{"id":"https://openalex.org/W4237411130","doi":"https://doi.org/10.1109/iccad.2017.8203754","title":"Exploring cache bypassing and partitioning for multi-tasking on GPUs","display_name":"Exploring cache bypassing and partitioning for multi-tasking on GPUs","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W4237411130","doi":"https://doi.org/10.1109/iccad.2017.8203754"},"language":"en","primary_location":{"id":"doi:10.1109/iccad.2017.8203754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad.2017.8203754","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":"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":"https://openalex.org/A5100604860","display_name":"Yun Liang","orcid":"https://orcid.org/0000-0002-9076-7998"},"institutions":[{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]},{"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","US"],"is_corresponding":true,"raw_author_name":"Yun Liang","raw_affiliation_strings":["School of EECS, Peking University"],"affiliations":[{"raw_affiliation_string":"School of EECS, Peking University","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]},{"author_position":"middle","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"]},{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Xiuhong Li","raw_affiliation_strings":["School of EECS, Peking University"],"affiliations":[{"raw_affiliation_string":"School of EECS, Peking University","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]},{"author_position":"last","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"]},{"id":"https://openalex.org/I111483173","display_name":"King University","ror":"https://ror.org/01evb6z23","country_code":"US","type":"education","lineage":["https://openalex.org/I111483173"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Xiaolong Xie","raw_affiliation_strings":["School of EECS, Peking University"],"affiliations":[{"raw_affiliation_string":"School of EECS, Peking University","institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100604860"],"corresponding_institution_ids":["https://openalex.org/I111483173","https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.26711027,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.55871886,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"9","last_page":"16"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9966999888420105,"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":0.9029548168182373},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.8407124876976013},{"id":"https://openalex.org/keywords/cache-invalidation","display_name":"Cache invalidation","score":0.8228614330291748},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.8058454990386963},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.7768637537956238},{"id":"https://openalex.org/keywords/smart-cache","display_name":"Smart Cache","score":0.7525872588157654},{"id":"https://openalex.org/keywords/cache-pollution","display_name":"Cache pollution","score":0.7312790155410767},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6443033218383789},{"id":"https://openalex.org/keywords/page-cache","display_name":"Page cache","score":0.5748180747032166},{"id":"https://openalex.org/keywords/cache-oblivious-algorithm","display_name":"Cache-oblivious algorithm","score":0.5119513273239136},{"id":"https://openalex.org/keywords/bus-sniffing","display_name":"Bus sniffing","score":0.49224892258644104},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.418653279542923},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.35768628120422363},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.2934733033180237}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9029548168182373},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.8407124876976013},{"id":"https://openalex.org/C25536678","wikidata":"https://www.wikidata.org/wiki/Q5015977","display_name":"Cache invalidation","level":5,"score":0.8228614330291748},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.8058454990386963},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.7768637537956238},{"id":"https://openalex.org/C167713795","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"Smart Cache","level":5,"score":0.7525872588157654},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.7312790155410767},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6443033218383789},{"id":"https://openalex.org/C36340418","wikidata":"https://www.wikidata.org/wiki/Q7124288","display_name":"Page cache","level":5,"score":0.5748180747032166},{"id":"https://openalex.org/C59687516","wikidata":"https://www.wikidata.org/wiki/Q5015938","display_name":"Cache-oblivious algorithm","level":5,"score":0.5119513273239136},{"id":"https://openalex.org/C51185590","wikidata":"https://www.wikidata.org/wiki/Q1017228","display_name":"Bus sniffing","level":5,"score":0.49224892258644104},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.418653279542923},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.35768628120422363},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.2934733033180237}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccad.2017.8203754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad.2017.8203754","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"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":21,"referenced_works":["https://openalex.org/W1982996921","https://openalex.org/W2027806965","https://openalex.org/W2067441262","https://openalex.org/W2079038734","https://openalex.org/W2081583983","https://openalex.org/W2082581695","https://openalex.org/W2091599698","https://openalex.org/W2098274770","https://openalex.org/W2125551452","https://openalex.org/W2129816520","https://openalex.org/W2143773524","https://openalex.org/W2144941482","https://openalex.org/W2150851481","https://openalex.org/W2152517358","https://openalex.org/W2171519206","https://openalex.org/W2346977986","https://openalex.org/W2482017438","https://openalex.org/W4235366964","https://openalex.org/W4237024478","https://openalex.org/W4239965559","https://openalex.org/W6679004590"],"related_works":["https://openalex.org/W2365803410","https://openalex.org/W2113875634","https://openalex.org/W1970102182","https://openalex.org/W2088799683","https://openalex.org/W2294602211","https://openalex.org/W2162744059","https://openalex.org/W2130688751","https://openalex.org/W4249918808","https://openalex.org/W4234336001","https://openalex.org/W1591870472"],"abstract_inverted_index":{"Graphics":[0],"Processing":[1],"Units":[2],"(GPUs)":[3],"computing":[4],"has":[5],"become":[6],"ubiquitous":[7],"for":[8,16,62,109,128,169,225],"embedded":[9],"system,":[10],"evidenced":[11],"by":[12,28,260],"its":[13,154],"wide":[14,247],"adoption":[15],"various":[17],"general":[18],"purpose":[19],"applications.":[20],"As":[21],"more":[22,24],"and":[23,46,124,138,223,233,236],"applications":[25,38,61,250],"are":[26,74],"accelerated":[27],"GPUs,":[29],"multi-tasking":[30,110,268],"scenario":[31],"starts":[32],"to":[33,39,55,76,95,117,150,185,190,193,217,265],"emerge.":[34],"Multi-tasking":[35],"allows":[36],"multiple":[37],"simultaneously":[40],"execute":[41],"on":[42,72,111,262,270],"the":[43,48,56,59,63,70,84,104,119,122,126,132,135,146,159,165,195,198,238,256,266],"same":[44],"GPU":[45],"share":[47],"resource.":[49],"This":[50],"brings":[51,140],"new":[52],"challenges":[53],"due":[54],"contention":[57],"among":[58,121,134,197],"different":[60,230],"shared":[64,105],"resources":[65],"such":[66],"as":[67,103],"caches.":[68],"However,":[69,131],"caches":[71],"GPUs":[73],"difficult":[75],"use.":[77],"If":[78],"used":[79],"inappropriately,":[80],"it":[81],"may":[82],"hurt":[83],"performance":[85],"instead":[86],"of":[87,241,249],"improving":[88],"it.":[89],"In":[90],"this":[91,201,242],"paper,":[92],"we":[93,175,181,203,212],"propose":[94,176],"use":[96,182,213],"cache":[97,101,106,136,148,155,162,166,183,188,205,209,215,231],"partitioning":[98,137,184,206,232],"together":[99],"with":[100,207],"bypassing":[102,139,156,163,216,234],"management":[107],"mechanism":[108],"GPUs.":[112,271],"The":[113],"combined":[114],"approach":[115],"aims":[116],"reduce":[118,194],"interference":[120,196],"tasks":[123],"preserve":[125],"locality":[127],"each":[129,151,170,191,226],"task.":[130,171,227],"interplay":[133],"greater":[141],"challenges.":[142],"On":[143,158],"one":[144],"hand,":[145,161],"partitioned":[147],"space":[149,189],"task":[152,192],"affects":[153,164],"decision.":[157],"other":[160],"capacity":[167],"required":[168],"To":[172],"address":[173],"this,":[174],"a":[177,246],"two-step":[178],"approach.":[179,243],"First,":[180],"assign":[186],"dedicated":[187],"tasks.":[199],"During":[200],"process,":[202],"compare":[204],"coarse-grained":[208],"bypassing.":[210],"Then,":[211],"fine-grained":[214],"selectively":[218],"bypass":[219],"certain":[220],"data":[221],"requests":[222],"threads":[224],"We":[228],"explore":[229],"designs":[235],"demonstrate":[237,251],"potential":[239],"benefits":[240],"Experiments":[244],"using":[245],"range":[248],"that":[252],"our":[253],"technique":[254],"improves":[255],"overall":[257],"system":[258],"throughput":[259],"52%":[261],"average":[263],"compared":[264],"default":[267],"solution":[269]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-02-07T08:09:18.108334","created_date":"2025-10-10T00:00:00"}