{"id":"https://openalex.org/W4389046642","doi":"https://doi.org/10.1145/3634703","title":"SparGD: A Sparse GEMM Accelerator with Dynamic Dataflow","display_name":"SparGD: A Sparse GEMM Accelerator with Dynamic Dataflow","publication_year":2023,"publication_date":"2023-11-27","ids":{"openalex":"https://openalex.org/W4389046642","doi":"https://doi.org/10.1145/3634703"},"language":"en","primary_location":{"id":"doi:10.1145/3634703","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3634703","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3634703","source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3634703","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111365385","display_name":"Bo Wang","orcid":"https://orcid.org/0009-0004-9441-0509"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Wang","raw_affiliation_strings":["School of Computer, National University of Defense Technology, China"],"raw_orcid":"https://orcid.org/0009-0004-9441-0509","affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760813","display_name":"Sheng Ma","orcid":"https://orcid.org/0000-0003-1710-4060"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Ma","raw_affiliation_strings":["School of Computer, National University of Defense Technology, China"],"raw_orcid":"https://orcid.org/0000-0003-1710-4060","affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102638449","display_name":"Shengbai Luo","orcid":"https://orcid.org/0009-0007-5551-2897"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengbai Luo","raw_affiliation_strings":["School of Computer, National University of Defense Technology, China"],"raw_orcid":"https://orcid.org/0009-0007-5551-2897","affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009217361","display_name":"Lizhou Wu","orcid":"https://orcid.org/0000-0003-4439-7436"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lizhou Wu","raw_affiliation_strings":["School of Computer, National University of Defense Technology, China"],"raw_orcid":"https://orcid.org/0000-0003-4439-7436","affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111365403","display_name":"Jianmin Zhang","orcid":"https://orcid.org/0000-0002-1008-4805"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianmin Zhang","raw_affiliation_strings":["School of Computer, National University of Defense Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-1008-4805","affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100710936","display_name":"Chunyuan Zhang","orcid":"https://orcid.org/0000-0002-0944-2708"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyuan Zhang","raw_affiliation_strings":["School of Computer, National University of Defense Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-0944-2708","affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101633853","display_name":"Tiejun Li","orcid":"https://orcid.org/0000-0003-1509-1761"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiejun Li","raw_affiliation_strings":["School of Computer, National University of Defense Technology, China"],"raw_orcid":"https://orcid.org/0000-0003-1509-1761","affiliations":[{"raw_affiliation_string":"School of Computer, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":1.3148,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.90857994,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"29","issue":"2","first_page":"1","last_page":"32"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11044","display_name":"Particle Detector Development and Performance","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/3106","display_name":"Nuclear and High Energy Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11044","display_name":"Particle Detector Development and Performance","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/3106","display_name":"Nuclear and High Energy Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9984999895095825,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9973000288009644,"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/dataflow","display_name":"Dataflow","score":0.9341293573379517},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.910722017288208},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.716931939125061},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3980615735054016},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.34330087900161743}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.9341293573379517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.910722017288208},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.716931939125061},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3980615735054016},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.34330087900161743}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3634703","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3634703","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3634703","source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3634703","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3634703","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3634703","source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5099999904632568}],"awards":[{"id":"https://openalex.org/G8613193636","display_name":null,"funder_award_id":"62172430","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389046642.pdf","grobid_xml":"https://content.openalex.org/works/W4389046642.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1999085092","https://openalex.org/W2183057791","https://openalex.org/W2285660444","https://openalex.org/W2289252105","https://openalex.org/W2516141709","https://openalex.org/W2606722458","https://openalex.org/W2618530766","https://openalex.org/W2910096450","https://openalex.org/W2945146780","https://openalex.org/W2953915593","https://openalex.org/W2962949934","https://openalex.org/W2963577671","https://openalex.org/W2979310060","https://openalex.org/W2979439447","https://openalex.org/W3005724337","https://openalex.org/W3019166713","https://openalex.org/W3134012069","https://openalex.org/W3158146252","https://openalex.org/W3159727696","https://openalex.org/W3184376546","https://openalex.org/W3187481008","https://openalex.org/W3213528054","https://openalex.org/W3217357178","https://openalex.org/W4221072574","https://openalex.org/W4225287131","https://openalex.org/W4230315356","https://openalex.org/W4232808712","https://openalex.org/W4236868170","https://openalex.org/W4244024631","https://openalex.org/W4245223843","https://openalex.org/W4245659846","https://openalex.org/W4285789112","https://openalex.org/W4360831848","https://openalex.org/W4381050415"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W2171015181","https://openalex.org/W4239447582","https://openalex.org/W1998888015"],"abstract_inverted_index":{"Deep":[0],"learning":[1,12,48,61],"has":[2,121],"become":[3,51],"a":[4,113,132],"highly":[5,71],"popular":[6],"research":[7],"field,":[8],"and":[9,18,45,67,73,77,93,97,110,128,131,140,152,180],"previously":[10],"deep":[11,26,43,47,60],"algorithms":[13],"ran":[14],"primarily":[15],"on":[16],"CPUs":[17],"GPUs.":[19],"However,":[20],"with":[21,117],"the":[22,37,56,87,95,104,156,161],"rapid":[23],"development":[24],"of":[25,42,55,103],"learning,":[27,44],"it":[28],"was":[29],"discovered":[30],"that":[31,172],"existing":[32],"processors":[33],"could":[34],"not":[35,90],"meet":[36],"specific":[38,122],"large-scale":[39],"computing":[40,162],"requirements":[41],"custom":[46],"accelerators":[49,82],"have":[50,99],"popular.":[52],"The":[53,75],"majority":[54],"primary":[57],"workloads":[58],"in":[59,83],"are":[62,70,79],"general":[63],"matrix-matrix":[64],"multiplications":[65],"(GEMMs),":[66],"emerging":[68],"GEMMs":[69],"sparse":[72,114,139],"irregular.":[74],"TPU":[76,88,96],"SIGMA":[78,98,181],"typical":[80],"GEMM":[81,115],"recent":[84],"years,":[85],"but":[86],"does":[89],"support":[91],"sparsity,":[92,151],"both":[94],"insufficient":[100],"utilization":[101,148],"rates":[102],"Processing":[105],"Element":[106],"(PE).":[107],"We":[108],"design":[109],"implement":[111],"SparGD,":[112],"accelerator":[116],"dynamic":[118],"dataflow.":[119],"SparGD":[120,143,173],"PE":[123,147],"structures,":[124],"flexible":[125],"distribution":[126],"networks":[127],"reduction":[129],"networks,":[130],"simple":[133],"dataflow":[134,158],"switching":[135],"module.":[136],"When":[137],"running":[138],"irregular":[141,166],"GEMMs,":[142,167],"can":[144,153],"maintain":[145],"high":[146],"while":[149],"utilizing":[150],"switch":[154],"to":[155,160],"optimal":[157],"according":[159],"environment.":[163],"For":[164],"sparse,":[165],"our":[168],"experimental":[169],"results":[170],"show":[171],"outperforms":[174],"systolic":[175],"arrays":[176],"by":[177,182],"30":[178],"times":[179],"3.6":[183],"times.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
