{"id":"https://openalex.org/W2053744175","doi":"https://doi.org/10.1109/hpca.2015.7056031","title":"Mascar: Speeding up GPU warps by reducing memory pitstops","display_name":"Mascar: Speeding up GPU warps by reducing memory pitstops","publication_year":2015,"publication_date":"2015-02-01","ids":{"openalex":"https://openalex.org/W2053744175","doi":"https://doi.org/10.1109/hpca.2015.7056031","mag":"2053744175"},"language":"en","primary_location":{"id":"doi:10.1109/hpca.2015.7056031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca.2015.7056031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 21st International Symposium on High Performance Computer Architecture (HPCA)","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/A5053200956","display_name":"Ankit Sethia","orcid":null},"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":"Ankit Sethia","raw_affiliation_strings":["Advanced Computer Architecture Laboratory University of Michigan, Ann Arbor, MI","Advanced Computer Architecture Laboratory University of Michigan - Ann Arbor, MI#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Computer Architecture Laboratory University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Advanced Computer Architecture Laboratory University of Michigan - Ann Arbor, MI#TAB#","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065079006","display_name":"D. Anoushe Jamshidi","orcid":null},"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":"D. Anoushe Jamshidi","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, US","Advanced Computer Architecture Laboratory University of Michigan - Ann Arbor, MI#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, US","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Advanced Computer Architecture Laboratory University of Michigan - Ann Arbor, MI#TAB#","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","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":["Advanced Computer Architecture Laboratory University of Michigan, Ann Arbor, MI","Advanced Computer Architecture Laboratory University of Michigan - Ann Arbor, MI#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Computer Architecture Laboratory University of Michigan, Ann Arbor, MI","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Advanced Computer Architecture Laboratory University of Michigan - Ann Arbor, MI#TAB#","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":95,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"174","last_page":"185"},"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":0.9993000030517578,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9990000128746033,"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":0.8863946199417114},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.775455892086029},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7241294384002686},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5262094140052795},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.44649896025657654},{"id":"https://openalex.org/keywords/uniform-memory-access","display_name":"Uniform memory access","score":0.44284096360206604},{"id":"https://openalex.org/keywords/cache-only-memory-architecture","display_name":"Cache-only memory architecture","score":0.42622295022010803},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.4140196144580841},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.34115666151046753},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3246731162071228},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.2194913625717163},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.12530875205993652}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8863946199417114},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.775455892086029},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7241294384002686},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5262094140052795},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.44649896025657654},{"id":"https://openalex.org/C51290061","wikidata":"https://www.wikidata.org/wiki/Q1936765","display_name":"Uniform memory access","level":4,"score":0.44284096360206604},{"id":"https://openalex.org/C3720319","wikidata":"https://www.wikidata.org/wiki/Q5015937","display_name":"Cache-only memory architecture","level":5,"score":0.42622295022010803},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.4140196144580841},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.34115666151046753},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3246731162071228},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.2194913625717163},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.12530875205993652}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpca.2015.7056031","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca.2015.7056031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 21st 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","display_name":"Affordable and clean energy","score":0.8399999737739563}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320313710","display_name":"Menzies School of Health Research","ror":"https://ror.org/006mbby82"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1979527452","https://openalex.org/W1983235612","https://openalex.org/W1989061323","https://openalex.org/W1992851788","https://openalex.org/W2008115889","https://openalex.org/W2033486618","https://openalex.org/W2043051266","https://openalex.org/W2047060659","https://openalex.org/W2048441570","https://openalex.org/W2049875313","https://openalex.org/W2061179133","https://openalex.org/W2061894527","https://openalex.org/W2067441262","https://openalex.org/W2078994750","https://openalex.org/W2080592089","https://openalex.org/W2084110734","https://openalex.org/W2090584832","https://openalex.org/W2093043622","https://openalex.org/W2096661534","https://openalex.org/W2097572763","https://openalex.org/W2098505406","https://openalex.org/W2100011668","https://openalex.org/W2136944230","https://openalex.org/W2140375692","https://openalex.org/W2142444503","https://openalex.org/W2150851481","https://openalex.org/W2153022014","https://openalex.org/W2156831150","https://openalex.org/W2160428323","https://openalex.org/W2160801071","https://openalex.org/W2166263440","https://openalex.org/W2169880332","https://openalex.org/W2273440736","https://openalex.org/W3137551601","https://openalex.org/W3145971282","https://openalex.org/W6648639734","https://openalex.org/W6694513646"],"related_works":["https://openalex.org/W2105141138","https://openalex.org/W1848192231","https://openalex.org/W2781952239","https://openalex.org/W1495085183","https://openalex.org/W3151393245","https://openalex.org/W254684032","https://openalex.org/W2318923906","https://openalex.org/W2349791858","https://openalex.org/W120214571","https://openalex.org/W1512842870"],"abstract_inverted_index":{"With":[0],"the":[1,12,45,124,141,157,165,168],"prevalence":[2],"of":[3,14,42,106,116,130,167,181],"GPUs":[4,38,82],"as":[5],"throughput":[6],"engines":[7],"for":[8,33,48,66,84,87,172,186],"data":[9],"parallel":[10],"workloads,":[11],"landscape":[13],"GPU":[15],"computing":[16],"is":[17,63],"changing":[18],"significantly.":[19],"Non-graphics":[20],"workloads":[21,51],"with":[22],"high":[23],"memory":[24,49,61,88,94,98,109,117,125,142,145,173],"intensity":[25],"and":[26,75,96,108,127,161],"irregular":[27],"access":[28,57],"patterns":[29],"are":[30,52],"frequently":[31],"targeted":[32],"acceleration":[34],"on":[35,81],"GPUs.":[36,67],"While":[37],"provide":[39],"large":[40],"numbers":[41],"compute":[43,107],"resources,":[44],"resources":[46,62],"needed":[47],"intensive":[50,89,174],"more":[53],"scarce.":[54],"Therefore,":[55],"managing":[56],"to":[58,102,119,140,144],"these":[59],"limited":[60,114],"a":[64,70,153],"challenge":[65],"We":[68],"propose":[69],"novel":[71],"Memory":[72],"Aware":[73],"Scheduling":[74],"Cache":[76],"Access":[77],"Re-execution":[78],"(Mascar)":[79],"system":[80],"tailored":[83],"better":[85,104],"performance":[86],"workloads.":[90,175,188],"This":[91],"scheme":[92],"detects":[93],"saturation":[95],"prioritizes":[97],"requests":[99,136],"among":[100],"warps":[101],"enable":[103],"overlapping":[105],"accesses.":[110],"Furthermore,":[111],"it":[112],"enables":[113],"re-execution":[115],"instructions":[118],"eliminate":[120],"structural":[121],"hazards":[122],"in":[123,133,184],"subsystem":[126],"take":[128],"advantage":[129],"cache":[131],"locality":[132],"cases":[134],"where":[135],"cannot":[137],"be":[138],"sent":[139],"due":[143],"saturation.":[146],"Our":[147],"results":[148],"show":[149],"that":[150],"Mascar":[151,176],"provides":[152],"34%":[154],"speedup":[155,163],"over":[156,164],"baseline":[158],"round-robin":[159],"scheduler":[160],"10%":[162],"state":[166],"art":[169],"warp":[170],"schedulers":[171],"also":[177],"achieves":[178],"an":[179],"average":[180],"12%":[182],"savings":[183],"energy":[185],"such":[187]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":15},{"year":2015,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
