{"id":"https://openalex.org/W4360831990","doi":"https://doi.org/10.1109/hpca56546.2023.10070957","title":"Mitigating GPU Core Partitioning Performance Effects","display_name":"Mitigating GPU Core Partitioning Performance Effects","publication_year":2023,"publication_date":"2023-02-01","ids":{"openalex":"https://openalex.org/W4360831990","doi":"https://doi.org/10.1109/hpca56546.2023.10070957"},"language":"en","primary_location":{"id":"doi:10.1109/hpca56546.2023.10070957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca56546.2023.10070957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"},"type":"article","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":null,"display_name":"Aaron Barnes","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aaron Barnes","raw_affiliation_strings":["Purdue University,School of ECE,West Lafayette,IN","School of ECE, Purdue University, West Lafayette, IN"],"affiliations":[{"raw_affiliation_string":"Purdue University,School of ECE,West Lafayette,IN","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"School of ECE, Purdue University, West Lafayette, IN","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046147640","display_name":"Fangjia Shen","orcid":"https://orcid.org/0000-0002-0902-5939"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fangjia Shen","raw_affiliation_strings":["Purdue University,School of ECE,West Lafayette,IN","School of ECE, Purdue University, West Lafayette, IN"],"affiliations":[{"raw_affiliation_string":"Purdue University,School of ECE,West Lafayette,IN","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"School of ECE, Purdue University, West Lafayette, IN","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038577900","display_name":"Timothy G. Rogers","orcid":"https://orcid.org/0009-0002-0736-3149"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Timothy G. Rogers","raw_affiliation_strings":["Purdue University,School of ECE,West Lafayette,IN","School of ECE, Purdue University, West Lafayette, IN"],"affiliations":[{"raw_affiliation_string":"Purdue University,School of ECE,West Lafayette,IN","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"School of ECE, Purdue University, West Lafayette, IN","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":4.5025,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.95368678,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"530","last_page":"542"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9993000030517578,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8395041227340698},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6255232095718384},{"id":"https://openalex.org/keywords/register-file","display_name":"Register file","score":0.6252846121788025},{"id":"https://openalex.org/keywords/operand","display_name":"Operand","score":0.5680414438247681},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5300720930099487},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5193615555763245},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.50030517578125},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4390881657600403},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4367064833641052},{"id":"https://openalex.org/keywords/processor-register","display_name":"Processor register","score":0.4238182604312897},{"id":"https://openalex.org/keywords/memory-address","display_name":"Memory address","score":0.08577913045883179}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8395041227340698},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6255232095718384},{"id":"https://openalex.org/C117280010","wikidata":"https://www.wikidata.org/wiki/Q180944","display_name":"Register file","level":3,"score":0.6252846121788025},{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.5680414438247681},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5300720930099487},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5193615555763245},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.50030517578125},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4390881657600403},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4367064833641052},{"id":"https://openalex.org/C2871975","wikidata":"https://www.wikidata.org/wiki/Q187466","display_name":"Processor register","level":4,"score":0.4238182604312897},{"id":"https://openalex.org/C153247305","wikidata":"https://www.wikidata.org/wiki/Q835713","display_name":"Memory address","level":3,"score":0.08577913045883179},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpca56546.2023.10070957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca56546.2023.10070957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.9100000262260437,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1972971542","https://openalex.org/W1983235612","https://openalex.org/W1991518265","https://openalex.org/W2016559894","https://openalex.org/W2018767489","https://openalex.org/W2047060659","https://openalex.org/W2049875313","https://openalex.org/W2079038734","https://openalex.org/W2080592089","https://openalex.org/W2081583983","https://openalex.org/W2090278477","https://openalex.org/W2096661534","https://openalex.org/W2120000030","https://openalex.org/W2128120785","https://openalex.org/W2132258839","https://openalex.org/W2134101883","https://openalex.org/W2152956697","https://openalex.org/W2155503253","https://openalex.org/W2159458033","https://openalex.org/W2160428323","https://openalex.org/W2171399035","https://openalex.org/W2235785597","https://openalex.org/W2238992335","https://openalex.org/W2273440736","https://openalex.org/W2328929289","https://openalex.org/W2409690919","https://openalex.org/W2502410587","https://openalex.org/W2537959404","https://openalex.org/W2612048219","https://openalex.org/W2796649226","https://openalex.org/W2798724095","https://openalex.org/W2903861837","https://openalex.org/W3102510044","https://openalex.org/W4243035950","https://openalex.org/W4245987560","https://openalex.org/W4255847023","https://openalex.org/W4255962840","https://openalex.org/W6655903725","https://openalex.org/W6673062827","https://openalex.org/W6674732022","https://openalex.org/W6694513646","https://openalex.org/W6750448596"],"related_works":["https://openalex.org/W2088203538","https://openalex.org/W2245451942","https://openalex.org/W1580009706","https://openalex.org/W2111693251","https://openalex.org/W563794549","https://openalex.org/W4389476319","https://openalex.org/W3034184422","https://openalex.org/W2009783759","https://openalex.org/W2100504584","https://openalex.org/W2123413169"],"abstract_inverted_index":{"Modern":[0],"GPU":[1],"Streaming":[2],"Multiprocessors":[3],"(SMs)":[4],"have":[5,76,128],"several":[6],"warp":[7,31,143],"schedulers,":[8],"execution":[9,36],"units,":[10,37],"and":[11,18,35,41,59,88,103,121,168],"register":[12,33,161],"file":[13,162],"banks.":[14],"To":[15],"reduce":[16],"area":[17,58],"energy-consumption,":[19],"recent":[20],"generations":[21],"divide":[22],"SMs":[23,120],"into":[24,54],"sub-cores.":[25],"Each":[26],"sub-core":[27,171],"contains":[28],"a":[29,68,79,129,188],"distinct":[30],"scheduler,":[32],"file,":[34],"sharing":[38],"L1":[39],"memory":[40],"scratchpad":[42],"resources":[43],"with":[44],"sub-cores":[45,55],"in":[46,86,134,156,182],"the":[47,52,57,74,82,96,109,157,196],"same":[48],"SM.":[49],"Although":[50],"partitioning":[51],"SM":[53,75,98,200],"decreases":[56],"energy":[60],"demands":[61],"of":[62,81,125,160,191,195],"larger":[63],"SMs,":[64],"it":[65],"comes":[66],"at":[67],"performance":[69,102,133,197],"cost.":[70],"Warps":[71],"assigned":[72],"to":[73,78,107,145,165,173,199],"access":[77],"fraction":[80],"SM\u2019s":[83],"resources,":[84],"resulting":[85],"contention":[87],"imbalance":[89,175],"issues.":[90,176],"In":[91],"this":[92],"paper,":[93],"we":[94,140],"examine":[95],"effect":[97],"sub-division":[99],"has":[100],"on":[101,132,137],"propose":[104,141],"novel":[105],"mechanisms":[106,180],"mitigate":[108,174],"negative":[110],"impacts.":[111],"We":[112],"identify":[113],"four":[114],"orthogonal":[115],"effects":[116,127],"caused":[117],"by":[118],"sub-dividing":[119],"demonstrate":[122],"that":[123,149],"two":[124],"these":[126,138],"significant":[130],"impact":[131],"practice.":[135],"Based":[136],"findings,":[139],"register-bank-aware":[142],"scheduling":[144,179],"avoid":[146],"bank":[147],"conflicts":[148],"arise":[150],"when":[151],"instruction":[152],"operands":[153],"are":[154],"placed":[155],"limited":[158],"number":[159],"banks":[163],"available":[164],"each":[166],"sub-core,":[167],"randomly":[169],"hashed":[170],"assignment":[172],"Our":[177],"intelligent":[178],"result":[181],"an":[183],"average":[184],"11.2%":[185],"speedup":[186],"across":[187],"diverse":[189],"set":[190],"applications":[192],"capturing":[193],"81%":[194],"lost":[198],"sub-division.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":7}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}