Design and Applications of Approximate Circuits by Gate-Level Pruning

Energy-efficiency is a critical concern for many systems, ranging from Internet of things objects and mobile devices to high-performance computers. Moreover, after 40 years of prosperity, Moore's law is starting to show its economic and technical limits. Noticing that many circuits are over-eng...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on very large scale integration (VLSI) systems 2017-05, Vol.25 (5), p.1694-1702
Hauptverfasser: Schlachter, Jeremy, Camus, Vincent, Palem, Krishna V., Enz, Christian
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 1702
container_issue 5
container_start_page 1694
container_title IEEE transactions on very large scale integration (VLSI) systems
container_volume 25
creator Schlachter, Jeremy
Camus, Vincent
Palem, Krishna V.
Enz, Christian
description Energy-efficiency is a critical concern for many systems, ranging from Internet of things objects and mobile devices to high-performance computers. Moreover, after 40 years of prosperity, Moore's law is starting to show its economic and technical limits. Noticing that many circuits are over-engineered and that many applications are error-resilient or require less precision than offered by the existing hardware, approximate computing has emerged as a potential solution to pursue improvements of digital circuits. In this regard, a technique to systematically tradeoff accuracy in exchange for area, power, and delay savings in digital circuits is proposed: gate-level pruning (GLP). A CAD tool is build and integrated into a standard digital flow to offer a wide range of cost-accuracy tradeoffs for any conventional design. The methodology is first demonstrated on adders, achieving up to 78% energy-delay-area reduction for 10% mean relative error. It is then detailed how this methodology can be applied on a more complex system composed of a multitude of arithmetic blocks and memory: the discrete cosine transform (DCT), which is a key building block for image and video processing applications. Even though arithmetic circuits represent less than 4% of the entire DCT area, it is shown that the GLP technique can lead to 21% energy-delay-area savings over the entire system for a reasonable image quality loss of 24 dB. This significant saving is achieved thanks to the pruned arithmetic circuits, which sets some nodes at constant values, enabling the synthesis tool to further simplify the circuit and memory.
doi_str_mv 10.1109/TVLSI.2017.2657799
format Article
fullrecord <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_7850945</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>7850945</ieee_id><sourcerecordid>1893706772</sourcerecordid><originalsourceid>FETCH-LOGICAL-c405t-cee72aa89ad68399699e6e0626d7c796705076f33dcd42566828a453d712d2b63</originalsourceid><addsrcrecordid>eNo9UE1LAzEQDaJgrf4BvQQ87zpJNsnmWGqthQUFq9eQbrIlpe7WZFfsvze1xbnMB-_NvHkI3RLICQH1sPyo3hY5BSJzKriUSp2hEeFcZirFeapBsKykBC7RVYwbAFIUCkZo9uiiX7fYtBZPdrutr03vuzbirjn0ofvxn6Z3eOpDPfg-4tUez9Mgq9y32-LXMLS-XV-ji8Zso7s55TF6f5otp89Z9TJfTCdVVhfA-6x2TlJjSmWsKJlSQiknHAgqrKylEhI4SNEwZmtbUC5ESUtTcGYloZauBBuj--PeJOxrcLHXm24IbTqpSamYBCElTSh6RNWhizG4Ru9C-iLsNQF9sEv_2aUPdumTXYl0dyR559w_QZYcVFLwCy9mZTQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1893706772</pqid></control><display><type>article</type><title>Design and Applications of Approximate Circuits by Gate-Level Pruning</title><source>IEEE Electronic Library (IEL)</source><creator>Schlachter, Jeremy ; Camus, Vincent ; Palem, Krishna V. ; Enz, Christian</creator><creatorcontrib>Schlachter, Jeremy ; Camus, Vincent ; Palem, Krishna V. ; Enz, Christian</creatorcontrib><description>Energy-efficiency is a critical concern for many systems, ranging from Internet of things objects and mobile devices to high-performance computers. Moreover, after 40 years of prosperity, Moore's law is starting to show its economic and technical limits. Noticing that many circuits are over-engineered and that many applications are error-resilient or require less precision than offered by the existing hardware, approximate computing has emerged as a potential solution to pursue improvements of digital circuits. In this regard, a technique to systematically tradeoff accuracy in exchange for area, power, and delay savings in digital circuits is proposed: gate-level pruning (GLP). A CAD tool is build and integrated into a standard digital flow to offer a wide range of cost-accuracy tradeoffs for any conventional design. The methodology is first demonstrated on adders, achieving up to 78% energy-delay-area reduction for 10% mean relative error. It is then detailed how this methodology can be applied on a more complex system composed of a multitude of arithmetic blocks and memory: the discrete cosine transform (DCT), which is a key building block for image and video processing applications. Even though arithmetic circuits represent less than 4% of the entire DCT area, it is shown that the GLP technique can lead to 21% energy-delay-area savings over the entire system for a reasonable image quality loss of 24 dB. This significant saving is achieved thanks to the pruned arithmetic circuits, which sets some nodes at constant values, enabling the synthesis tool to further simplify the circuit and memory.</description><identifier>ISSN: 1063-8210</identifier><identifier>EISSN: 1557-9999</identifier><identifier>DOI: 10.1109/TVLSI.2017.2657799</identifier><identifier>CODEN: IEVSE9</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Accuracy ; Adders ; Approximate adders ; approximate circuit design ; approximate computing ; Arithmetic ; Circuits ; Complex systems ; Delay ; Design standards ; Digital electronics ; Discrete cosine transform ; Discrete cosine transforms ; Error reduction ; Hardware ; Image processing ; Image quality ; Internet of Things ; Internet of things (IoT) ; Logic gates ; lowpower digital circuits ; Probabilistic logic ; Pruning ; Tradeoffs ; Video ; Wires</subject><ispartof>IEEE transactions on very large scale integration (VLSI) systems, 2017-05, Vol.25 (5), p.1694-1702</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2017</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c405t-cee72aa89ad68399699e6e0626d7c796705076f33dcd42566828a453d712d2b63</citedby><cites>FETCH-LOGICAL-c405t-cee72aa89ad68399699e6e0626d7c796705076f33dcd42566828a453d712d2b63</cites><orcidid>0000-0003-1483-3591</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/7850945$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/7850945$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Schlachter, Jeremy</creatorcontrib><creatorcontrib>Camus, Vincent</creatorcontrib><creatorcontrib>Palem, Krishna V.</creatorcontrib><creatorcontrib>Enz, Christian</creatorcontrib><title>Design and Applications of Approximate Circuits by Gate-Level Pruning</title><title>IEEE transactions on very large scale integration (VLSI) systems</title><addtitle>TVLSI</addtitle><description>Energy-efficiency is a critical concern for many systems, ranging from Internet of things objects and mobile devices to high-performance computers. Moreover, after 40 years of prosperity, Moore's law is starting to show its economic and technical limits. Noticing that many circuits are over-engineered and that many applications are error-resilient or require less precision than offered by the existing hardware, approximate computing has emerged as a potential solution to pursue improvements of digital circuits. In this regard, a technique to systematically tradeoff accuracy in exchange for area, power, and delay savings in digital circuits is proposed: gate-level pruning (GLP). A CAD tool is build and integrated into a standard digital flow to offer a wide range of cost-accuracy tradeoffs for any conventional design. The methodology is first demonstrated on adders, achieving up to 78% energy-delay-area reduction for 10% mean relative error. It is then detailed how this methodology can be applied on a more complex system composed of a multitude of arithmetic blocks and memory: the discrete cosine transform (DCT), which is a key building block for image and video processing applications. Even though arithmetic circuits represent less than 4% of the entire DCT area, it is shown that the GLP technique can lead to 21% energy-delay-area savings over the entire system for a reasonable image quality loss of 24 dB. This significant saving is achieved thanks to the pruned arithmetic circuits, which sets some nodes at constant values, enabling the synthesis tool to further simplify the circuit and memory.</description><subject>Accuracy</subject><subject>Adders</subject><subject>Approximate adders</subject><subject>approximate circuit design</subject><subject>approximate computing</subject><subject>Arithmetic</subject><subject>Circuits</subject><subject>Complex systems</subject><subject>Delay</subject><subject>Design standards</subject><subject>Digital electronics</subject><subject>Discrete cosine transform</subject><subject>Discrete cosine transforms</subject><subject>Error reduction</subject><subject>Hardware</subject><subject>Image processing</subject><subject>Image quality</subject><subject>Internet of Things</subject><subject>Internet of things (IoT)</subject><subject>Logic gates</subject><subject>lowpower digital circuits</subject><subject>Probabilistic logic</subject><subject>Pruning</subject><subject>Tradeoffs</subject><subject>Video</subject><subject>Wires</subject><issn>1063-8210</issn><issn>1557-9999</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2017</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9UE1LAzEQDaJgrf4BvQQ87zpJNsnmWGqthQUFq9eQbrIlpe7WZFfsvze1xbnMB-_NvHkI3RLICQH1sPyo3hY5BSJzKriUSp2hEeFcZirFeapBsKykBC7RVYwbAFIUCkZo9uiiX7fYtBZPdrutr03vuzbirjn0ofvxn6Z3eOpDPfg-4tUez9Mgq9y32-LXMLS-XV-ji8Zso7s55TF6f5otp89Z9TJfTCdVVhfA-6x2TlJjSmWsKJlSQiknHAgqrKylEhI4SNEwZmtbUC5ESUtTcGYloZauBBuj--PeJOxrcLHXm24IbTqpSamYBCElTSh6RNWhizG4Ru9C-iLsNQF9sEv_2aUPdumTXYl0dyR559w_QZYcVFLwCy9mZTQ</recordid><startdate>20170501</startdate><enddate>20170501</enddate><creator>Schlachter, Jeremy</creator><creator>Camus, Vincent</creator><creator>Palem, Krishna V.</creator><creator>Enz, Christian</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>8FD</scope><scope>L7M</scope><orcidid>https://orcid.org/0000-0003-1483-3591</orcidid></search><sort><creationdate>20170501</creationdate><title>Design and Applications of Approximate Circuits by Gate-Level Pruning</title><author>Schlachter, Jeremy ; Camus, Vincent ; Palem, Krishna V. ; Enz, Christian</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c405t-cee72aa89ad68399699e6e0626d7c796705076f33dcd42566828a453d712d2b63</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2017</creationdate><topic>Accuracy</topic><topic>Adders</topic><topic>Approximate adders</topic><topic>approximate circuit design</topic><topic>approximate computing</topic><topic>Arithmetic</topic><topic>Circuits</topic><topic>Complex systems</topic><topic>Delay</topic><topic>Design standards</topic><topic>Digital electronics</topic><topic>Discrete cosine transform</topic><topic>Discrete cosine transforms</topic><topic>Error reduction</topic><topic>Hardware</topic><topic>Image processing</topic><topic>Image quality</topic><topic>Internet of Things</topic><topic>Internet of things (IoT)</topic><topic>Logic gates</topic><topic>lowpower digital circuits</topic><topic>Probabilistic logic</topic><topic>Pruning</topic><topic>Tradeoffs</topic><topic>Video</topic><topic>Wires</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Schlachter, Jeremy</creatorcontrib><creatorcontrib>Camus, Vincent</creatorcontrib><creatorcontrib>Palem, Krishna V.</creatorcontrib><creatorcontrib>Enz, Christian</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><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</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>Schlachter, Jeremy</au><au>Camus, Vincent</au><au>Palem, Krishna V.</au><au>Enz, Christian</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Design and Applications of Approximate Circuits by Gate-Level Pruning</atitle><jtitle>IEEE transactions on very large scale integration (VLSI) systems</jtitle><stitle>TVLSI</stitle><date>2017-05-01</date><risdate>2017</risdate><volume>25</volume><issue>5</issue><spage>1694</spage><epage>1702</epage><pages>1694-1702</pages><issn>1063-8210</issn><eissn>1557-9999</eissn><coden>IEVSE9</coden><abstract>Energy-efficiency is a critical concern for many systems, ranging from Internet of things objects and mobile devices to high-performance computers. Moreover, after 40 years of prosperity, Moore's law is starting to show its economic and technical limits. Noticing that many circuits are over-engineered and that many applications are error-resilient or require less precision than offered by the existing hardware, approximate computing has emerged as a potential solution to pursue improvements of digital circuits. In this regard, a technique to systematically tradeoff accuracy in exchange for area, power, and delay savings in digital circuits is proposed: gate-level pruning (GLP). A CAD tool is build and integrated into a standard digital flow to offer a wide range of cost-accuracy tradeoffs for any conventional design. The methodology is first demonstrated on adders, achieving up to 78% energy-delay-area reduction for 10% mean relative error. It is then detailed how this methodology can be applied on a more complex system composed of a multitude of arithmetic blocks and memory: the discrete cosine transform (DCT), which is a key building block for image and video processing applications. Even though arithmetic circuits represent less than 4% of the entire DCT area, it is shown that the GLP technique can lead to 21% energy-delay-area savings over the entire system for a reasonable image quality loss of 24 dB. This significant saving is achieved thanks to the pruned arithmetic circuits, which sets some nodes at constant values, enabling the synthesis tool to further simplify the circuit and memory.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TVLSI.2017.2657799</doi><tpages>9</tpages><orcidid>https://orcid.org/0000-0003-1483-3591</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1063-8210
ispartof IEEE transactions on very large scale integration (VLSI) systems, 2017-05, Vol.25 (5), p.1694-1702
issn 1063-8210
1557-9999
language eng
recordid cdi_ieee_primary_7850945
source IEEE Electronic Library (IEL)
subjects Accuracy
Adders
Approximate adders
approximate circuit design
approximate computing
Arithmetic
Circuits
Complex systems
Delay
Design standards
Digital electronics
Discrete cosine transform
Discrete cosine transforms
Error reduction
Hardware
Image processing
Image quality
Internet of Things
Internet of things (IoT)
Logic gates
lowpower digital circuits
Probabilistic logic
Pruning
Tradeoffs
Video
Wires
title Design and Applications of Approximate Circuits by Gate-Level Pruning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T21%3A50%3A18IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Design%20and%20Applications%20of%20Approximate%20Circuits%20by%20Gate-Level%20Pruning&rft.jtitle=IEEE%20transactions%20on%20very%20large%20scale%20integration%20(VLSI)%20systems&rft.au=Schlachter,%20Jeremy&rft.date=2017-05-01&rft.volume=25&rft.issue=5&rft.spage=1694&rft.epage=1702&rft.pages=1694-1702&rft.issn=1063-8210&rft.eissn=1557-9999&rft.coden=IEVSE9&rft_id=info:doi/10.1109/TVLSI.2017.2657799&rft_dat=%3Cproquest_RIE%3E1893706772%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1893706772&rft_id=info:pmid/&rft_ieee_id=7850945&rfr_iscdi=true