hh.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
E€iffcient Implementation of Convolution Neural Networks Inference On Manycore Architectures
Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), Centre for Research on Embedded Systems (CERES).
Amrita University, Bengaluru, India.
Halmstad University, School of Information Technology, Halmstad Embedded and Intelligent Systems Research (EIS), Centre for Research on Embedded Systems (CERES).ORCID iD: 0000-0002-4932-4036
2017 (English)Conference paper, Poster (with or without abstract) (Refereed)
Abstract [en]

The convolution module of convolution neural networks is highly computation demanding. In order to execute a neural network inference on embedded platforms, an ecient implementation of the convolution is required. Low precision parameters can provide an implementation that requires less memory, less computation time, and less power consumption. Nevertheless, streaming the convolution computation over parallelized processing units saves a lot of memory, which is a key concern in memory constrained embedded platforms. In this paper, we show how the convolution module can be implemented on Epiphany manycore architecture. Low precision parameters are used with ternary weights of +1, 0, and -1 values. The computation is done through a pipeline by streaming data through processing units. The proposed approach decreases the memory requirements for CNN implementation and could reach up to 282 GOPS and up to 5.6 GOPs/watt.

Place, publisher, year, edition, pages
2017.
National Category
Embedded Systems
Identifiers
URN: urn:nbn:se:hh:diva-38289OAI: oai:DiVA.org:hh-38289DiVA, id: diva2:1261997
Conference
10th Nordic Workshop on Multi-Core computing (MCC2017), Uppsala, Sweden, Nov. 30 - Dec. 1, 2017
Available from: 2018-11-09 Created: 2018-11-09 Last updated: 2019-01-11Bibliographically approved

Open Access in DiVA

No full text in DiVA

Authority records BETA

Rezk, NesmaUl-Abdin, Zain

Search in DiVA

By author/editor
Rezk, NesmaUl-Abdin, Zain
By organisation
Centre for Research on Embedded Systems (CERES)
Embedded Systems

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 132 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf