---
_id: '59816'
author:
- first_name: Gerrit
  full_name: Pape, Gerrit
  last_name: Pape
- first_name: Bjarne
  full_name: Wintermann, Bjarne
  id: '62900'
  last_name: Wintermann
  orcid: 0009-0000-0856-6250
- first_name: Linus
  full_name: Jungemann, Linus
  id: '67601'
  last_name: Jungemann
  orcid: 0009-0003-9757-988X
- first_name: Michael
  full_name: Lass, Michael
  last_name: Lass
- first_name: Marius
  full_name: Meyer, Marius
  last_name: Meyer
- first_name: Heinrich
  full_name: Riebler, Heinrich
  id: '8961'
  last_name: Riebler
- first_name: Christian
  full_name: Plessl, Christian
  id: '16153'
  last_name: Plessl
  orcid: 0000-0001-5728-9982
citation:
  ama: 'Pape G, Wintermann B, Jungemann L, et al. AuroraFlow, an Easy-to-Use, Low-Latency
    FPGA Communication Solution Demonstrated on Multi-FPGA Neural Network Inference.
    In: <i>Proceedings of the 15th International Symposium on Highly Efficient Accelerators
    and Reconfigurable Technologies</i>. ; 2025. doi:<a href="https://doi.org/10.1145/3728179.3728190">10.1145/3728179.3728190</a>'
  apa: Pape, G., Wintermann, B., Jungemann, L., Lass, M., Meyer, M., Riebler, H.,
    &#38; Plessl, C. (2025). AuroraFlow, an Easy-to-Use, Low-Latency FPGA Communication
    Solution Demonstrated on Multi-FPGA Neural Network Inference. <i>Proceedings of
    the 15th International Symposium on Highly Efficient Accelerators and Reconfigurable
    Technologies</i>. The International Symposium on Highly Efficient Accelerators
    and Reconfigurable Technologies 2025 (HEART 2025) , Kumamoto, Japan. <a href="https://doi.org/10.1145/3728179.3728190">https://doi.org/10.1145/3728179.3728190</a>
  bibtex: '@inproceedings{Pape_Wintermann_Jungemann_Lass_Meyer_Riebler_Plessl_2025,
    title={AuroraFlow, an Easy-to-Use, Low-Latency FPGA Communication Solution Demonstrated
    on Multi-FPGA Neural Network Inference}, DOI={<a href="https://doi.org/10.1145/3728179.3728190">10.1145/3728179.3728190</a>},
    booktitle={Proceedings of the 15th International Symposium on Highly Efficient
    Accelerators and Reconfigurable Technologies}, author={Pape, Gerrit and Wintermann,
    Bjarne and Jungemann, Linus and Lass, Michael and Meyer, Marius and Riebler, Heinrich
    and Plessl, Christian}, year={2025} }'
  chicago: Pape, Gerrit, Bjarne Wintermann, Linus Jungemann, Michael Lass, Marius
    Meyer, Heinrich Riebler, and Christian Plessl. “AuroraFlow, an Easy-to-Use, Low-Latency
    FPGA Communication Solution Demonstrated on Multi-FPGA Neural Network Inference.”
    In <i>Proceedings of the 15th International Symposium on Highly Efficient Accelerators
    and Reconfigurable Technologies</i>, 2025. <a href="https://doi.org/10.1145/3728179.3728190">https://doi.org/10.1145/3728179.3728190</a>.
  ieee: 'G. Pape <i>et al.</i>, “AuroraFlow, an Easy-to-Use, Low-Latency FPGA Communication
    Solution Demonstrated on Multi-FPGA Neural Network Inference,” presented at the
    The International Symposium on Highly Efficient Accelerators and Reconfigurable
    Technologies 2025 (HEART 2025) , Kumamoto, Japan, 2025, doi: <a href="https://doi.org/10.1145/3728179.3728190">10.1145/3728179.3728190</a>.'
  mla: Pape, Gerrit, et al. “AuroraFlow, an Easy-to-Use, Low-Latency FPGA Communication
    Solution Demonstrated on Multi-FPGA Neural Network Inference.” <i>Proceedings
    of the 15th International Symposium on Highly Efficient Accelerators and Reconfigurable
    Technologies</i>, 2025, doi:<a href="https://doi.org/10.1145/3728179.3728190">10.1145/3728179.3728190</a>.
  short: 'G. Pape, B. Wintermann, L. Jungemann, M. Lass, M. Meyer, H. Riebler, C.
    Plessl, in: Proceedings of the 15th International Symposium on Highly Efficient
    Accelerators and Reconfigurable Technologies, 2025.'
conference:
  end_date: 2025-05-28
  location: Kumamoto, Japan
  name: 'The International Symposium on Highly Efficient Accelerators and Reconfigurable
    Technologies 2025 (HEART 2025) '
  start_date: 2025-05-26
date_created: 2025-05-06T09:53:41Z
date_updated: 2025-06-23T08:40:28Z
department:
- _id: '27'
doi: 10.1145/3728179.3728190
language:
- iso: eng
project:
- _id: '296'
  name: 'EKI-App: EKI-App: Energieeffiziente Künstliche Intelligenz im Rechenzentrum
    durch Approximation von tiefen neuronalen Netzen für Field-Programmable Gate Arrays'
publication: Proceedings of the 15th International Symposium on Highly Efficient Accelerators
  and Reconfigurable Technologies
publication_status: published
status: public
title: AuroraFlow, an Easy-to-Use, Low-Latency FPGA Communication Solution Demonstrated
  on Multi-FPGA Neural Network Inference
type: conference
user_id: '67601'
year: '2025'
...