{"id":"https://openalex.org/W2039727401","doi":"https://doi.org/10.1145/2807591.2807598","title":"ELF","display_name":"ELF","publication_year":2015,"publication_date":"2015-10-27","ids":{"openalex":"https://openalex.org/W2039727401","doi":"https://doi.org/10.1145/2807591.2807598","mag":"2039727401"},"language":"en","primary_location":{"id":"doi:10.1145/2807591.2807598","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2807591.2807598","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2807598&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=2807598&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023758504","display_name":"Jason Jong Kyu Park","orcid":"https://orcid.org/0000-0002-5457-219X"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Jong Kyu Park","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086980677","display_name":"Yongjun Park","orcid":"https://orcid.org/0000-0003-3725-0380"},"institutions":[{"id":"https://openalex.org/I94588446","display_name":"Hongik University","ror":"https://ror.org/00egdv862","country_code":"KR","type":"education","lineage":["https://openalex.org/I94588446"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yongjun Park","raw_affiliation_strings":["Hongik University, Seoul, Korea","Hongik University , Seoul , Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hongik University, Seoul, Korea","institution_ids":["https://openalex.org/I94588446"]},{"raw_affiliation_string":"Hongik University , Seoul , Korea","institution_ids":["https://openalex.org/I94588446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002075773","display_name":"Scott Mahlke","orcid":"https://orcid.org/0000-0002-0438-0616"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Mahlke","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]}]}],"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":true,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9988999962806702,"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":0.998199999332428,"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":0.8370182514190674},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5959691405296326},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5890682935714722},{"id":"https://openalex.org/keywords/fetch","display_name":"Fetch","score":0.583468496799469},{"id":"https://openalex.org/keywords/context-switch","display_name":"Context switch","score":0.5635245442390442},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.46266981959342957},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3640395998954773},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.34098780155181885},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09254434704780579},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09144648909568787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8370182514190674},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5959691405296326},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5890682935714722},{"id":"https://openalex.org/C131918245","wikidata":"https://www.wikidata.org/wiki/Q1409090","display_name":"Fetch","level":2,"score":0.583468496799469},{"id":"https://openalex.org/C53833338","wikidata":"https://www.wikidata.org/wiki/Q1061424","display_name":"Context switch","level":2,"score":0.5635245442390442},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.46266981959342957},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3640395998954773},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34098780155181885},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09254434704780579},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09144648909568787},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"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/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2807591.2807598","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2807591.2807598","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2807598&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2807591.2807598","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2807591.2807598","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2807598&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.6100000143051147,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G1677117989","display_name":"SHF: Small: Scaling the Compute Efficiency of General-Purpose Processors","funder_award_id":"1217917","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7397408956","display_name":null,"funder_award_id":"SHF-1217917","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2039727401.pdf","grobid_xml":"https://content.openalex.org/works/W2039727401.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1979527452","https://openalex.org/W2001784723","https://openalex.org/W2013281054","https://openalex.org/W2019674193","https://openalex.org/W2047060659","https://openalex.org/W2048441570","https://openalex.org/W2053744175","https://openalex.org/W2067441262","https://openalex.org/W2079038734","https://openalex.org/W2080592089","https://openalex.org/W2090584832","https://openalex.org/W2095804977","https://openalex.org/W2096661534","https://openalex.org/W2097572763","https://openalex.org/W2098505406","https://openalex.org/W2099084006","https://openalex.org/W2101865620","https://openalex.org/W2120692212","https://openalex.org/W2122422937","https://openalex.org/W2123608497","https://openalex.org/W2136944230","https://openalex.org/W2142444503","https://openalex.org/W2143749395","https://openalex.org/W2156355519","https://openalex.org/W2166918318","https://openalex.org/W2207094710","https://openalex.org/W2273440736","https://openalex.org/W3138340923","https://openalex.org/W3144376511","https://openalex.org/W4232096869"],"related_works":["https://openalex.org/W4214970455","https://openalex.org/W2175646991","https://openalex.org/W2027386296","https://openalex.org/W2614583728","https://openalex.org/W2138256251","https://openalex.org/W1910690003","https://openalex.org/W2128177192","https://openalex.org/W2068882541","https://openalex.org/W3177314448","https://openalex.org/W2148341624"],"abstract_inverted_index":{"Graphics":[0],"processing":[1],"units":[2],"(GPUs)":[3],"are":[4,105,118],"increasingly":[5],"utilized":[6],"as":[7,51,53],"throughput":[8],"engines":[9],"in":[10],"the":[11,36,41,73,80,84,88,94,99,131],"modern":[12],"computer":[13],"systems.":[14],"GPUs":[15],"rely":[16],"on":[17],"fast":[18],"context":[19],"switching":[20],"between":[21],"thousands":[22],"of":[23,139],"threads":[24],"to":[25,35,55,79,87],"hide":[26],"long":[27],"latency":[28],"operations,":[29],"however,":[30],"they":[31],"still":[32],"stall":[33],"due":[34],"memory":[37,43,90,120],"operations.":[38],"To":[39],"minimize":[40],"stalls,":[42],"operations":[44,50],"should":[45],"be":[46],"overlapped":[47],"with":[48,143],"other":[49,144],"much":[52],"possible":[54],"maximize":[56],"memory-level":[57],"parallelism":[58],"(MLP).":[59],"In":[60],"this":[61],"paper,":[62],"we":[63],"propose":[64],"Earliest":[65],"Load":[66],"First":[67],"(ELF)":[68],"warp":[69,96],"scheduling,":[70],"which":[71],"maximizes":[72],"MLP":[74],"by":[75,133],"giving":[76],"higher":[77],"priority":[78,97],"warps":[81],"that":[82,103,110,127],"have":[83],"fewest":[85],"instructions":[86],"next":[89],"load.":[91],"ELF":[92,111,128],"utilizes":[93],"same":[95],"for":[98],"fetch":[100,123],"scheduling":[101],"so":[102],"both":[104],"coordinated.":[106],"We":[107],"also":[108],"show":[109,126],"reveals":[112],"its":[113],"full":[114],"benefits":[115],"when":[116,141],"there":[117],"fewer":[119],"conflicts":[121],"and":[122,135],"stalls.":[124],"Evaluations":[125],"can":[129],"improve":[130],"performance":[132],"4.1%":[134],"achieve":[136],"total":[137],"improvement":[138],"11.9%":[140],"used":[142],"techniques":[145],"over":[146],"commonly-used":[147],"greedy-then-oldest":[148],"scheduling.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2016-06-24T00:00:00"}