{"id":"https://openalex.org/W2235724720","doi":"https://doi.org/10.1145/2830772.2830830","title":"WarpPool","display_name":"WarpPool","publication_year":2015,"publication_date":"2015-12-05","ids":{"openalex":"https://openalex.org/W2235724720","doi":"https://doi.org/10.1145/2830772.2830830","mag":"2235724720"},"language":"en","primary_location":{"id":"doi:10.1145/2830772.2830830","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2830772.2830830","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2830772.2830830","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Symposium on Microarchitecture","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2830772.2830830","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071784605","display_name":"John Kloosterman","orcid":"https://orcid.org/0000-0001-8180-1237"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"John Kloosterman","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103007743","display_name":"Jonathan Beaumont","orcid":"https://orcid.org/0000-0001-5092-9094"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Beaumont","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015032126","display_name":"Mick Wollman","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mick Wollman","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053200956","display_name":"Ankit Sethia","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankit Sethia","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067855786","display_name":"Ron Dreslinski","orcid":null},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ron Dreslinski","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037541525","display_name":"Trevor Mudge","orcid":"https://orcid.org/0000-0001-7845-2187"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trevor Mudge","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]}]},{"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\u2013Ann Arbor","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"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5071784605"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":3.5528,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.92971073,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"433","last_page":"444"},"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":0.9994000196456909,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8822495937347412},{"id":"https://openalex.org/keywords/thrashing","display_name":"Thrashing","score":0.746523380279541},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.7076894640922546},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6966036558151245},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6404070258140564},{"id":"https://openalex.org/keywords/page-cache","display_name":"Page cache","score":0.4919295310974121},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.45286861062049866},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.4448454976081848},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.43900150060653687},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.4361552894115448},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4255506992340088},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.4224853515625},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.29768964648246765},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2869083881378174}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8822495937347412},{"id":"https://openalex.org/C28362024","wikidata":"https://www.wikidata.org/wiki/Q2067413","display_name":"Thrashing","level":2,"score":0.746523380279541},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.7076894640922546},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6966036558151245},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6404070258140564},{"id":"https://openalex.org/C36340418","wikidata":"https://www.wikidata.org/wiki/Q7124288","display_name":"Page cache","level":5,"score":0.4919295310974121},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.45286861062049866},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.4448454976081848},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.43900150060653687},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.4361552894115448},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4255506992340088},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.4224853515625},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.29768964648246765},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2869083881378174},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2830772.2830830","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2830772.2830830","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2830772.2830830","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Symposium on Microarchitecture","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2830772.2830830","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2830772.2830830","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2830772.2830830","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International Symposium on Microarchitecture","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4329474313","display_name":null,"funder_award_id":"PERFECT","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"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/W2235724720.pdf","grobid_xml":"https://content.openalex.org/works/W2235724720.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1782174992","https://openalex.org/W1979527452","https://openalex.org/W1983235612","https://openalex.org/W1984993578","https://openalex.org/W2008115889","https://openalex.org/W2027806965","https://openalex.org/W2033486618","https://openalex.org/W2042264308","https://openalex.org/W2047060659","https://openalex.org/W2053744175","https://openalex.org/W2061313045","https://openalex.org/W2067441262","https://openalex.org/W2079038734","https://openalex.org/W2080592089","https://openalex.org/W2086479094","https://openalex.org/W2092283255","https://openalex.org/W2093043622","https://openalex.org/W2098505406","https://openalex.org/W2126089060","https://openalex.org/W2128120785","https://openalex.org/W2129232868","https://openalex.org/W2142444503","https://openalex.org/W2147520174","https://openalex.org/W2155861433","https://openalex.org/W2170634604","https://openalex.org/W2273440736","https://openalex.org/W4235870392"],"related_works":["https://openalex.org/W4252128743","https://openalex.org/W2121761261","https://openalex.org/W2608420839","https://openalex.org/W2946385497","https://openalex.org/W2014594137","https://openalex.org/W2102041801","https://openalex.org/W2751225241","https://openalex.org/W1963833896","https://openalex.org/W4226062505","https://openalex.org/W2774113522"],"abstract_inverted_index":{"Although":[0],"graphics":[1],"processing":[2],"units":[3],"(GPUs)":[4],"are":[5,76],"capable":[6],"of":[7,44,68,91,166],"high":[8,182],"compute":[9,69],"throughput,":[10],"their":[11],"memory":[12,62,74,149,190],"systems":[13,75],"need":[14,186],"to":[15,26,41,65,78,109,114,133,136,156,187],"supply":[16],"the":[17,38,46,49,54,61,84,115,120,123,127,154,157,162,164,185],"arithmetic":[18],"pipelines":[19],"with":[20],"data":[21],"at":[22],"a":[23,58,89,145],"sufficient":[24],"rate":[25],"avoid":[27],"stalls.":[28],"For":[29],"benchmarks":[30],"that":[31,174],"have":[32],"divergent":[33],"access":[34,191],"patterns":[35],"or":[36],"cause":[37],"L1":[39,55,116,158,167],"cache":[40,56,138],"run":[42],"out":[43],"resources,":[45],"link":[47],"between":[48,81,94,122],"GPU's":[50],"load/store":[51,124],"unit":[52,125],"and":[53,126,129,161,205],"becomes":[57],"bottleneck":[59,121],"in":[60,83,96,106],"system,":[63],"leading":[64],"low":[66],"utilization":[67],"resources.":[70],"While":[71],"current":[72,107],"GPU":[73,178,203],"able":[77],"coalesce":[79],"requests":[80,111,135],"threads":[82,95],"same":[85],"warp,":[86],"we":[87],"identify":[88],"form":[90],"spatial":[92],"locality":[93],"multiple":[97],"warps.":[98],"We":[99,171],"use":[100],"this":[101],"locality,":[102],"which":[103],"is":[104],"overlooked":[105],"systems,":[108],"merge":[110],"being":[112],"sent":[113],"cache.":[117],"This":[118],"relieves":[119],"cache,":[128],"provides":[130],"an":[131],"opportunity":[132],"prioritize":[134],"minimize":[137],"thrashing.":[139],"Our":[140],"implementation,":[141],"WarpPool":[142,175,199],",":[143],"yields":[144],"38%":[146],"speedup":[147],"on":[148],"throughput-limited":[150],"kernels":[151],"by":[152,159,169,180],"increasing":[153],"throughput":[155],"8%":[160],"reducing":[163],"number":[165],"misses":[168],"23%.":[170],"also":[172],"demonstrate":[173],"can":[176],"improve":[177],"programmability":[179],"achieving":[181],"performance":[183],"without":[184],"optimize":[188],"workloads'":[189],"patterns.":[192],"A":[193],"Verilog":[194],"implementation":[195],"including":[196],"place-androute":[197],"shows":[198],"requires":[200],"1.0%":[201],"added":[202,207],"area":[204],"0.8%":[206],"power.":[208]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}