{"id":"https://openalex.org/W2293405513","doi":"https://doi.org/10.1109/aspdac.2016.7427984","title":"Performance-centric register file design for GPUs using racetrack memory","display_name":"Performance-centric register file design for GPUs using racetrack memory","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2293405513","doi":"https://doi.org/10.1109/aspdac.2016.7427984","mag":"2293405513"},"language":"en","primary_location":{"id":"doi:10.1109/aspdac.2016.7427984","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspdac.2016.7427984","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 21st Asia and South Pacific Design Automation Conference (ASP-DAC)","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/A5100400173","display_name":"Shuo Wang","orcid":"https://orcid.org/0000-0002-7907-9676"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Wang","raw_affiliation_strings":["Center for Energy-Efficient Computing and Applications (CECA) EECS School, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Energy-Efficient Computing and Applications (CECA) EECS School, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100604860","display_name":"Yun Liang","orcid":"https://orcid.org/0000-0002-9076-7998"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Liang","raw_affiliation_strings":["Center for Energy-Efficient Computing and Applications (CECA) EECS School, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Energy-Efficient Computing and Applications (CECA) EECS School, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100739850","display_name":"Chao Zhang","orcid":"https://orcid.org/0000-0001-8260-1210"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Center for Energy-Efficient Computing and Applications (CECA) EECS School, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Energy-Efficient Computing and Applications (CECA) EECS School, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101761686","display_name":"Xiaolong Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolong Xie","raw_affiliation_strings":["Center for Energy-Efficient Computing and Applications (CECA) EECS School, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Energy-Efficient Computing and Applications (CECA) EECS School, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101850376","display_name":"Guangyu Sun","orcid":"https://orcid.org/0000-0001-6436-0820"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyu Sun","raw_affiliation_strings":["Center for Energy-Efficient Computing and Applications (CECA) EECS School, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Energy-Efficient Computing and Applications (CECA) EECS School, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045721867","display_name":"Yongpan Liu","orcid":"https://orcid.org/0000-0002-4892-2309"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongpan Liu","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100445148","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0002-0597-3544"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114246744","display_name":"Xiuhong Li","orcid":"https://orcid.org/0000-0002-4896-121X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiuhong Li","raw_affiliation_strings":["Center for Energy-Efficient Computing and Applications (CECA) EECS School, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Energy-Efficient Computing and Applications (CECA) EECS School, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"320","issue":null,"first_page":"25","last_page":"30"},"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":0.9995999932289124,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/register-file","display_name":"Register file","score":0.8988707065582275},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8570924997329712},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.67777419090271},{"id":"https://openalex.org/keywords/racetrack-memory","display_name":"Racetrack memory","score":0.6594850420951843},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.49036431312561035},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4822867214679718},{"id":"https://openalex.org/keywords/processor-register","display_name":"Processor register","score":0.4682878851890564},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.39103731513023376},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.35490936040878296},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.34064024686813354},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.33231231570243835},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.2820366621017456},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.18233168125152588},{"id":"https://openalex.org/keywords/interleaved-memory","display_name":"Interleaved memory","score":0.169306218624115},{"id":"https://openalex.org/keywords/memory-address","display_name":"Memory address","score":0.16109588742256165}],"concepts":[{"id":"https://openalex.org/C117280010","wikidata":"https://www.wikidata.org/wiki/Q180944","display_name":"Register file","level":3,"score":0.8988707065582275},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8570924997329712},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.67777419090271},{"id":"https://openalex.org/C43363307","wikidata":"https://www.wikidata.org/wiki/Q1651623","display_name":"Racetrack memory","level":5,"score":0.6594850420951843},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.49036431312561035},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4822867214679718},{"id":"https://openalex.org/C2871975","wikidata":"https://www.wikidata.org/wiki/Q187466","display_name":"Processor register","level":4,"score":0.4682878851890564},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.39103731513023376},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.35490936040878296},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.34064024686813354},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.33231231570243835},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.2820366621017456},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.18233168125152588},{"id":"https://openalex.org/C63511323","wikidata":"https://www.wikidata.org/wiki/Q908936","display_name":"Interleaved memory","level":4,"score":0.169306218624115},{"id":"https://openalex.org/C153247305","wikidata":"https://www.wikidata.org/wiki/Q835713","display_name":"Memory address","level":3,"score":0.16109588742256165}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aspdac.2016.7427984","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspdac.2016.7427984","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 21st Asia and South Pacific Design Automation Conference (ASP-DAC)","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":0.6600000262260437}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1972077953","https://openalex.org/W1981443800","https://openalex.org/W1982996921","https://openalex.org/W2005242923","https://openalex.org/W2017198297","https://openalex.org/W2017836239","https://openalex.org/W2034639175","https://openalex.org/W2047379549","https://openalex.org/W2078760460","https://openalex.org/W2084110734","https://openalex.org/W2084309410","https://openalex.org/W2088440019","https://openalex.org/W2108048675","https://openalex.org/W2111096793","https://openalex.org/W2136800915","https://openalex.org/W2152517358","https://openalex.org/W2153826642","https://openalex.org/W2232645663","https://openalex.org/W3144303468","https://openalex.org/W4236340184","https://openalex.org/W4237024478","https://openalex.org/W4254988766","https://openalex.org/W6655050512","https://openalex.org/W6676647767"],"related_works":["https://openalex.org/W2224192221","https://openalex.org/W1482836228","https://openalex.org/W2356166161","https://openalex.org/W3144620029","https://openalex.org/W2130533867","https://openalex.org/W1969937427","https://openalex.org/W2540018280","https://openalex.org/W2014882201","https://openalex.org/W4281749670","https://openalex.org/W2295701766"],"abstract_inverted_index":{"The":[0,48],"key":[1],"to":[2,12,64,90,135,159,166,170,202],"high":[3,92,122],"performance":[4,123,209],"for":[5,72,81,120,126,210],"GPU":[6,73,127,214],"architecture":[7],"lies":[8],"in":[9,26,208],"massive":[10,70],"threading":[11,23,71],"drive":[13],"the":[14,28,40,43,66,102,111,137,142,151,154,160,168,171,175],"large":[15,55,83],"number":[16,29,143],"of":[17,22,30,42,57,69,100,106,144,153,213],"cores":[18],"and":[19,187],"enable":[20],"overlapping":[21],"execution.":[24],"However,":[25,96,149],"reality,":[27],"threads":[31,145],"that":[32,60,146,197],"can":[33],"simultaneously":[34,147],"execute":[35],"is":[36,77],"often":[37],"limited":[38],"by":[39],"size":[41],"register":[44,51,85,124,183,191],"file":[45,52,86,125,184],"on":[46,87,205],"GPUs.":[47],"traditional":[49],"SRAM-based":[50],"costs":[53],"so":[54],"amount":[56],"chip":[58],"area":[59],"it":[61],"cannot":[62],"scale":[63],"meet":[65],"increasing":[67],"demand":[68],"applications.":[74,215],"Racetrack":[75],"memory":[76,108,119,133],"a":[78,182,188,211],"promising":[79],"technology":[80],"designing":[82,121],"capacity":[84],"GPUs":[88],"due":[89],"its":[91],"data":[93],"storage":[94,130],"density.":[95],"without":[97],"careful":[98],"deployment":[99],"registers,":[101],"lengthy":[103],"shift":[104,162,176],"operation":[105,177],"racetrack":[107,118,132],"may":[109],"hurt":[110],"performance.":[112],"In":[113],"this":[114],"paper,":[115],"we":[116,180],"explore":[117],"architecture.":[128],"High":[129],"density":[131],"helps":[134],"improve":[136],"thread":[138],"level":[139],"parallelism,":[140],"i.e.,":[141],"execute.":[148],"if":[150],"bits":[152,169],"registers":[155],"are":[156,164],"not":[157],"aligned":[158],"ports,":[161],"operations":[163],"required":[165],"move":[167],"ports.":[172],"To":[173],"mitigate":[174],"overhead":[178],"problem,":[179],"develop":[181],"preshifting":[185],"strategy":[186],"compile-time":[189],"managed":[190],"mapping":[192],"algorithm.":[193],"Experimental":[194],"results":[195],"demonstrate":[196],"our":[198],"technique":[199],"achieves":[200],"up":[201],"24%":[203],"(19%":[204],"average)":[206],"improvement":[207],"variety":[212]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}