{"id":"https://openalex.org/W7127408130","doi":"https://doi.org/10.48550/arxiv.2602.01996","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":2026,"publication_date":"2026-02-02","ids":{"openalex":"https://openalex.org/W7127408130","doi":"https://doi.org/10.48550/arxiv.2602.01996"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.01996","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.01996","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2602.01996","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099870925","display_name":"Theologos Anthimopoulos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anthimopoulos, Theologos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056501771","display_name":"Milad Kokhazadeh","orcid":"https://orcid.org/0009-0001-7430-3691"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kokhazadeh, Milad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099870926","display_name":"Vasilios Kelefouras","orcid":"https://orcid.org/0000-0002-3340-3792"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kelefouras, Vasilios","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075338234","display_name":"Benjamin Himpel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Himpel, Benjamin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keramidas, Georgios","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T12303","display_name":"Tensor decomposition and applications","score":0.7838000059127808,"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":0.7838000059127808,"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":0.045099999755620956,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.02669999934732914,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.6430000066757202},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.602400004863739},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.4706999957561493},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4627000093460083},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.4474000036716461},{"id":"https://openalex.org/keywords/nested-loop-join","display_name":"Nested loop join","score":0.392300009727478},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.38040000200271606},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.3441999852657318},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.3375000059604645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8159000277519226},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.6430000066757202},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.602400004863739},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.4706999957561493},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4627000093460083},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.4474000036716461},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.41260001063346863},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.40619999170303345},{"id":"https://openalex.org/C1306188","wikidata":"https://www.wikidata.org/wiki/Q4060687","display_name":"Nested loop join","level":2,"score":0.392300009727478},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.38040000200271606},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.361299991607666},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3441999852657318},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C42704193","wikidata":"https://www.wikidata.org/wiki/Q7851097","display_name":"Tucker decomposition","level":4,"score":0.29980000853538513},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C189930140","wikidata":"https://www.wikidata.org/wiki/Q1112878","display_name":"CAS latency","level":4,"score":0.28139999508857727},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.27649998664855957},{"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/C104060986","wikidata":"https://www.wikidata.org/wiki/Q180046","display_name":"Space exploration","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C34972735","wikidata":"https://www.wikidata.org/wiki/Q2920267","display_name":"Engineering design process","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2694000005722046},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26499998569488525},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C157170001","wikidata":"https://www.wikidata.org/wiki/Q4781507","display_name":"Applications of artificial intelligence","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C48262172","wikidata":"https://www.wikidata.org/wiki/Q16908765","display_name":"Design process","level":3,"score":0.26179999113082886},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C2986737658","wikidata":"https://www.wikidata.org/wiki/Q30103009","display_name":"Tensor decomposition","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.01996","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.01996","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2602.01996","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.01996","pdf_url":null,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.5705941319465637}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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],"trade-offs":[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],"paper":[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],"3x":[164],"faster":[165,170],"than":[166,171],"IREE":[167],"8x":[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":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-02-04T00:00:00"}