{"id":"https://openalex.org/W2117610793","doi":"https://doi.org/10.1145/2145816.2145820","title":"Efficient performance evaluation of memory hierarchy for highly multithreaded graphics processors","display_name":"Efficient performance evaluation of memory hierarchy for highly multithreaded graphics processors","publication_year":2012,"publication_date":"2012-02-25","ids":{"openalex":"https://openalex.org/W2117610793","doi":"https://doi.org/10.1145/2145816.2145820","mag":"2117610793"},"language":"en","primary_location":{"id":"doi:10.1145/2145816.2145820","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2145816.2145820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGPLAN symposium on Principles and Practice of Parallel Programming","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/A5016397835","display_name":"Sara S. Baghsorkhi","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sara S. Baghsorkhi","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA","University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034214277","display_name":"Isaac Gelado","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Isaac Gelado","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA","University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015665965","display_name":"Matthieu Delahaye","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthieu Delahaye","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA","University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040404999","display_name":"Wen\u2010mei Hwu","orcid":"https://orcid.org/0000-0003-2532-5349"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen-mei W. Hwu","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA","University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"34"},"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":0.9983999729156494,"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":0.9977999925613403,"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":0.8909028172492981},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.7157760858535767},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.5638116598129272},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5382921695709229},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.48491793870925903},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.47914594411849976},{"id":"https://openalex.org/keywords/memory-model","display_name":"Memory model","score":0.4376674294471741},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.32237473130226135},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.2855917811393738},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2127504050731659},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2024592161178589}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8909028172492981},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.7157760858535767},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.5638116598129272},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5382921695709229},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.48491793870925903},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.47914594411849976},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.4376674294471741},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32237473130226135},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.2855917811393738},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2127504050731659},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2024592161178589},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2145816.2145820","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2145816.2145820","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM SIGPLAN symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.228.5980","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.228.5980","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://impact.crhc.illinois.edu/ftp/conference/baghsorkhi-2012.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W66083404","https://openalex.org/W1631513913","https://openalex.org/W1979527452","https://openalex.org/W1991824795","https://openalex.org/W1993988399","https://openalex.org/W2000335122","https://openalex.org/W2016309114","https://openalex.org/W2097869070","https://openalex.org/W2103884786","https://openalex.org/W2113282196","https://openalex.org/W2130336316","https://openalex.org/W2133037007","https://openalex.org/W2136434791","https://openalex.org/W2153185479","https://openalex.org/W2153492376","https://openalex.org/W2160227371","https://openalex.org/W2167334577","https://openalex.org/W2399715892","https://openalex.org/W2999431506","https://openalex.org/W4246166885","https://openalex.org/W6636444237"],"related_works":["https://openalex.org/W2170268965","https://openalex.org/W1579918296","https://openalex.org/W1509211761","https://openalex.org/W3033052750","https://openalex.org/W2187267005","https://openalex.org/W2133693067","https://openalex.org/W2370476667","https://openalex.org/W4232453487","https://openalex.org/W2028173051","https://openalex.org/W1967497030"],"abstract_inverted_index":{"With":[0],"the":[1,21,27,40,47,64,71,76,93,112,158,168,171,178,204,216,230,241,253,257,269,283,299,302],"emergence":[2],"of":[3,17,43,49,59,95,97,133,151,162,170,181,225,246,301],"highly":[4,32,117],"multithreaded":[5,33,118],"architectures,":[6],"performance":[7,18,29,60,86,115,152,259],"monitoring":[8,111],"techniques":[9],"face":[10],"new":[11],"challenges":[12],"in":[13,20,31,92,116,229,282],"efficiently":[14],"locating":[15],"sources":[16],"discrepancies":[19],"program":[22,50,66],"source":[23,231],"code.":[24],"For":[25],"example,":[26],"state-of-the-art":[28],"counters":[30,61,260],"graphics":[34,120],"processing":[35],"units":[36],"(GPUs)":[37],"report":[38],"only":[39],"overall":[41,172],"occurrences":[42],"microarchitecture":[44],"events":[45,164],"at":[46,88],"end":[48],"execution.":[51,136],"Furthermore,":[52],"even":[53],"if":[54],"supported,":[55],"any":[56],"fine-grained":[57,187],"sampling":[58,90],"will":[62,69],"distort":[63],"actual":[65],"behavior":[67,169],"and":[68,208,233,289],"make":[70],"sampled":[72],"values":[73,254],"inaccurate.":[74],"On":[75],"other":[77],"hand,":[78],"it":[79],"is":[80,125],"difficult":[81],"to":[82,186,202,214,240,295],"achieve":[83],"high":[84,270],"resolution":[85,271],"information":[87],"low":[89],"rates":[91],"presence":[94],"thousands":[96],"concurrently":[98],"running":[99],"threads.":[100],"In":[101],"this":[102],"paper,":[103],"we":[104,194,278],"present":[105],"a":[106,143,209],"novel":[107],"software-based":[108],"approach":[109,176,190],"for":[110,131],"memory":[113,128,139,211,227,242,280],"hierarchy":[114,140,212],"general-purpose":[119],"processors.":[121],"The":[122,174,189,219],"proposed":[123,220],"analysis":[124],"based":[126],"on":[127,261,268,298],"traces":[129],"collected":[130],"snapshots":[132],"an":[134,196,262],"application":[135],"A":[137,244],"trace-based":[138],"model":[141,213,277],"with":[142,238,252],"Monte":[144],"Carlo":[145],"experimental":[146],"methodology":[147],"generates":[148],"statistical":[149,175],"bounds":[150],"measures":[153],"without":[154],"being":[155],"concerned":[156],"about":[157],"exact":[159],"inter-thread":[160],"ordering":[161],"individual":[163,226],"but":[165],"rather":[166],"studying":[167],"system.":[173,243],"overcomes":[177],"classical":[179],"problem":[180],"disturbed":[182],"execution":[183],"timing":[184],"due":[185],"instrumentation.":[188],"scales":[191],"well":[192],"as":[193],"deploy":[195],"efficient":[197],"parallel":[198],"trace":[199,205],"collection":[200],"technique":[201],"reduce":[203,215],"generation":[206],"overhead":[207],"simple":[210],"simulation":[217],"time.":[218],"scheme":[221],"also":[222],"keeps":[223],"track":[224],"operations":[228],"code":[232],"can":[234],"quantify":[235],"their":[236],"efficiency":[237],"respect":[239],"cross-validation":[245],"our":[247,276],"results":[248],"shows":[249],"close":[250],"agreement":[251],"read":[255],"from":[256,293],"hardware":[258],"NVIDIA":[263],"Tesla":[264],"C2050":[265],"GPU.":[266],"Based":[267],"profile":[272],"data":[273],"produced":[274],"by":[275],"optimized":[279],"accesses":[281],"sparse":[284],"matrix":[285],"vector":[286],"multiply":[287],"kernel":[288],"achieved":[290],"speedups":[291],"ranging":[292],"2.4":[294],"14.8":[296],"depending":[297],"characteristics":[300],"input":[303],"matrices.":[304]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
