Energy Complexity Model for Convolutional Neural Networks

Result code in 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>

Alternative codes found

RIV/00216305:26230/23:PU149415

Result on the web

<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>

Result language

angličtina

Original language name

Energy Complexity Model for Convolutional Neural Networks

Original language description

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.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

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

Project

<a href="/en/project/GA22-02067S" target="_blank" >GA22-02067S: AppNeCo: Approximate Neurocomputing</a><br>

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2023

Confidentiality

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

Article name in the collection

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

ISBN

978-3-031-44203-2

ISSN

0302-9743

e-ISSN

—

Number of pages

13

Pages from-to

186-198

Publisher name

Springer

Place of publication

Cham

Event location

Heraklion

Event date

Sep 26, 2023

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

001157311300016