Optimization of XNOR Convolution for Binary Convolutional Neural Networks on GPU

Binary convolutional networks have lower computational load and lower memory foot-print compared to their full-precision counterparts. So, they are a feasible alternative for the deployment of computer vision applications on limited capacity embedded devices. Once trained on less resource-constraine...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-07
Main Authors: Mete Can Kaya, Alperen İnci, Temizel, Alptekin
Format: Article
Language:English
Subjects:
Artificial neural networks
Computer vision
Convolution
Electronic devices
Embedded systems
Inference
Optimization
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Mete Can Kaya
Alperen İnci
Temizel, Alptekin
description Binary convolutional networks have lower computational load and lower memory foot-print compared to their full-precision counterparts. So, they are a feasible alternative for the deployment of computer vision applications on limited capacity embedded devices. Once trained on less resource-constrained computational environments, they can be deployed for real-time inference on such devices. In this study, we propose an implementation of binary convolutional network inference on GPU by focusing on optimization of XNOR convolution. Experimental results show that using GPU can provide a speed-up of up to \(42.61\times\) with a kernel size of \(3\times3\). The implementation is publicly available at https://github.com/metcan/Binary-Convolutional-Neural-Network-Inference-on-GPU
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2428261494</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2428261494</sourcerecordid><originalsourceid>FETCH-proquest_journals_24282614943</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mQI8C8oyczNrEosyczPU8hPU4jw8w9ScM7PK8vPKQWLpeUXKThl5iUWVSILJ-Yo-KWWFoGpkvL8ouxiBaBa94BQHgbWtMSc4lReKM3NoOzmGuLsoVtQlF9YmlpcEp-VX1oE1F8cb2RiZGFkZmhiaWJMnCoAXMM-0g</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2428261494</pqid></control><display><type>article</type><title>Optimization of XNOR Convolution for Binary Convolutional Neural Networks on GPU</title><source>Publicly Available Content (ProQuest)</source><creator>Mete Can Kaya ; Alperen İnci ; Temizel, Alptekin</creator><creatorcontrib>Mete Can Kaya ; Alperen İnci ; Temizel, Alptekin</creatorcontrib><description>Binary convolutional networks have lower computational load and lower memory foot-print compared to their full-precision counterparts. So, they are a feasible alternative for the deployment of computer vision applications on limited capacity embedded devices. Once trained on less resource-constrained computational environments, they can be deployed for real-time inference on such devices. In this study, we propose an implementation of binary convolutional network inference on GPU by focusing on optimization of XNOR convolution. Experimental results show that using GPU can provide a speed-up of up to \(42.61\times\) with a kernel size of \(3\times3\). The implementation is publicly available at https://github.com/metcan/Binary-Convolutional-Neural-Network-Inference-on-GPU</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Artificial neural networks ; Computer vision ; Convolution ; Electronic devices ; Embedded systems ; Inference ; Optimization</subject><ispartof>arXiv.org, 2020-07</ispartof><rights>2020. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2428261494?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>776,780,25731,36989,44566</link.rule.ids></links><search><creatorcontrib>Mete Can Kaya</creatorcontrib><creatorcontrib>Alperen İnci</creatorcontrib><creatorcontrib>Temizel, Alptekin</creatorcontrib><title>Optimization of XNOR Convolution for Binary Convolutional Neural Networks on GPU</title><title>arXiv.org</title><description>Binary convolutional networks have lower computational load and lower memory foot-print compared to their full-precision counterparts. So, they are a feasible alternative for the deployment of computer vision applications on limited capacity embedded devices. Once trained on less resource-constrained computational environments, they can be deployed for real-time inference on such devices. In this study, we propose an implementation of binary convolutional network inference on GPU by focusing on optimization of XNOR convolution. Experimental results show that using GPU can provide a speed-up of up to \(42.61\times\) with a kernel size of \(3\times3\). The implementation is publicly available at https://github.com/metcan/Binary-Convolutional-Neural-Network-Inference-on-GPU</description><subject>Artificial neural networks</subject><subject>Computer vision</subject><subject>Convolution</subject><subject>Electronic devices</subject><subject>Embedded systems</subject><subject>Inference</subject><subject>Optimization</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mQI8C8oyczNrEosyczPU8hPU4jw8w9ScM7PK8vPKQWLpeUXKThl5iUWVSILJ-Yo-KWWFoGpkvL8ouxiBaBa94BQHgbWtMSc4lReKM3NoOzmGuLsoVtQlF9YmlpcEp-VX1oE1F8cb2RiZGFkZmhiaWJMnCoAXMM-0g</recordid><startdate>20200728</startdate><enddate>20200728</enddate><creator>Mete Can Kaya</creator><creator>Alperen İnci</creator><creator>Temizel, Alptekin</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20200728</creationdate><title>Optimization of XNOR Convolution for Binary Convolutional Neural Networks on GPU</title><author>Mete Can Kaya ; Alperen İnci ; Temizel, Alptekin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_24282614943</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Artificial neural networks</topic><topic>Computer vision</topic><topic>Convolution</topic><topic>Electronic devices</topic><topic>Embedded systems</topic><topic>Inference</topic><topic>Optimization</topic><toplevel>online_resources</toplevel><creatorcontrib>Mete Can Kaya</creatorcontrib><creatorcontrib>Alperen İnci</creatorcontrib><creatorcontrib>Temizel, Alptekin</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content (ProQuest)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Mete Can Kaya</au><au>Alperen İnci</au><au>Temizel, Alptekin</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Optimization of XNOR Convolution for Binary Convolutional Neural Networks on GPU</atitle><jtitle>arXiv.org</jtitle><date>2020-07-28</date><risdate>2020</risdate><eissn>2331-8422</eissn><abstract>Binary convolutional networks have lower computational load and lower memory foot-print compared to their full-precision counterparts. So, they are a feasible alternative for the deployment of computer vision applications on limited capacity embedded devices. Once trained on less resource-constrained computational environments, they can be deployed for real-time inference on such devices. In this study, we propose an implementation of binary convolutional network inference on GPU by focusing on optimization of XNOR convolution. Experimental results show that using GPU can provide a speed-up of up to \(42.61\times\) with a kernel size of \(3\times3\). The implementation is publicly available at https://github.com/metcan/Binary-Convolutional-Neural-Network-Inference-on-GPU</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2020-07
issn 2331-8422
language eng
recordid cdi_proquest_journals_2428261494
source Publicly Available Content (ProQuest)
subjects Artificial neural networks
Computer vision
Convolution
Electronic devices
Embedded systems
Inference
Optimization
title Optimization of XNOR Convolution for Binary Convolutional Neural Networks on GPU
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-03T01%3A20%3A02IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Optimization%20of%20XNOR%20Convolution%20for%20Binary%20Convolutional%20Neural%20Networks%20on%20GPU&rft.jtitle=arXiv.org&rft.au=Mete%20Can%20Kaya&rft.date=2020-07-28&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2428261494%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_24282614943%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2428261494&rft_id=info:pmid/&rfr_iscdi=true