Technology comparison for large last-level caches (L3Cs): Low-leakage SRAM, low write-energy STT-RAM, and refresh-optimized eDRAM

Large last-level caches (L 3 Cs) are frequently used to bridge the performance and power gap between processor and memory. Although traditional processors implement caches as SRAMs, technologies such as STT-RAM (MRAM), and eDRAM have been used and/or considered for the implementation of L 3 Cs. Each...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mu-Tien Chang, Rosenfeld, P., Shih-Lien Lu, Jacob, B.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 154
container_issue
container_start_page 143
container_title
container_volume
creator Mu-Tien Chang
Rosenfeld, P.
Shih-Lien Lu
Jacob, B.
description Large last-level caches (L 3 Cs) are frequently used to bridge the performance and power gap between processor and memory. Although traditional processors implement caches as SRAMs, technologies such as STT-RAM (MRAM), and eDRAM have been used and/or considered for the implementation of L 3 Cs. Each of these technologies has inherent weaknesses: SRAM is relatively low density and has high leakage current; STT-RAM has high write latency and write energy consumption; and eDRAM requires refresh operations. As future processors are expected to have larger last-level caches, the goal of this paper is to study the trade-offs associated with using each of these technologies to implement L 3 Cs. In order to make useful comparisons between SRAM, STTRAM, and eDRAM L 3 Cs, we model them in detail and apply low power techniques to each of these technologies to address their respective weaknesses. We optimize SRAM for low leakage and optimize STT-RAM for low write energy. Moreover, we classify eDRAM refresh-reduction schemes into two categories and demonstrate the effectiveness of using dead-line prediction to eliminate unnecessary refreshes. A comparison of these technologies through full-system simulation shows that the proposed refresh-reduction method makes eDRAM a viable, energy-efficient technology for implementing L 3 Cs.
doi_str_mv 10.1109/HPCA.2013.6522314
format Conference Proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6522314</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6522314</ieee_id><sourcerecordid>6522314</sourcerecordid><originalsourceid>FETCH-LOGICAL-c204t-b61763f6ed9fecb7d8953d398ff2e5f472f2c25eb3871a12d69a8ebdf56fb9233</originalsourceid><addsrcrecordid>eNo1kDtPwzAYRc1Loi39AYjFI0i4-FHHMVsVHkUKAtEgsVVO8rkNpHFlR1Rl458TQVnuHc7VGS5Cp4yOGKP6avqcTEacMjGKJOeCjffQUKuYjSMlpIwV30c9LlRMOBVvB6j_DyQ_RD0mBSU01uoY9UN4p5RyLVkPfWdQLBtXu8UWF261Nr4KrsHWeVwbv4AuQ0tq-IQaF6ZYQsDnqUjCxTVO3aYD5sN0q9nL5PES126DN75qgUADvjPOsoz8EtOU2IP1EJbErdtqVX1BieGmgyfoyJo6wHDXA_R6d5slU5I-3T8kk5QUnI5bkkdMRcJGUGoLRa7KWEtRCh1by0HaseKWF1xCLmLFDONlpE0MeWllZHPNhRigsz9vBQDzta9Wxm_nuyvFD9lcY4I</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Technology comparison for large last-level caches (L3Cs): Low-leakage SRAM, low write-energy STT-RAM, and refresh-optimized eDRAM</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Mu-Tien Chang ; Rosenfeld, P. ; Shih-Lien Lu ; Jacob, B.</creator><creatorcontrib>Mu-Tien Chang ; Rosenfeld, P. ; Shih-Lien Lu ; Jacob, B.</creatorcontrib><description>Large last-level caches (L 3 Cs) are frequently used to bridge the performance and power gap between processor and memory. Although traditional processors implement caches as SRAMs, technologies such as STT-RAM (MRAM), and eDRAM have been used and/or considered for the implementation of L 3 Cs. Each of these technologies has inherent weaknesses: SRAM is relatively low density and has high leakage current; STT-RAM has high write latency and write energy consumption; and eDRAM requires refresh operations. As future processors are expected to have larger last-level caches, the goal of this paper is to study the trade-offs associated with using each of these technologies to implement L 3 Cs. In order to make useful comparisons between SRAM, STTRAM, and eDRAM L 3 Cs, we model them in detail and apply low power techniques to each of these technologies to address their respective weaknesses. We optimize SRAM for low leakage and optimize STT-RAM for low write energy. Moreover, we classify eDRAM refresh-reduction schemes into two categories and demonstrate the effectiveness of using dead-line prediction to eliminate unnecessary refreshes. A comparison of these technologies through full-system simulation shows that the proposed refresh-reduction method makes eDRAM a viable, energy-efficient technology for implementing L 3 Cs.</description><identifier>ISSN: 1530-0897</identifier><identifier>ISBN: 1467355852</identifier><identifier>ISBN: 9781467355858</identifier><identifier>EISSN: 2378-203X</identifier><identifier>EISBN: 9781467355872</identifier><identifier>EISBN: 1467355860</identifier><identifier>EISBN: 1467355879</identifier><identifier>EISBN: 9781467355865</identifier><identifier>DOI: 10.1109/HPCA.2013.6522314</identifier><language>eng</language><publisher>IEEE</publisher><subject>Capacitors ; CMOS integrated circuits ; CMOS technology ; Magnetic tunneling ; Radiation detectors ; Random access memory ; Transistors</subject><ispartof>2013 IEEE 19th International Symposium on High Performance Computer Architecture (HPCA), 2013, p.143-154</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c204t-b61763f6ed9fecb7d8953d398ff2e5f472f2c25eb3871a12d69a8ebdf56fb9233</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6522314$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6522314$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Mu-Tien Chang</creatorcontrib><creatorcontrib>Rosenfeld, P.</creatorcontrib><creatorcontrib>Shih-Lien Lu</creatorcontrib><creatorcontrib>Jacob, B.</creatorcontrib><title>Technology comparison for large last-level caches (L3Cs): Low-leakage SRAM, low write-energy STT-RAM, and refresh-optimized eDRAM</title><title>2013 IEEE 19th International Symposium on High Performance Computer Architecture (HPCA)</title><addtitle>HPCA</addtitle><description>Large last-level caches (L 3 Cs) are frequently used to bridge the performance and power gap between processor and memory. Although traditional processors implement caches as SRAMs, technologies such as STT-RAM (MRAM), and eDRAM have been used and/or considered for the implementation of L 3 Cs. Each of these technologies has inherent weaknesses: SRAM is relatively low density and has high leakage current; STT-RAM has high write latency and write energy consumption; and eDRAM requires refresh operations. As future processors are expected to have larger last-level caches, the goal of this paper is to study the trade-offs associated with using each of these technologies to implement L 3 Cs. In order to make useful comparisons between SRAM, STTRAM, and eDRAM L 3 Cs, we model them in detail and apply low power techniques to each of these technologies to address their respective weaknesses. We optimize SRAM for low leakage and optimize STT-RAM for low write energy. Moreover, we classify eDRAM refresh-reduction schemes into two categories and demonstrate the effectiveness of using dead-line prediction to eliminate unnecessary refreshes. A comparison of these technologies through full-system simulation shows that the proposed refresh-reduction method makes eDRAM a viable, energy-efficient technology for implementing L 3 Cs.</description><subject>Capacitors</subject><subject>CMOS integrated circuits</subject><subject>CMOS technology</subject><subject>Magnetic tunneling</subject><subject>Radiation detectors</subject><subject>Random access memory</subject><subject>Transistors</subject><issn>1530-0897</issn><issn>2378-203X</issn><isbn>1467355852</isbn><isbn>9781467355858</isbn><isbn>9781467355872</isbn><isbn>1467355860</isbn><isbn>1467355879</isbn><isbn>9781467355865</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2013</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNo1kDtPwzAYRc1Loi39AYjFI0i4-FHHMVsVHkUKAtEgsVVO8rkNpHFlR1Rl458TQVnuHc7VGS5Cp4yOGKP6avqcTEacMjGKJOeCjffQUKuYjSMlpIwV30c9LlRMOBVvB6j_DyQ_RD0mBSU01uoY9UN4p5RyLVkPfWdQLBtXu8UWF261Nr4KrsHWeVwbv4AuQ0tq-IQaF6ZYQsDnqUjCxTVO3aYD5sN0q9nL5PES126DN75qgUADvjPOsoz8EtOU2IP1EJbErdtqVX1BieGmgyfoyJo6wHDXA_R6d5slU5I-3T8kk5QUnI5bkkdMRcJGUGoLRa7KWEtRCh1by0HaseKWF1xCLmLFDONlpE0MeWllZHPNhRigsz9vBQDzta9Wxm_nuyvFD9lcY4I</recordid><startdate>201302</startdate><enddate>201302</enddate><creator>Mu-Tien Chang</creator><creator>Rosenfeld, P.</creator><creator>Shih-Lien Lu</creator><creator>Jacob, B.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201302</creationdate><title>Technology comparison for large last-level caches (L3Cs): Low-leakage SRAM, low write-energy STT-RAM, and refresh-optimized eDRAM</title><author>Mu-Tien Chang ; Rosenfeld, P. ; Shih-Lien Lu ; Jacob, B.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c204t-b61763f6ed9fecb7d8953d398ff2e5f472f2c25eb3871a12d69a8ebdf56fb9233</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2013</creationdate><topic>Capacitors</topic><topic>CMOS integrated circuits</topic><topic>CMOS technology</topic><topic>Magnetic tunneling</topic><topic>Radiation detectors</topic><topic>Random access memory</topic><topic>Transistors</topic><toplevel>online_resources</toplevel><creatorcontrib>Mu-Tien Chang</creatorcontrib><creatorcontrib>Rosenfeld, P.</creatorcontrib><creatorcontrib>Shih-Lien Lu</creatorcontrib><creatorcontrib>Jacob, B.</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 Electronic Library (IEL)</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>Mu-Tien Chang</au><au>Rosenfeld, P.</au><au>Shih-Lien Lu</au><au>Jacob, B.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Technology comparison for large last-level caches (L3Cs): Low-leakage SRAM, low write-energy STT-RAM, and refresh-optimized eDRAM</atitle><btitle>2013 IEEE 19th International Symposium on High Performance Computer Architecture (HPCA)</btitle><stitle>HPCA</stitle><date>2013-02</date><risdate>2013</risdate><spage>143</spage><epage>154</epage><pages>143-154</pages><issn>1530-0897</issn><eissn>2378-203X</eissn><isbn>1467355852</isbn><isbn>9781467355858</isbn><eisbn>9781467355872</eisbn><eisbn>1467355860</eisbn><eisbn>1467355879</eisbn><eisbn>9781467355865</eisbn><abstract>Large last-level caches (L 3 Cs) are frequently used to bridge the performance and power gap between processor and memory. Although traditional processors implement caches as SRAMs, technologies such as STT-RAM (MRAM), and eDRAM have been used and/or considered for the implementation of L 3 Cs. Each of these technologies has inherent weaknesses: SRAM is relatively low density and has high leakage current; STT-RAM has high write latency and write energy consumption; and eDRAM requires refresh operations. As future processors are expected to have larger last-level caches, the goal of this paper is to study the trade-offs associated with using each of these technologies to implement L 3 Cs. In order to make useful comparisons between SRAM, STTRAM, and eDRAM L 3 Cs, we model them in detail and apply low power techniques to each of these technologies to address their respective weaknesses. We optimize SRAM for low leakage and optimize STT-RAM for low write energy. Moreover, we classify eDRAM refresh-reduction schemes into two categories and demonstrate the effectiveness of using dead-line prediction to eliminate unnecessary refreshes. A comparison of these technologies through full-system simulation shows that the proposed refresh-reduction method makes eDRAM a viable, energy-efficient technology for implementing L 3 Cs.</abstract><pub>IEEE</pub><doi>10.1109/HPCA.2013.6522314</doi><tpages>12</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1530-0897
ispartof 2013 IEEE 19th International Symposium on High Performance Computer Architecture (HPCA), 2013, p.143-154
issn 1530-0897
2378-203X
language eng
recordid cdi_ieee_primary_6522314
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Capacitors
CMOS integrated circuits
CMOS technology
Magnetic tunneling
Radiation detectors
Random access memory
Transistors
title Technology comparison for large last-level caches (L3Cs): Low-leakage SRAM, low write-energy STT-RAM, and refresh-optimized eDRAM
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-30T21%3A39%3A24IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Technology%20comparison%20for%20large%20last-level%20caches%20(L3Cs):%20Low-leakage%20SRAM,%20low%20write-energy%20STT-RAM,%20and%20refresh-optimized%20eDRAM&rft.btitle=2013%20IEEE%2019th%20International%20Symposium%20on%20High%20Performance%20Computer%20Architecture%20(HPCA)&rft.au=Mu-Tien%20Chang&rft.date=2013-02&rft.spage=143&rft.epage=154&rft.pages=143-154&rft.issn=1530-0897&rft.eissn=2378-203X&rft.isbn=1467355852&rft.isbn_list=9781467355858&rft_id=info:doi/10.1109/HPCA.2013.6522314&rft_dat=%3Cieee_6IE%3E6522314%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781467355872&rft.eisbn_list=1467355860&rft.eisbn_list=1467355879&rft.eisbn_list=9781467355865&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6522314&rfr_iscdi=true