{"id":"https://openalex.org/W4406220477","doi":"https://doi.org/10.1145/3711871","title":"EITHOT: Efficient In-place Transposition of High Order Tensors on GPUs","display_name":"EITHOT: Efficient In-place Transposition of High Order Tensors on GPUs","publication_year":2025,"publication_date":"2025-01-09","ids":{"openalex":"https://openalex.org/W4406220477","doi":"https://doi.org/10.1145/3711871"},"language":"en","primary_location":{"id":"doi:10.1145/3711871","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711871","pdf_url":null,"source":{"id":"https://openalex.org/S2483380313","display_name":"ACM Transactions on Parallel Computing","issn_l":"2329-4949","issn":["2329-4949","2329-4957"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Parallel Computing","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/A5103574693","display_name":"Chun-Mei Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chun-Yu Wu","raw_affiliation_strings":["National Tsing-Hua University Department of Computer Science, Hsinchu, Taiwan","National Tsing-Hua University Department of Computer Science,  Hsinchu, Taiwan"],"raw_orcid":"https://orcid.org/0009-0003-7582-2762","affiliations":[{"raw_affiliation_string":"National Tsing-Hua University Department of Computer Science, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"National Tsing-Hua University Department of Computer Science,  Hsinchu, Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018194767","display_name":"Chih-Chieh Tu","orcid":"https://orcid.org/0009-0001-3675-5099"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chih-Chieh Tu","raw_affiliation_strings":["National Tsing-Hua University Department of Computer Science, Hsinchu Taiwan","National Tsing-Hua University Department of Computer Science,  Hsinchu Taiwan"],"raw_orcid":"https://orcid.org/0009-0001-3675-5099","affiliations":[{"raw_affiliation_string":"National Tsing-Hua University Department of Computer Science, Hsinchu Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"National Tsing-Hua University Department of Computer Science,  Hsinchu Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065950372","display_name":"Kai-Jung Cheng","orcid":"https://orcid.org/0009-0005-0620-6442"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Kai-Jung Cheng","raw_affiliation_strings":["National Tsing-Hua University Department of Computer Science, Hsinchu Taiwan","National Tsing-Hua University Department of Computer Science,  Hsinchu Taiwan"],"raw_orcid":"https://orcid.org/0009-0005-0620-6442","affiliations":[{"raw_affiliation_string":"National Tsing-Hua University Department of Computer Science, Hsinchu Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"National Tsing-Hua University Department of Computer Science,  Hsinchu Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058589126","display_name":"Che\u2013Rung Lee","orcid":"https://orcid.org/0000-0003-3940-4478"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Che-Rung Lee","raw_affiliation_strings":["National Tsing-Hua University Department of Computer Science, Hsinchu Taiwan","National Tsing-Hua University Department of Computer Science,  Hsinchu Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-3940-4478","affiliations":[{"raw_affiliation_string":"National Tsing-Hua University Department of Computer Science, Hsinchu Taiwan","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"National Tsing-Hua University Department of Computer Science,  Hsinchu Taiwan","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103574693"],"corresponding_institution_ids":["https://openalex.org/I25846049"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01457976,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":"1","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9934999942779541,"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/T11304","display_name":"Advanced Neuroimaging Techniques and Applications","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transposition","display_name":"Transposition (logic)","score":0.84722900390625},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.5593755841255188},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48724809288978577},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4826958179473877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09160387516021729},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.05429926514625549}],"concepts":[{"id":"https://openalex.org/C12455157","wikidata":"https://www.wikidata.org/wiki/Q7835331","display_name":"Transposition (logic)","level":2,"score":0.84722900390625},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.5593755841255188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48724809288978577},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4826958179473877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09160387516021729},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.05429926514625549},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711871","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711871","pdf_url":null,"source":{"id":"https://openalex.org/S2483380313","display_name":"ACM Transactions on Parallel Computing","issn_l":"2329-4949","issn":["2329-4949","2329-4957"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Parallel Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1493774699","https://openalex.org/W1987882202","https://openalex.org/W2006826424","https://openalex.org/W2006973305","https://openalex.org/W2019463754","https://openalex.org/W2024165284","https://openalex.org/W2028122240","https://openalex.org/W2037271374","https://openalex.org/W2037365376","https://openalex.org/W2051325990","https://openalex.org/W2083746907","https://openalex.org/W2092795222","https://openalex.org/W2093135480","https://openalex.org/W2111309482","https://openalex.org/W2113055885","https://openalex.org/W2149381887","https://openalex.org/W2152240519","https://openalex.org/W2268122618","https://openalex.org/W2466677533","https://openalex.org/W2471966094","https://openalex.org/W2588061952","https://openalex.org/W2885972351","https://openalex.org/W2911343044","https://openalex.org/W2953907816","https://openalex.org/W2963137752","https://openalex.org/W2963482281","https://openalex.org/W3014060182","https://openalex.org/W3106620263","https://openalex.org/W3163329758","https://openalex.org/W3204998121","https://openalex.org/W4243454915","https://openalex.org/W4293075156","https://openalex.org/W4301353660","https://openalex.org/W4385270195","https://openalex.org/W4392543760"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2073700517","https://openalex.org/W4288062113","https://openalex.org/W3151485003","https://openalex.org/W2356141215","https://openalex.org/W2361312893","https://openalex.org/W3215624820","https://openalex.org/W4292765704"],"abstract_inverted_index":{"Tensor":[0],"transposition":[1,98],"is":[2],"a":[3,13,88,97,100,104,120],"fundamental":[4],"operation":[5],"in":[6,28],"tensor":[7,23,31,102,108,122,130],"calculations":[8],"with":[9],"various":[10,190],"applications.":[11],"However,":[12],"naive":[14],"implementation":[15,146],"that":[16,160],"copies":[17],"each":[18,128],"element":[19],"from":[20],"the":[21,25,29,113,133,141,152,167,178],"source":[22],"to":[24,95,139,166,183],"transposed":[26,134],"position":[27],"target":[30],"requires":[32,71],"double":[33,177],"space,":[34],"making":[35,186],"it":[36,187],"unsuitable":[37],"for":[38,61,78,189],"large-scale":[39],"tensors":[40,125,136,181],"on":[41,68,112],"memory-limited":[42],"accelerators,":[43],"like":[44],"Graphic":[45],"Processing":[46],"Units":[47],"(GPUs).":[48],"In":[49],"this":[50],"article,":[51],"we":[52],"propose":[53],"an":[54],"algorithm":[55],"and":[56,126],"its":[57],"implementation,":[58],"called":[59,92],"EITHOT,":[60],"In-place":[62],"Transposition":[63],"of":[64,99,106,180,192],"High":[65],"Order":[66],"Tensors":[67],"GPUs,":[69],"which":[70],"only":[72],"5%":[73],"additional":[74],"memory":[75,116,148],"at":[76],"most":[77],"large":[79,121],"high":[80],"order":[81],"tensors.":[82,194],"To":[83],"achieve":[84],"this,":[85],"EITHOT":[86,118,161,173],"uses":[87],"newly":[89],"proposed":[90],"method,":[91],"permutation":[93],"decomposition,":[94],"factorize":[96],"high-order":[101],"into":[103,123],"sequence":[105],"low-order":[107],"transpositions.":[109],"Then,":[110],"based":[111],"estimated":[114],"extra":[115],"requirements,":[117],"divides":[119],"smaller":[124,129,135],"transposes":[127],"separately.":[131],"Finally,":[132],"are":[137],"combined":[138],"form":[140],"desired":[142],"result.":[143],"The":[144],"GPU":[145,170],"optimizes":[147],"access":[149],"performance":[150,164],"using":[151],"cooperative":[153],"groups":[154],"programming":[155],"model.":[156],"Our":[157],"experiments":[158],"demonstrate":[159],"delivers":[162],"competitive":[163],"compared":[165,182],"state-of-the-art":[168],"out-of-place":[169,184],"implementations.":[171],"Furthermore,":[172],"can":[174],"handle":[175],"nearly":[176],"size":[179],"methods,":[185],"suitable":[188],"transpositions":[191],"N-order":[193]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
