{"id":"https://openalex.org/W7098348443","doi":null,"title":"Memory-Bandwidth Based Performance Tuning and Prediction","display_name":"Memory-Bandwidth Based Performance Tuning and Prediction","alternate_titles":[],"publication_year":null,"publication_date":null,"ids":{"openalex":"https://openalex.org/W7098348443"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.48.242","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.48.242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://softlib.rice.edu/pub/CRPC-TRs/reports/CRPC-TR98742.ps.gz","raw_type":"text"},"parent_works":[],"lineage":["https://openalex.org/W7098348443"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Chen Ding","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Chen Ding","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Ken Kennedy","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Ken Kennedy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"reviewed_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T12127","display_name":"Software System Performance and Reliability","score":9.999999747378752e-05,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/memory-bandwidth","display_name":"memory bandwidth","score":1.0},{"id":"https://openalex.org/keywords/performance-tuning","display_name":"performance tuning","score":0.8370000123977661},{"id":"https://openalex.org/keywords/performance-prediction","display_name":"performance prediction","score":0.9959999918937683},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"memory hierarchy","score":0.8669999837875366},{"id":"https://openalex.org/keywords/performance-analysis-tools","display_name":"performance analysis tools","score":0.5090000033378601},{"id":"https://openalex.org/keywords/loop-nest-optimization","display_name":"loop nest optimization","score":0.5490000247955322},{"id":"https://openalex.org/keywords/scientific-program","display_name":"scientific program","score":0.48500001430511475},{"id":"https://openalex.org/keywords/commodity-processors","display_name":"commodity processors","score":0.5740000009536743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7732999920845032},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.7634000182151794},{"id":"https://openalex.org/C2777138346","wikidata":"https://www.wikidata.org/wiki/Q1714153","display_name":"Performance tuning","level":2,"score":0.6083999872207642},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4959000051021576},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.46970000863075256},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.40470001101493835},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.4009000062942505},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.3677000105381012},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C187123476","wikidata":"https://www.wikidata.org/wiki/Q1197550","display_name":"Computer performance","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.349700003862381},{"id":"https://openalex.org/C133371097","wikidata":"https://www.wikidata.org/wiki/Q868014","display_name":"Non-uniform memory access","level":5,"score":0.3368000090122223},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3176000118255615},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C135510737","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance indicator","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2833000123500824},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.28189998865127563},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.27900001406669617},{"id":"https://openalex.org/C3720319","wikidata":"https://www.wikidata.org/wiki/Q5015937","display_name":"Cache-only memory architecture","level":5,"score":0.2676999866962433},{"id":"https://openalex.org/C63511323","wikidata":"https://www.wikidata.org/wiki/Q908936","display_name":"Interleaved memory","level":4,"score":0.26589998602867126},{"id":"https://openalex.org/C51290061","wikidata":"https://www.wikidata.org/wiki/Q1936765","display_name":"Uniform memory access","level":4,"score":0.2653999924659729},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.48.242","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.48.242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://softlib.rice.edu/pub/CRPC-TRs/reports/CRPC-TR98742.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W73235601","https://openalex.org/W7095152742","https://openalex.org/W2032450372","https://openalex.org/W7098023350","https://openalex.org/W7046723442","https://openalex.org/W2201109483","https://openalex.org/W2109811664","https://openalex.org/W2978553361","https://openalex.org/W84554036","https://openalex.org/W2626276659"],"abstract_inverted_index":{"It":[0],"is":[1,29,49],"the":[2,12,41,95,133,138],"contention":[3,28],"of":[4,17,34,63,97,126],"this":[5,103,141],"paper":[6],"that":[7,71,152],"memory":[8,47,79,117,149],"bandwidth":[9,48,109],"has":[10],"become":[11],"single":[13],"most":[14],"important":[15],"determinant":[16],"performance":[18,54,99,114,119,151],"on":[19,40,102,132],"modern":[20],"computer":[21],"systems":[22],"built":[23],"from":[24],"commodity":[25],"processors.":[26],"This":[27,65,105],"supported":[30],"by":[31],"a":[32,98,128],"study":[33],"several":[35],"representative":[36],"scientific":[37],"programs":[38],"executed":[39],"Silicon":[42],"Graphics":[43],"Origin2000,":[44],"in":[45],"which":[46],"far":[50],"more":[51],"critical":[52],"to":[53,69,87,111],"than":[55],"CPU":[56],"speed":[57],"or":[58],"bandwidths":[59],"between":[60,78],"different":[61],"levels":[62],"cache.":[64],"result":[66],"leads":[67],"us":[68],"conjecture":[70],"measuring":[72],"and":[73,80,89,115],"predicting":[74],"data":[75],"transfer":[76],"time":[77],"cache":[81],"could":[82,107],"be":[83],"an":[84,122],"effective":[85],"way":[86],"predict":[88,112],"tune":[90],"program":[91,113],"performance.":[92],"We":[93],"present":[94],"design":[96],"tool":[100,106,129],"based":[101],"idea.":[104],"use":[108],"analysis":[110],"locate":[116],"hierarchy":[118,150],"problems":[120],"within":[121],"application.":[123],"The":[124],"effectiveness":[125],"such":[127],"was":[130],"demonstrated":[131],"NAS":[134],"SP":[135],"benchmark.":[136],"In":[137],"tuning":[139],"step,":[140],"approach":[142],"identified":[143],"three":[144],"loop":[145],"nests":[146],"with":[147],"low":[148],"...":[153]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W7098348443","counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2025-10-27T00:00:00"}
