{"id":"https://openalex.org/W4240280370","doi":"https://doi.org/10.1109/iccad.2017.8203850","title":"Towards warp-scheduler friendly STT-RAM/SRAM hybrid GPGPU register file design","display_name":"Towards warp-scheduler friendly STT-RAM/SRAM hybrid GPGPU register file design","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W4240280370","doi":"https://doi.org/10.1109/iccad.2017.8203850"},"language":"en","primary_location":{"id":"doi:10.1109/iccad.2017.8203850","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad.2017.8203850","pdf_url":null,"source":{"id":"https://openalex.org/S4363608376","display_name":"2017 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012771136","display_name":"Quan Deng","orcid":"https://orcid.org/0000-0002-1454-8486"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Deng","raw_affiliation_strings":["College of Computer, National University of Defense Technolog, Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technolog, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026996875","display_name":"Youtao Zhang","orcid":"https://orcid.org/0000-0001-8425-8743"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Youtao Zhang","raw_affiliation_strings":["Department of Computer Science, University of Pittsburgh, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Pittsburgh, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110908049","display_name":"Minxuan Zhang","orcid":"https://orcid.org/0009-0001-1340-6638"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minxuan Zhang","raw_affiliation_strings":["College of Computer, National University of Defense Technolog, Changsha, Hunan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technolog, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101605460","display_name":"Jun Yang","orcid":"https://orcid.org/0000-0001-8372-6541"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Yang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Pittsburgh, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Pittsburgh, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"736","last_page":"742"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10049","display_name":"Magnetic properties of thin films","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/static-random-access-memory","display_name":"Static random-access memory","score":0.8403593301773071},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6756304502487183},{"id":"https://openalex.org/keywords/register-file","display_name":"Register file","score":0.6392321586608887},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.46225661039352417},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4103521704673767},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.31425195932388306},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3014303147792816},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.2037239670753479}],"concepts":[{"id":"https://openalex.org/C68043766","wikidata":"https://www.wikidata.org/wiki/Q267416","display_name":"Static random-access memory","level":2,"score":0.8403593301773071},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6756304502487183},{"id":"https://openalex.org/C117280010","wikidata":"https://www.wikidata.org/wiki/Q180944","display_name":"Register file","level":3,"score":0.6392321586608887},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.46225661039352417},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4103521704673767},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.31425195932388306},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3014303147792816},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.2037239670753479},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccad.2017.8203850","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad.2017.8203850","pdf_url":null,"source":{"id":"https://openalex.org/S4363608376","display_name":"2017 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8999999761581421}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1678569174","https://openalex.org/W1979527452","https://openalex.org/W2000553861","https://openalex.org/W2047060659","https://openalex.org/W2064977311","https://openalex.org/W2072656003","https://openalex.org/W2093043622","https://openalex.org/W2303605678","https://openalex.org/W2321829186","https://openalex.org/W2323693848","https://openalex.org/W2328929289","https://openalex.org/W2333417550","https://openalex.org/W2403204284","https://openalex.org/W2511591270","https://openalex.org/W2532453544","https://openalex.org/W2584872994","https://openalex.org/W2584875058","https://openalex.org/W3101392438","https://openalex.org/W4236340184","https://openalex.org/W4240163901","https://openalex.org/W6637235533","https://openalex.org/W6652940909","https://openalex.org/W6676647767"],"related_works":["https://openalex.org/W2042399072","https://openalex.org/W3144620029","https://openalex.org/W2356166161","https://openalex.org/W4392590355","https://openalex.org/W2130533867","https://openalex.org/W2540018280","https://openalex.org/W2139082473","https://openalex.org/W2045163867","https://openalex.org/W2059502833","https://openalex.org/W2155131180"],"abstract_inverted_index":{"Modern":[0],"Graphics":[1],"Processing":[2],"Units":[3],"(GPUs)":[4],"widely":[5],"adopt":[6],"large":[7,18,51],"SRAM":[8,19,62,129],"based":[9],"register":[10],"file":[11],"(RF)":[12],"to":[13,24,114,130],"enable":[14],"fast":[15],"context-switch.":[16],"A":[17],"RF":[20,46,58,100,134],"may":[21],"consume":[22],"20%":[23],"40%":[25],"GPU":[26],"power,":[27],"which":[28,78],"has":[29],"become":[30],"one":[31],"of":[32],"the":[33,42,65,71,116,165],"major":[34],"design":[35,101,168],"challenges":[36],"for":[37],"GPUs.":[38],"Recent":[39],"studies":[40],"mitigate":[41],"issue":[43],"through":[44],"hybrid":[45,99,105,167],"designs":[47],"that":[48],"architect":[49],"a":[50,60,96],"STT-RAM":[52,67,75,120,131],"(Spin":[53],"Transfer":[54],"Torque":[55],"Magnetic":[56],"memory)":[57],"and":[59,76,121,140,159],"small":[61],"buffer.":[63],"However,":[64],"long":[66],"write":[68],"latency":[69],"throttles":[70],"data":[72,126],"exchange":[73],"between":[74,119],"SRAM,":[77],"deprecates":[79],"warp":[80,145,174],"scheduler":[81],"with":[82],"frequent":[83],"context":[84],"switches,":[85],"e.g.,":[86],"round":[87],"robin":[88],"scheduler.":[89,146,175],"In":[90],"this":[91],"paper,":[92],"we":[93],"propose":[94],"HC-RF,":[95],"warp-scheduler":[97],"friendly":[98],"using":[102],"novel":[103],"SRAM/STT-RAM":[104],"cell":[106,111],"(HC)":[107],"structure.":[108],"HC-RF":[109,136,154],"exploits":[110],"level":[112],"integration":[113],"improve":[115],"effective":[117],"bandwidth":[118],"SRAM.":[122],"By":[123],"enabling":[124],"silent":[125],"transfer":[127],"from":[128],"without":[132],"blocking":[133],"banks,":[135],"supports":[137],"concurrent":[138],"context-switching":[139],"decouples":[141],"its":[142],"dependency":[143],"on":[144,152],"Our":[147],"experimental":[148],"results":[149],"show":[150],"that,":[151],"average,":[153],"achieves":[155],"50%":[156],"performance":[157],"improvement":[158],"44%":[160],"energy":[161],"consumption":[162],"reduction":[163],"over":[164],"coarse-grained":[166],"when":[169],"adopting":[170],"LRR(Loose":[171],"Round":[172],"Robin)":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}