{"id":"https://openalex.org/W1987882202","doi":"https://doi.org/10.1109/tpds.2015.2412549","title":"In-Place Matrix Transposition on GPUs","display_name":"In-Place Matrix Transposition on GPUs","publication_year":2015,"publication_date":"2015-03-12","ids":{"openalex":"https://openalex.org/W1987882202","doi":"https://doi.org/10.1109/tpds.2015.2412549","mag":"1987882202"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2015.2412549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2015.2412549","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5044416322","display_name":"Juan G\u00f3mez-Luna","orcid":"https://orcid.org/0000-0002-6514-1571"},"institutions":[{"id":"https://openalex.org/I53110688","display_name":"University of C\u00f3rdoba","ror":"https://ror.org/05yc77b46","country_code":"ES","type":"education","lineage":["https://openalex.org/I53110688"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Juan Gomez-Luna","raw_affiliation_strings":["University of C\u00f3rdoba, Spain","University of Cordoba, Spain"],"affiliations":[{"raw_affiliation_string":"University of C\u00f3rdoba, Spain","institution_ids":["https://openalex.org/I53110688"]},{"raw_affiliation_string":"University of Cordoba, Spain","institution_ids":["https://openalex.org/I53110688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083714166","display_name":"I-Jui Sung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"I-Jui Sung","raw_affiliation_strings":["Multicoreware, Inc",", Multicoreware, Inc"],"affiliations":[{"raw_affiliation_string":"Multicoreware, Inc","institution_ids":[]},{"raw_affiliation_string":", Multicoreware, Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043931807","display_name":"Li\u2010Wen Chang","orcid":"https://orcid.org/0000-0001-6515-6733"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li-Wen Chang","raw_affiliation_strings":["University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069104967","display_name":"Jos\u00e9 Mar\u00eda Gonz\u00e1lez-Linares","orcid":"https://orcid.org/0000-0002-0545-5958"},"institutions":[{"id":"https://openalex.org/I82767444","display_name":"Universidad de M\u00e1laga","ror":"https://ror.org/036b2ww28","country_code":"ES","type":"education","lineage":["https://openalex.org/I82767444"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jose Maria Gonzalez-Linares","raw_affiliation_strings":["University of M\u00e1laga, Spain","University of Malaga -- Spain"],"affiliations":[{"raw_affiliation_string":"University of M\u00e1laga, Spain","institution_ids":["https://openalex.org/I82767444"]},{"raw_affiliation_string":"University of Malaga -- Spain","institution_ids":["https://openalex.org/I82767444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029567783","display_name":"Nicol\u00e1s Guil","orcid":"https://orcid.org/0000-0003-3431-6516"},"institutions":[{"id":"https://openalex.org/I82767444","display_name":"Universidad de M\u00e1laga","ror":"https://ror.org/036b2ww28","country_code":"ES","type":"education","lineage":["https://openalex.org/I82767444"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Nicolas Guil","raw_affiliation_strings":["University of M\u00e1laga, Spain","University of Malaga -- Spain"],"affiliations":[{"raw_affiliation_string":"University of M\u00e1laga, Spain","institution_ids":["https://openalex.org/I82767444"]},{"raw_affiliation_string":"University of Malaga -- Spain","institution_ids":["https://openalex.org/I82767444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040404999","display_name":"Wen\u2010mei Hwu","orcid":"https://orcid.org/0000-0003-2532-5349"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen-Mei W. Hwu","raw_affiliation_strings":["University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5044416322"],"corresponding_institution_ids":["https://openalex.org/I53110688"],"apc_list":null,"apc_paid":null,"fwci":1.9379,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.85626746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"27","issue":"3","first_page":"776","last_page":"788"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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":0.998199999332428,"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":0.9961000084877014,"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":0.861208975315094},{"id":"https://openalex.org/keywords/transpose","display_name":"Transpose","score":0.7872320413589478},{"id":"https://openalex.org/keywords/padding","display_name":"Padding","score":0.7557841539382935},{"id":"https://openalex.org/keywords/transposition","display_name":"Transposition (logic)","score":0.6952751874923706},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6726927757263184},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5215566158294678},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4674946367740631},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.46503207087516785},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.450877845287323},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3932138979434967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11917328834533691},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10723358392715454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.861208975315094},{"id":"https://openalex.org/C200106649","wikidata":"https://www.wikidata.org/wiki/Q223683","display_name":"Transpose","level":3,"score":0.7872320413589478},{"id":"https://openalex.org/C165435473","wikidata":"https://www.wikidata.org/wiki/Q1509884","display_name":"Padding","level":2,"score":0.7557841539382935},{"id":"https://openalex.org/C12455157","wikidata":"https://www.wikidata.org/wiki/Q7835331","display_name":"Transposition (logic)","level":2,"score":0.6952751874923706},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6726927757263184},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5215566158294678},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4674946367740631},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.46503207087516785},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.450877845287323},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3932138979434967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11917328834533691},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10723358392715454},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2015.2412549","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2015.2412549","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1538710729","display_name":null,"funder_award_id":"TIC-1692","funder_id":"https://openalex.org/F4320321562","funder_display_name":"Consejer\u00eda de Econom\u00eda, Innovaci\u00f3n, Ciencia y Empleo, Junta de Andaluc\u00eda"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320311265","display_name":"Universidad de M\u00e1laga","ror":"https://ror.org/036b2ww28"},{"id":"https://openalex.org/F4320321562","display_name":"Consejer\u00eda de Econom\u00eda, Innovaci\u00f3n, Ciencia y Empleo, Junta de Andaluc\u00eda","ror":"https://ror.org/03kak1729"},{"id":"https://openalex.org/F4320326754","display_name":"Junta de Andaluc\u00eda","ror":"https://ror.org/01jem9c82"},{"id":"https://openalex.org/F4320332222","display_name":"University of Illinois at Urbana-Champaign","ror":"https://ror.org/047426m28"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W145625079","https://openalex.org/W182691100","https://openalex.org/W1591180289","https://openalex.org/W1660914831","https://openalex.org/W1964704819","https://openalex.org/W1981663184","https://openalex.org/W1982439848","https://openalex.org/W2016279572","https://openalex.org/W2028122240","https://openalex.org/W2029102349","https://openalex.org/W2036895269","https://openalex.org/W2047614366","https://openalex.org/W2102182691","https://openalex.org/W2102200144","https://openalex.org/W2105937753","https://openalex.org/W2111309482","https://openalex.org/W2117148224","https://openalex.org/W2139801399","https://openalex.org/W2158261096","https://openalex.org/W2621185017","https://openalex.org/W6605891495"],"related_works":["https://openalex.org/W2039763788","https://openalex.org/W2161462353","https://openalex.org/W2047588290","https://openalex.org/W4296337698","https://openalex.org/W1997955449","https://openalex.org/W2965967938","https://openalex.org/W2611747087","https://openalex.org/W2011498909","https://openalex.org/W2471156688","https://openalex.org/W2170268965"],"abstract_inverted_index":{"Matrix":[0],"transposition":[1,28,33,58,82],"is":[2,87,123,170],"an":[3,132],"important":[4],"algorithmic":[5],"building":[6],"block":[7],"for":[8,39,84,97,107,127],"many":[9],"numeric":[10],"algorithms":[11,59],"such":[12],"as":[13],"FFT.":[14],"With":[15,161],"more":[16,18],"and":[17,49,65,101,120,141,154,164],"algebra":[19],"libraries":[20],"offloading":[21],"to":[22,43,70,134,144,178],"GPUs,":[23],"a":[24,36,156],"high":[25,50],"performance":[26],"in-place":[27,32,57,80],"becomes":[29],"necessary.":[30],"Intuitively,":[31],"should":[34],"be":[35],"good":[37,72],"fit":[38],"GPU":[40,69],"architectures":[41],"due":[42],"limited":[44],"available":[45],"on-board":[46],"memory":[47],"capacity":[48],"throughput.":[51],"However,":[52],"direct":[53],"application":[54],"of":[55,63,114,138,151],"CPU":[56],"lacks":[60],"the":[61,98,103,124,136,149,167],"amount":[62],"parallelism":[64],"locality":[66],"required":[67],"by":[68],"achieve":[71,117],"performance.":[73],"In":[74],"this":[75],"paper":[76],"we":[77,110,174],"present":[78,131],"our":[79,152,176],"matrix":[81],"approach":[83],"GPUs":[85],"that":[86,116],"performed":[88],"using":[89,158],"elementary":[90,99],"tile-wise":[91],"transpositions.":[92],"We":[93,130,147],"propose":[94,155],"low-level":[95],"optimizations":[96],"transpositions,":[100],"find":[102],"best":[104],"performing":[105],"configurations":[106],"them.":[108],"Then,":[109],"compare":[111,142,175],"all":[112],"sequences":[113],"transpositions":[115],"full":[118],"transposition,":[119],"detect":[121],"which":[122],"most":[125],"favorable":[126],"each":[128],"matrix.":[129],"heuristic":[133],"guide":[135],"selection":[137],"tile":[139],"sizes,":[140],"them":[143],"brute-force":[145],"search.":[146],"diagnose":[148],"drawback":[150],"approach,":[153],"solution":[157],"minimal":[159],"padding.":[160],"fast":[162],"padding":[163],"unpadding":[165],"kernels,":[166],"overall":[168],"throughput":[169],"significantly":[171],"increased.":[172],"Finally,":[173],"method":[177],"another":[179],"recent":[180],"implementation.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
