{"id":"https://openalex.org/W4391827238","doi":"https://doi.org/10.1109/tc.2024.3365936","title":"TetriX: Flexible Architecture and Optimal Mapping for Tensorized Neural Network Processing","display_name":"TetriX: Flexible Architecture and Optimal Mapping for Tensorized Neural Network Processing","publication_year":2024,"publication_date":"2024-02-14","ids":{"openalex":"https://openalex.org/W4391827238","doi":"https://doi.org/10.1109/tc.2024.3365936"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2024.3365936","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2024.3365936","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","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/A5076596358","display_name":"Zhang Jie-Fang\ue00b","orcid":"https://orcid.org/0000-0002-6609-4383"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie-Fang Zhang","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA","Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, Michigan, USA"],"raw_orcid":"https://orcid.org/0000-0002-6609-4383","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, Michigan, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109439305","display_name":"Cheng\u2010Hsun Lu","orcid":"https://orcid.org/0000-0002-4794-9438"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng-Hsun Lu","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA","Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, Michigan, USA"],"raw_orcid":"https://orcid.org/0009-0002-8044-6186","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, Michigan, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038110244","display_name":"Zhengya Zhang","orcid":"https://orcid.org/0000-0001-5963-9018"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengya Zhang","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA","Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, Michigan, USA"],"raw_orcid":"https://orcid.org/0000-0001-5963-9018","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, Michigan, USA","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":0.4315,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.44940476,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"73","issue":"5","first_page":"1219","last_page":"1232"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9918000102043152,"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/computer-science","display_name":"Computer science","score":0.6110252141952515},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5915628671646118},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5910240411758423},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.4602166414260864},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.45892977714538574},{"id":"https://openalex.org/keywords/tensor-product","display_name":"Tensor product","score":0.43368491530418396},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.42359215021133423},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23943182826042175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21215727925300598},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0874532163143158}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6110252141952515},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5915628671646118},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5910240411758423},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.4602166414260864},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.45892977714538574},{"id":"https://openalex.org/C51255310","wikidata":"https://www.wikidata.org/wiki/Q1163016","display_name":"Tensor product","level":2,"score":0.43368491530418396},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.42359215021133423},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23943182826042175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21215727925300598},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0874532163143158},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2024.3365936","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2024.3365936","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.4099999964237213}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1993482030","https://openalex.org/W2000045479","https://openalex.org/W2024165284","https://openalex.org/W2058641082","https://openalex.org/W2067523571","https://openalex.org/W2088025933","https://openalex.org/W2109626307","https://openalex.org/W2431890537","https://openalex.org/W2570702650","https://openalex.org/W2593564159","https://openalex.org/W2606722458","https://openalex.org/W2612076670","https://openalex.org/W2619959423","https://openalex.org/W2775020237","https://openalex.org/W2893813411","https://openalex.org/W2894006184","https://openalex.org/W2895561155","https://openalex.org/W2899644485","https://openalex.org/W2919207648","https://openalex.org/W2962766718","https://openalex.org/W2963688311","https://openalex.org/W2963838731","https://openalex.org/W2966234499","https://openalex.org/W3012561096","https://openalex.org/W3023960238","https://openalex.org/W3033301241","https://openalex.org/W3037399553","https://openalex.org/W3080923968","https://openalex.org/W3105213343","https://openalex.org/W3124048260","https://openalex.org/W3126937085","https://openalex.org/W3130920634","https://openalex.org/W3134893068","https://openalex.org/W3173832704","https://openalex.org/W3176934054","https://openalex.org/W4287644718","https://openalex.org/W4296499650","https://openalex.org/W4313142361","https://openalex.org/W4380875583","https://openalex.org/W4385151994","https://openalex.org/W6638060716","https://openalex.org/W6684563725","https://openalex.org/W6717575008","https://openalex.org/W6741042017","https://openalex.org/W6746810134","https://openalex.org/W6764409202","https://openalex.org/W6777283564","https://openalex.org/W6784198299","https://openalex.org/W6789141709"],"related_works":["https://openalex.org/W2000785801","https://openalex.org/W986318368","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W2004734601","https://openalex.org/W2130149817","https://openalex.org/W2990194547","https://openalex.org/W4386687603","https://openalex.org/W4307007469","https://openalex.org/W4288558775"],"abstract_inverted_index":{"The":[0],"continuous":[1],"growth":[2],"of":[3,14,66,113,189],"deep":[4],"neural":[5,39],"network":[6],"model":[7,29],"size":[8,30],"and":[9,44,69,75,89,107,130,149,191,196],"complexity":[10],"hinders":[11],"the":[12,28,36,127,135,146,159,165,182],"adoption":[13],"large":[15,32],"models":[16],"in":[17,26,110,156,193],"resource-constrained":[18],"platforms.":[19],"Tensor":[20],"decomposition":[21,173],"has":[22],"been":[23],"shown":[24],"effective":[25],"reducing":[27],"by":[31,103,152],"compression":[33],"ratios,":[34],"but":[35],"resulting":[37],"tensorized":[38],"networks":[40],"(TNNs)":[41],"require":[42],"complex":[43,100],"versatile":[45],"tensor":[46,49,101,114,172],"shaping":[47,102],"for":[48,56,73,133,181],"contraction,":[50],"causing":[51],"a":[52,64,81,111,117,177],"low":[53],"processing":[54,83],"efficiency":[55],"existing":[57,171],"hardware":[58],"architectures.":[59],"This":[60],"work":[61,167],"presents":[62],"TetriX,":[63],"co-design":[65],"flexible":[67,76],"architecture":[68,84],"optimal":[70,136],"workload":[71,131],"mapping":[72,94,132],"efficient":[74],"TNN":[77,161,178],"processing.":[78],"TetriX":[79,142,163,186],"adopts":[80],"unified":[82],"to":[85,98,125,154,168,176],"support":[86,169],"both":[87],"inner":[88,106],"outer":[90,108],"product.":[91],"A":[92],"hybrid":[93],"scheme":[95],"is":[96,123,164],"proposed":[97,124],"eliminate":[99],"alternating":[104],"between":[105],"product":[109],"sequence":[112,120,129],"contractions.":[115],"Finally,":[116],"mapping-aware":[118],"contraction":[119,128],"search":[121],"(MCSS)":[122],"identify":[126],"achieving":[134],"latency":[137],"on":[138],"TetriX.":[139],"Remarkably,":[140],"combining":[141],"with":[143],"MCSS":[144],"outperforms":[145],"single-mode":[147],"inner-product":[148],"outer-product":[150],"baselines":[151],"up":[153],"46.8\u00d7":[155],"performance":[157],"across":[158],"collected":[160],"workloads.":[162],"first":[166],"all":[170],"methods.":[174],"Compared":[175],"accelerator":[179],"designed":[180],"hierarchical":[183],"Tucker":[184],"method,":[185],"achieves":[187],"improvements":[188],"6.5\u00d7":[190],"1.1\u00d7":[192],"inference":[194],"throughput":[195],"efficiency,":[197],"respectively.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}