim Rodrigues ; Luca Pezzarossa ; Viktor Aberg ; Baktash Behmanesh. Institute of Electrical and Electronics Engineers Inc., 2024.
Download
@inproceedings{d1de86c7a04a4833a3b6222b6952e2c6,
title = "ZuSE-KI-Mobil AI Chip Design Platform: An Overview",
abstract = "The ZuSE-KI-Mobil (ZuKIMo) project, a nationally funded initiative, focuses on creating an advanced ecosystem optimized for AI-driven applications in automotive, drone, and industrial domains. At the heart of this effort is a state-of-the-art System-on-Chip (SoC), successfully taped out using 22 nm FDX technology, integrating a novel AI accelerator tailored to specific use case requirements, along with proof-of-concept demonstrators that validate the platform's real-world application potential. Key aspects include the customized compiler flow, the hardware generation process of the novel AI accelerator, and the acceleration of different applications using the ZuKIMo platform. Examples of these applications are 3D object detection and disengagement prediction in autonomous driving. The paper provides an overview of the ZuKIMo ecosystem, highlighting its contributions to AI performance, energy efficiency, and safety in heterogeneous AI hardware platforms.",
keywords = "AI Accelerator, Compiler, System-on-Chip",
author = "Shaown Mojumder and Simon Friedrich and Emil Matus and Gerhard Fettweis and Matthias Lueders and Martin Friedrich and Oliver Renke and Holger Blume and Julian Hoefer and Patrick Schmidt and Juergen Becker and Darius Grantz and Markus Kock and Jens Benndorf and Nael Fasfous and Pierpaolo Mori and Voegel, {Hans Joerg} and Samira Ahmadifarsani and Leonidas Kontopoulos and Ulf Schlichtmann and Kay Bierzynski",
note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 10th IEEE Nordic Circuits and Systems Conference, NORCAS 2024 ; Conference date: 29-10-2024 Through 30-10-2024",
year = "2024",
month = oct,
day = "29",
doi = "10.1109/NorCAS64408.2024.10752454",
language = "English",
isbn = "979-8-3315-1767-0",
editor = "Jari Nurmi and Joachim Rodrigues and Luca Pezzarossa and Viktor Aberg and Baktash Behmanesh",
booktitle = "2024 IEEE Nordic Circuits and Systems Conference, NORCAS 2024 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Download

TY - GEN

T1 - ZuSE-KI-Mobil AI Chip Design Platform

T2 - 10th IEEE Nordic Circuits and Systems Conference, NORCAS 2024

AU - Mojumder, Shaown

AU - Friedrich, Simon

AU - Matus, Emil

AU - Fettweis, Gerhard

AU - Lueders, Matthias

AU - Friedrich, Martin

AU - Renke, Oliver

AU - Blume, Holger

AU - Hoefer, Julian

AU - Schmidt, Patrick

AU - Becker, Juergen

AU - Grantz, Darius

AU - Kock, Markus

AU - Benndorf, Jens

AU - Fasfous, Nael

AU - Mori, Pierpaolo

AU - Voegel, Hans Joerg

AU - Ahmadifarsani, Samira

AU - Kontopoulos, Leonidas

AU - Schlichtmann, Ulf

AU - Bierzynski, Kay

N1 - Publisher Copyright: © 2024 IEEE.

PY - 2024/10/29

Y1 - 2024/10/29

N2 - The ZuSE-KI-Mobil (ZuKIMo) project, a nationally funded initiative, focuses on creating an advanced ecosystem optimized for AI-driven applications in automotive, drone, and industrial domains. At the heart of this effort is a state-of-the-art System-on-Chip (SoC), successfully taped out using 22 nm FDX technology, integrating a novel AI accelerator tailored to specific use case requirements, along with proof-of-concept demonstrators that validate the platform's real-world application potential. Key aspects include the customized compiler flow, the hardware generation process of the novel AI accelerator, and the acceleration of different applications using the ZuKIMo platform. Examples of these applications are 3D object detection and disengagement prediction in autonomous driving. The paper provides an overview of the ZuKIMo ecosystem, highlighting its contributions to AI performance, energy efficiency, and safety in heterogeneous AI hardware platforms.

AB - The ZuSE-KI-Mobil (ZuKIMo) project, a nationally funded initiative, focuses on creating an advanced ecosystem optimized for AI-driven applications in automotive, drone, and industrial domains. At the heart of this effort is a state-of-the-art System-on-Chip (SoC), successfully taped out using 22 nm FDX technology, integrating a novel AI accelerator tailored to specific use case requirements, along with proof-of-concept demonstrators that validate the platform's real-world application potential. Key aspects include the customized compiler flow, the hardware generation process of the novel AI accelerator, and the acceleration of different applications using the ZuKIMo platform. Examples of these applications are 3D object detection and disengagement prediction in autonomous driving. The paper provides an overview of the ZuKIMo ecosystem, highlighting its contributions to AI performance, energy efficiency, and safety in heterogeneous AI hardware platforms.

KW - AI Accelerator

KW - Compiler

KW - System-on-Chip

UR - http://www.scopus.com/inward/record.url?scp=85211924264&partnerID=8YFLogxK

U2 - 10.1109/NorCAS64408.2024.10752454

DO - 10.1109/NorCAS64408.2024.10752454

M3 - Conference contribution

AN - SCOPUS:85211924264

SN - 979-8-3315-1767-0

BT - 2024 IEEE Nordic Circuits and Systems Conference, NORCAS 2024 - Proceedings

A2 - Nurmi, Jari

A2 - Rodrigues, Joachim

A2 - Pezzarossa, Luca

A2 - Aberg, Viktor

A2 - Behmanesh, Baktash

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 29 October 2024 through 30 October 2024

ER -

By the same author(s)