{"id":"https://openalex.org/W2060087084","doi":"https://doi.org/10.1145/2716282.2716291","title":"Efficient utilization of GPGPU cache hierarchy","display_name":"Efficient utilization of GPGPU cache hierarchy","publication_year":2015,"publication_date":"2015-02-03","ids":{"openalex":"https://openalex.org/W2060087084","doi":"https://doi.org/10.1145/2716282.2716291","mag":"2060087084"},"language":"en","primary_location":{"id":"doi:10.1145/2716282.2716291","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2716282.2716291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th Workshop on General Purpose Processing using GPUs","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/A5020959383","display_name":"Mahmoud Khairy","orcid":null},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]}],"countries":["EG"],"is_corresponding":true,"raw_author_name":"Mahmoud Khairy","raw_affiliation_strings":["Cairo University, Egypt"],"affiliations":[{"raw_affiliation_string":"Cairo University, Egypt","institution_ids":["https://openalex.org/I145487455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027316186","display_name":"Mohamed Zahran","orcid":"https://orcid.org/0000-0003-0190-7643"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohamed Zahran","raw_affiliation_strings":["New York University, USA"],"affiliations":[{"raw_affiliation_string":"New York University, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049534161","display_name":"Amr G. Wassal","orcid":"https://orcid.org/0000-0001-6009-4174"},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Amr G. Wassal","raw_affiliation_strings":["Cairo University, Egypt"],"affiliations":[{"raw_affiliation_string":"Cairo University, Egypt","institution_ids":["https://openalex.org/I145487455"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020959383"],"corresponding_institution_ids":["https://openalex.org/I145487455"],"apc_list":null,"apc_paid":null,"fwci":6.4596,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.96981166,"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":"36","last_page":"47"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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":0.9979000091552734,"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":0.8777322769165039},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7962305545806885},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.7845132350921631},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.582920491695404},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5784500241279602},{"id":"https://openalex.org/keywords/thrashing","display_name":"Thrashing","score":0.5448437333106995},{"id":"https://openalex.org/keywords/smart-cache","display_name":"Smart Cache","score":0.5380446910858154},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.5191899538040161},{"id":"https://openalex.org/keywords/cache-invalidation","display_name":"Cache invalidation","score":0.41877561807632446},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.3637358546257019},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22543326020240784}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8777322769165039},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7962305545806885},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.7845132350921631},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.582920491695404},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5784500241279602},{"id":"https://openalex.org/C28362024","wikidata":"https://www.wikidata.org/wiki/Q2067413","display_name":"Thrashing","level":2,"score":0.5448437333106995},{"id":"https://openalex.org/C167713795","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"Smart Cache","level":5,"score":0.5380446910858154},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.5191899538040161},{"id":"https://openalex.org/C25536678","wikidata":"https://www.wikidata.org/wiki/Q5015977","display_name":"Cache invalidation","level":5,"score":0.41877561807632446},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.3637358546257019},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22543326020240784},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2716282.2716291","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2716282.2716291","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th Workshop on General Purpose Processing using GPUs","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1762731526","https://openalex.org/W1968902482","https://openalex.org/W1979527452","https://openalex.org/W2000335122","https://openalex.org/W2008115889","https://openalex.org/W2024122052","https://openalex.org/W2026307700","https://openalex.org/W2027806965","https://openalex.org/W2047060659","https://openalex.org/W2048441570","https://openalex.org/W2051688423","https://openalex.org/W2056971515","https://openalex.org/W2067441262","https://openalex.org/W2079038734","https://openalex.org/W2080592089","https://openalex.org/W2089670343","https://openalex.org/W2090283364","https://openalex.org/W2090994050","https://openalex.org/W2098505406","https://openalex.org/W2100011668","https://openalex.org/W2105853930","https://openalex.org/W2109432325","https://openalex.org/W2113755305","https://openalex.org/W2128022558","https://openalex.org/W2128120785","https://openalex.org/W2131926352","https://openalex.org/W2132258839","https://openalex.org/W2142444503","https://openalex.org/W2149234156","https://openalex.org/W2149412408","https://openalex.org/W2169880332","https://openalex.org/W2254138160","https://openalex.org/W2356631387","https://openalex.org/W2547815835","https://openalex.org/W2914479353","https://openalex.org/W4233785673","https://openalex.org/W4250981202"],"related_works":["https://openalex.org/W2133489088","https://openalex.org/W2114386333","https://openalex.org/W2126408955","https://openalex.org/W2363769136","https://openalex.org/W2115222420","https://openalex.org/W2148571123","https://openalex.org/W2369103246","https://openalex.org/W2098406302","https://openalex.org/W2734782074","https://openalex.org/W2750716983"],"abstract_inverted_index":{"Recent":[0],"GPUs":[1],"are":[2,122],"equipped":[3],"with":[4,124],"general-purpose":[5],"L1":[6],"and":[7,18,40,59,73,140,165,205,222,227,237,245],"L2":[8],"caches":[9,34],"in":[10,201],"an":[11],"attempt":[12],"to":[13,29,56,70,94,130,203,231],"reduce":[14],"memory":[15,75,208],"bandwidth":[16],"demand":[17],"improve":[19,60,216],"the":[20,30,46,61,82,100,109,132,142,150,217],"performance":[21,47,62,219,239],"of":[22,63,102,127,135,152,180,220],"some":[23],"irregular":[24],"GPGPU":[25,33,64,158],"applications.":[26],"However,":[27],"due":[28],"massive":[31],"multithreading,":[32],"suffer":[35,160],"from":[36,161],"severe":[37,162],"resource":[38],"contention":[39,223],"low":[41],"data-sharing":[42],"which":[43],"may":[44],"degrade":[45],"instead.":[48],"In":[49,81,176],"this":[50,177],"work,":[51,178,233],"we":[52,85,182],"propose":[53,86],"three":[54],"techniques":[55,215],"efficiently":[57],"utilize":[58],"caches.":[65],"The":[66,213],"first":[67],"technique":[68,148],"aims":[69],"dynamically":[71],"detect":[72],"bypass":[74],"accesses":[76,209],"that":[77,137,194],"show":[78],"streaming":[79,221],"behavior.":[80],"second":[83],"technique,":[84],"dynamic":[87],"warp":[88],"throttling":[89,99],"via":[90],"cores":[91,121],"sampling":[92],"(DWT-CS)":[93],"alleviate":[95],"cache":[96,154,171,186,211],"thrashing":[97,139],"by":[98,225],"number":[101,126,134],"active":[103,128],"warps":[104,129,136],"per":[105],"core.":[106],"DWT-CS":[107],"monitors":[108],"MPKI":[110],"at":[111],"L1,":[112],"when":[113],"it":[114,234],"exceeds":[115],"a":[116,184],"specific":[117],"threshold,":[118],"all":[119],"GPU":[120,153],"sampled":[123],"different":[125],"find":[131],"optimal":[133],"mitigates":[138],"achieves":[141,235],"highest":[143],"performance.":[144],"Our":[145],"proposed":[146,170,214],"third":[147],"addresses":[149],"problem":[151],"associativity":[155,163,174],"since":[156],"many":[157],"applications":[159,224],"stalls":[164],"conflict":[166],"misses.":[167],"Prior":[168],"work":[169],"bypassing":[172],"on":[173,197],"stalls.":[175],"instead":[179],"bypassing,":[181],"employ":[183],"better":[185],"indexing":[187],"function,":[188],"Pseudo":[189],"Random":[190],"Interleaving":[191],"Cache":[192],"(PRIC),":[193],"is":[195],"based":[196],"polynomial":[198],"modulus":[199],"mapping,":[200],"order":[202],"fairly":[204],"evenly":[206],"distribute":[207],"over":[210,241],"sets.":[212],"average":[218],"1.2X":[226],"2.3X":[228],"respectively.":[229,250],"Compared":[230],"prior":[232],"1.7X":[236],"1.5X":[238],"improvement":[240],"Cache-Conscious":[242],"Wavefront":[243],"Scheduler":[244],"Memory":[246],"Request":[247],"Prioritization":[248],"Buffer":[249]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}