{"id":"https://openalex.org/W4390956112","doi":"https://doi.org/10.1109/lca.2024.3355178","title":"DeMM: A Decoupled Matrix Multiplication Engine Supporting Relaxed Structured Sparsity","display_name":"DeMM: A Decoupled Matrix Multiplication Engine Supporting Relaxed Structured Sparsity","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4390956112","doi":"https://doi.org/10.1109/lca.2024.3355178"},"language":"en","primary_location":{"id":"doi:10.1109/lca.2024.3355178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2024.3355178","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"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 Computer Architecture Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2401.08179","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063756965","display_name":"Christodoulos Peltekis","orcid":"https://orcid.org/0009-0000-8930-9431"},"institutions":[{"id":"https://openalex.org/I147962203","display_name":"Democritus University of Thrace","ror":"https://ror.org/03bfqnx40","country_code":"GR","type":"education","lineage":["https://openalex.org/I147962203"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Christodoulos Peltekis","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece","institution_ids":["https://openalex.org/I147962203"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093264909","display_name":"Vasileios Titopoulos","orcid":"https://orcid.org/0009-0009-0123-5737"},"institutions":[{"id":"https://openalex.org/I147962203","display_name":"Democritus University of Thrace","ror":"https://ror.org/03bfqnx40","country_code":"GR","type":"education","lineage":["https://openalex.org/I147962203"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Vasileios Titopoulos","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece","institution_ids":["https://openalex.org/I147962203"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035714231","display_name":"Chrysostomos Nicopoulos","orcid":"https://orcid.org/0000-0001-6389-6068"},"institutions":[{"id":"https://openalex.org/I34771391","display_name":"University of Cyprus","ror":"https://ror.org/02qjrjx09","country_code":"CY","type":"education","lineage":["https://openalex.org/I34771391"]}],"countries":["CY"],"is_corresponding":false,"raw_author_name":"Chrysostomos Nicopoulos","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Cyprus, Nicosia, Cyprus"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Cyprus, Nicosia, Cyprus","institution_ids":["https://openalex.org/I34771391"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074704256","display_name":"Giorgos Dimitrakopoulos","orcid":"https://orcid.org/0000-0003-3688-7865"},"institutions":[{"id":"https://openalex.org/I147962203","display_name":"Democritus University of Thrace","ror":"https://ror.org/03bfqnx40","country_code":"GR","type":"education","lineage":["https://openalex.org/I147962203"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Giorgos Dimitrakopoulos","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece","institution_ids":["https://openalex.org/I147962203"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063756965"],"corresponding_institution_ids":["https://openalex.org/I147962203"],"apc_list":null,"apc_paid":null,"fwci":1.5337,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79912609,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"23","issue":"1","first_page":"17","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9919000267982483,"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":0.9919000267982483,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9678000211715698,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9502999782562256,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/notation","display_name":"Notation","score":0.6046401262283325},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.559345543384552},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.45040163397789},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.43224990367889404},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.42836278676986694},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4123362600803375},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39509543776512146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32358235120773315},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3165058493614197},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.31395524740219116},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.251379132270813},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09307602047920227}],"concepts":[{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.6046401262283325},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.559345543384552},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.45040163397789},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.43224990367889404},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.42836278676986694},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4123362600803375},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39509543776512146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32358235120773315},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3165058493614197},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.31395524740219116},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.251379132270813},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09307602047920227},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lca.2024.3355178","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2024.3355178","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"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 Computer Architecture Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2401.08179","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.08179","pdf_url":"https://arxiv.org/pdf/2401.08179","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2401.08179","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.08179","pdf_url":"https://arxiv.org/pdf/2401.08179","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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4390956112.pdf"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2980186997","https://openalex.org/W3012178976","https://openalex.org/W3103168911","https://openalex.org/W3118927099","https://openalex.org/W3155922894","https://openalex.org/W3185702163","https://openalex.org/W4224612674","https://openalex.org/W4281685651","https://openalex.org/W4312443924","https://openalex.org/W4327911471","https://openalex.org/W4360831840","https://openalex.org/W4380875466","https://openalex.org/W6677580257","https://openalex.org/W6758823024","https://openalex.org/W6770699648","https://openalex.org/W6789946416","https://openalex.org/W6790503700","https://openalex.org/W6794457956"],"related_works":["https://openalex.org/W2504004674","https://openalex.org/W1975949872","https://openalex.org/W3159871278","https://openalex.org/W2230552005","https://openalex.org/W2905242764","https://openalex.org/W2963177394","https://openalex.org/W3109411864","https://openalex.org/W2498744856","https://openalex.org/W4390482104","https://openalex.org/W3017846737"],"abstract_inverted_index":{"Deep":[0],"Learning":[1],"(DL)":[2],"has":[3,14,82],"achieved":[4],"unprecedented":[5],"success":[6],"in":[7,27,64,205],"various":[8],"application":[9],"domains.":[10],"Meanwhile,":[11],"model":[12],"pruning":[13],"emerged":[15],"as":[16],"a":[17,54,112,206],"viable":[18],"solution":[19],"to":[20,44,86,142,184,197],"reduce":[21],"the":[22,36,119,143,148,152,156,160,177,185,203],"footprint":[23],"of":[24,59,67,90,105,115,155,179,187],"DL":[25,42,51,120],"models":[26,43,52],"mobile":[28],"applications,":[29],"without":[30],"compromising":[31],"their":[32,47],"accuracy.":[33],"To":[34],"enable":[35],"matrix":[37],"engines":[38,230],"built":[39,231],"for":[40,102,118,232],"dense":[41,216],"also":[45,84],"handle":[46],"pruned":[48,50],"counterparts,":[49],"follow":[53],"fine-grained":[55,233],"structured":[56,138,236],"sparsity":[57,81,116],"pattern":[58],"1:4,":[60],"or":[61,74,96],"2:4,":[62],"whereby":[63],"each":[65,198],"group":[66],"four":[68],"contiguous":[69],"values,":[70],"at":[71],"least":[72],"one,":[73],"two,":[75],"respectively,":[76],"must":[77],"be":[78],"non-zero.":[79],"Structured":[80],"recently":[83],"moved":[85],"coarser":[87],"(relaxed)":[88],"cases":[89],"<inline-formula":[91,97,106,170],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[92,98,107,171],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[93,99,108,172],"notation=\"LaTeX\">$N$</tex-math></inline-formula>":[94,100,109,173],":128,":[95],":256,":[101],"small":[103],"values":[104],",":[110],"targeting":[111],"wider":[113],"range":[114],"(10%-90%)":[117],"models.":[121],"In":[122,140],"this":[123],"work,":[124],"we":[125],"design":[126],"an":[127],"accelerator":[128],"that":[129],"operates,":[130],"by":[131],"construction,":[132],"on":[133],"wide":[134],"blocks":[135],"with":[136,176],"relaxed":[137,235],"sparsity.":[139,237],"contrast":[141],"conventional":[144],"systolic":[145,157,228],"array":[146,158,229],"archetype,":[147],"new":[149],"engine":[150],"decouples":[151],"memory":[153,164],"part":[154],"from":[159],"multiply-add":[161,193],"units.":[162],"The":[163,192,218],"block":[165],"comprises":[166],"1":[167],"write":[168],"and":[169,201,234],"read":[174,180,199],"ports,":[175],"number":[178,186],"ports":[181],"being":[182],"equal":[183],"non-zero":[188],"elements":[189],"per":[190],"row.":[191],"units":[194],"connect":[195],"directly":[196],"port":[200],"complete":[202],"multiplication":[204],"row-wise":[207],"product-first":[208],"order.":[209],"More":[210],"importantly,":[211],"simple":[212],"reconfiguration":[213],"facilitates":[214],"more":[215],"patterns.":[217],"experimental":[219],"evaluation":[220],"demonstrates":[221],"substantial":[222],"latency":[223],"improvements":[224],"over":[225],"current":[226],"state-of-the-art":[227]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2024-01-18T00:00:00"}
