ZuSE-KI-AVF: Application-Specific AI Processor for Intelligent Sensor Signal Processing in Autonomous Driving

被引:7
作者
Thieu, Gia Bao [1 ]
Gesper, Sven [1 ]
Paya-Vaya, Guillermo [1 ]
Riggers, Christoph [2 ]
Renke, Oliver [2 ]
Fiedler, Till [2 ]
Marten, Jakob [2 ]
Stuckenberg, Tobias [2 ]
Blume, Holger [2 ]
Weis, Christian [3 ]
Steiner, Lukas [3 ]
Sudarshan, Chirag [3 ]
Wehn, Norbert [3 ]
Reimann, Lennart M. [4 ]
Leupers, Rainer [4 ]
Beyer, Michael [5 ]
Koehler, Daniel [5 ]
Jauch, Alisa [5 ]
Borrmann, Jan Micha [5 ]
Jaberansari, Setareh [5 ]
Berthold, Tim [6 ]
Blawat, Meinolf [6 ]
Kock, Markus [6 ]
Schewior, Gregor [6 ]
Benndorf, Jens [6 ]
Kautz, Frederik [7 ]
Bluethgen, Hans-Martin [7 ]
Sauer, Christian [7 ]
机构
[1] Tech Univ Carolo Wilhelmina Braunschweig, Chair Chip Design Embedded Comp, Braunschweig, Germany
[2] Leibniz Univ Hannover, Inst Microelect Syst, Hannover, Germany
[3] Tech Univ Kaiserslautern, Microelect Syst Design Res Grp, Kaiserslautern, Germany
[4] Rhein Westfal TH Aachen, Inst Commun Technol & Embedded Syst, Aachen, Germany
[5] Robert Bosch GmbH, Gerlingen, Germany
[6] Dream Chip Technol GmbH, Garbsen, Germany
[7] Cadence Design Syst, Feldkirchen, Germany
来源
2023 DESIGN, AUTOMATION & TEST IN EUROPE CONFERENCE & EXHIBITION, DATE | 2023年
关键词
RISC-V; vertical vector processor; hardware-software system; AI acceleration; sensor processing; FPGA; ASIC;
D O I
10.23919/DATE56975.2023.10136978
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Modern and future AI-based automotive applications, such as autonomous driving, require the efficient real-time processing of huge amounts of data from different sensors, like camera, radar, and LiDAR. In the ZuSE-KI-AVF project, multiple university, and industry partners collaborate to develop a novel massive parallel processor architecture, based on a customized RISC-V host processor, and an efficient high-performance vertical vector coprocessor. In addition, a software development framework is also provided to efficiently program AI-based sensor processing applications. The proposed processor system was verified and evaluated on a state-of-the-art UltraScale+ FPGA board, reaching a processing performance of up to 126.9 FPS, while executing the YOLO-LITE CNN on 224x224 input images. Further optimizations of the FPGA design and the realization of the processor system on a 22nm FDSOI CMOS technology are planned.
引用
收藏
页数:6
相关论文
共 14 条
  • [1] Ang S.-S., 2006, RECONFIGURABLE COMPU
  • [2] Beyer M., 2022, 30 EUROPEAN SIGNAL P
  • [3] Cortinhal Tiago, 2020, Advances in Visual Computing. 15th International Symposium, ISVC 2020. Proceedings. Lecture Notes in Computer Science (LNCS 12510), P207, DOI 10.1007/978-3-030-64559-5_16
  • [4] A methodology and tool suite for C compiler generation from ADL processor models
    Hohenauer, M
    Scharwaechter, H
    Karuri, K
    Wahlen, O
    Kogel, T
    Leupers, R
    Ascheid, G
    Meyr, H
    Braun, G
    van Someren, H
    [J]. DESIGN, AUTOMATION AND TEST IN EUROPE CONFERENCE AND EXHIBITION, VOLS 1 AND 2, PROCEEDINGS, 2004, : 1276 - 1281
  • [5] Huang R, 2018, IEEE INT CONF BIG DA, P2503, DOI 10.1109/BigData.2018.8621865
  • [6] ConGen: An Application Specific DRAM Memory Controller Generator
    Jung, Matthias
    Mathew, Deepak M.
    Weis, Christian
    Wehn, Norbert
    Heinrich, Irene
    Natale, Marco V.
    Krumke, Sven O.
    [J]. MEMSYS 2016: PROCEEDINGS OF THE INTERNATIONAL SYMPOSIUM ON MEMORY SYSTEMS, 2016, : 257 - 267
  • [7] Methodology for an Early Exploration of Embedded Systems using Portable Test and Stimulus Standard
    Kautz, Frederik
    Blume, Holger
    Sauer, Christian
    [J]. 2022 35TH SBC/SBMICRO/IEEE/ACM SYMPOSIUM ON INTEGRATED CIRCUITS AND SYSTEMS DESIGN (SBCCI 2022), 2022,
  • [8] Nolting S., 2017, 2017 27 INT C FIELD, P1
  • [9] Sauer C, 2014, PROCEEDINGS OF THE 2014 FORUM ON SPECIFICATION & DESIGN LANGUAGES (FDL)
  • [10] Logic Locking at the Frontiers of Machine Learning: A Survey on Developments and Opportunities
    Sisejkovic, Dominik
    Reimann, Lennart M.
    Moussavi, Elmira
    Merchant, Farhad
    Leupers, Rainer
    [J]. PROCEEDINGS OF THE 2021 IFIP/IEEE INTERNATIONAL CONFERENCE ON VERY LARGE SCALE INTEGRATION (VLSI-SOC), 2021, : 7 - 12