{"id":"https://openalex.org/W4412610707","doi":"https://doi.org/10.1109/hpcc64274.2024.00027","title":"HSAMM: A Hybrid-Strassen Algorithm-Based Asynchronous Architecture for Sparse Matrix Multiplication","display_name":"HSAMM: A Hybrid-Strassen Algorithm-Based Asynchronous Architecture for Sparse Matrix Multiplication","publication_year":2024,"publication_date":"2024-12-13","ids":{"openalex":"https://openalex.org/W4412610707","doi":"https://doi.org/10.1109/hpcc64274.2024.00027"},"language":"en","primary_location":{"id":"doi:10.1109/hpcc64274.2024.00027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc64274.2024.00027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on High Performance Computing and Communications (HPCC)","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Lingzhuang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingzhuang Zhang","raw_affiliation_strings":["Lanzhou University,School of Information Science and Engineering,Lanzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lanzhou University,School of Information Science and Engineering,Lanzhou,China","institution_ids":["https://openalex.org/I76214153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074252142","display_name":"Rui Hu","orcid":"https://orcid.org/0000-0002-3771-2920"},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongqing Hu","raw_affiliation_strings":["Lanzhou University,School of Information Science and Engineering,Lanzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lanzhou University,School of Information Science and Engineering,Lanzhou,China","institution_ids":["https://openalex.org/I76214153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100620095","display_name":"Hongrui Zhang","orcid":"https://orcid.org/0009-0006-0920-2452"},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongrui Zhang","raw_affiliation_strings":["Lanzhou University,School of Information Science and Engineering,Lanzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lanzhou University,School of Information Science and Engineering,Lanzhou,China","institution_ids":["https://openalex.org/I76214153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101493762","display_name":"Yilong Jiang","orcid":"https://orcid.org/0000-0001-6218-6400"},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yilong Jiang","raw_affiliation_strings":["Lanzhou University,School of Information Science and Engineering,Lanzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lanzhou University,School of Information Science and Engineering,Lanzhou,China","institution_ids":["https://openalex.org/I76214153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100678900","display_name":"Jun Ma","orcid":"https://orcid.org/0000-0002-9739-0855"},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Ma","raw_affiliation_strings":["Lanzhou University,School of Information Science and Engineering,Lanzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lanzhou University,School of Information Science and Engineering,Lanzhou,China","institution_ids":["https://openalex.org/I76214153"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101512098","display_name":"Yanqi Li","orcid":"https://orcid.org/0000-0003-1366-7771"},"institutions":[{"id":"https://openalex.org/I4210158899","display_name":"Gansu Great Wall Electrical and Electronics Engineering Research Institute","ror":"https://ror.org/05j0ypg59","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210158899"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinglong Li","raw_affiliation_strings":["Tianshui Tianguang Semiconductor Co., LTD,Tianshui,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianshui Tianguang Semiconductor Co., LTD,Tianshui,China","institution_ids":["https://openalex.org/I4210158899"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045333131","display_name":"Anping He","orcid":"https://orcid.org/0000-0003-1913-2057"},"institutions":[{"id":"https://openalex.org/I76214153","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32","country_code":"CN","type":"education","lineage":["https://openalex.org/I76214153"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anping He","raw_affiliation_strings":["Lanzhou University,School of Information Science and Engineering,Lanzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lanzhou University,School of Information Science and Engineering,Lanzhou,China","institution_ids":["https://openalex.org/I76214153"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.43873011,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"127","last_page":"134"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9959999918937683,"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"}},"topics":[{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9959999918937683,"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"}},{"id":"https://openalex.org/T10363","display_name":"Low-power high-performance VLSI design","score":0.9929999709129333,"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":0.9829999804496765,"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/strassen-algorithm","display_name":"Strassen algorithm","score":0.9870141744613647},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7245721220970154},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6475263833999634},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6173851490020752},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.553840160369873},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5130995512008667},{"id":"https://openalex.org/keywords/multiplication-algorithm","display_name":"Multiplication algorithm","score":0.4911646544933319},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4813992977142334},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.46120399236679077},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.44976526498794556},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.18845930695533752},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17902931571006775},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.05908659100532532},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.057309508323669434}],"concepts":[{"id":"https://openalex.org/C39096654","wikidata":"https://www.wikidata.org/wiki/Q728507","display_name":"Strassen algorithm","level":4,"score":0.9870141744613647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7245721220970154},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6475263833999634},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6173851490020752},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.553840160369873},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5130995512008667},{"id":"https://openalex.org/C201290732","wikidata":"https://www.wikidata.org/wiki/Q130762","display_name":"Multiplication algorithm","level":3,"score":0.4911646544933319},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4813992977142334},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.46120399236679077},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.44976526498794556},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.18845930695533752},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17902931571006775},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.05908659100532532},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.057309508323669434},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpcc64274.2024.00027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcc64274.2024.00027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on High Performance Computing and Communications (HPCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313889","display_name":"Lanzhou University","ror":"https://ror.org/01mkqqe32"},{"id":"https://openalex.org/F4320322880","display_name":"Natural Science Foundation of Gansu Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2022219663","https://openalex.org/W2064941923","https://openalex.org/W2071429830","https://openalex.org/W2606722458","https://openalex.org/W2793976828","https://openalex.org/W2794952988","https://openalex.org/W2966509008","https://openalex.org/W3016542674","https://openalex.org/W3016832937","https://openalex.org/W4205680171","https://openalex.org/W4231905827","https://openalex.org/W4321063215","https://openalex.org/W4380874786","https://openalex.org/W6947749875"],"related_works":["https://openalex.org/W2170716619","https://openalex.org/W2145889866","https://openalex.org/W2949595835","https://openalex.org/W2392656174","https://openalex.org/W3204033665","https://openalex.org/W2613375081","https://openalex.org/W4301181185","https://openalex.org/W2269364368","https://openalex.org/W2032839380","https://openalex.org/W1809313304"],"abstract_inverted_index":{"General":[0],"sparse":[1,87,101,109],"matrix-matrix":[2],"multiplication":[3,103],"(SpGEMM)":[4],"is":[5,90,114,136],"a":[6],"fundamental":[7],"computational":[8],"method":[9],"with":[10,79],"wide-ranging":[11],"applications":[12],"in":[13,30,154],"scientific":[14],"simulations,":[15],"machine":[16],"learning,":[17],"and":[18,37,49,71,120,124,132,141,169,178],"image":[19],"processing.":[20],"However,":[21],"when":[22],"tackling":[23],"large-scale":[24],"SpGEMM,":[25],"single-core":[26],"processors":[27,39],"fall":[28],"short":[29],"managing":[31],"the":[32,83,117,122,128,145,172,175,179],"computation-intensive":[33],"tasks,":[34],"while":[35],"multi-core":[36],"many-core":[38],"encounter":[40],"challenges":[41],"such":[42],"as":[43],"complex":[44,64],"scheduling,":[45],"high":[46],"communication":[47],"overhead,":[48],"substantial":[50],"energy":[51],"consumption.":[52],"Existing":[53],"platforms":[54],"for":[55,107,127,159],"SpGEMM":[56,155],"that":[57],"base":[58],"on":[59,116,144],"synchronous":[60],"circuit":[61],"design":[62],"require":[63],"state":[65],"machines":[66],"to":[67,92],"implement":[68],"parsing":[69],"mechanisms,":[70],"they":[72],"suffer":[73],"from":[74],"power":[75],"consumption":[76],"issues":[77],"associated":[78],"clock":[80],"trees.":[81],"Therefore,":[82],"exploration":[84],"of":[85,130,166],"asynchronous":[86,100],"matrix":[88,102],"accelerators":[89],"essential":[91],"address":[93],"these":[94],"issues.":[95],"This":[96],"paper":[97],"presents":[98],"an":[99],"accelerator":[104],"architecture":[105],"designed":[106],"128\u00d7128":[108],"matrices,":[110],"called":[111],"HSAMM,":[112],"which":[113],"based":[115],"Hybrid-Strassen":[118],"algorithm":[119],"employs":[121],"BCSR":[123],"BCSC":[125],"formats":[126],"storage":[129],"input":[131],"output":[133],"matrices.":[134],"HSAMM":[135],"validated":[137],"through":[138],"prototype":[139],"implementation":[140],"performance":[142,152],"evaluation":[143],"FACE-VUP":[146],"platform.":[147],"Simulation":[148],"results":[149],"demonstrate":[150],"significant":[151],"enhancements":[153],"(sparsity":[156],"\u2264":[157],"0.8%)":[158],"int32":[160],"data":[161],"type,":[162],"achieving":[163],"average":[164],"accelerations":[165],"3.2\u00d7,":[167],"8.2\u00d7":[168],"83.3\u00d7":[170],"over":[171],"Intel":[173],"MKL,":[174],"Eigen":[176],"library":[177],"matlab,":[180],"respectively.":[181]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
