A smart hybrid memory scheduling approach using neural models
Conclusion SmartS is a novel solution for hybrid memory scheduling using neural models. It proposes a novel collective-page prediction approach, effectively reducing training and inference costs. It also proposes a clustering-based approach to address the class explosion problem. Experiments show th...
Gespeichert in:
| Veröffentlicht in: | Science China. Information sciences 2024-04, Vol.67 (4), p.149102, Article 149102 |
|---|---|
| Hauptverfasser: | , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | 4 |
| container_start_page | 149102 |
| container_title | Science China. Information sciences |
| container_volume | 67 |
| creator | Zhen, Yanjie Zhang, Huijun Deng, Yongheng Chen, Weining Gao, Wei Ren, Ju Chen, Yu |
| description | Conclusion
SmartS is a novel solution for hybrid memory scheduling using neural models. It proposes a novel collective-page prediction approach, effectively reducing training and inference costs. It also proposes a clustering-based approach to address the class explosion problem. Experiments show that SmartS improves hybrid memory effectiveness significantly. It also reduces the cost of neural models to allow their practical deployment in real-world hybrid, representing a substantial step towards practical neural-model-based scheduling. |
| doi_str_mv | 10.1007/s11432-023-3925-2 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_3031715428</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3031715428</sourcerecordid><originalsourceid>FETCH-LOGICAL-c296t-21a558691ecfdb64d0f9176a4bf89c86149694e2e39644f49b8f7cb1b47eb2943</originalsourceid><addsrcrecordid>eNqFkE1LAzEQhoMoWGp_gLeA52gmyebj4KEUtULBi4K3sNlN-sF-1KR76L83ywqexLnMDLzvO8OD0C3Qe6BUPSQAwRmhjBNuWEHYBZqBloaAAXOZZ6kEUZx_XqNFSgeai3PKlJ6hxyVObRlPeHd2cV_j1rd9PONU7Xw9NPtui8vjMfZltcNDGtfOD7FscNvXvkk36CqUTfKLnz5HH89P76s12by9vK6WG1IxI0-EQVkU-R_wVaidFDUNBpQshQvaVFqCMNIIzzw3UoggjNNBVQ6cUN4xI_gc3U25-ZWvwaeTPfRD7PJJyykHBYVg-j-V0FqpMQsmVRX7lKIP9hj3GcHZArUjTjvhtBmnHXFalj1s8qSs7bY-_ib_bfoGHAt1nQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3031488774</pqid></control><display><type>article</type><title>A smart hybrid memory scheduling approach using neural models</title><source>Springer Nature - Complete Springer Journals</source><source>Alma/SFX Local Collection</source><creator>Zhen, Yanjie ; Zhang, Huijun ; Deng, Yongheng ; Chen, Weining ; Gao, Wei ; Ren, Ju ; Chen, Yu</creator><creatorcontrib>Zhen, Yanjie ; Zhang, Huijun ; Deng, Yongheng ; Chen, Weining ; Gao, Wei ; Ren, Ju ; Chen, Yu</creatorcontrib><description>Conclusion
SmartS is a novel solution for hybrid memory scheduling using neural models. It proposes a novel collective-page prediction approach, effectively reducing training and inference costs. It also proposes a clustering-based approach to address the class explosion problem. Experiments show that SmartS improves hybrid memory effectiveness significantly. It also reduces the cost of neural models to allow their practical deployment in real-world hybrid, representing a substantial step towards practical neural-model-based scheduling.</description><identifier>ISSN: 1674-733X</identifier><identifier>EISSN: 1869-1919</identifier><identifier>DOI: 10.1007/s11432-023-3925-2</identifier><language>eng</language><publisher>Beijing: Science China Press</publisher><subject>Clustering ; Computer Science ; Information Systems and Communication Service ; Letter ; Scheduling</subject><ispartof>Science China. Information sciences, 2024-04, Vol.67 (4), p.149102, Article 149102</ispartof><rights>Science China Press 2024</rights><rights>Science China Press 2024.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c296t-21a558691ecfdb64d0f9176a4bf89c86149694e2e39644f49b8f7cb1b47eb2943</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s11432-023-3925-2$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s11432-023-3925-2$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,778,782,27911,27912,41475,42544,51306</link.rule.ids></links><search><creatorcontrib>Zhen, Yanjie</creatorcontrib><creatorcontrib>Zhang, Huijun</creatorcontrib><creatorcontrib>Deng, Yongheng</creatorcontrib><creatorcontrib>Chen, Weining</creatorcontrib><creatorcontrib>Gao, Wei</creatorcontrib><creatorcontrib>Ren, Ju</creatorcontrib><creatorcontrib>Chen, Yu</creatorcontrib><title>A smart hybrid memory scheduling approach using neural models</title><title>Science China. Information sciences</title><addtitle>Sci. China Inf. Sci</addtitle><description>Conclusion
SmartS is a novel solution for hybrid memory scheduling using neural models. It proposes a novel collective-page prediction approach, effectively reducing training and inference costs. It also proposes a clustering-based approach to address the class explosion problem. Experiments show that SmartS improves hybrid memory effectiveness significantly. It also reduces the cost of neural models to allow their practical deployment in real-world hybrid, representing a substantial step towards practical neural-model-based scheduling.</description><subject>Clustering</subject><subject>Computer Science</subject><subject>Information Systems and Communication Service</subject><subject>Letter</subject><subject>Scheduling</subject><issn>1674-733X</issn><issn>1869-1919</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><recordid>eNqFkE1LAzEQhoMoWGp_gLeA52gmyebj4KEUtULBi4K3sNlN-sF-1KR76L83ywqexLnMDLzvO8OD0C3Qe6BUPSQAwRmhjBNuWEHYBZqBloaAAXOZZ6kEUZx_XqNFSgeai3PKlJ6hxyVObRlPeHd2cV_j1rd9PONU7Xw9NPtui8vjMfZltcNDGtfOD7FscNvXvkk36CqUTfKLnz5HH89P76s12by9vK6WG1IxI0-EQVkU-R_wVaidFDUNBpQshQvaVFqCMNIIzzw3UoggjNNBVQ6cUN4xI_gc3U25-ZWvwaeTPfRD7PJJyykHBYVg-j-V0FqpMQsmVRX7lKIP9hj3GcHZArUjTjvhtBmnHXFalj1s8qSs7bY-_ib_bfoGHAt1nQ</recordid><startdate>20240401</startdate><enddate>20240401</enddate><creator>Zhen, Yanjie</creator><creator>Zhang, Huijun</creator><creator>Deng, Yongheng</creator><creator>Chen, Weining</creator><creator>Gao, Wei</creator><creator>Ren, Ju</creator><creator>Chen, Yu</creator><general>Science China Press</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope><scope>JQ2</scope></search><sort><creationdate>20240401</creationdate><title>A smart hybrid memory scheduling approach using neural models</title><author>Zhen, Yanjie ; Zhang, Huijun ; Deng, Yongheng ; Chen, Weining ; Gao, Wei ; Ren, Ju ; Chen, Yu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c296t-21a558691ecfdb64d0f9176a4bf89c86149694e2e39644f49b8f7cb1b47eb2943</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Clustering</topic><topic>Computer Science</topic><topic>Information Systems and Communication Service</topic><topic>Letter</topic><topic>Scheduling</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhen, Yanjie</creatorcontrib><creatorcontrib>Zhang, Huijun</creatorcontrib><creatorcontrib>Deng, Yongheng</creatorcontrib><creatorcontrib>Chen, Weining</creatorcontrib><creatorcontrib>Gao, Wei</creatorcontrib><creatorcontrib>Ren, Ju</creatorcontrib><creatorcontrib>Chen, Yu</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Computer Science Collection</collection><jtitle>Science China. Information sciences</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhen, Yanjie</au><au>Zhang, Huijun</au><au>Deng, Yongheng</au><au>Chen, Weining</au><au>Gao, Wei</au><au>Ren, Ju</au><au>Chen, Yu</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A smart hybrid memory scheduling approach using neural models</atitle><jtitle>Science China. Information sciences</jtitle><stitle>Sci. China Inf. Sci</stitle><date>2024-04-01</date><risdate>2024</risdate><volume>67</volume><issue>4</issue><spage>149102</spage><pages>149102-</pages><artnum>149102</artnum><issn>1674-733X</issn><eissn>1869-1919</eissn><abstract>Conclusion
SmartS is a novel solution for hybrid memory scheduling using neural models. It proposes a novel collective-page prediction approach, effectively reducing training and inference costs. It also proposes a clustering-based approach to address the class explosion problem. Experiments show that SmartS improves hybrid memory effectiveness significantly. It also reduces the cost of neural models to allow their practical deployment in real-world hybrid, representing a substantial step towards practical neural-model-based scheduling.</abstract><cop>Beijing</cop><pub>Science China Press</pub><doi>10.1007/s11432-023-3925-2</doi></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1674-733X |
| ispartof | Science China. Information sciences, 2024-04, Vol.67 (4), p.149102, Article 149102 |
| issn | 1674-733X 1869-1919 |
| language | eng |
| recordid | cdi_proquest_journals_3031715428 |
| source | Springer Nature - Complete Springer Journals; Alma/SFX Local Collection |
| subjects | Clustering Computer Science Information Systems and Communication Service Letter Scheduling |
| title | A smart hybrid memory scheduling approach using neural models |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-15T12%3A45%3A14IST&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=A%20smart%20hybrid%20memory%20scheduling%20approach%20using%20neural%20models&rft.jtitle=Science%20China.%20Information%20sciences&rft.au=Zhen,%20Yanjie&rft.date=2024-04-01&rft.volume=67&rft.issue=4&rft.spage=149102&rft.pages=149102-&rft.artnum=149102&rft.issn=1674-733X&rft.eissn=1869-1919&rft_id=info:doi/10.1007/s11432-023-3925-2&rft_dat=%3Cproquest_cross%3E3031715428%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3031488774&rft_id=info:pmid/&rfr_iscdi=true |