{"id":"https://openalex.org/W4412891128","doi":"https://doi.org/10.1145/3747847","title":"SpMARD: A Sparse-Sparse Matrix Multiplication Accelerator with Reconfigurable Dataflow for DNN Workloads","display_name":"SpMARD: A Sparse-Sparse Matrix Multiplication Accelerator with Reconfigurable Dataflow for DNN Workloads","publication_year":2025,"publication_date":"2025-08-04","ids":{"openalex":"https://openalex.org/W4412891128","doi":"https://doi.org/10.1145/3747847"},"language":"en","primary_location":{"id":"doi:10.1145/3747847","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3747847","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"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 Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1145/3747847","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":["College of Computer Science and Technology, National University of Defense Technology","College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0004-9441-0509","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, 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":["College of Computer Science and Technology, National University of Defense Technology","College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-1710-4060","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020072616","display_name":"Yunping Zhao","orcid":"https://orcid.org/0000-0002-5600-3740"},"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":"Yunping Zhao","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology","College of Computer Science and Technology, National University of Defense Technology, changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-5600-3740","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, changsha, 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":["College of Computer Science and Technology, National University of Defense Technology","College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0007-5551-2897","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, 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":["College of Computer Science and Technology, National University of Defense Technology","College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-4439-7436","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, 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":["College of Computer Science and Technology, National University of Defense Technology","College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-1008-4805","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440903","display_name":"Dongsheng Li","orcid":"https://orcid.org/0000-0001-9743-2034"},"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":"Dongsheng Li","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology","College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-9743-2034","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","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":["College of Computer Science and Technology, National University of Defense Technology","College of Computer Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-1509-1761","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027732281","display_name":"Zhuojun Chen","orcid":"https://orcid.org/0000-0003-0431-8852"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]},{"id":"https://openalex.org/I198357462","display_name":"Changsha University","ror":"https://ror.org/011d8sm39","country_code":"CN","type":"education","lineage":["https://openalex.org/I198357462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuojun Chen","raw_affiliation_strings":["School of Physics & Electronics, Hunan University","School of Physics & Electronics, Hunan University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-0431-8852","affiliations":[{"raw_affiliation_string":"School of Physics & Electronics, Hunan University","institution_ids":["https://openalex.org/I16609230"]},{"raw_affiliation_string":"School of Physics & Electronics, Hunan University, Changsha, China","institution_ids":["https://openalex.org/I16609230","https://openalex.org/I198357462"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11715611,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"3","first_page":"1","last_page":"23"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9997000098228455,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.8568140268325806},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8346397876739502},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6897633075714111},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6455401182174683},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6285884380340576},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5326895713806152},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4310323894023895},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4258694052696228},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4152320325374603}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8568140268325806},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8346397876739502},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6897633075714111},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6455401182174683},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6285884380340576},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5326895713806152},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4310323894023895},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4258694052696228},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4152320325374603},{"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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3747847","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3747847","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"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 Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3747847","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3747847","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"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 Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2450220850","display_name":null,"funder_award_id":"62472435, 62025208, 62172430","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2618530766","https://openalex.org/W2794952988","https://openalex.org/W2948634622","https://openalex.org/W2979310060","https://openalex.org/W2984140583","https://openalex.org/W3006363700","https://openalex.org/W3016542674","https://openalex.org/W3016832937","https://openalex.org/W3040646053","https://openalex.org/W3103168911","https://openalex.org/W3155922894","https://openalex.org/W3184376546","https://openalex.org/W3210117238","https://openalex.org/W4244024631","https://openalex.org/W4285335127","https://openalex.org/W4293024984","https://openalex.org/W4318540786","https://openalex.org/W4327930477","https://openalex.org/W4381050415","https://openalex.org/W4386764750","https://openalex.org/W4389046642","https://openalex.org/W4393407064","https://openalex.org/W4401212175","https://openalex.org/W4401753418","https://openalex.org/W4404133827","https://openalex.org/W4404955137","https://openalex.org/W4405399416"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W4318347836","https://openalex.org/W2995605830","https://openalex.org/W4206811032","https://openalex.org/W2086123442","https://openalex.org/W2596457687","https://openalex.org/W3212757063"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"becomes":[2],"increasingly":[3],"popular,":[4],"and":[5,56,63,75,81,91,97,120,138,196],"its":[6],"main":[7],"workload":[8],"is":[9,77,117,185],"Sparse-Sparse":[10],"Matrix":[11],"Multiplication":[12],"(SpMSpM).":[13],"Most":[14],"SpMSpM":[15,107,175],"accelerators":[16,49],"usually":[17],"only":[18],"support":[19,84,123],"a":[20,106,132,139,163],"single":[21],"dataflow.":[22,87,111],"Different":[23],"dataflows":[24,95,170],"have":[25],"different":[26,29,54],"performance":[27,40,178],"in":[28,41],"computing":[30],"environments.":[31,43],"Therefore,":[32],"the":[33,38,58,70,129,152,156,174,177,181],"single-dataflow":[34,46],"accelerator":[35,108],"cannot":[36,83,93],"maintain":[37],"highest":[39],"all":[42],"Compared":[44],"with":[45,109],"accelerators,":[47],"multi-dataflow":[48,67],"provide":[50],"flexible":[51],"options":[52],"for":[53],"workloads":[55],"improve":[57],"overall":[59],"performance.":[60],"Flexagon,":[61,89,190],"Sparm,":[62,90,195],"SPADA":[64,82,92],"are":[65],"state-of-the-art":[66],"accelerators.":[68],"However,":[69],"computation":[71,113],"process":[72,114],"of":[73,115,131,159,180,189,194,200],"Flexagon":[74],"Sparm":[76],"not":[78],"fully":[79,118],"pipelined,":[80,119],"inner":[85],"product":[86],"Additionally,":[88],"switch":[94,169],"quickly":[96],"accurately.":[98],"Inspired":[99],"by":[100],"these":[101],"observations,":[102],"we":[103,161,183],"present":[104],"SpMARD,":[105],"reconfigurable":[110],"The":[112],"SpMARD":[116,121,144,182],"can":[122,145,150,168],"six":[124],"dataflow":[125],"variants":[126],"simultaneously.":[127],"Through":[128,155],"design":[130],"Two-stage":[133],"Pipeline":[134],"Adder":[135],"Network":[136],"(TPAN)":[137],"Position-based":[140],"Psum":[141],"Array":[142],"(PPA),":[143],"execute":[146],"element-level":[147],"merging,":[148],"which":[149,167],"hide":[151],"merging":[153],"overhead.":[154],"quantitative":[157],"analysis":[158],"dataflows,":[160],"implement":[162],"Dataflow":[164],"Switcher":[165],"(DSwitcher),":[166],"more":[171],"efficiently.":[172],"For":[173],"workload,":[176],"(GOPS)":[179],"proposed":[184],"1.27":[186],"times":[187,192,198],"that":[188,193,199],"1.18":[191],"1.22":[197],"SPADA.":[201]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
