Energy-Efficient Approximate Multiplication for Digital Signal Processing and Classification Applications

The need to support various digital signal processing (DSP) and classification applications on energy-constrained devices has steadily grown. Such applications often extensively perform matrix multiplications using fixed-point arithmetic while exhibiting tolerance for some computational errors. Henc...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on very large scale integration (VLSI) systems 2015-06, Vol.23 (6), p.1180-1184
Hauptverfasser:	Narayanamoorthy, Srinivasan, Moghaddam, Hadi Asghari, Zhenhong Liu, Taejoon Park, Nam Sung Kim
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Algorithm design and analysis Approximation Digital signal processing Energy consumption energy efficiency Image recognition Multiplexing multiplication Very large scale integration
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

container_end_page	1184
container_issue	6
container_start_page	1180
container_title	IEEE transactions on very large scale integration (VLSI) systems
container_volume	23
creator	Narayanamoorthy, Srinivasan Moghaddam, Hadi Asghari Zhenhong Liu Taejoon Park Nam Sung Kim
description	The need to support various digital signal processing (DSP) and classification applications on energy-constrained devices has steadily grown. Such applications often extensively perform matrix multiplications using fixed-point arithmetic while exhibiting tolerance for some computational errors. Hence, improving the energy efficiency of multiplications is critical. In this brief, we propose multiplier architectures that can tradeoff computational accuracy with energy consumption at design time. Compared with a precise multiplier, the proposed multiplier can consume 58% less energy/op with average computational error of \sim 1 %. Finally, we demonstrate that such a small computational error does not notably impact the quality of DSP and the accuracy of classification applications.
doi_str_mv	10.1109/TVLSI.2014.2333366
format	Article
fullrecord	<record><control><sourceid>crossref_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_TVLSI_2014_2333366</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6858039</ieee_id><sourcerecordid>10_1109_TVLSI_2014_2333366</sourcerecordid><originalsourceid>FETCH-LOGICAL-c451t-c0d24ce5c1c1aab4db9b573634fb69f7226d048b9883d4e037fbdbbe4fbcb75f3</originalsourceid><addsrcrecordid>eNo9kN9KwzAUxoMoOKcvoDd5gc78b3M56tRBRWHT25KkSYnUtiQV3Nubuc1z853DOb8PzgfALUYLjJG8335Um_WCIMwWhKYS4gzMMOd5JlOdpx4JmhUEo0twFeMnSpdMohnwq96GdpetnPPG236Cy3EMw4__UpOFL9_d5MfOGzX5oYduCPDBt35SHdz4tk_yFgZjY_R9C1XfwLJTaXAnIHmd4HgNLpzqor056hy8P6625XNWvT6ty2WVGcbxlBnUEGYsN9hgpTRrtNQ8p4Iyp4V0OSGiQazQsihowyyiudON1jatjc65o3NADr4mDDEG6-oxpG_Crsao3odV_4VV78Oqj2El6O4AeWvtPyAKXiAq6S-qK2m_</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Energy-Efficient Approximate Multiplication for Digital Signal Processing and Classification Applications</title><source>IEEE Electronic Library (IEL)</source><creator>Narayanamoorthy, Srinivasan ; Moghaddam, Hadi Asghari ; Zhenhong Liu ; Taejoon Park ; Nam Sung Kim</creator><creatorcontrib>Narayanamoorthy, Srinivasan ; Moghaddam, Hadi Asghari ; Zhenhong Liu ; Taejoon Park ; Nam Sung Kim</creatorcontrib><description>The need to support various digital signal processing (DSP) and classification applications on energy-constrained devices has steadily grown. Such applications often extensively perform matrix multiplications using fixed-point arithmetic while exhibiting tolerance for some computational errors. Hence, improving the energy efficiency of multiplications is critical. In this brief, we propose multiplier architectures that can tradeoff computational accuracy with energy consumption at design time. Compared with a precise multiplier, the proposed multiplier can consume 58% less energy/op with average computational error of \sim 1 %. Finally, we demonstrate that such a small computational error does not notably impact the quality of DSP and the accuracy of classification applications.</description><identifier>ISSN: 1063-8210</identifier><identifier>EISSN: 1557-9999</identifier><identifier>DOI: 10.1109/TVLSI.2014.2333366</identifier><identifier>CODEN: IEVSE9</identifier><language>eng</language><publisher>IEEE</publisher><subject>Accuracy ; Algorithm design and analysis ; Approximation ; Digital signal processing ; Energy consumption ; energy efficiency ; Image recognition ; Multiplexing ; multiplication ; Very large scale integration</subject><ispartof>IEEE transactions on very large scale integration (VLSI) systems, 2015-06, Vol.23 (6), p.1180-1184</ispartof><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c451t-c0d24ce5c1c1aab4db9b573634fb69f7226d048b9883d4e037fbdbbe4fbcb75f3</citedby><cites>FETCH-LOGICAL-c451t-c0d24ce5c1c1aab4db9b573634fb69f7226d048b9883d4e037fbdbbe4fbcb75f3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6858039$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,777,781,793,27905,27906,54739</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6858039$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Narayanamoorthy, Srinivasan</creatorcontrib><creatorcontrib>Moghaddam, Hadi Asghari</creatorcontrib><creatorcontrib>Zhenhong Liu</creatorcontrib><creatorcontrib>Taejoon Park</creatorcontrib><creatorcontrib>Nam Sung Kim</creatorcontrib><title>Energy-Efficient Approximate Multiplication for Digital Signal Processing and Classification Applications</title><title>IEEE transactions on very large scale integration (VLSI) systems</title><addtitle>TVLSI</addtitle><description>The need to support various digital signal processing (DSP) and classification applications on energy-constrained devices has steadily grown. Such applications often extensively perform matrix multiplications using fixed-point arithmetic while exhibiting tolerance for some computational errors. Hence, improving the energy efficiency of multiplications is critical. In this brief, we propose multiplier architectures that can tradeoff computational accuracy with energy consumption at design time. Compared with a precise multiplier, the proposed multiplier can consume 58% less energy/op with average computational error of \sim 1 %. Finally, we demonstrate that such a small computational error does not notably impact the quality of DSP and the accuracy of classification applications.</description><subject>Accuracy</subject><subject>Algorithm design and analysis</subject><subject>Approximation</subject><subject>Digital signal processing</subject><subject>Energy consumption</subject><subject>energy efficiency</subject><subject>Image recognition</subject><subject>Multiplexing</subject><subject>multiplication</subject><subject>Very large scale integration</subject><issn>1063-8210</issn><issn>1557-9999</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2015</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9kN9KwzAUxoMoOKcvoDd5gc78b3M56tRBRWHT25KkSYnUtiQV3Nubuc1z853DOb8PzgfALUYLjJG8335Um_WCIMwWhKYS4gzMMOd5JlOdpx4JmhUEo0twFeMnSpdMohnwq96GdpetnPPG236Cy3EMw4__UpOFL9_d5MfOGzX5oYduCPDBt35SHdz4tk_yFgZjY_R9C1XfwLJTaXAnIHmd4HgNLpzqor056hy8P6625XNWvT6ty2WVGcbxlBnUEGYsN9hgpTRrtNQ8p4Iyp4V0OSGiQazQsihowyyiudON1jatjc65o3NADr4mDDEG6-oxpG_Crsao3odV_4VV78Oqj2El6O4AeWvtPyAKXiAq6S-qK2m_</recordid><startdate>20150601</startdate><enddate>20150601</enddate><creator>Narayanamoorthy, Srinivasan</creator><creator>Moghaddam, Hadi Asghari</creator><creator>Zhenhong Liu</creator><creator>Taejoon Park</creator><creator>Nam Sung Kim</creator><general>IEEE</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20150601</creationdate><title>Energy-Efficient Approximate Multiplication for Digital Signal Processing and Classification Applications</title><author>Narayanamoorthy, Srinivasan ; Moghaddam, Hadi Asghari ; Zhenhong Liu ; Taejoon Park ; Nam Sung Kim</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c451t-c0d24ce5c1c1aab4db9b573634fb69f7226d048b9883d4e037fbdbbe4fbcb75f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2015</creationdate><topic>Accuracy</topic><topic>Algorithm design and analysis</topic><topic>Approximation</topic><topic>Digital signal processing</topic><topic>Energy consumption</topic><topic>energy efficiency</topic><topic>Image recognition</topic><topic>Multiplexing</topic><topic>multiplication</topic><topic>Very large scale integration</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Narayanamoorthy, Srinivasan</creatorcontrib><creatorcontrib>Moghaddam, Hadi Asghari</creatorcontrib><creatorcontrib>Zhenhong Liu</creatorcontrib><creatorcontrib>Taejoon Park</creatorcontrib><creatorcontrib>Nam Sung Kim</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><jtitle>IEEE transactions on very large scale integration (VLSI) systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Narayanamoorthy, Srinivasan</au><au>Moghaddam, Hadi Asghari</au><au>Zhenhong Liu</au><au>Taejoon Park</au><au>Nam Sung Kim</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Energy-Efficient Approximate Multiplication for Digital Signal Processing and Classification Applications</atitle><jtitle>IEEE transactions on very large scale integration (VLSI) systems</jtitle><stitle>TVLSI</stitle><date>2015-06-01</date><risdate>2015</risdate><volume>23</volume><issue>6</issue><spage>1180</spage><epage>1184</epage><pages>1180-1184</pages><issn>1063-8210</issn><eissn>1557-9999</eissn><coden>IEVSE9</coden><abstract>The need to support various digital signal processing (DSP) and classification applications on energy-constrained devices has steadily grown. Such applications often extensively perform matrix multiplications using fixed-point arithmetic while exhibiting tolerance for some computational errors. Hence, improving the energy efficiency of multiplications is critical. In this brief, we propose multiplier architectures that can tradeoff computational accuracy with energy consumption at design time. Compared with a precise multiplier, the proposed multiplier can consume 58% less energy/op with average computational error of \sim 1 %. Finally, we demonstrate that such a small computational error does not notably impact the quality of DSP and the accuracy of classification applications.</abstract><pub>IEEE</pub><doi>10.1109/TVLSI.2014.2333366</doi><tpages>5</tpages><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier	ISSN: 1063-8210
ispartof	IEEE transactions on very large scale integration (VLSI) systems, 2015-06, Vol.23 (6), p.1180-1184
issn	1063-8210 1557-9999
language	eng
recordid	cdi_crossref_primary_10_1109_TVLSI_2014_2333366
source	IEEE Electronic Library (IEL)
subjects	Accuracy Algorithm design and analysis Approximation Digital signal processing Energy consumption energy efficiency Image recognition Multiplexing multiplication Very large scale integration
title	Energy-Efficient Approximate Multiplication for Digital Signal Processing and Classification Applications
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-18T11%3A24%3A11IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-crossref_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Energy-Efficient%20Approximate%20Multiplication%20for%20Digital%20Signal%20Processing%20and%20Classification%20Applications&rft.jtitle=IEEE%20transactions%20on%20very%20large%20scale%20integration%20(VLSI)%20systems&rft.au=Narayanamoorthy,%20Srinivasan&rft.date=2015-06-01&rft.volume=23&rft.issue=6&rft.spage=1180&rft.epage=1184&rft.pages=1180-1184&rft.issn=1063-8210&rft.eissn=1557-9999&rft.coden=IEVSE9&rft_id=info:doi/10.1109/TVLSI.2014.2333366&rft_dat=%3Ccrossref_RIE%3E10_1109_TVLSI_2014_2333366%3C/crossref_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6858039&rfr_iscdi=true