{"id":"https://openalex.org/W2117148224","doi":"https://doi.org/10.1145/2555243.2555253","title":"A decomposition for in-place matrix transposition","display_name":"A decomposition for in-place matrix transposition","publication_year":2014,"publication_date":"2014-02-06","ids":{"openalex":"https://openalex.org/W2117148224","doi":"https://doi.org/10.1145/2555243.2555253","mag":"2117148224"},"language":"en","primary_location":{"id":"doi:10.1145/2555243.2555253","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2555243.2555253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM SIGPLAN symposium on Principles and practice of parallel programming","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/A5066242985","display_name":"Bryan Catanzaro","orcid":"https://orcid.org/0000-0003-0034-7728"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Bryan Catanzaro","raw_affiliation_strings":["NVIDIA, Santa Clara, CA, USA","[Nvidia, Santa Clara, CA, USA]"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"[Nvidia, Santa Clara, CA, USA]","institution_ids":["https://openalex.org/I1304085615"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101586135","display_name":"Alexander Keller","orcid":"https://orcid.org/0000-0002-9144-5982"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Keller","raw_affiliation_strings":["NVIDIA, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Berlin, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024606205","display_name":"Michael Garland","orcid":"https://orcid.org/0000-0001-6093-7602"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Michael Garland","raw_affiliation_strings":["NVIDIA, Santa Clara, CA, USA","[Nvidia, Santa Clara, CA, USA]"],"affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"[Nvidia, Santa Clara, CA, USA]","institution_ids":["https://openalex.org/I1304085615"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066242985"],"corresponding_institution_ids":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":5.9726,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.96574934,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"193","last_page":"206"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.9979000091552734,"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/transpose","display_name":"Transpose","score":0.6889104843139648},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6876562237739563},{"id":"https://openalex.org/keywords/transposition","display_name":"Transposition (logic)","score":0.6744335889816284},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.655515193939209},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.624830424785614},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.519936740398407},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.5135438442230225},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5119960904121399},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5075169801712036},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.49723532795906067},{"id":"https://openalex.org/keywords/row","display_name":"Row","score":0.47543883323669434},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37680763006210327},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2860115170478821},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.1744323968887329},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.15238997340202332},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.11756843328475952},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08693388104438782}],"concepts":[{"id":"https://openalex.org/C200106649","wikidata":"https://www.wikidata.org/wiki/Q223683","display_name":"Transpose","level":3,"score":0.6889104843139648},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6876562237739563},{"id":"https://openalex.org/C12455157","wikidata":"https://www.wikidata.org/wiki/Q7835331","display_name":"Transposition (logic)","level":2,"score":0.6744335889816284},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.655515193939209},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.624830424785614},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.519936740398407},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.5135438442230225},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5119960904121399},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5075169801712036},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.49723532795906067},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.47543883323669434},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37680763006210327},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2860115170478821},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.1744323968887329},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15238997340202332},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.11756843328475952},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08693388104438782},{"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/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2555243.2555253","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2555243.2555253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM SIGPLAN symposium on Principles and practice of parallel programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1530458829","https://openalex.org/W2028122240","https://openalex.org/W2028499920","https://openalex.org/W2071054511","https://openalex.org/W2083746907","https://openalex.org/W2105937753","https://openalex.org/W2111309482","https://openalex.org/W2139801399","https://openalex.org/W2224273441","https://openalex.org/W2752853835","https://openalex.org/W3138798301"],"related_works":["https://openalex.org/W2003786218","https://openalex.org/W4313549635","https://openalex.org/W2376104713","https://openalex.org/W2356636683","https://openalex.org/W4205331489","https://openalex.org/W2083746907","https://openalex.org/W2182450835","https://openalex.org/W2183938881","https://openalex.org/W1851212222","https://openalex.org/W2176617845"],"abstract_inverted_index":{"We":[0],"describe":[1],"a":[2,128],"decomposition":[3,55,80],"for":[4,106],"in-place":[5,22,67],"matrix":[6,23],"transposition,":[7,68],"with":[8],"applications":[9],"to":[10,21,31,48,61,72,82,117],"Array":[11],"of":[12,36,94,115,119,124,131],"Structures":[13,116,118],"memory":[14],"accesses":[15],"on":[16,34,64,97],"SIMD":[17],"processors.":[18],"Traditional":[19],"approaches":[20],"transposition":[24],"involve":[25],"cycle":[26],"following,":[27],"which":[28],"is":[29],"difficult":[30],"parallelize,":[32],"and":[33,59,85,127],"matrices":[35,109],"dimension":[37],"m":[38],"by":[39],"n":[40],"require":[41],"O(mn":[42],"log":[43],"mn)":[44],"work":[45,70],"when":[46,112],"limited":[47],"less":[49],"than":[50],"O(mn)":[51],"auxiliary":[52,77],"space.":[53,78],"Our":[54],"allows":[56],"the":[57,107],"rows":[58],"columns":[60],"be":[62],"operated":[63],"independently":[65],"during":[66],"reducing":[69],"complexity":[71],"O(mn),":[73],"given":[74],"O(max(m,":[75],"n))":[76],"This":[79],"leads":[81],"an":[83,98],"efficient":[84],"naturally":[86],"parallel":[87],"algorithm:":[88],"we":[89],"have":[90],"measured":[91],"median":[92,122],"throughput":[93,123,130],"19.5":[95],"GB/s":[96],"NVIDIA":[99],"Tesla":[100],"K20c":[101],"processor.":[102],"An":[103],"implementation":[104],"specialized":[105],"skinny":[108],"that":[110],"arise":[111],"converting":[113],"Arrays":[114,120],"yields":[121],"34.3":[125],"GB/s,":[126],"maximum":[129],"51":[132],"GB/s.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}