ZuSE-KI-Mobil: AI Chip Design Platform for Automotive and Industrial Applications

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Autorschaft

  • Shaown Mojumder
  • Simon Friedrich
  • Emil Matúš
  • Matthias Lüders
  • Martin Friedrich
  • Oliver Renke
  • Holger Blume
  • Markus Kock
  • Gregor Schewior
  • Darius Grantz
  • Jens Benndorf
  • Julian Hoefer
  • Patrick Schmidt
  • Jürgen Becker
  • Nael Fasfous
  • Pierpaolo Mori
  • Hans Jörg Vögel
  • Samira Ahmadifarsani
  • Leonidas Kontopoulos
  • Ulf Schlichtmann
  • Yun Jin Li
  • Gerhard P. Fettweis

Externe Organisationen

  • Technische Universität Dresden (TUD)
  • Dream Chip Technologies GmbH
  • Karlsruher Institut für Technologie (KIT)
  • Bayerische Motoren Werke AG
  • Technische Universität München (TUM)
  • Infineon Technologies AG
Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Seiten (von - bis)2961-2974
Seitenumfang14
FachzeitschriftIEEE Transactions on Very Large Scale Integration (VLSI) Systems
Jahrgang33
Ausgabenummer11
Frühes Online-Datum12 Sept. 2025
PublikationsstatusVeröffentlicht - 31 Okt. 2025

Abstract

The ZuSE-KI-Mobil (ZuKIMo) research project presents a heterogeneous system-on-chip (SoC) designed for use in a variety of automotive and industrial edge applications. Implemented using GlobalFoundries (GF) 22-nm FD-SOI technology, the SoC features a modular architecture with a configurable, bit-serial, mixed-precision neural processing unit (NPU) core. This core can be adapted to different use cases, comes with a compact instruction set, and improves the performance of dilated convolutions. A hardware-accelerated, tunable image signal processor (ISP) hyperparameter pipeline reduces tuning time and increases detection confidence for AI tasks. The system also incorporates a selective, per-layer fault-tolerance mechanism and supports rapid prototyping via an Apache TVM-driven compiler flow and cycle-accurate simulation. The adaptable hardware generation process is designed with future chiplet-based scaling in mind, providing a flexible foundation for upcoming heterogeneous SoC designs.

ASJC Scopus Sachgebiete

Zitieren

ZuSE-KI-Mobil: AI Chip Design Platform for Automotive and Industrial Applications. / Mojumder, Shaown; Friedrich, Simon; Matúš, Emil et al.
in: IEEE Transactions on Very Large Scale Integration (VLSI) Systems, Jahrgang 33, Nr. 11, 31.10.2025, S. 2961-2974.

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Mojumder, S, Friedrich, S, Matúš, E, Lüders, M, Friedrich, M, Renke, O, Blume, H, Kock, M, Schewior, G, Grantz, D, Benndorf, J, Hoefer, J, Schmidt, P, Becker, J, Fasfous, N, Mori, P, Vögel, HJ, Ahmadifarsani, S, Kontopoulos, L, Schlichtmann, U, Li, YJ & Fettweis, GP 2025, 'ZuSE-KI-Mobil: AI Chip Design Platform for Automotive and Industrial Applications', IEEE Transactions on Very Large Scale Integration (VLSI) Systems, Jg. 33, Nr. 11, S. 2961-2974. https://doi.org/10.1109/TVLSI.2025.3603887
Mojumder, S., Friedrich, S., Matúš, E., Lüders, M., Friedrich, M., Renke, O., Blume, H., Kock, M., Schewior, G., Grantz, D., Benndorf, J., Hoefer, J., Schmidt, P., Becker, J., Fasfous, N., Mori, P., Vögel, H. J., Ahmadifarsani, S., Kontopoulos, L., ... Fettweis, G. P. (2025). ZuSE-KI-Mobil: AI Chip Design Platform for Automotive and Industrial Applications. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 33(11), 2961-2974. https://doi.org/10.1109/TVLSI.2025.3603887
Mojumder S, Friedrich S, Matúš E, Lüders M, Friedrich M, Renke O et al. ZuSE-KI-Mobil: AI Chip Design Platform for Automotive and Industrial Applications. IEEE Transactions on Very Large Scale Integration (VLSI) Systems. 2025 Okt 31;33(11):2961-2974. Epub 2025 Sep 12. doi: 10.1109/TVLSI.2025.3603887
Mojumder, Shaown ; Friedrich, Simon ; Matúš, Emil et al. / ZuSE-KI-Mobil : AI Chip Design Platform for Automotive and Industrial Applications. in: IEEE Transactions on Very Large Scale Integration (VLSI) Systems. 2025 ; Jahrgang 33, Nr. 11. S. 2961-2974.
Download
@article{842ccc5bed3d46ea94fea0d40d1019c0,
title = "ZuSE-KI-Mobil: AI Chip Design Platform for Automotive and Industrial Applications",
abstract = "The ZuSE-KI-Mobil (ZuKIMo) research project presents a heterogeneous system-on-chip (SoC) designed for use in a variety of automotive and industrial edge applications. Implemented using GlobalFoundries (GF) 22-nm FD-SOI technology, the SoC features a modular architecture with a configurable, bit-serial, mixed-precision neural processing unit (NPU) core. This core can be adapted to different use cases, comes with a compact instruction set, and improves the performance of dilated convolutions. A hardware-accelerated, tunable image signal processor (ISP) hyperparameter pipeline reduces tuning time and increases detection confidence for AI tasks. The system also incorporates a selective, per-layer fault-tolerance mechanism and supports rapid prototyping via an Apache TVM-driven compiler flow and cycle-accurate simulation. The adaptable hardware generation process is designed with future chiplet-based scaling in mind, providing a flexible foundation for upcoming heterogeneous SoC designs.",
keywords = "AI accelerator, autonomous systems, compiler, edge computing, system-on-chip (SoC)",
author = "Shaown Mojumder and Simon Friedrich and Emil Mat{\'u}{\v s} and Matthias L{\"u}ders and Martin Friedrich and Oliver Renke and Holger Blume and Markus Kock and Gregor Schewior and Darius Grantz and Jens Benndorf and Julian Hoefer and Patrick Schmidt and J{\"u}rgen Becker and Nael Fasfous and Pierpaolo Mori and V{\"o}gel, {Hans J{\"o}rg} and Samira Ahmadifarsani and Leonidas Kontopoulos and Ulf Schlichtmann and Li, {Yun Jin} and Fettweis, {Gerhard P.}",
note = "Publisher Copyright: {\textcopyright} 1993-2012 IEEE.",
year = "2025",
month = oct,
day = "31",
doi = "10.1109/TVLSI.2025.3603887",
language = "English",
volume = "33",
pages = "2961--2974",
journal = "IEEE Transactions on Very Large Scale Integration (VLSI) Systems",
issn = "1063-8210",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "11",

}

Download

TY - JOUR

T1 - ZuSE-KI-Mobil

T2 - AI Chip Design Platform for Automotive and Industrial Applications

AU - Mojumder, Shaown

AU - Friedrich, Simon

AU - Matúš, Emil

AU - Lüders, Matthias

AU - Friedrich, Martin

AU - Renke, Oliver

AU - Blume, Holger

AU - Kock, Markus

AU - Schewior, Gregor

AU - Grantz, Darius

AU - Benndorf, Jens

AU - Hoefer, Julian

AU - Schmidt, Patrick

AU - Becker, Jürgen

AU - Fasfous, Nael

AU - Mori, Pierpaolo

AU - Vögel, Hans Jörg

AU - Ahmadifarsani, Samira

AU - Kontopoulos, Leonidas

AU - Schlichtmann, Ulf

AU - Li, Yun Jin

AU - Fettweis, Gerhard P.

N1 - Publisher Copyright: © 1993-2012 IEEE.

PY - 2025/10/31

Y1 - 2025/10/31

N2 - The ZuSE-KI-Mobil (ZuKIMo) research project presents a heterogeneous system-on-chip (SoC) designed for use in a variety of automotive and industrial edge applications. Implemented using GlobalFoundries (GF) 22-nm FD-SOI technology, the SoC features a modular architecture with a configurable, bit-serial, mixed-precision neural processing unit (NPU) core. This core can be adapted to different use cases, comes with a compact instruction set, and improves the performance of dilated convolutions. A hardware-accelerated, tunable image signal processor (ISP) hyperparameter pipeline reduces tuning time and increases detection confidence for AI tasks. The system also incorporates a selective, per-layer fault-tolerance mechanism and supports rapid prototyping via an Apache TVM-driven compiler flow and cycle-accurate simulation. The adaptable hardware generation process is designed with future chiplet-based scaling in mind, providing a flexible foundation for upcoming heterogeneous SoC designs.

AB - The ZuSE-KI-Mobil (ZuKIMo) research project presents a heterogeneous system-on-chip (SoC) designed for use in a variety of automotive and industrial edge applications. Implemented using GlobalFoundries (GF) 22-nm FD-SOI technology, the SoC features a modular architecture with a configurable, bit-serial, mixed-precision neural processing unit (NPU) core. This core can be adapted to different use cases, comes with a compact instruction set, and improves the performance of dilated convolutions. A hardware-accelerated, tunable image signal processor (ISP) hyperparameter pipeline reduces tuning time and increases detection confidence for AI tasks. The system also incorporates a selective, per-layer fault-tolerance mechanism and supports rapid prototyping via an Apache TVM-driven compiler flow and cycle-accurate simulation. The adaptable hardware generation process is designed with future chiplet-based scaling in mind, providing a flexible foundation for upcoming heterogeneous SoC designs.

KW - AI accelerator

KW - autonomous systems

KW - compiler

KW - edge computing

KW - system-on-chip (SoC)

UR - http://www.scopus.com/inward/record.url?scp=105016243712&partnerID=8YFLogxK

U2 - 10.1109/TVLSI.2025.3603887

DO - 10.1109/TVLSI.2025.3603887

M3 - Article

AN - SCOPUS:105016243712

VL - 33

SP - 2961

EP - 2974

JO - IEEE Transactions on Very Large Scale Integration (VLSI) Systems

JF - IEEE Transactions on Very Large Scale Integration (VLSI) Systems

SN - 1063-8210

IS - 11

ER -

Von denselben Autoren