{"id":"https://openalex.org/W2138677746","doi":"https://doi.org/10.1145/1024393.1024416","title":"Compiler orchestrated prefetching via speculation and predication","display_name":"Compiler orchestrated prefetching via speculation and predication","publication_year":2004,"publication_date":"2004-10-07","ids":{"openalex":"https://openalex.org/W2138677746","doi":"https://doi.org/10.1145/1024393.1024416","mag":"2138677746"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/1024393.1024416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5001159571","display_name":"Rodric Rabbah","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"funder","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rodric M. Rabbah","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055671465","display_name":"Hariharan Sandanagobalane","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"funder","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hariharan Sandanagobalane","raw_affiliation_strings":["National University of Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019117213","display_name":"Mongkol Ekpanyapong","orcid":"https://orcid.org/0000-0002-0192-6249"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"funder","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mongkol Ekpanyapong","raw_affiliation_strings":["[Georgia Institute of Technology.]"],"affiliations":[{"raw_affiliation_string":"[Georgia Institute of Technology.]","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023989495","display_name":"Weng\u2010Fai Wong","orcid":"https://orcid.org/0000-0002-4281-2053"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"funder","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Weng-Fai Wong","raw_affiliation_strings":["National University of Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.754,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.840314,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":92},"biblio":{"volume":null,"issue":null,"first_page":"189","last_page":"198"},"is_retracted":false,"is_paratext":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":0.9988,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9981,"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/instruction-prefetch","display_name":"Instruction prefetch","score":0.79201746},{"id":"https://openalex.org/keywords/spec#","display_name":"Spec#","score":0.5749053}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.88108104},{"id":"https://openalex.org/C133588205","wikidata":"https://www.wikidata.org/wiki/Q28455645","display_name":"Instruction prefetch","level":3,"score":0.79201746},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6586362},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6507313},{"id":"https://openalex.org/C2778565505","wikidata":"https://www.wikidata.org/wiki/Q2207566","display_name":"Spec#","level":2,"score":0.5749053},{"id":"https://openalex.org/C150202949","wikidata":"https://www.wikidata.org/wiki/Q107602","display_name":"Pointer (user interface)","level":2,"score":0.5243559},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.43244022},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4134071},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.35613325},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.34697855},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.30928284},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22602099},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.16388223}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/1024393.1024416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.42,"id":"https://metadata.un.org/sdg/9"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":38,"referenced_works":["https://openalex.org/W111204614","https://openalex.org/W146984120","https://openalex.org/W1976623675","https://openalex.org/W1984248430","https://openalex.org/W2009711341","https://openalex.org/W2010220656","https://openalex.org/W2063255488","https://openalex.org/W2072737419","https://openalex.org/W2075651377","https://openalex.org/W2095679548","https://openalex.org/W2099958604","https://openalex.org/W2103330947","https://openalex.org/W2107782879","https://openalex.org/W2116299797","https://openalex.org/W2118924037","https://openalex.org/W2122287586","https://openalex.org/W2125424217","https://openalex.org/W2128104279","https://openalex.org/W2131498141","https://openalex.org/W2131667412","https://openalex.org/W2136348740","https://openalex.org/W2146173591","https://openalex.org/W2146246439","https://openalex.org/W2152958194","https://openalex.org/W2154761638","https://openalex.org/W2155010932","https://openalex.org/W2160395504","https://openalex.org/W2160976782","https://openalex.org/W2161178924","https://openalex.org/W2166639949","https://openalex.org/W2168214303","https://openalex.org/W2170585292","https://openalex.org/W2170675137","https://openalex.org/W2295099251","https://openalex.org/W37253703","https://openalex.org/W4230296794","https://openalex.org/W4231002400","https://openalex.org/W4250395788"],"related_works":["https://openalex.org/W56552447","https://openalex.org/W3117515082","https://openalex.org/W2379283503","https://openalex.org/W2285914869","https://openalex.org/W2167639078","https://openalex.org/W2141676084","https://openalex.org/W2140324148","https://openalex.org/W2121199344","https://openalex.org/W2113441357","https://openalex.org/W1564979325"],"abstract_inverted_index":{"This":[0],"paper":[1,186],"introduces":[2],"a":[3,9,153],"compiler":[4],"orchestrated":[5],"prefetching":[6],"system":[7,132,179],"as":[8],"unified":[10],"framework":[11],"geared":[12],"toward":[13],"ameliorating":[14],"the":[15,26,29,35,42,80,130,139,170,177,202],"gap":[16],"between":[17],"processing":[18],"speeds":[19],"and":[20,51,67,88,111,123,146,197],"memory":[21,43,71,131,178,191],"access":[22,44],"latencies.":[23],"We":[24,55],"focus":[25,137],"scope":[27],"of":[28,34,46,84,143,156,169,204],"optimization":[30],"on":[31,94,138],"specific":[32],"subsets":[33],"program":[36,58],"dependence":[37],"graph":[38],"that":[39,127,167,173],"succinctly":[40],"characterize":[41],"pattern":[45],"both":[47],"regular":[48],"array-based":[49],"applications":[50],"irregular":[52],"pointer-intensive":[53],"programs.":[54],"illustrate":[56],"how":[57,148],"embedded":[59],"precomputation":[60],"via":[61],"speculative":[62],"execution":[63],"can":[64,187,198],"accurately":[65],"predict":[66],"effectively":[68,188],"prefetch":[69],"future":[70],"references":[72],"with":[73,193],"negligible":[74],"overhead.":[75],"The":[76,99,182],"proposed":[77],"techniques":[78,183],"reduce":[79],"total":[81],"running":[82],"time":[83],"seven":[85],"SPEC":[86,164],"benchmarks":[87,91,165],"two":[89],"OLDEN":[90],"by":[92,176],"27%":[93],"an":[95],"Itanium":[96],"2":[97],"processor.":[98],"improvements":[100],"are":[101,174,180],"in":[102,184],"addition":[103],"to":[104,120,201],"several":[105],"state-of-the-art":[106],"optimizations":[107],"including":[108],"software":[109],"pipelining":[110],"data":[112],"prefetching.":[113,159],"In":[114,134],"addition,":[115],"we":[116,136],"use":[117],"cycle-accurate":[118],"simulations":[119],"identify":[121],"important":[122],"lightweight":[124],"architectural":[125],"innovations":[126],"further":[128],"mitigate":[129],"bottleneck.":[133],"particular,":[135],"notoriously":[140],"challenging":[141],"class":[142],"pointer-chasing":[144],"applications,":[145],"demonstrate":[147,166],"they":[149],"may":[150],"benefit":[151],"from":[152],"novel":[154],"scheme":[155],"it":[157],"sentineled":[158],"Our":[160],"results":[161],"for":[162],"twelve":[163],"45%":[168],"processor":[171],"stalls":[172],"caused":[175],"avoidable.":[181],"this":[185],"mask":[189],"long":[190],"latencies":[192],"little":[194],"instruction":[195],"overhead,":[196],"readily":[199],"contribute":[200],"performance":[203],"processors":[205],"today.":[206]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2138677746","counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4}],"updated_date":"2025-03-22T05:25:36.621379","created_date":"2016-06-24"}