Loading…
Fine-grain real-time reconfigurable pipelining
In many computations, average data rates are often significantly lower than the peak rate possible. Consequently, VLSI systems capable of processing data at a maximum specified rate can be excessively dissipative when data rates are low. Such inefficiencies are particularly pronounced in heavily pip...
Saved in:
Published in: | IBM journal of research and development 2003-09, Vol.47 (5-6), p.599-609 |
---|---|
Main Authors: | , , |
Format: | Article |
Language: | English |
Subjects: | |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | |
---|---|
cites | |
container_end_page | 609 |
container_issue | 5-6 |
container_start_page | 599 |
container_title | IBM journal of research and development |
container_volume | 47 |
creator | Kim, Suhwan Ziesler, Conrad H Papaefthymiou, Marios C |
description | In many computations, average data rates are often significantly lower than the peak rate possible. Consequently, VLSI systems capable of processing data at a maximum specified rate can be excessively dissipative when data rates are low. Such inefficiencies are particularly pronounced in heavily pipelined designs, in which registers account for the bulk of energy dissipation in a system. This paper describes a novel methodology for designing reconfigurable pipelines that achieve very low power dissipation by adapting their resources to their computational requirements. In our fine-grain reconfigurable pipelines, energy is saved by disabling and bypassing an appropriate number of pipeline stages whenever data rates are low. In contrast, coarse-grain approaches, such as dynamic voltage scaling, are often unable to capture savings from short-time-scale variations in throughput requirements because of the long time needed to reconfigure the voltage. To evaluate our methodology, we designed an inverse discrete cosine transform (IDCT) module for MPEG-2. Our IDCT included pipelined multipliers that were dynamically reconfigurable on the basis of the number of nonzero coefficients per block and picture size. In comparison with conventional multipliers in corresponding IDCT implementations, our reconfigurable multipliers dissipated about 12-65% less power. [PUBLICATION ABSTRACT] |
doi_str_mv | 10.1147/rd.475.0599 |
format | article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_743201195</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>502257651</sourcerecordid><originalsourceid>FETCH-LOGICAL-c279t-2fa9a45ccaa08d1fc1ac55bb088d5ca1d8bc683745d6c73a91489635fcebbdd63</originalsourceid><addsrcrecordid>eNp90DtLA0EUBeBBFIzRyj8QLLSQXef9KCUYFQI2Wg93Z2bDhM3sOpMt_PduiIVYWN1TfBy4B6FrgmtCuHrIvuZK1FgYc4JmGBNdacnl6a98ji5K2WKMBedmhupVTKHaZIhpkQN01T7uwpRcn9q4GTM0XVgMcQhdTDFtLtFZC10JVz93jj5WT-_Ll2r99vy6fFxXjiqzr2gLBrhwDgBrT1pHwAnRNFhrLxwQrxsnNVNceOkUA0O4NpKJ1oWm8V6yObo79g65_xxD2dtdLC50HaTQj8UqzigmxIhJ3v4rqdKKMKonePMHbvsxp-kLSymWQhJBJ3R_RC73peTQ2iHHHeQvS7A9TGyzt9PE9jAx-wbKQW3P</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>220656152</pqid></control><display><type>article</type><title>Fine-grain real-time reconfigurable pipelining</title><source>IEEE Xplore All Journals</source><source>ABI/INFORM Collection</source><creator>Kim, Suhwan ; Ziesler, Conrad H ; Papaefthymiou, Marios C</creator><creatorcontrib>Kim, Suhwan ; Ziesler, Conrad H ; Papaefthymiou, Marios C</creatorcontrib><description>In many computations, average data rates are often significantly lower than the peak rate possible. Consequently, VLSI systems capable of processing data at a maximum specified rate can be excessively dissipative when data rates are low. Such inefficiencies are particularly pronounced in heavily pipelined designs, in which registers account for the bulk of energy dissipation in a system. This paper describes a novel methodology for designing reconfigurable pipelines that achieve very low power dissipation by adapting their resources to their computational requirements. In our fine-grain reconfigurable pipelines, energy is saved by disabling and bypassing an appropriate number of pipeline stages whenever data rates are low. In contrast, coarse-grain approaches, such as dynamic voltage scaling, are often unable to capture savings from short-time-scale variations in throughput requirements because of the long time needed to reconfigure the voltage. To evaluate our methodology, we designed an inverse discrete cosine transform (IDCT) module for MPEG-2. Our IDCT included pipelined multipliers that were dynamically reconfigurable on the basis of the number of nonzero coefficients per block and picture size. In comparison with conventional multipliers in corresponding IDCT implementations, our reconfigurable multipliers dissipated about 12-65% less power. [PUBLICATION ABSTRACT]</description><identifier>ISSN: 0018-8646</identifier><identifier>EISSN: 0018-8646</identifier><identifier>EISSN: 2151-8556</identifier><identifier>DOI: 10.1147/rd.475.0599</identifier><identifier>CODEN: IBMJAE</identifier><language>eng</language><publisher>Armonk: International Business Machines Corporation</publisher><subject>Data processing ; Design ; Efficiency ; Energy consumption ; Energy dissipation ; Microelectronics ; Multimedia communications ; Pipelines ; Real time</subject><ispartof>IBM journal of research and development, 2003-09, Vol.47 (5-6), p.599-609</ispartof><rights>Copyright International Business Machines Corporation Sep-Nov 2003</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.proquest.com/docview/220656152/fulltextPDF?pq-origsite=primo$$EPDF$$P50$$Gproquest$$H</linktopdf><linktohtml>$$Uhttps://www.proquest.com/docview/220656152?pq-origsite=primo$$EHTML$$P50$$Gproquest$$H</linktohtml><link.rule.ids>314,780,784,11688,27924,27925,36060,36061,44363,74895</link.rule.ids></links><search><creatorcontrib>Kim, Suhwan</creatorcontrib><creatorcontrib>Ziesler, Conrad H</creatorcontrib><creatorcontrib>Papaefthymiou, Marios C</creatorcontrib><title>Fine-grain real-time reconfigurable pipelining</title><title>IBM journal of research and development</title><description>In many computations, average data rates are often significantly lower than the peak rate possible. Consequently, VLSI systems capable of processing data at a maximum specified rate can be excessively dissipative when data rates are low. Such inefficiencies are particularly pronounced in heavily pipelined designs, in which registers account for the bulk of energy dissipation in a system. This paper describes a novel methodology for designing reconfigurable pipelines that achieve very low power dissipation by adapting their resources to their computational requirements. In our fine-grain reconfigurable pipelines, energy is saved by disabling and bypassing an appropriate number of pipeline stages whenever data rates are low. In contrast, coarse-grain approaches, such as dynamic voltage scaling, are often unable to capture savings from short-time-scale variations in throughput requirements because of the long time needed to reconfigure the voltage. To evaluate our methodology, we designed an inverse discrete cosine transform (IDCT) module for MPEG-2. Our IDCT included pipelined multipliers that were dynamically reconfigurable on the basis of the number of nonzero coefficients per block and picture size. In comparison with conventional multipliers in corresponding IDCT implementations, our reconfigurable multipliers dissipated about 12-65% less power. [PUBLICATION ABSTRACT]</description><subject>Data processing</subject><subject>Design</subject><subject>Efficiency</subject><subject>Energy consumption</subject><subject>Energy dissipation</subject><subject>Microelectronics</subject><subject>Multimedia communications</subject><subject>Pipelines</subject><subject>Real time</subject><issn>0018-8646</issn><issn>0018-8646</issn><issn>2151-8556</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2003</creationdate><recordtype>article</recordtype><sourceid>M0C</sourceid><recordid>eNp90DtLA0EUBeBBFIzRyj8QLLSQXef9KCUYFQI2Wg93Z2bDhM3sOpMt_PduiIVYWN1TfBy4B6FrgmtCuHrIvuZK1FgYc4JmGBNdacnl6a98ji5K2WKMBedmhupVTKHaZIhpkQN01T7uwpRcn9q4GTM0XVgMcQhdTDFtLtFZC10JVz93jj5WT-_Ll2r99vy6fFxXjiqzr2gLBrhwDgBrT1pHwAnRNFhrLxwQrxsnNVNceOkUA0O4NpKJ1oWm8V6yObo79g65_xxD2dtdLC50HaTQj8UqzigmxIhJ3v4rqdKKMKonePMHbvsxp-kLSymWQhJBJ3R_RC73peTQ2iHHHeQvS7A9TGyzt9PE9jAx-wbKQW3P</recordid><startdate>20030901</startdate><enddate>20030901</enddate><creator>Kim, Suhwan</creator><creator>Ziesler, Conrad H</creator><creator>Papaefthymiou, Marios C</creator><general>International Business Machines Corporation</general><scope>AAYXX</scope><scope>CITATION</scope><scope>0U~</scope><scope>1-H</scope><scope>3V.</scope><scope>7WY</scope><scope>7WZ</scope><scope>7XB</scope><scope>87Z</scope><scope>88I</scope><scope>8AL</scope><scope>8AO</scope><scope>8FE</scope><scope>8FG</scope><scope>8FK</scope><scope>8FL</scope><scope>8G5</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BEC</scope><scope>BENPR</scope><scope>BEZIV</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FRNLG</scope><scope>F~G</scope><scope>GNUQQ</scope><scope>GUQSH</scope><scope>HCIFZ</scope><scope>JQ2</scope><scope>K60</scope><scope>K6~</scope><scope>K7-</scope><scope>L.-</scope><scope>L.0</scope><scope>M0C</scope><scope>M0N</scope><scope>M2O</scope><scope>M2P</scope><scope>MBDVC</scope><scope>P5Z</scope><scope>P62</scope><scope>PQBIZ</scope><scope>PQBZA</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>Q9U</scope><scope>7SC</scope><scope>8FD</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>20030901</creationdate><title>Fine-grain real-time reconfigurable pipelining</title><author>Kim, Suhwan ; Ziesler, Conrad H ; Papaefthymiou, Marios C</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c279t-2fa9a45ccaa08d1fc1ac55bb088d5ca1d8bc683745d6c73a91489635fcebbdd63</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2003</creationdate><topic>Data processing</topic><topic>Design</topic><topic>Efficiency</topic><topic>Energy consumption</topic><topic>Energy dissipation</topic><topic>Microelectronics</topic><topic>Multimedia communications</topic><topic>Pipelines</topic><topic>Real time</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Kim, Suhwan</creatorcontrib><creatorcontrib>Ziesler, Conrad H</creatorcontrib><creatorcontrib>Papaefthymiou, Marios C</creatorcontrib><collection>CrossRef</collection><collection>Global News & ABI/Inform Professional</collection><collection>Trade PRO</collection><collection>ProQuest Central (Corporate)</collection><collection>ABI/INFORM Collection</collection><collection>ABI/INFORM Global (PDF only)</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>ABI/INFORM Global (Alumni Edition)</collection><collection>Science Database (Alumni Edition)</collection><collection>Computing Database (Alumni Edition)</collection><collection>ProQuest Pharma Collection</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ABI/INFORM Collection (Alumni Edition)</collection><collection>Research Library (Alumni Edition)</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>Advanced Technologies & Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>eLibrary</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>Business Premium Collection</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Business Premium Collection (Alumni)</collection><collection>ABI/INFORM Global (Corporate)</collection><collection>ProQuest Central Student</collection><collection>Research Library Prep</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Computer Science Collection</collection><collection>ProQuest Business Collection (Alumni Edition)</collection><collection>ProQuest Business Collection</collection><collection>Computer Science Database</collection><collection>ABI/INFORM Professional Advanced</collection><collection>ABI/INFORM Professional Standard</collection><collection>ABI/INFORM Collection</collection><collection>Computing Database</collection><collection>ProQuest research library</collection><collection>Science Database</collection><collection>Research Library (Corporate)</collection><collection>Advanced Technologies & Aerospace Database</collection><collection>ProQuest Advanced Technologies & Aerospace Collection</collection><collection>One Business (ProQuest)</collection><collection>ProQuest One Business (Alumni)</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>ProQuest Central Basic</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IBM journal of research and development</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Kim, Suhwan</au><au>Ziesler, Conrad H</au><au>Papaefthymiou, Marios C</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Fine-grain real-time reconfigurable pipelining</atitle><jtitle>IBM journal of research and development</jtitle><date>2003-09-01</date><risdate>2003</risdate><volume>47</volume><issue>5-6</issue><spage>599</spage><epage>609</epage><pages>599-609</pages><issn>0018-8646</issn><eissn>0018-8646</eissn><eissn>2151-8556</eissn><coden>IBMJAE</coden><abstract>In many computations, average data rates are often significantly lower than the peak rate possible. Consequently, VLSI systems capable of processing data at a maximum specified rate can be excessively dissipative when data rates are low. Such inefficiencies are particularly pronounced in heavily pipelined designs, in which registers account for the bulk of energy dissipation in a system. This paper describes a novel methodology for designing reconfigurable pipelines that achieve very low power dissipation by adapting their resources to their computational requirements. In our fine-grain reconfigurable pipelines, energy is saved by disabling and bypassing an appropriate number of pipeline stages whenever data rates are low. In contrast, coarse-grain approaches, such as dynamic voltage scaling, are often unable to capture savings from short-time-scale variations in throughput requirements because of the long time needed to reconfigure the voltage. To evaluate our methodology, we designed an inverse discrete cosine transform (IDCT) module for MPEG-2. Our IDCT included pipelined multipliers that were dynamically reconfigurable on the basis of the number of nonzero coefficients per block and picture size. In comparison with conventional multipliers in corresponding IDCT implementations, our reconfigurable multipliers dissipated about 12-65% less power. [PUBLICATION ABSTRACT]</abstract><cop>Armonk</cop><pub>International Business Machines Corporation</pub><doi>10.1147/rd.475.0599</doi><tpages>11</tpages></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0018-8646 |
ispartof | IBM journal of research and development, 2003-09, Vol.47 (5-6), p.599-609 |
issn | 0018-8646 0018-8646 2151-8556 |
language | eng |
recordid | cdi_proquest_miscellaneous_743201195 |
source | IEEE Xplore All Journals; ABI/INFORM Collection |
subjects | Data processing Design Efficiency Energy consumption Energy dissipation Microelectronics Multimedia communications Pipelines Real time |
title | Fine-grain real-time reconfigurable pipelining |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-27T04%3A35%3A04IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Fine-grain%20real-time%20reconfigurable%20pipelining&rft.jtitle=IBM%20journal%20of%20research%20and%20development&rft.au=Kim,%20Suhwan&rft.date=2003-09-01&rft.volume=47&rft.issue=5-6&rft.spage=599&rft.epage=609&rft.pages=599-609&rft.issn=0018-8646&rft.eissn=0018-8646&rft.coden=IBMJAE&rft_id=info:doi/10.1147/rd.475.0599&rft_dat=%3Cproquest_cross%3E502257651%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c279t-2fa9a45ccaa08d1fc1ac55bb088d5ca1d8bc683745d6c73a91489635fcebbdd63%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=220656152&rft_id=info:pmid/&rfr_iscdi=true |