{"id":"https://openalex.org/W3136309901","doi":"https://doi.org/10.1109/tpds.2021.3067825","title":"Spartan: A Sparsity-Adaptive Framework to Accelerate Deep Neural Network Training on GPUs","display_name":"Spartan: A Sparsity-Adaptive Framework to Accelerate Deep Neural Network Training on GPUs","publication_year":2021,"publication_date":"2021-03-22","ids":{"openalex":"https://openalex.org/W3136309901","doi":"https://doi.org/10.1109/tpds.2021.3067825","mag":"3136309901"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2021.3067825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3067825","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["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/A5101947049","display_name":"Shi Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shi Dong","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041025969","display_name":"Yifan Sun","orcid":"https://orcid.org/0000-0003-3532-6521"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Sun","raw_affiliation_strings":["William & Mary, Sadler Center, Williamsburg, VA, USA"],"affiliations":[{"raw_affiliation_string":"William & Mary, Sadler Center, Williamsburg, VA, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057498242","display_name":"N\u00edcolas Bohm Agostini","orcid":"https://orcid.org/0000-0003-1855-3810"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicolas Bohm Agostini","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058119214","display_name":"Elmira Karimi","orcid":"https://orcid.org/0000-0003-3849-4918"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elmira Karimi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022915639","display_name":"Daniel Lowell","orcid":"https://orcid.org/0000-0002-8929-7837"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Lowell","raw_affiliation_strings":["Advanced Micro Devices Inc., Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices Inc., Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101850837","display_name":"Jing Zhou","orcid":"https://orcid.org/0000-0002-4294-3985"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Zhou","raw_affiliation_strings":["Advanced Micro Devices Inc., Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices Inc., Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008501980","display_name":"Jos\u00e9 Cano","orcid":"https://orcid.org/0000-0002-2243-389X"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jose Cano","raw_affiliation_strings":["University of Glasgow, Glasgow, U.K"],"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, U.K","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007832959","display_name":"Jos\u00e9 Luis Abell\u00e1n","orcid":"https://orcid.org/0000-0003-3550-720X"},"institutions":[{"id":"https://openalex.org/I68763199","display_name":"Universidad Cat\u00f3lica de Murcia","ror":"https://ror.org/05b1rsv17","country_code":"ES","type":"education","lineage":["https://openalex.org/I68763199"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jose L. Abellan","raw_affiliation_strings":["UCAM Universidad Cat\u00f3lica de Murcia, Murcia, Spain"],"affiliations":[{"raw_affiliation_string":"UCAM Universidad Cat\u00f3lica de Murcia, Murcia, Spain","institution_ids":["https://openalex.org/I68763199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061128237","display_name":"David Kaeli","orcid":"https://orcid.org/0000-0002-5692-0151"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Kaeli","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101947049"],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":0.7751,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.72854272,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"32","issue":"10","first_page":"2448","last_page":"2463"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12676","display_name":"Machine Learning and ELM","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8906478881835938},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6699956059455872},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6206977367401123},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.5349302291870117},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5245733261108398},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5009958744049072},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4997420310974121},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4895256459712982},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4875902533531189},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.4762287735939026},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.44405239820480347},{"id":"https://openalex.org/keywords/spartan","display_name":"Spartan","score":0.4254774749279022},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4143204092979431},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.3721049427986145},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.21146121621131897},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13325726985931396}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8906478881835938},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6699956059455872},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6206977367401123},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.5349302291870117},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5245733261108398},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5009958744049072},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4997420310974121},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4895256459712982},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4875902533531189},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.4762287735939026},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.44405239820480347},{"id":"https://openalex.org/C10689553","wikidata":"https://www.wikidata.org/wiki/Q405953","display_name":"Spartan","level":3,"score":0.4254774749279022},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4143204092979431},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.3721049427986145},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.21146121621131897},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13325726985931396},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpds.2021.3067825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3067825","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:eprints.gla.ac.uk:240696","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Articles"}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:240696","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Articles"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1667652561","https://openalex.org/W1686810756","https://openalex.org/W2007259720","https://openalex.org/W2038071684","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2131825507","https://openalex.org/W2142801765","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2285660444","https://openalex.org/W2302255633","https://openalex.org/W2304648132","https://openalex.org/W2474119684","https://openalex.org/W2513554817","https://openalex.org/W2516141709","https://openalex.org/W2585720638","https://openalex.org/W2587914027","https://openalex.org/W2657126969","https://openalex.org/W2763421725","https://openalex.org/W2795994638","https://openalex.org/W2796013597","https://openalex.org/W2883283076","https://openalex.org/W2890392327","https://openalex.org/W2902400410","https://openalex.org/W2904902077","https://openalex.org/W2915106038","https://openalex.org/W2945146780","https://openalex.org/W2949674408","https://openalex.org/W2952928793","https://openalex.org/W2962821792","https://openalex.org/W2963112338","https://openalex.org/W2963896595","https://openalex.org/W2966206672","https://openalex.org/W2978754339","https://openalex.org/W3008522202","https://openalex.org/W3012561096","https://openalex.org/W3016542674","https://openalex.org/W3104805932","https://openalex.org/W3117255825","https://openalex.org/W3118608800","https://openalex.org/W3141915942","https://openalex.org/W4302296459","https://openalex.org/W6637151318","https://openalex.org/W6637373629","https://openalex.org/W6684191040","https://openalex.org/W6697974390","https://openalex.org/W6698183232","https://openalex.org/W6745245109","https://openalex.org/W6768871568","https://openalex.org/W6774619220","https://openalex.org/W6787972765","https://openalex.org/W6792622593"],"related_works":["https://openalex.org/W3110137422","https://openalex.org/W3215016102","https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2047513257","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2013643406"],"abstract_inverted_index":{"Deep":[0],"Neural":[1],"Networks":[2],"(DNNs)":[3],"have":[4],"emerged":[5],"as":[6],"an":[7,31,116],"important":[8],"class":[9],"of":[10,21,59,69],"machine":[11],"learning":[12],"algorithms,":[13],"providing":[14],"accurate":[15],"solutions":[16],"to":[17,33,55,79,92,107],"a":[18,88,97,101,120,126],"broad":[19],"range":[20],"applications.":[22],"Sparsity":[23],"in":[24,27],"activation":[25,38,46,70,109],"maps":[26,71],"DNN":[28,94],"training":[29,49,95,166],"presents":[30,40],"opportunity":[32],"reduce":[34,136],"computations.":[35],"However,":[36],"exploiting":[37],"sparsity":[39,47,60,110,118,137],"two":[41],"major":[42],"challenges:":[43],"i)":[44],"profiling":[45,138],"during":[48,76,112],"comes":[50],"with":[51],"significant":[52,80],"overhead":[53,139],"due":[54],"computing":[56],"the":[57,62,66,145,168],"degree":[58],"and":[61,103,125,161],"data":[63],"movement;":[64],"ii)":[65],"dynamic":[67,73],"nature":[68],"requires":[72],"dense-to-sparse":[74],"conversion":[75],"training,":[77],"leading":[78],"overhead.":[81],"In":[82],"this":[83],"article,":[84],"we":[85,152],"present":[86],"Spartan,":[87],"lightweight":[89],"hardware/software":[90],"framework":[91],"accelerate":[93],"on":[96,142,167],"GPU.":[98],"Spartan":[99,114,134],"provides":[100,115],"cost-effective":[102],"programmer-transparent":[104],"microarchitectural":[105],"solution":[106],"exploit":[108],"detected":[111],"training.":[113],"efficient":[117],"monitor,":[119],"tile-based":[121],"sparse":[122],"GEMM":[123],"algorithm,":[124],"novel":[127],"compaction":[128],"engine":[129],"designed":[130],"for":[131],"GPU":[132],"workloads.":[133],"can":[135,153],"by":[140,156,159,163],"52.5\u00d7":[141],"average.":[143],"For":[144],"most":[146],"compute-intensive":[147],"layers,":[148,151],"i.e.,":[149],"convolutional":[150],"speedup":[154],"AlexNet":[155],"3.4\u00d7,":[157],"VGGNet-16":[158],"2.14\u00d7,":[160],"ResNet-18":[162],"2.02\u00d7,":[164],"when":[165],"ImageNet":[169],"dataset.":[170]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}