{"id":"https://openalex.org/W4414344423","doi":"https://doi.org/10.1145/3768624","title":"Optimizing Tensor Train Decomposition in DNNs for RISC-V Architectures Using Design Space Exploration and Compiler Optimizations","display_name":"Optimizing Tensor Train Decomposition in DNNs for RISC-V Architectures Using Design Space Exploration and Compiler Optimizations","publication_year":2025,"publication_date":"2025-09-18","ids":{"openalex":"https://openalex.org/W4414344423","doi":"https://doi.org/10.1145/3768624"},"language":"en","primary_location":{"id":"doi:10.1145/3768624","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3768624","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"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 Embedded Computing Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099870925","display_name":"Theologos Anthimopoulos","orcid":null},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Theologos Anthimopoulos","raw_affiliation_strings":["School of Informatics, Aristotle University of Thessaloniki","School of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece"],"raw_orcid":"https://orcid.org/0009-0007-3620-4637","affiliations":[{"raw_affiliation_string":"School of Informatics, Aristotle University of Thessaloniki","institution_ids":["https://openalex.org/I21370196"]},{"raw_affiliation_string":"School of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056501771","display_name":"Milad Kokhazadeh","orcid":"https://orcid.org/0009-0001-7430-3691"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Milad Kokhazadeh","raw_affiliation_strings":["School of Informatics, Aristotle University of Thessaloniki","School of Informatics, Aristotle University of Thessaloniki, Thessaloniki Greece"],"raw_orcid":"https://orcid.org/0009-0001-7430-3691","affiliations":[{"raw_affiliation_string":"School of Informatics, Aristotle University of Thessaloniki","institution_ids":["https://openalex.org/I21370196"]},{"raw_affiliation_string":"School of Informatics, Aristotle University of Thessaloniki, Thessaloniki Greece","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090157400","display_name":"Vasilios Kelefouras","orcid":"https://orcid.org/0000-0001-9591-913X"},"institutions":[{"id":"https://openalex.org/I897542642","display_name":"University of Plymouth","ror":"https://ror.org/008n7pv89","country_code":"GB","type":"education","lineage":["https://openalex.org/I897542642"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vasilios Kelefouras","raw_affiliation_strings":["School of Engineering, Computing and Mathematics, University of Plymouth","School of Engineering, Computing and Mathematics, University of Plymouth, Plymouth, United Kingdom of Great Britain and Northern Ireland"],"raw_orcid":"https://orcid.org/0000-0001-9591-913X","affiliations":[{"raw_affiliation_string":"School of Engineering, Computing and Mathematics, University of Plymouth","institution_ids":["https://openalex.org/I897542642"]},{"raw_affiliation_string":"School of Engineering, Computing and Mathematics, University of Plymouth, Plymouth, United Kingdom of Great Britain and Northern Ireland","institution_ids":["https://openalex.org/I897542642"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075338234","display_name":"Benjamin Himpel","orcid":null},"institutions":[{"id":"https://openalex.org/I57589565","display_name":"Reutlingen University","ror":"https://ror.org/00q644y50","country_code":"DE","type":"education","lineage":["https://openalex.org/I57589565"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Benjamin Himpel","raw_affiliation_strings":["Informatics, Hochschule Reutlingen","Informatics, Hochschule Reutlingen, Reutlingen Germany"],"raw_orcid":"https://orcid.org/0000-0002-3737-8379","affiliations":[{"raw_affiliation_string":"Informatics, Hochschule Reutlingen","institution_ids":["https://openalex.org/I57589565"]},{"raw_affiliation_string":"Informatics, Hochschule Reutlingen, Reutlingen Germany","institution_ids":["https://openalex.org/I57589565"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074371053","display_name":"\u0393\u03b5\u03ce\u03c1\u03b3\u03b9\u03bf\u03c2 \u039a\u03b5\u03c1\u03b1\u03bc\u03af\u03b4\u03b1\u03c2","orcid":"https://orcid.org/0000-0003-0460-6061"},"institutions":[{"id":"https://openalex.org/I4210106481","display_name":"Hellenic Agency for Local Development and Local Government","ror":"https://ror.org/0126xra53","country_code":"GR","type":"government","lineage":["https://openalex.org/I4210106481"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Georgios Keramidas","raw_affiliation_strings":["School of Informatics","School of Informatics, Thessaloniki Greece"],"raw_orcid":"https://orcid.org/0000-0003-0460-6061","affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]},{"raw_affiliation_string":"School of Informatics, Thessaloniki Greece","institution_ids":["https://openalex.org/I4210106481"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7995,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.71945701,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"24","issue":"6","first_page":"1","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9995999932289124,"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":0.9995999932289124,"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":0.965499997138977,"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/design-space-exploration","display_name":"Design space exploration","score":0.6622999906539917},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5849999785423279},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.489300012588501},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4595000147819519},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.44830000400543213},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4018000066280365},{"id":"https://openalex.org/keywords/nested-loop-join","display_name":"Nested loop join","score":0.38749998807907104},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.35510000586509705},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.3433000147342682}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8080000281333923},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.6622999906539917},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5849999785423279},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.489300012588501},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4595000147819519},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.44830000400543213},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4092999994754791},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4018000066280365},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3961000144481659},{"id":"https://openalex.org/C1306188","wikidata":"https://www.wikidata.org/wiki/Q4060687","display_name":"Nested loop join","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3767000138759613},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.35510000586509705},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C42704193","wikidata":"https://www.wikidata.org/wiki/Q7851097","display_name":"Tucker decomposition","level":4,"score":0.3086000084877014},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3057999908924103},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C189930140","wikidata":"https://www.wikidata.org/wiki/Q1112878","display_name":"CAS latency","level":4,"score":0.27559998631477356},{"id":"https://openalex.org/C104060986","wikidata":"https://www.wikidata.org/wiki/Q180046","display_name":"Space exploration","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C34972735","wikidata":"https://www.wikidata.org/wiki/Q2920267","display_name":"Engineering design process","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C48262172","wikidata":"https://www.wikidata.org/wiki/Q16908765","display_name":"Design process","level":3,"score":0.2711000144481659},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2678000032901764},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C157170001","wikidata":"https://www.wikidata.org/wiki/Q4781507","display_name":"Applications of artificial intelligence","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C2986737658","wikidata":"https://www.wikidata.org/wiki/Q30103009","display_name":"Tensor decomposition","level":3,"score":0.25}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3768624","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3768624","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"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 Embedded Computing Systems","raw_type":"journal-article"},{"id":"pmh:doi:10.48550/arxiv.2602.01996","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:arXiv.org:2602.01996","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.01996","pdf_url":"https://arxiv.org/pdf/2602.01996","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"pmh:oai:opus.reutlingen-university.de:5904","is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bsz:rt2-opus4-59048","pdf_url":"https://publikationen.reutlingen-university.de/files/5904/5904.pdf","source":{"id":"https://openalex.org/S4306400499","display_name":"Reutlingen University Academic Bibliography (Reutlingen University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I57589565","host_organization_name":"Reutlingen University","host_organization_lineage":["https://openalex.org/I57589565"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.01996","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W69540849","https://openalex.org/W1993482030","https://openalex.org/W2252007067","https://openalex.org/W2783318359","https://openalex.org/W2810421208","https://openalex.org/W2884367402","https://openalex.org/W2912581782","https://openalex.org/W2952689122","https://openalex.org/W2993464084","https://openalex.org/W3001774049","https://openalex.org/W3041222599","https://openalex.org/W3177643164","https://openalex.org/W3190730109","https://openalex.org/W3200229151","https://openalex.org/W3201271601","https://openalex.org/W4240515487","https://openalex.org/W4281681808","https://openalex.org/W4306809382","https://openalex.org/W4310147199","https://openalex.org/W4386162282","https://openalex.org/W4391885548","https://openalex.org/W4400224472","https://openalex.org/W4400224652","https://openalex.org/W4412046573"],"related_works":[],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNNs)":[3],"have":[4],"become":[5],"indispensable":[6],"in":[7,25],"many":[8],"real-life":[9],"applications":[10],"like":[11],"natural":[12],"language":[13],"processing,":[14],"and":[15,35,75,82,94,130,154,168,189],"autonomous":[16],"systems.":[17],"However,":[18],"deploying":[19,185],"DNNs":[20,186],"on":[21,103,137,173,187],"resource-constrained":[22],"devices,":[23],"e.g.,":[24],"RISC-V":[26,104,138,194],"platforms,":[27],"remains":[28],"challenging":[29],"due":[30],"to":[31,54,145],"the":[32,59,78,116,120,174],"high":[33],"computational":[34,156],"memory":[36,71],"demands":[37],"of":[38,63],"fully":[39],"connected":[40],"(FC)":[41],"layers,":[42,57],"which":[43],"dominate":[44],"resource":[45],"consumption.":[46],"Low-rank":[47],"factorization":[48],"(LRF)":[49],"offers":[50],"an":[51,87,181],"effective":[52],"approach":[53],"compressing":[55],"FC":[56,101],"but":[58],"vast":[60],"design":[61,90,97,122],"space":[62,91,123],"LRF":[64,79,89,121],"solutions":[65,132],"involves":[66],"complex":[67,81],"tradeoffs":[68],"among":[69],"FLOPs,":[70],"size,":[72],"inference":[73,135,152],"time,":[74],"accuracy,":[76],"making":[77],"process":[80],"time-consuming.":[83],"This":[84,178],"article":[85],"introduces":[86],"end-to-end":[88],"exploration":[92],"methodology":[93],"a":[95],"specialized":[96],"tool":[98],"for":[99,184],"optimizing":[100],"layers":[102,162],"processors.":[105],"Using":[106],"Tensor":[107],"Train":[108],"Decomposition":[109],"(TTD)":[110],"offered":[111],"by":[112,124,193],"TensorFlow":[113],"T3F":[114,148],"library,":[115],"proposed":[117],"work":[118,179],"prunes":[119],"excluding":[125],"first,":[126],"inefficient":[127],"decomposition":[128],"shapes":[129],"second,":[131],"with":[133],"poor":[134],"performance":[136],"architectures.":[139,195],"Compiler":[140],"optimizations":[141],"are":[142],"then":[143],"applied":[144],"enhance":[146],"custom":[147],"layer":[149],"performance,":[150],"minimizing":[151],"time":[153],"boosting":[155],"efficiency.":[157],"On":[158],"average,":[159],"our":[160],"TT-decomposed":[161],"run":[163],"3\u00d7":[164],"faster":[165,170],"than":[166,171],"IREE":[167],"8\u00d7":[169],"Pluto":[172],"same":[175],"compressed":[176],"model.":[177],"provides":[180],"efficient":[182],"solution":[183],"edge":[188],"embedded":[190],"devices":[191],"powered":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}