{"id":"https://openalex.org/W1965829023","doi":"https://doi.org/10.1145/2676723.2693618","title":"Selecting the Optimal Hardware Prefetching Algorithm for Parallel Workloads (Abstract Only)","display_name":"Selecting the Optimal Hardware Prefetching Algorithm for Parallel Workloads (Abstract Only)","publication_year":2015,"publication_date":"2015-02-24","ids":{"openalex":"https://openalex.org/W1965829023","doi":"https://doi.org/10.1145/2676723.2693618","mag":"1965829023"},"language":"en","primary_location":{"id":"doi:10.1145/2676723.2693618","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2676723.2693618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th ACM Technical Symposium on Computer Science Education","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/A5020530000","display_name":"Saami Rahman","orcid":null},"institutions":[{"id":"https://openalex.org/I13511017","display_name":"Texas State University","ror":"https://ror.org/05h9q1g27","country_code":"US","type":"education","lineage":["https://openalex.org/I13511017"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Saami Rahman","raw_affiliation_strings":["Texas State University, San Marcos, TX, USA","Texas State University-San Marcos, TX, USA"],"affiliations":[{"raw_affiliation_string":"Texas State University, San Marcos, TX, USA","institution_ids":["https://openalex.org/I13511017"]},{"raw_affiliation_string":"Texas State University-San Marcos, TX, USA","institution_ids":["https://openalex.org/I13511017"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5020530000"],"corresponding_institution_ids":["https://openalex.org/I13511017"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05839416,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"719","last_page":"719"},"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":0.9995999932289124,"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":0.9988999962806702,"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":0.9704886674880981},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9073821306228638},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.670610785484314},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6411169767379761},{"id":"https://openalex.org/keywords/parsec","display_name":"Parsec","score":0.6165956854820251},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.577036440372467},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5388474464416504},{"id":"https://openalex.org/keywords/cas-latency","display_name":"CAS latency","score":0.4839482605457306},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4775972366333008},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4619012773036957},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4514656066894531},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.42609095573425293},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.26059669256210327},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2557442784309387},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.24712958931922913}],"concepts":[{"id":"https://openalex.org/C133588205","wikidata":"https://www.wikidata.org/wiki/Q28455645","display_name":"Instruction prefetch","level":3,"score":0.9704886674880981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9073821306228638},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.670610785484314},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6411169767379761},{"id":"https://openalex.org/C44060867","wikidata":"https://www.wikidata.org/wiki/Q12129","display_name":"Parsec","level":3,"score":0.6165956854820251},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.577036440372467},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5388474464416504},{"id":"https://openalex.org/C189930140","wikidata":"https://www.wikidata.org/wiki/Q1112878","display_name":"CAS latency","level":4,"score":0.4839482605457306},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4775972366333008},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4619012773036957},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4514656066894531},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.42609095573425293},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.26059669256210327},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2557442784309387},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.24712958931922913},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C150846664","wikidata":"https://www.wikidata.org/wiki/Q7602306","display_name":"Stars","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C100800780","wikidata":"https://www.wikidata.org/wiki/Q1175867","display_name":"Memory controller","level":3,"score":0.0},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2676723.2693618","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2676723.2693618","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 46th ACM Technical Symposium on Computer Science Education","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3006725354","display_name":null,"funder_award_id":"CNS-1253292","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1530597339","https://openalex.org/W2336226224","https://openalex.org/W134340165","https://openalex.org/W2404628714","https://openalex.org/W2068131691","https://openalex.org/W1557286738","https://openalex.org/W2028296512","https://openalex.org/W2546695182","https://openalex.org/W2101018784","https://openalex.org/W3113336200"],"abstract_inverted_index":{"Prefetching":[0],"is":[1,84,129],"a":[2,47,98,112],"commonly":[3],"used":[4,110],"technique":[5],"of":[6,16,44,50,118,138,167,175],"improving":[7],"low-level":[8],"cache":[9],"usage":[10],"that":[11,64,81,103,121,130],"predicts":[12],"memory":[13,24],"requests":[14],"ahead":[15],"time":[17],"and":[18,86,100],"thus,":[19],"improves":[20],"performance":[21,91],"by":[22,58,92],"hiding":[23],"latency.":[25],"Several":[26],"prefetching":[27],"algorithms":[28],"are":[29,56],"implemented":[30],"in":[31,151,163],"hardware.":[32],"For":[33,148],"example,":[34],"the":[35,62,65,135,152,171],"Intel":[36,157],"Core2":[37,158],"processor":[38],"has":[39],"4":[40],"different":[41,48],"prefetchers,":[42],"each":[43],"which":[45,105],"serves":[46],"type":[49],"data":[51],"access":[52],"pattern.":[53],"These":[54],"prefetchers":[55],"enabled":[57],"default,":[59],"based":[60],"on":[61,155],"assumption":[63,83],"prefetch":[66,75],"unit":[67],"will":[68],"be":[69,109],"triggered":[70],"when":[71],"it":[72,123,131],"can":[73,87],"successfully":[74],"data.":[76],"However,":[77],"we":[78],"have":[79],"discovered":[80],"this":[82,119],"incorrect":[85],"at":[88],"times":[89],"hurt":[90],"up":[93],"to":[94,170],"11%.":[95],"We":[96],"present":[97],"simple":[99],"easy-to-use":[101],"framework":[102,161],"determines":[104],"hardware-prefetching":[106],"configuration":[107],"should":[108],"for":[111],"specific":[113,146],"workload.":[114],"The":[115],"guiding":[116],"principle":[117],"work":[120],"sets":[122],"apart":[124],"from":[125],"other":[126],"similar":[127],"ones":[128],"fits":[132],"well":[133],"within":[134],"development":[136],"process":[137],"an":[139,156,164],"average":[140],"programmer":[141],"possessing":[142],"no":[143],"detailed":[144],"hardware":[145],"knowledge.":[147],"two":[149],"programs":[150],"PARSEC":[153],"benchmark,":[154],"machine,":[159],"our":[160],"results":[162],"effective":[165],"speedup":[166],"19%":[168],"compared":[169],"baseline":[172],"default":[173],"setting":[174],"using":[176],"all":[177],"available":[178],"prefetchers.":[179]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}