{"id":"https://openalex.org/W4391468153","doi":"https://doi.org/10.1109/tvlsi.2024.3355499","title":"FSpGEMM: A Framework for Accelerating Sparse General Matrix\u2013Matrix Multiplication Using Gustavson\u2019s Algorithm on FPGAs","display_name":"FSpGEMM: A Framework for Accelerating Sparse General Matrix\u2013Matrix Multiplication Using Gustavson\u2019s Algorithm on FPGAs","publication_year":2024,"publication_date":"2024-02-02","ids":{"openalex":"https://openalex.org/W4391468153","doi":"https://doi.org/10.1109/tvlsi.2024.3355499"},"language":"en","primary_location":{"id":"doi:10.1109/tvlsi.2024.3355499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2024.3355499","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"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 Very Large Scale Integration (VLSI) Systems","raw_type":"journal-article"},"type":"article","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":"https://openalex.org/A5078467314","display_name":"Erfan Bank Tavakoli","orcid":"https://orcid.org/0000-0002-3248-9301"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Erfan Bank Tavakoli","raw_affiliation_strings":["Arizona State University, Tempe, AZ, USA"],"raw_orcid":"https://orcid.org/0000-0002-3248-9301","affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064382372","display_name":"Michael Riera","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Riera","raw_affiliation_strings":["Arizona State University, Tempe, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040424471","display_name":"Masudul Hassan Quraishi","orcid":"https://orcid.org/0000-0001-6939-1669"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Masudul Hassan Quraishi","raw_affiliation_strings":["Arizona State University, Tempe, AZ, USA"],"raw_orcid":"https://orcid.org/0000-0001-6939-1669","affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083744126","display_name":"Fengbo Ren","orcid":"https://orcid.org/0000-0002-6509-8753"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fengbo Ren","raw_affiliation_strings":["Arizona State University, Tempe, AZ, USA"],"raw_orcid":"https://orcid.org/0000-0002-6509-8753","affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078467314"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":4.7435,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.95967642,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"32","issue":"4","first_page":"633","last_page":"644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9966999888420105,"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":0.9966999888420105,"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/T11693","display_name":"Cryptography and Residue Arithmetic","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11130","display_name":"Coding theory and cryptography","score":0.9926000237464905,"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/matrix-multiplication","display_name":"Matrix multiplication","score":0.6197175979614258},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.6126654744148254},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6046948432922363},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.602327287197113},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5454609394073486},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5294256806373596},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5021157264709473},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.459835946559906},{"id":"https://openalex.org/keywords/matrix-algebra","display_name":"Matrix algebra","score":0.44825008511543274},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3613603711128235},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2310989797115326},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.22052502632141113},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.16503489017486572},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12477979063987732},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.06640607118606567}],"concepts":[{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6197175979614258},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.6126654744148254},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6046948432922363},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.602327287197113},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5454609394073486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5294256806373596},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5021157264709473},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.459835946559906},{"id":"https://openalex.org/C2988995629","wikidata":"https://www.wikidata.org/wiki/Q2915729","display_name":"Matrix algebra","level":3,"score":0.44825008511543274},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3613603711128235},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2310989797115326},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.22052502632141113},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.16503489017486572},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12477979063987732},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.06640607118606567},{"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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tvlsi.2024.3355499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2024.3355499","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"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 Very Large Scale Integration (VLSI) Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6571019166","display_name":null,"funder_award_id":"IIS/CPS-1652038","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W111684325","https://openalex.org/W1973918431","https://openalex.org/W1985312666","https://openalex.org/W1985938427","https://openalex.org/W1997542937","https://openalex.org/W2014730252","https://openalex.org/W2035080386","https://openalex.org/W2038071684","https://openalex.org/W2089939118","https://openalex.org/W2095249664","https://openalex.org/W2114977680","https://openalex.org/W2126004407","https://openalex.org/W2129419431","https://openalex.org/W2134237243","https://openalex.org/W2286210831","https://openalex.org/W2321154369","https://openalex.org/W2605739168","https://openalex.org/W2751658790","https://openalex.org/W2794952988","https://openalex.org/W2808128431","https://openalex.org/W2902593271","https://openalex.org/W2914086833","https://openalex.org/W2914631005","https://openalex.org/W2962780877","https://openalex.org/W2997329429","https://openalex.org/W2999347085","https://openalex.org/W3000305333","https://openalex.org/W3016832937","https://openalex.org/W3035154866","https://openalex.org/W3103168911","https://openalex.org/W3155922894","https://openalex.org/W3191577936","https://openalex.org/W3202303936","https://openalex.org/W4220912491","https://openalex.org/W4236868170","https://openalex.org/W4308075209","https://openalex.org/W4327911434","https://openalex.org/W4378804782","https://openalex.org/W4379116149","https://openalex.org/W6675533150","https://openalex.org/W6696080121","https://openalex.org/W6750122613"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W4206811032","https://openalex.org/W2995605830","https://openalex.org/W4239424132","https://openalex.org/W2596457687","https://openalex.org/W3212757063","https://openalex.org/W2086123442"],"abstract_inverted_index":{"General":[0],"sparse":[1,121,127,186],"matrix\u2013matrix":[2],"multiplication":[3],"(SpGEMM)":[4],"is":[5],"integral":[6],"to":[7,51,95,113,138],"many":[8],"high-performance":[9],"computing":[10],"(HPC)":[11],"and":[12,32,49,80,129,142,160,180,246],"machine":[13],"learning":[14],"applications.":[15],"However,":[16],"prior":[17],"field-programmable":[18],"gate":[19],"array":[20],"(FPGA)-based":[21],"SpGEMM":[22,62,66],"accelerators":[23],"either":[24],"use":[25],"the":[26,97,164,190,204,208,216,221,243],"inner":[27],"product":[28],"algorithm":[29,37,71,115],"with":[30,38,85,182,215,242],"wasted":[31],"costly":[33],"operations":[34],"or":[35,89],"Gustavson\u2019s":[36,104,114],"a":[39,78,108,118,130,135,150,183,195,251],"cache-based":[40],"hardware":[41,82],"architecture":[42,83],"suffering":[43],"from":[44,189],"long-latency":[45],"cache":[46],"miss":[47],"penalties":[48],"limited":[50],"embedded":[52],"devices.":[53],"In":[54,93],"this":[55],"work,":[56],"we":[57,106],"propose":[58,107],"framework":[59,67,148],"for":[60,68,125,156,168,178,250],"accelerating":[61,69],"(FSpGEMM),":[63],"an":[64,74,227],"OpenCL-based":[65],"Gustvason\u2019s":[70],"that":[72,203],"includes":[73,149],"FPGA":[75,176,198,224],"kernel":[76],"implementing":[77,153],"throughput-optimized":[79],"scalable":[81],"compatible":[84],"high-bandwidth":[86],"memory":[87,99,247],"(HBM)":[88],"traditional":[90],"DDR-based":[91],"memory.":[92],"addition,":[94],"address":[96],"irregular":[98],"access":[100],"patterns":[101],"incurred":[102],"by":[103,117,212,226],"algorithm,":[105],"new":[109,119],"buffering":[110],"scheme":[111],"tailored":[112],"enabled":[116],"compressed":[120],"vector":[122],"(CSV)":[123],"format":[124,167],"representing":[126],"matrices":[128,159,187],"row":[131],"reordering":[132,157,205],"technique":[133,206],"as":[134],"preprocessing":[136,154],"step":[137],"improve":[139],"data":[140],"reuse,":[141],"consequently,":[143],"resource":[144],"utilization.":[145],"The":[146,200],"proposed":[147,165],"host":[151],"program":[152],"functions":[155],"input":[158],"storing":[161],"them":[162],"in":[163,237],"CSV":[166],"further":[169],"use.":[170],"We":[171],"implemented":[172],"FSpGEMM":[173,219],"using":[174],"Intel":[175],"SDK":[177],"OpenCL":[179],"experimented":[181],"benchmark":[184,245],"of":[185,229,239],"selected":[188],"SuiteSparse":[191],"Matrix":[192],"Collection":[193],"on":[194,210],"Bittware":[196],"520N-MX":[197],"board.":[199],"results":[201],"show":[202],"improves":[207],"performance":[209],"average":[211,228],"20.3%":[213],"compared":[214],"baseline.":[217],"Finally,":[218],"outperforms":[220],"state-of-the-art":[222],"(SOTA)":[223],"implementation":[225],"<inline-formula":[230],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[231],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[232],"<tex-math":[233],"notation=\"LaTeX\">$2.23\\times":[234],"$":[235],"</tex-math></inline-formula>":[236],"terms":[238],"execution":[240],"cycles":[241],"same":[244],"system":[248],"configuration":[249],"fair":[252],"comparison.":[253]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}