Energy Complexity Model for Convolutional Neural Networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F23%3A00573373" target="_blank" >RIV/67985807:_____/23:00573373 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/00216305:26230/23:PU149415

Výsledek na webu

<a href="https://dx.doi.org/10.1007/978-3-031-44204-9_16" target="_blank" >https://dx.doi.org/10.1007/978-3-031-44204-9_16</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-44204-9_16" target="_blank" >10.1007/978-3-031-44204-9_16</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Energy Complexity Model for Convolutional Neural Networks

Popis výsledku v původním jazyce

The energy efficiency of hardware implementations of convolutional neural networks (CNNs) is critical to their widespread deployment in low-power mobile devices. Recently, a plethora of methods have been proposed providing energy-optimal mappings of CNNs onto diverse hardware accelerators. Their estimated power consumption is related to specific implementation details and hardware parameters, which does not allow for machine-independent exploration of CNN energy measures. In this paper, we introduce a simplified theoretical energy complexity model for CNNs, based on only two-level memory hierarchy that captures asymptotically all important sources of power consumption of different CNN hardware implementations. We calculate energy complexity in this model for two common dataflows which, according to statistical tests, fits asymptotically very well the power consumption estimated by the Time/Accelergy program for convolutional layers on the Simba and Eyeriss hardware platforms. The model opens the possibility of proving principal limits on the energy efficiency of CNN hardware accelerators.

Název v anglickém jazyce

Energy Complexity Model for Convolutional Neural Networks

Popis výsledku anglicky

The energy efficiency of hardware implementations of convolutional neural networks (CNNs) is critical to their widespread deployment in low-power mobile devices. Recently, a plethora of methods have been proposed providing energy-optimal mappings of CNNs onto diverse hardware accelerators. Their estimated power consumption is related to specific implementation details and hardware parameters, which does not allow for machine-independent exploration of CNN energy measures. In this paper, we introduce a simplified theoretical energy complexity model for CNNs, based on only two-level memory hierarchy that captures asymptotically all important sources of power consumption of different CNN hardware implementations. We calculate energy complexity in this model for two common dataflows which, according to statistical tests, fits asymptotically very well the power consumption estimated by the Time/Accelergy program for convolutional layers on the Simba and Eyeriss hardware platforms. The model opens the possibility of proving principal limits on the energy efficiency of CNN hardware accelerators.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA22-02067S" target="_blank" >GA22-02067S: AppNeCo: Aproximativní neurovýpočty</a><br>

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Artificial Neural Networks and Machine Learning – ICANN 2023. Proceedings, Part X

ISBN

978-3-031-44203-2

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

13

Strana od-do

186-198

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Heraklion

Datum konání akce

26. 9. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001157311300016