{"id":"https://openalex.org/W2111309482","doi":"https://doi.org/10.1145/2555243.2555266","title":"In-place transposition of rectangular matrices on accelerators","display_name":"In-place transposition of rectangular matrices on accelerators","publication_year":2014,"publication_date":"2014-02-06","ids":{"openalex":"https://openalex.org/W2111309482","doi":"https://doi.org/10.1145/2555243.2555266","mag":"2111309482"},"language":"en","primary_location":{"id":"doi:10.1145/2555243.2555266","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2555243.2555266","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/A5083714166","display_name":"I-Jui Sung","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"I-Jui Sung","raw_affiliation_strings":["MulticoreWare, Inc, Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"MulticoreWare, Inc, Champaign, IL, USA","institution_ids":[]}]},{"author_position":"middle","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":false,"raw_author_name":"Juan G\u00f3mez-Luna","raw_affiliation_strings":["University of C\u00f3rdoba, C\u00f3rdoba, Spain"],"affiliations":[{"raw_affiliation_string":"University of C\u00f3rdoba, C\u00f3rdoba, Spain","institution_ids":["https://openalex.org/I53110688"]}]},{"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":"Jos\u00e9 Mar\u00eda Gonz\u00e1lez-Linares","raw_affiliation_strings":["University of M\u00e1laga, M\u00e1laga, Spain"],"affiliations":[{"raw_affiliation_string":"University of M\u00e1laga, M\u00e1laga, 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":"Nicol\u00e1s Guil","raw_affiliation_strings":["University of M\u00e1laga, M\u00e1laga, Spain"],"affiliations":[{"raw_affiliation_string":"University of M\u00e1laga, M\u00e1laga, 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, Urbana, IL, USA","University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5083714166"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4578,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.92732385,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"207","last_page":"218"},"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":0.9991000294685364,"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":0.9972000122070312,"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":0.8529988527297974},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7377339005470276},{"id":"https://openalex.org/keywords/transpose","display_name":"Transpose","score":0.7198977470397949},{"id":"https://openalex.org/keywords/transposition","display_name":"Transposition (logic)","score":0.6927278637886047},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.47590455412864685},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.45113593339920044},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4471761882305145},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15264290571212769},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.11233001947402954}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8529988527297974},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7377339005470276},{"id":"https://openalex.org/C200106649","wikidata":"https://www.wikidata.org/wiki/Q223683","display_name":"Transpose","level":3,"score":0.7198977470397949},{"id":"https://openalex.org/C12455157","wikidata":"https://www.wikidata.org/wiki/Q7835331","display_name":"Transposition (logic)","level":2,"score":0.6927278637886047},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.47590455412864685},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.45113593339920044},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4471761882305145},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15264290571212769},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.11233001947402954},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2555243.2555266","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2555243.2555266","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W145625079","https://openalex.org/W1591180289","https://openalex.org/W1719340579","https://openalex.org/W1965942711","https://openalex.org/W1976139981","https://openalex.org/W1981663184","https://openalex.org/W1982439848","https://openalex.org/W1988949113","https://openalex.org/W2016352575","https://openalex.org/W2028122240","https://openalex.org/W2029102349","https://openalex.org/W2036895269","https://openalex.org/W2063186542","https://openalex.org/W2073061372","https://openalex.org/W2088134616","https://openalex.org/W2102182691","https://openalex.org/W2102200144","https://openalex.org/W2105937753","https://openalex.org/W2117148224","https://openalex.org/W2139801399","https://openalex.org/W2158261096","https://openalex.org/W2224273441","https://openalex.org/W2752908210"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2083746907","https://openalex.org/W2076915000","https://openalex.org/W2183938881","https://openalex.org/W1966837078","https://openalex.org/W2078379271","https://openalex.org/W2043460294","https://openalex.org/W4210712718","https://openalex.org/W1905398909","https://openalex.org/W2176617845"],"abstract_inverted_index":{"Matrix":[0],"transposition":[1,40,45,70,96,109,123,141,209,231],"is":[2,103,114,124],"an":[3,117,197],"important":[4],"algorithmic":[5],"building":[6],"block":[7],"for":[8,51,98],"many":[9],"numeric":[10],"algorithms":[11,71,168],"such":[12],"as":[13,126],"FFT.":[14],"It":[15],"has":[16],"also":[17,179],"been":[18],"used":[19],"to":[20,34,55,82,189,205,210],"convert":[21],"the":[22,73,91,99,129,151,176,186],"storage":[23],"layout":[24],"of":[25,67,75,128,215,229],"arrays.":[26],"With":[27],"more":[28,30,190,216],"and":[29,61,77,134,157,224],"algebra":[31],"libraries":[32],"offloaded":[33],"GPUs,":[35],"a":[36,48,106,162,213],"high":[37,62],"performance":[38],"in-place":[39,44,69,94,207,230],"becomes":[41],"necessary.":[42],"Intuitively,":[43],"should":[46],"be":[47],"good":[49,84],"fit":[50],"GPU":[52,133],"architectures":[53],"due":[54],"limited":[56],"available":[57],"on-board":[58],"memory":[59,130],"capacity":[60],"throughput.":[63],"However,":[64],"direct":[65],"application":[66],"CPU":[68,203],"lacks":[72],"amount":[74],"parallelism":[76],"locality":[78],"required":[79],"by":[80,143],"GPUs":[81],"achieve":[83],"performance.":[85],"In":[86],"this":[87],"paper":[88],"we":[89,195],"present":[90],"first":[92],"known":[93],"matrix":[95,208],"approach":[97,138],"GPUs.":[100],"Our":[101],"implementation":[102],"based":[104,169],"on":[105,170,175,232],"novel":[107],"3-stage":[108,152],"algorithm":[110,153],"where":[111],"each":[112],"stage":[113],"performed":[115],"using":[116],"elementary":[118,173],"tiled-wise":[119],"transposition.":[120],"Additionally,":[121],"when":[122],"done":[125],"part":[127],"transfer":[131],"between":[132],"host,":[135],"our":[136,171,181],"staged":[137],"allows":[139,154,202],"hiding":[140],"overhead":[142],"overlap":[144],"with":[145,166],"PCIe":[146],"transfer.":[147],"We":[148,178],"show":[149,180],"that":[150,201],"larger":[155],"tiles":[156],"achieves":[158],"3X":[159],"speedup":[160],"over":[161],"traditional":[163],"4-stage":[164],"algorithm,":[165],"both":[167],"high-performance":[172],"transpositions":[174],"GPU.":[177],"proposed":[182],"low-level":[183],"optimizations":[184],"improve":[185],"sustained":[187],"throughput":[188,214],"than":[191,217],"20":[192],"GB/s.":[193],"Finally,":[194],"propose":[196],"asynchronous":[198],"execution":[199],"scheme":[200],"threads":[204],"delegate":[206],"GPU,":[211],"achieving":[212],"3.4":[218],"GB/s":[219],"(including":[220],"data":[221],"transfers":[222],"costs),":[223],"improving":[225],"current":[226],"multithreaded":[227],"implementations":[228],"CPU.":[233]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
