{"id":"https://openalex.org/W4416073545","doi":"https://doi.org/10.48550/arxiv.2506.03686","title":"GenTT: Generate Vectorized Codes for General Tensor Permutation","display_name":"GenTT: Generate Vectorized Codes for General Tensor Permutation","publication_year":2025,"publication_date":"2025-06-04","ids":{"openalex":"https://openalex.org/W4416073545","doi":"https://doi.org/10.48550/arxiv.2506.03686"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2506.03686","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.03686","pdf_url":"https://arxiv.org/pdf/2506.03686","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.03686","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033807671","display_name":"Yaojian Chen","orcid":"https://orcid.org/0000-0002-6363-134X","observed_orcids":["https://orcid.org/0000-0002-6363-134X"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Yaojian","raw_affiliation_strings":["Tsinghua University Haidian Qu , Beijing Shi , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University Haidian Qu , Beijing Shi , China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ma, Tianyu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ma, Tianyu","raw_affiliation_strings":["Tsinghua University Haidian Qu , Beijing Shi , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University Haidian Qu , Beijing Shi , China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100459624","display_name":"Yang An","orcid":"https://orcid.org/0000-0002-3304-1349","observed_orcids":["https://orcid.org/0000-0002-3304-1349"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, An","raw_affiliation_strings":["Tsinghua University Haidian Qu , Beijing Shi , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University Haidian Qu , Beijing Shi , China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100528858","display_name":"Lin Gan","orcid":"https://orcid.org/0000-0003-2160-5722","observed_orcids":["https://orcid.org/0000-0003-2160-5722"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gan, Lin","raw_affiliation_strings":["Tsinghua University Haidian Qu , Beijing Shi , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University Haidian Qu , Beijing Shi , China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015849734","display_name":"Wenlai Zhao","orcid":"https://orcid.org/0000-0003-1036-4732","observed_orcids":["https://orcid.org/0000-0003-1036-4732"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao, Wenlai","raw_affiliation_strings":["Tsinghua University Haidian Qu , Beijing Shi , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University Haidian Qu , Beijing Shi , China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115591592","display_name":"Guangwen Yang","orcid":"https://orcid.org/0000-0002-8673-8254","observed_orcids":["https://orcid.org/0000-0002-8673-8254"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Guangwen","raw_affiliation_strings":["Tsinghua University Haidian Qu , Beijing Shi , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University Haidian Qu , Beijing Shi , China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9937000274658203,"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":0.9937000274658203,"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/T12303","display_name":"Tensor decomposition and applications","score":0.0007999999797903001,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.0005000000237487257,"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/tensor-contraction","display_name":"tensor contraction","score":0.6380000114440918},{"id":"https://openalex.org/keywords/permutation-patterns","display_name":"permutation patterns","score":0.49300000071525574}],"concepts":[{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.7797999978065491},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.7480000257492065},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5906000137329102},{"id":"https://openalex.org/C68965932","wikidata":"https://www.wikidata.org/wiki/Q7169369","display_name":"Permutation graph","level":3,"score":0.5313000082969666},{"id":"https://openalex.org/C175473596","wikidata":"https://www.wikidata.org/wiki/Q4918660","display_name":"Bit-reversal permutation","level":4,"score":0.5171999931335449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4765999913215637},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4375},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4291999936103821},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.41670000553131104},{"id":"https://openalex.org/C145633696","wikidata":"https://www.wikidata.org/wiki/Q1401935","display_name":"Partial permutation","level":4,"score":0.3968999981880188},{"id":"https://openalex.org/C77670614","wikidata":"https://www.wikidata.org/wiki/Q212130","display_name":"Cyclic permutation","level":3,"score":0.37940001487731934},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.36010000109672546},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.33719998598098755},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.329800009727478},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3109000027179718},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.30649998784065247},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2996000051498413},{"id":"https://openalex.org/C92957085","wikidata":"https://www.wikidata.org/wiki/Q1412905","display_name":"Permutation group","level":3,"score":0.29829999804496765},{"id":"https://openalex.org/C84140500","wikidata":"https://www.wikidata.org/wiki/Q851512","display_name":"Permutation matrix","level":3,"score":0.28380000591278076},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C51255310","wikidata":"https://www.wikidata.org/wiki/Q1163016","display_name":"Tensor product","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C20295870","wikidata":"https://www.wikidata.org/wiki/Q5532500","display_name":"Generalized permutation matrix","level":4,"score":0.2565999925136566},{"id":"https://openalex.org/C38298161","wikidata":"https://www.wikidata.org/wiki/Q1207920","display_name":"Derangement","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2506.03686","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.03686","pdf_url":"https://arxiv.org/pdf/2506.03686","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.03686","doi":"https://doi.org/10.48550/arxiv.2506.03686","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.03686","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.03686","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.03686","pdf_url":"https://arxiv.org/pdf/2506.03686","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416073545.pdf","grobid_xml":"https://content.openalex.org/works/W4416073545.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2611747087","https://openalex.org/W4415155338","https://openalex.org/W4416070486"],"related_works":["https://openalex.org/W7099741924","https://openalex.org/W2159846564","https://openalex.org/W1595548352","https://openalex.org/W4245987756","https://openalex.org/W2377118259","https://openalex.org/W3020952492","https://openalex.org/W2295543477","https://openalex.org/W7102501812","https://openalex.org/W3203579016","https://openalex.org/W4407863037"],"abstract_inverted_index":{"Tensor":[0],"permutation":[1,24,32,109,115,126],"is":[2,17,136],"a":[3,28,107],"fundamental":[4],"operation":[5],"widely":[6],"applied":[7],"in":[8,37],"AI,":[9],"tensor":[10,69,80,123],"networks,":[11],"and":[12,20,23,89,125,147],"related":[13],"fields.":[14],"However,":[15],"it":[16],"extremely":[18],"complex,":[19],"different":[21],"shapes":[22],"maps":[25],"can":[26],"make":[27],"huge":[29],"difference.":[30],"SIMD":[31,92,108],"began":[33],"to":[34,47,55,138,141,153],"be":[35],"studied":[36],"2006,":[38],"but":[39],"the":[40,61],"best":[41],"method":[42],"at":[43],"that":[44,112],"time":[45],"was":[46],"split":[48],"complex":[49,65],"permutations":[50,54,77,85,100],"into":[51],"multiple":[52],"simple":[53],"do":[56],"SIMD,":[57],"which":[58],"might":[59],"increase":[60],"complexity":[62],"for":[63,98,117,144,149],"very":[64],"permutations.":[66],"Subsequently,":[67],"as":[68],"contraction":[70],"gained":[71],"significant":[72],"attention,":[73],"researchers":[74],"explored":[75],"structured":[76],"associated":[78],"with":[79,90],"contraction.":[81],"Progress":[82],"on":[83],"general":[84,150],"has":[86,101],"been":[87],"limited,":[88],"increasing":[91],"bit":[93,121],"widths,":[94,122],"achieving":[95],"efficient":[96],"performance":[97],"these":[99],"become":[102],"increasingly":[103],"challenging.":[104],"We":[105],"propose":[106],"toolkit,":[110],"\\system,":[111],"generates":[113],"optimized":[114],"code":[116],"arbitrary":[118],"instruction":[119],"sets,":[120],"shapes,":[124],"patterns,":[127],"while":[128],"maintaining":[129],"low":[130],"complexity.":[131],"In":[132],"our":[133],"experiments,":[134],"\\system":[135],"able":[137],"achieve":[139],"up":[140],"$38\\times$":[142],"speedup":[143],"special":[145],"cases":[146],"$5\\times$":[148],"gases":[151],"compared":[152],"Numpy.":[154]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}