{"id":"https://openalex.org/W4378804782","doi":"https://doi.org/10.1109/tcad.2023.3281719","title":"An Efficient Gustavson-Based Sparse Matrix\u2013Matrix Multiplication Accelerator on Embedded FPGAs","display_name":"An Efficient Gustavson-Based Sparse Matrix\u2013Matrix Multiplication Accelerator on Embedded FPGAs","publication_year":2023,"publication_date":"2023-05-31","ids":{"openalex":"https://openalex.org/W4378804782","doi":"https://doi.org/10.1109/tcad.2023.3281719"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2023.3281719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2023.3281719","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"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 Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://dr.ntu.edu.sg/bitstream/10356/169151/2/TCAD3281719.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101832883","display_name":"Shiqing Li","orcid":"https://orcid.org/0000-0002-6875-5691"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Shiqing Li","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086240263","display_name":"Shuo Huai","orcid":"https://orcid.org/0000-0002-4744-304X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shuo Huai","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038598144","display_name":"Weichen Liu","orcid":"https://orcid.org/0000-0001-9348-4662"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Weichen Liu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101832883"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":6.0261,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.96982627,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"42","issue":"12","first_page":"4671","last_page":"4680"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9987000226974487,"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":0.9987000226974487,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.995199978351593,"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/matrix-multiplication","display_name":"Matrix multiplication","score":0.6833333969116211},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.667590320110321},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6172122955322266},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.6018698811531067},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5162584781646729},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48911458253860474},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4434839189052582},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3819437623023987},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23111680150032043},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.20797890424728394},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.18977299332618713},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.13529911637306213},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.13132303953170776},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.10165706276893616},{"id":"https://openalex.org/keywords/computational-chemistry","display_name":"Computational chemistry","score":0.08449485898017883}],"concepts":[{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6833333969116211},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.667590320110321},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6172122955322266},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.6018698811531067},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5162584781646729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48911458253860474},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4434839189052582},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3819437623023987},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23111680150032043},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.20797890424728394},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.18977299332618713},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.13529911637306213},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.13132303953170776},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.10165706276893616},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.08449485898017883},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcad.2023.3281719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2023.3281719","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"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 Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/169151","is_oa":true,"landing_page_url":"https://hdl.handle.net/10356/169151","pdf_url":"https://dr.ntu.edu.sg/bitstream/10356/169151/2/TCAD3281719.pdf","source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:dr.ntu.edu.sg:10356/169151","is_oa":true,"landing_page_url":"https://hdl.handle.net/10356/169151","pdf_url":"https://dr.ntu.edu.sg/bitstream/10356/169151/2/TCAD3281719.pdf","source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5016601650","display_name":null,"funder_award_id":"Academic Research Fund","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"},{"id":"https://openalex.org/G5329702239","display_name":null,"funder_award_id":"M4082282/04INS000515C130","funder_id":"https://openalex.org/F4320320766","funder_display_name":"Nanyang Technological University"},{"id":"https://openalex.org/G6854926366","display_name":null,"funder_award_id":"Tier 2","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"},{"id":"https://openalex.org/G739051916","display_name":null,"funder_award_id":"M4082282","funder_id":"https://openalex.org/F4320320766","funder_display_name":"Nanyang Technological University"},{"id":"https://openalex.org/G901625343","display_name":null,"funder_award_id":"Academic Research F","funder_id":"https://openalex.org/F4320320751","funder_display_name":"Ministry of Education - Singapore"}],"funders":[{"id":"https://openalex.org/F4320320751","display_name":"Ministry of Education - Singapore","ror":"https://ror.org/01kcva023"},{"id":"https://openalex.org/F4320320766","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4378804782.pdf","grobid_xml":"https://content.openalex.org/works/W4378804782.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1482471750","https://openalex.org/W2003168947","https://openalex.org/W2003458338","https://openalex.org/W2010370862","https://openalex.org/W2020545624","https://openalex.org/W2035080386","https://openalex.org/W2089437293","https://openalex.org/W2089939118","https://openalex.org/W2121564430","https://openalex.org/W2294458850","https://openalex.org/W2321154369","https://openalex.org/W2535419693","https://openalex.org/W2794952988","https://openalex.org/W2915106038","https://openalex.org/W2917336187","https://openalex.org/W2998631742","https://openalex.org/W3016832937","https://openalex.org/W3103168911","https://openalex.org/W3155922894","https://openalex.org/W3198975860","https://openalex.org/W3205727737","https://openalex.org/W3212950641","https://openalex.org/W4200467342","https://openalex.org/W4226337995","https://openalex.org/W4242679152","https://openalex.org/W4321637181","https://openalex.org/W4379116149","https://openalex.org/W6810821987"],"related_works":["https://openalex.org/W3099313426","https://openalex.org/W4287593139","https://openalex.org/W752783541","https://openalex.org/W1506547947","https://openalex.org/W2995605830","https://openalex.org/W4206811032","https://openalex.org/W2086123442","https://openalex.org/W2596457687","https://openalex.org/W3212757063","https://openalex.org/W2093666864"],"abstract_inverted_index":{"Sparse":[0],"matrix\u2013matrix":[1],"multiplication":[2],"(SpMM)":[3],"is":[4,35],"an":[5,89,253],"important":[6],"kernel":[7],"in":[8,215],"multiple":[9],"areas,":[10],"e.g.,":[11],"data":[12,26],"analytics":[13],"and":[14,28,71,111,125,183,186,219],"machine":[15],"learning.":[16],"Due":[17],"to":[18,78,127,156,174,188,201,265],"the":[19,24,29,46,52,55,102,112,120,123,129,136,152,203,216,229,240,249,266],"low":[20],"on-chip":[21],"memory":[22,48,106,181],"requirement,":[23],"consistent":[25],"format,":[27],"simplified":[30],"control":[31],"logic,":[32],"Gustavson\u2019s":[33,64,115],"algorithm":[34,39,65,124,130],"a":[36,148,162,235],"promising":[37],"backbone":[38],"for":[40],"SpMM":[41,92],"on":[42,58,94,108,205,228],"hardware":[43],"accelerators.":[44],"However,":[45],"off-chip":[47,105],"traffic":[49],"still":[50],"limits":[51],"performance":[53,262],"of":[54,104,114,122,139,195,207,237],"algorithm,":[56],"especially":[57],"embedded":[59,79,95,109],"FPGAs.":[60,96],"Previous":[61],"researchers":[62],"optimize":[63],"targeting":[66],"high":[67],"bandwidth":[68],"memory-based":[69],"architectures":[70],"their":[72],"solutions":[73],"cannot":[74],"be":[75],"directly":[76],"applied":[77],"FPGAs":[80,110],"with":[81,131,234],"traditional":[82,153],"DDRs.":[83],"In":[84],"this":[85],"work,":[86],"we":[87,118,146,160,199,225],"propose":[88,126,161,200],"efficient":[90],"Gustavson-based":[91],"accelerator":[93],"The":[97,244],"proposed":[98,250],"design":[99,251],"fully":[100],"considers":[101],"feature":[103],"access":[107,164,192],"dataflow":[113],"algorithm.":[116],"First,":[117],"analyze":[119],"parallelism":[121],"perform":[128,202],"element-wise":[132],"parallelism,":[133],"which":[134,170,210],"reduces":[135],"idle":[137],"time":[138],"processing":[140],"elements":[141,194],"caused":[142,178],"by":[143,179],"synchronization.":[144],"Further,":[145],"show":[147,247],"counter-intuitive":[149],"example":[150],"that":[151,191,248],"cache":[154,166],"leads":[155],"worse":[157],"performance.":[158],"Then,":[159],"novel":[163],"pattern-aware":[165],"scheme":[167],"called":[168],"SpCache,":[169],"provides":[171],"quick":[172],"responses":[173],"reduce":[175],"bank":[176],"conflicts":[177],"irregular":[180],"accesses":[182],"combines":[184],"streaming":[185],"caching":[187],"handle":[189],"requests":[190],"ordered":[193],"unpredictable":[196],"length.":[197],"Moreover,":[198],"merge":[204],"part":[206],"partial":[208],"results,":[209],"removes":[211],"some":[212],"redundant":[213],"merges":[214],"naive":[217],"implementation":[218],"has":[220],"little":[221],"postprocessing":[222],"overhead.":[223],"Finally,":[224],"conduct":[226],"experiments":[227],"Xilinx":[230],"Zynq-UltraScale":[231],"ZCU106":[232],"platform":[233],"set":[236],"benchmarks":[238],"from":[239],"SuiteSparse":[241],"matrix":[242],"collection.":[243],"experimental":[245],"results":[246],"achieves":[252],"average":[254],"<inline-formula":[255],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[256],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[257],"<tex-math":[258],"notation=\"LaTeX\">$1.75\\times":[259],"$":[260],"</tex-math></inline-formula>":[261],"speedup":[263],"compared":[264],"baseline.":[267]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-12T07:58:50.170612","created_date":"2025-10-10T00:00:00"}
