---
_id: '28099'
abstract:
- lang: eng
  text: N-body methods are one of the essential algorithmic building blocks of high-performance
    and parallel computing. Previous research has shown promising performance for
    implementing n-body simulations with pairwise force calculations on FPGAs. However,
    to avoid challenges with accumulation and memory access patterns, the presented
    designs calculate each pair of forces twice, along with both force sums of the
    involved particles. Also, they require large problem instances with hundreds of
    thousands of particles to reach their respective peak performance, limiting the
    applicability for strong scaling scenarios. This work addresses both issues by
    presenting a novel FPGA design that uses each calculated force twice and overlaps
    data transfers and computations in a way that allows to reach peak performance
    even for small problem instances, outperforming previous single precision results
    even in double precision, and scaling linearly over multiple interconnected FPGAs.
    For a comparison across architectures, we provide an equally optimized CPU reference,
    which for large problems actually achieves higher peak performance per device,
    however, given the strong scaling advantages of the FPGA design, in parallel setups
    with few thousand particles per device, the FPGA platform achieves highest performance
    and power efficiency.
article_type: original
author:
- first_name: Johannes
  full_name: Menzel, Johannes
  last_name: Menzel
- first_name: Christian
  full_name: Plessl, Christian
  id: '16153'
  last_name: Plessl
  orcid: 0000-0001-5728-9982
- first_name: Tobias
  full_name: Kenter, Tobias
  id: '3145'
  last_name: Kenter
citation:
  ama: Menzel J, Plessl C, Kenter T. The Strong Scaling Advantage of FPGAs in HPC
    for N-body Simulations. <i>ACM Transactions on Reconfigurable Technology and Systems</i>.
    2021;15(1):1-30. doi:<a href="https://doi.org/10.1145/3491235">10.1145/3491235</a>
  apa: Menzel, J., Plessl, C., &#38; Kenter, T. (2021). The Strong Scaling Advantage
    of FPGAs in HPC for N-body Simulations. <i>ACM Transactions on Reconfigurable
    Technology and Systems</i>, <i>15</i>(1), 1–30. <a href="https://doi.org/10.1145/3491235">https://doi.org/10.1145/3491235</a>
  bibtex: '@article{Menzel_Plessl_Kenter_2021, title={The Strong Scaling Advantage
    of FPGAs in HPC for N-body Simulations}, volume={15}, DOI={<a href="https://doi.org/10.1145/3491235">10.1145/3491235</a>},
    number={1}, journal={ACM Transactions on Reconfigurable Technology and Systems},
    author={Menzel, Johannes and Plessl, Christian and Kenter, Tobias}, year={2021},
    pages={1–30} }'
  chicago: 'Menzel, Johannes, Christian Plessl, and Tobias Kenter. “The Strong Scaling
    Advantage of FPGAs in HPC for N-Body Simulations.” <i>ACM Transactions on Reconfigurable
    Technology and Systems</i> 15, no. 1 (2021): 1–30. <a href="https://doi.org/10.1145/3491235">https://doi.org/10.1145/3491235</a>.'
  ieee: 'J. Menzel, C. Plessl, and T. Kenter, “The Strong Scaling Advantage of FPGAs
    in HPC for N-body Simulations,” <i>ACM Transactions on Reconfigurable Technology
    and Systems</i>, vol. 15, no. 1, pp. 1–30, 2021, doi: <a href="https://doi.org/10.1145/3491235">10.1145/3491235</a>.'
  mla: Menzel, Johannes, et al. “The Strong Scaling Advantage of FPGAs in HPC for
    N-Body Simulations.” <i>ACM Transactions on Reconfigurable Technology and Systems</i>,
    vol. 15, no. 1, 2021, pp. 1–30, doi:<a href="https://doi.org/10.1145/3491235">10.1145/3491235</a>.
  short: J. Menzel, C. Plessl, T. Kenter, ACM Transactions on Reconfigurable Technology
    and Systems 15 (2021) 1–30.
date_created: 2021-11-30T10:00:31Z
date_updated: 2022-01-06T06:57:51Z
department:
- _id: '27'
- _id: '518'
doi: 10.1145/3491235
intvolume: '        15'
issue: '1'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://dl.acm.org/doi/10.1145/3491235
oa: '1'
page: 1-30
publication: ACM Transactions on Reconfigurable Technology and Systems
publication_identifier:
  issn:
  - 1936-7406
  - 1936-7414
publication_status: published
quality_controlled: '1'
status: public
title: The Strong Scaling Advantage of FPGAs in HPC for N-body Simulations
type: journal_article
user_id: '3145'
volume: 15
year: '2021'
...