Correlation manipulating circuits for stochastic computing

Stochastic computing (SC) is an emerging computing technique that promises high density, low power, and error tolerant solutions. In SC, values are encoded as unary bitstreams and SC arithmetic circuits operate on one or more bitstreams. In many cases, the input bitstreams must be correlated or unco...

Full description

Saved in:
Bibliographic Details
Main Authors: Lee, Vincent T., Alaghi, Armin, Ceze, Luis
Format: Conference Proceeding
Language:English
Subjects:
Adders
Correlation
correlation manipulation
Decorrelation
Image coding
Pipelines
Stochastic computing
Synchronization
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c290t-31daf71f7ad1556528706b0956b4cd7746d91e6d23489fba187e2f472686b7953
cites
container_end_page 1422
container_issue
container_start_page 1417
container_title
container_volume
creator Lee, Vincent T.
Alaghi, Armin
Ceze, Luis
description Stochastic computing (SC) is an emerging computing technique that promises high density, low power, and error tolerant solutions. In SC, values are encoded as unary bitstreams and SC arithmetic circuits operate on one or more bitstreams. In many cases, the input bitstreams must be correlated or uncorrelated for SC arithmetic to produce accurate results. As a result, a key challenge for designing SC accelerators is manipulating the impact of correlation across SC operations. This paper presents and evaluates a set of novel correlation manipulating circuits to manage correlation in SC computation: a synchronizer, desynchronizer, and decorrelator. We then use these circuits to propose improved SC maximum, minimum, and saturating adder designs. Compared to existing correlation manipulation techniques, our circuits are more accurate and up to 3× more energy efficient. In the context of an image processing pipeline, these circuits can reduce the total energy consumption by up to 24%.
doi_str_mv 10.23919/DATE.2018.8342234
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_8342234</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8342234</ieee_id><sourcerecordid>8342234</sourcerecordid><originalsourceid>FETCH-LOGICAL-c290t-31daf71f7ad1556528706b0956b4cd7746d91e6d23489fba187e2f472686b7953</originalsourceid><addsrcrecordid>eNotj8tKAzEYhaMgWGtfQDd5gRnzJ5PL766MrQoFN3VdMplEI50LyczCt7fFrg4HDh_fIeQBWMkFAj69rPebkjMwpREV56K6IivURqAB5EowvCYLkNIUAAxuyV3OP4wxKTguyHM9pOSPdopDTzvbx3E-l_6LupjcHKdMw5Bongb3bfMUHXVDN87nxT25CfaY_eqSS_K53ezrt2L38fper3eF48imQkBrg4agbXuSUJIbzVTDUKqmcq3WlWoRvGpP3gZDY8Foz0OluTKq0SjFkjz-c6P3_jCm2Nn0e7hcFX-MMkel</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Correlation manipulating circuits for stochastic computing</title><source>IEEE Xplore All Conference Series</source><creator>Lee, Vincent T. ; Alaghi, Armin ; Ceze, Luis</creator><creatorcontrib>Lee, Vincent T. ; Alaghi, Armin ; Ceze, Luis</creatorcontrib><description>Stochastic computing (SC) is an emerging computing technique that promises high density, low power, and error tolerant solutions. In SC, values are encoded as unary bitstreams and SC arithmetic circuits operate on one or more bitstreams. In many cases, the input bitstreams must be correlated or uncorrelated for SC arithmetic to produce accurate results. As a result, a key challenge for designing SC accelerators is manipulating the impact of correlation across SC operations. This paper presents and evaluates a set of novel correlation manipulating circuits to manage correlation in SC computation: a synchronizer, desynchronizer, and decorrelator. We then use these circuits to propose improved SC maximum, minimum, and saturating adder designs. Compared to existing correlation manipulation techniques, our circuits are more accurate and up to 3× more energy efficient. In the context of an image processing pipeline, these circuits can reduce the total energy consumption by up to 24%.</description><identifier>EISSN: 1558-1101</identifier><identifier>EISBN: 9783981926309</identifier><identifier>EISBN: 3981926307</identifier><identifier>DOI: 10.23919/DATE.2018.8342234</identifier><language>eng</language><publisher>EDAA</publisher><subject>Adders ; Correlation ; correlation manipulation ; Decorrelation ; Image coding ; Pipelines ; Stochastic computing ; Synchronization</subject><ispartof>2018 Design, Automation &amp; Test in Europe Conference &amp; Exhibition (DATE), 2018, p.1417-1422</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c290t-31daf71f7ad1556528706b0956b4cd7746d91e6d23489fba187e2f472686b7953</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8342234$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,27924,54554,54931</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/8342234$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Lee, Vincent T.</creatorcontrib><creatorcontrib>Alaghi, Armin</creatorcontrib><creatorcontrib>Ceze, Luis</creatorcontrib><title>Correlation manipulating circuits for stochastic computing</title><title>2018 Design, Automation &amp; Test in Europe Conference &amp; Exhibition (DATE)</title><addtitle>DATE</addtitle><description>Stochastic computing (SC) is an emerging computing technique that promises high density, low power, and error tolerant solutions. In SC, values are encoded as unary bitstreams and SC arithmetic circuits operate on one or more bitstreams. In many cases, the input bitstreams must be correlated or uncorrelated for SC arithmetic to produce accurate results. As a result, a key challenge for designing SC accelerators is manipulating the impact of correlation across SC operations. This paper presents and evaluates a set of novel correlation manipulating circuits to manage correlation in SC computation: a synchronizer, desynchronizer, and decorrelator. We then use these circuits to propose improved SC maximum, minimum, and saturating adder designs. Compared to existing correlation manipulation techniques, our circuits are more accurate and up to 3× more energy efficient. In the context of an image processing pipeline, these circuits can reduce the total energy consumption by up to 24%.</description><subject>Adders</subject><subject>Correlation</subject><subject>correlation manipulation</subject><subject>Decorrelation</subject><subject>Image coding</subject><subject>Pipelines</subject><subject>Stochastic computing</subject><subject>Synchronization</subject><issn>1558-1101</issn><isbn>9783981926309</isbn><isbn>3981926307</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2018</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotj8tKAzEYhaMgWGtfQDd5gRnzJ5PL766MrQoFN3VdMplEI50LyczCt7fFrg4HDh_fIeQBWMkFAj69rPebkjMwpREV56K6IivURqAB5EowvCYLkNIUAAxuyV3OP4wxKTguyHM9pOSPdopDTzvbx3E-l_6LupjcHKdMw5Bongb3bfMUHXVDN87nxT25CfaY_eqSS_K53ezrt2L38fper3eF48imQkBrg4agbXuSUJIbzVTDUKqmcq3WlWoRvGpP3gZDY8Foz0OluTKq0SjFkjz-c6P3_jCm2Nn0e7hcFX-MMkel</recordid><startdate>201803</startdate><enddate>201803</enddate><creator>Lee, Vincent T.</creator><creator>Alaghi, Armin</creator><creator>Ceze, Luis</creator><general>EDAA</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201803</creationdate><title>Correlation manipulating circuits for stochastic computing</title><author>Lee, Vincent T. ; Alaghi, Armin ; Ceze, Luis</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c290t-31daf71f7ad1556528706b0956b4cd7746d91e6d23489fba187e2f472686b7953</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Adders</topic><topic>Correlation</topic><topic>correlation manipulation</topic><topic>Decorrelation</topic><topic>Image coding</topic><topic>Pipelines</topic><topic>Stochastic computing</topic><topic>Synchronization</topic><toplevel>online_resources</toplevel><creatorcontrib>Lee, Vincent T.</creatorcontrib><creatorcontrib>Alaghi, Armin</creatorcontrib><creatorcontrib>Ceze, Luis</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE/IET Electronic Library</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Lee, Vincent T.</au><au>Alaghi, Armin</au><au>Ceze, Luis</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Correlation manipulating circuits for stochastic computing</atitle><btitle>2018 Design, Automation &amp; Test in Europe Conference &amp; Exhibition (DATE)</btitle><stitle>DATE</stitle><date>2018-03</date><risdate>2018</risdate><spage>1417</spage><epage>1422</epage><pages>1417-1422</pages><eissn>1558-1101</eissn><eisbn>9783981926309</eisbn><eisbn>3981926307</eisbn><abstract>Stochastic computing (SC) is an emerging computing technique that promises high density, low power, and error tolerant solutions. In SC, values are encoded as unary bitstreams and SC arithmetic circuits operate on one or more bitstreams. In many cases, the input bitstreams must be correlated or uncorrelated for SC arithmetic to produce accurate results. As a result, a key challenge for designing SC accelerators is manipulating the impact of correlation across SC operations. This paper presents and evaluates a set of novel correlation manipulating circuits to manage correlation in SC computation: a synchronizer, desynchronizer, and decorrelator. We then use these circuits to propose improved SC maximum, minimum, and saturating adder designs. Compared to existing correlation manipulation techniques, our circuits are more accurate and up to 3× more energy efficient. In the context of an image processing pipeline, these circuits can reduce the total energy consumption by up to 24%.</abstract><pub>EDAA</pub><doi>10.23919/DATE.2018.8342234</doi><tpages>6</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 1558-1101
ispartof 2018 Design, Automation & Test in Europe Conference & Exhibition (DATE), 2018, p.1417-1422
issn 1558-1101
language eng
recordid cdi_ieee_primary_8342234
source IEEE Xplore All Conference Series
subjects Adders
Correlation
correlation manipulation
Decorrelation
Image coding
Pipelines
Stochastic computing
Synchronization
title Correlation manipulating circuits for stochastic computing
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-12T13%3A46%3A00IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Correlation%20manipulating%20circuits%20for%20stochastic%20computing&rft.btitle=2018%20Design,%20Automation%20&%20Test%20in%20Europe%20Conference%20&%20Exhibition%20(DATE)&rft.au=Lee,%20Vincent%20T.&rft.date=2018-03&rft.spage=1417&rft.epage=1422&rft.pages=1417-1422&rft.eissn=1558-1101&rft_id=info:doi/10.23919/DATE.2018.8342234&rft.eisbn=9783981926309&rft.eisbn_list=3981926307&rft_dat=%3Cieee_CHZPO%3E8342234%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c290t-31daf71f7ad1556528706b0956b4cd7746d91e6d23489fba187e2f472686b7953%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=8342234&rfr_iscdi=true