Cargando…

Benchmarking Neuromorphic Hardware and Its Energy Expenditure

We propose and discuss a platform overarching benchmark suite for neuromorphic hardware. This suite covers benchmarks from low-level characterization to high-level application evaluation using benchmark specific metrics. With this rather broad approach we are able to compare various hardware systems...

Descripción completa

Detalles Bibliográficos
Autores principales: Ostrau, Christoph, Klarhorst, Christian, Thies, Michael, Rückert, Ulrich
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9201569/
https://www.ncbi.nlm.nih.gov/pubmed/35720731
http://dx.doi.org/10.3389/fnins.2022.873935
_version_ 1784728351047417856
author Ostrau, Christoph
Klarhorst, Christian
Thies, Michael
Rückert, Ulrich
author_facet Ostrau, Christoph
Klarhorst, Christian
Thies, Michael
Rückert, Ulrich
author_sort Ostrau, Christoph
collection PubMed
description We propose and discuss a platform overarching benchmark suite for neuromorphic hardware. This suite covers benchmarks from low-level characterization to high-level application evaluation using benchmark specific metrics. With this rather broad approach we are able to compare various hardware systems including mixed-signal and fully digital neuromorphic architectures. Selected benchmarks are discussed and results for several target platforms are presented revealing characteristic differences between the various systems. Furthermore, a proposed energy model allows to combine benchmark performance metrics with energy efficiency. This model enables the prediction of the energy expenditure of a network on a target system without actually having access to it. To quantify the efficiency gap between neuromorphics and the biological paragon of the human brain, the energy model is used to estimate the energy required for a full brain simulation. This reveals that current neuromorphic systems are at least four orders of magnitude less efficient. It is argued, that even with a modern fabrication process, two to three orders of magnitude are remaining. Finally, for selected benchmarks the performance and efficiency of the neuromorphic solution is compared to standard approaches.
format Online
Article
Text
id pubmed-9201569
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-92015692022-06-17 Benchmarking Neuromorphic Hardware and Its Energy Expenditure Ostrau, Christoph Klarhorst, Christian Thies, Michael Rückert, Ulrich Front Neurosci Neuroscience We propose and discuss a platform overarching benchmark suite for neuromorphic hardware. This suite covers benchmarks from low-level characterization to high-level application evaluation using benchmark specific metrics. With this rather broad approach we are able to compare various hardware systems including mixed-signal and fully digital neuromorphic architectures. Selected benchmarks are discussed and results for several target platforms are presented revealing characteristic differences between the various systems. Furthermore, a proposed energy model allows to combine benchmark performance metrics with energy efficiency. This model enables the prediction of the energy expenditure of a network on a target system without actually having access to it. To quantify the efficiency gap between neuromorphics and the biological paragon of the human brain, the energy model is used to estimate the energy required for a full brain simulation. This reveals that current neuromorphic systems are at least four orders of magnitude less efficient. It is argued, that even with a modern fabrication process, two to three orders of magnitude are remaining. Finally, for selected benchmarks the performance and efficiency of the neuromorphic solution is compared to standard approaches. Frontiers Media S.A. 2022-06-02 /pmc/articles/PMC9201569/ /pubmed/35720731 http://dx.doi.org/10.3389/fnins.2022.873935 Text en Copyright © 2022 Ostrau, Klarhorst, Thies and Rückert. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Ostrau, Christoph
Klarhorst, Christian
Thies, Michael
Rückert, Ulrich
Benchmarking Neuromorphic Hardware and Its Energy Expenditure
title Benchmarking Neuromorphic Hardware and Its Energy Expenditure
title_full Benchmarking Neuromorphic Hardware and Its Energy Expenditure
title_fullStr Benchmarking Neuromorphic Hardware and Its Energy Expenditure
title_full_unstemmed Benchmarking Neuromorphic Hardware and Its Energy Expenditure
title_short Benchmarking Neuromorphic Hardware and Its Energy Expenditure
title_sort benchmarking neuromorphic hardware and its energy expenditure
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9201569/
https://www.ncbi.nlm.nih.gov/pubmed/35720731
http://dx.doi.org/10.3389/fnins.2022.873935
work_keys_str_mv AT ostrauchristoph benchmarkingneuromorphichardwareanditsenergyexpenditure
AT klarhorstchristian benchmarkingneuromorphichardwareanditsenergyexpenditure
AT thiesmichael benchmarkingneuromorphichardwareanditsenergyexpenditure
AT ruckertulrich benchmarkingneuromorphichardwareanditsenergyexpenditure