{"id":"https://openalex.org/W2017345827","doi":"https://doi.org/10.1145/1122018.1122054","title":"Automatic benchmark generation for cache optimization of matrix operations","display_name":"Automatic benchmark generation for cache optimization of matrix operations","publication_year":1995,"publication_date":"1995-01-01","ids":{"openalex":"https://openalex.org/W2017345827","doi":"https://doi.org/10.1145/1122018.1122054","mag":"2017345827"},"language":"en","primary_location":{"id":"doi:10.1145/1122018.1122054","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1122018.1122054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd annual on Southeast regional conference  - ACM-SE 33","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/A5061731648","display_name":"John D. McCalpin","orcid":"https://orcid.org/0000-0002-2535-1355"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John McCalpin","raw_affiliation_strings":["University of Delaware, Newark, DE","University of Delaware; Newark DE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, DE","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"University of Delaware; Newark DE","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016449794","display_name":"Mark Smotherman","orcid":null},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Smotherman","raw_affiliation_strings":["Clemson University, Clemson, SC","Clemson University Clemson. SC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Clemson University, Clemson, SC","institution_ids":["https://openalex.org/I8078737"]},{"raw_affiliation_string":"Clemson University Clemson. SC","institution_ids":["https://openalex.org/I8078737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.12420551,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"195","last_page":"195"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9986000061035156,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9975000023841858,"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":0.8745179176330566},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7843196988105774},{"id":"https://openalex.org/keywords/cache-oblivious-algorithm","display_name":"Cache-oblivious algorithm","score":0.7175266742706299},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6859122514724731},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6100463271141052},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.456135094165802},{"id":"https://openalex.org/keywords/loop-unrolling","display_name":"Loop unrolling","score":0.4288691282272339},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.42241108417510986},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.4138296842575073},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3263609707355499},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.3233431577682495},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.24292051792144775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8745179176330566},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7843196988105774},{"id":"https://openalex.org/C59687516","wikidata":"https://www.wikidata.org/wiki/Q5015938","display_name":"Cache-oblivious algorithm","level":5,"score":0.7175266742706299},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6859122514724731},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6100463271141052},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.456135094165802},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.4288691282272339},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.42241108417510986},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.4138296842575073},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3263609707355499},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.3233431577682495},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.24292051792144775},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1122018.1122054","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1122018.1122054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd annual on Southeast regional conference  - ACM-SE 33","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2098220211","https://openalex.org/W2119609467","https://openalex.org/W2130252507","https://openalex.org/W2138166974","https://openalex.org/W2159309967"],"related_works":["https://openalex.org/W1752260482","https://openalex.org/W1529275186","https://openalex.org/W2106965283","https://openalex.org/W1543046963","https://openalex.org/W2074326206","https://openalex.org/W1534408758","https://openalex.org/W1569026695","https://openalex.org/W1616582327","https://openalex.org/W2182253727","https://openalex.org/W2014594137"],"abstract_inverted_index":{"Computationally":[0],"intensive":[1],"algorithms":[2,24],"must":[3],"usually":[4],"be":[5],"restructured":[6],"to":[7,27],"make":[8],"the":[9,35,38,77,83,96],"best":[10],"use":[11],"of":[12,37,76,89,116],"cache":[13,22,39],"memory":[14,19],"in":[15,61],"current":[16],"high-performance,":[17],"hierarchical":[18],"computers.":[20],"Unfortunately,":[21],"conscious":[23],"are":[25,105],"sensitive":[26],"object":[28],"sizes":[29],"and":[30,40,45,52,67,102,121],"addresses":[31],"as":[32,34],"well":[33],"details":[36],"translation":[41],"lookaside":[42],"buffer":[43],"geometries,":[44],"this":[46,62,108],"sensitivity":[47],"makes":[48],"both":[49],"automatic":[50],"restructuring":[51,98,114],"hand-turning":[53],"difficult":[54],"tasks.":[55],"An":[56],"optimization":[57],"approach":[58,109],"is":[59],"presented":[60],"paper":[63],"that":[64],"automatically":[65],"generates":[66],"executes":[68],"a":[69,73],"benchmark":[70],"program":[71],"from":[72],"concise":[74],"specification":[75],"algorithm's":[78],"structure.":[79],"This":[80],"technique":[81],"provides":[82],"performance":[84],"data":[85],"needed":[86],"for":[87,110],"verification":[88],"code":[90],"generation":[91],"heuristics":[92],"or":[93],"search":[94],"among":[95],"various":[97],"options.":[99],"Matrix":[100],"transpose":[101],"matrix":[103],"multiplication":[104],"examined":[106],"using":[107],"several":[111],"workstations":[112],"with":[113],"options":[115],"loop":[117],"order,":[118],"tiling":[119],"(blocking),":[120],"unrolling.":[122]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
