{"id":"https://openalex.org/W2038945443","doi":"https://doi.org/10.1145/1152154.1152190","title":"Combining analytical and empirical approaches in tuning matrix transposition","display_name":"Combining analytical and empirical approaches in tuning matrix transposition","publication_year":2006,"publication_date":"2006-09-16","ids":{"openalex":"https://openalex.org/W2038945443","doi":"https://doi.org/10.1145/1152154.1152190","mag":"2038945443"},"language":"en","primary_location":{"id":"doi:10.1145/1152154.1152190","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1152154.1152190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on Parallel architectures and compilation techniques","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/A5045083341","display_name":"Qingda Lu","orcid":"https://orcid.org/0009-0003-8492-6096"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qingda Lu","raw_affiliation_strings":["The Ohio State University, Columbus, OH","Department of Computer Science and Engineering The Ohio State University Columbus, OH USA"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering The Ohio State University Columbus, OH USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006650430","display_name":"Sriram Krishnamoorthy","orcid":"https://orcid.org/0000-0002-4682-1002"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sriram Krishnamoorthy","raw_affiliation_strings":["The Ohio State University, Columbus, OH","Department of Computer Science and Engineering The Ohio State University Columbus, OH USA"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering The Ohio State University Columbus, OH USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027517817","display_name":"P. Sadayappan","orcid":"https://orcid.org/0000-0002-4737-2034"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Sadayappan","raw_affiliation_strings":["The Ohio State University, Columbus, OH","Department of Computer Science and Engineering The Ohio State University Columbus, OH USA"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering The Ohio State University Columbus, OH USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045083341"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.8362,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.71814426,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"233","last_page":"242"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9983000159263611,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9973999857902527,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8508578538894653},{"id":"https://openalex.org/keywords/powerpc","display_name":"PowerPC","score":0.8161555528640747},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6601062417030334},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.6558271646499634},{"id":"https://openalex.org/keywords/pentium","display_name":"Pentium","score":0.5204213261604309},{"id":"https://openalex.org/keywords/program-optimization","display_name":"Program optimization","score":0.5074898600578308},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4819085896015167},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4436016082763672},{"id":"https://openalex.org/keywords/transposition","display_name":"Transposition (logic)","score":0.43016815185546875},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19310978055000305},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.1325553059577942},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.13202548027038574},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.08728146553039551}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8508578538894653},{"id":"https://openalex.org/C56005371","wikidata":"https://www.wikidata.org/wiki/Q209860","display_name":"PowerPC","level":3,"score":0.8161555528640747},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6601062417030334},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.6558271646499634},{"id":"https://openalex.org/C46268123","wikidata":"https://www.wikidata.org/wiki/Q214314","display_name":"Pentium","level":2,"score":0.5204213261604309},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.5074898600578308},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4819085896015167},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4436016082763672},{"id":"https://openalex.org/C12455157","wikidata":"https://www.wikidata.org/wiki/Q7835331","display_name":"Transposition (logic)","level":2,"score":0.43016815185546875},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19310978055000305},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.1325553059577942},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.13202548027038574},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.08728146553039551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1152154.1152190","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1152154.1152190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on Parallel architectures and compilation techniques","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1834452789","https://openalex.org/W1851570257","https://openalex.org/W1912350778","https://openalex.org/W1964031104","https://openalex.org/W1965638741","https://openalex.org/W2000059748","https://openalex.org/W2007451249","https://openalex.org/W2036895269","https://openalex.org/W2038228036","https://openalex.org/W2050191620","https://openalex.org/W2059385032","https://openalex.org/W2061382358","https://openalex.org/W2062512647","https://openalex.org/W2092139011","https://openalex.org/W2099059741","https://openalex.org/W2099404643","https://openalex.org/W2105287631","https://openalex.org/W2135653967","https://openalex.org/W2141867451","https://openalex.org/W2161823660","https://openalex.org/W2167639788","https://openalex.org/W2582377663","https://openalex.org/W3084024371","https://openalex.org/W3136479147","https://openalex.org/W4245987756","https://openalex.org/W6680007323"],"related_works":["https://openalex.org/W2042203635","https://openalex.org/W2184274109","https://openalex.org/W1767235216","https://openalex.org/W98758690","https://openalex.org/W2027104021","https://openalex.org/W4213188177","https://openalex.org/W1980503095","https://openalex.org/W2090841116","https://openalex.org/W2357231105","https://openalex.org/W2097971372"],"abstract_inverted_index":{"Matrix":[0],"transposition":[1],"is":[2,89,105,118],"an":[3,21,41],"important":[4,136],"kernel":[5],"used":[6,90],"in":[7,78],"many":[8,19],"applications.":[9],"Even":[10],"though":[11],"its":[12],"optimization":[13,22,43,133],"has":[14,32],"been":[15,34],"the":[16,26,54,67,70,74,93,112,115,154,157],"subject":[17],"of":[18,28,49,59,69,84,99,111,131,156],"studies,":[20],"procedure":[23],"that":[24,45,134],"targets":[25],"characteristics":[27],"current":[29,79],"processor":[30],"architectures":[31],"not":[33],"developed.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39],"develop":[40],"integrated":[42],"framework":[44],"addresses":[46],"a":[47],"number":[48],"issues,":[50],"including":[51],"tiling":[52],"for":[53,137],"memory":[55,60,63],"hierarchy,":[56],"effective":[57],"handling":[58],"misalignment,":[61],"utilizing":[62],"subsystem":[64],"characteristics,":[65],"and":[66,86,149],"exploitation":[68],"parallelism":[71],"provided":[72],"by":[73,107],"vector":[75],"instruction":[76],"sets":[77],"processors.":[80],"A":[81],"judicious":[82],"combination":[83],"analytical":[85],"empirical":[87,132],"approaches":[88],"to":[91],"determine":[92],"most":[94],"appropriate":[95],"optimizations.":[96],"The":[97,127],"absence":[98],"problem":[100],"information":[101],"until":[102],"execution":[103],"time":[104],"handled":[106],"generating":[108],"multiple":[109],"versions":[110],"code":[113],"-":[114],"best":[116],"version":[117],"chosen":[119],"at":[120],"runtime,":[121],"with":[122,140],"assistance":[123],"from":[124],"minimal-overhead":[125],"inspectors.":[126],"approach":[128],"highlights":[129],"aspects":[130],"are":[135],"similar":[138],"computations":[139],"little":[141],"temporal":[142],"reuse.":[143],"Experimental":[144],"results":[145],"on":[146],"PowerPC":[147],"G5":[148],"Intel":[150],"Pentium":[151],"4":[152],"demonstrate":[153],"effectiveness":[155],"developed":[158],"framework.":[159]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
