{"id":"https://openalex.org/W4401568107","doi":"https://doi.org/10.23919/date58400.2024.10546672","title":"Cuper: Customized Dataflow and Perceptual Decoding for Sparse Matrix-Vector Multiplication on HBM-Equipped FPGAs","display_name":"Cuper: Customized Dataflow and Perceptual Decoding for Sparse Matrix-Vector Multiplication on HBM-Equipped FPGAs","publication_year":2024,"publication_date":"2024-03-25","ids":{"openalex":"https://openalex.org/W4401568107","doi":"https://doi.org/10.23919/date58400.2024.10546672"},"language":"en","primary_location":{"id":"doi:10.23919/date58400.2024.10546672","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date58400.2024.10546672","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Design, Automation &amp;amp; Test in Europe Conference &amp;amp; Exhibition (DATE)","raw_type":"proceedings-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/A5001168716","display_name":"Enxin Yi","orcid":"https://orcid.org/0009-0000-0286-9429"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Enxin Yi","raw_affiliation_strings":["China University of Petroleum,Super Scientific Software Laboratory,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Petroleum,Super Scientific Software Laboratory,Beijing,China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112733268","display_name":"Yiru Duan","orcid":null},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiru Duan","raw_affiliation_strings":["China University of Petroleum,Super Scientific Software Laboratory,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Petroleum,Super Scientific Software Laboratory,Beijing,China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022952712","display_name":"Yinuo Bai","orcid":"https://orcid.org/0009-0005-5668-4610"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinuo Bai","raw_affiliation_strings":["China University of Petroleum,Super Scientific Software Laboratory,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Petroleum,Super Scientific Software Laboratory,Beijing,China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027087200","display_name":"Kang Zhao","orcid":"https://orcid.org/0000-0003-0502-8523"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kang Zhao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Department of Integrated Circuits,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Department of Integrated Circuits,China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057257864","display_name":"Zhou Jin","orcid":"https://orcid.org/0000-0002-0632-9494"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Jin","raw_affiliation_strings":["China University of Petroleum,Super Scientific Software Laboratory,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Petroleum,Super Scientific Software Laboratory,Beijing,China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100444152","display_name":"Weifeng Liu","orcid":"https://orcid.org/0000-0002-2150-5759"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weifeng Liu","raw_affiliation_strings":["China University of Petroleum,Super Scientific Software Laboratory,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China University of Petroleum,Super Scientific Software Laboratory,Beijing,China","institution_ids":["https://openalex.org/I204553293"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001168716"],"corresponding_institution_ids":["https://openalex.org/I204553293"],"apc_list":null,"apc_paid":null,"fwci":2.0572,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.87185462,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10363","display_name":"Low-power high-performance VLSI design","score":0.9919999837875366,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9919999837875366,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9919000267982483,"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/T11034","display_name":"Digital Filter Design and Implementation","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7454255223274231},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.7001845836639404},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6691932082176208},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6602337956428528},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6518685817718506},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5972156524658203},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.491190642118454},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4647362232208252},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4437468349933624},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.4202331304550171},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.41734012961387634},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25085437297821045},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.20389169454574585},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19236460328102112},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13249054551124573},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.07156190276145935}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7454255223274231},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.7001845836639404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6691932082176208},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6602337956428528},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6518685817718506},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5972156524658203},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.491190642118454},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4647362232208252},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4437468349933624},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.4202331304550171},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.41734012961387634},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25085437297821045},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.20389169454574585},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19236460328102112},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13249054551124573},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.07156190276145935},{"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/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},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date58400.2024.10546672","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date58400.2024.10546672","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Design, Automation &amp;amp; Test in Europe Conference &amp;amp; Exhibition (DATE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8979851392","display_name":null,"funder_award_id":"U23A20301,62204265","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2035080386","https://openalex.org/W2955092019","https://openalex.org/W2998631742","https://openalex.org/W3133347161","https://openalex.org/W3175189837","https://openalex.org/W3198975860","https://openalex.org/W3206136464","https://openalex.org/W4200197440","https://openalex.org/W4200467342","https://openalex.org/W4211147898","https://openalex.org/W4293024216","https://openalex.org/W4318685745"],"related_works":["https://openalex.org/W2999668243","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"],"abstract_inverted_index":{"Sparse":[0],"matrix-vector":[1],"multiplication":[2],"(<tex>$S$</tex>pMV)":[3],"is":[4,27,67],"pivotal":[5],"in":[6,23],"many":[7],"scientific":[8],"computing":[9],"and":[10,17,108,125,149,155,167,179,188],"engineering":[11],"applications.":[12],"Considering":[13],"the":[14,31,38,53,85,91,96,122,141,159,171,195],"memory-intensive":[15],"nature":[16],"irregular":[18],"data":[19],"access":[20,65],"patterns":[21],"inherent":[22],"SpMV,":[24],"its":[25],"acceleration":[26],"typically":[28],"bounded":[29],"by":[30,151],"limited":[32],"bandwidth.":[33],"Multiple":[34],"memory":[35,42,64,127],"channels":[36],"of":[37,55,131,192],"emerging":[39],"high":[40,59],"bandwidth":[41,60,97,161],"(HBM)":[43],"provide":[44],"exceptional":[45],"bandwidth,":[46],"offering":[47],"a":[48,76,104],"great":[49],"opportunity":[50],"to":[51,87,115],"boost":[52],"performance":[54],"SpMV.":[56],"However,":[57],"ensuring":[58],"utilization":[61,98],"with":[62,90],"low":[63],"conflicts":[66],"still":[68],"non-trivial.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73],"present":[74],"Cuper,":[75],"high-performance":[77],"SpMV":[78,144],"accelerator":[79],"on":[80,198],"HBM-equipped":[81],"FPGAs.":[82],"Through":[83],"customizing":[84],"dataflow":[86],"be":[88,100],"HBM-compatible":[89],"proposed":[92],"sparse":[93],"storage":[94],"format,":[95],"can":[99],"sufficiently":[101],"enhanced.":[102],"Furthermore,":[103,158],"two-step":[105],"reordering":[106],"algorithm":[107],"perceptual":[109],"decoder-centric":[110],"hardware":[111],"architecture":[112],"are":[113],"designed":[114],"greatly":[116],"mitigate":[117],"read-after-write":[118],"(RAW)":[119],"conflicts,":[120],"enhance":[121],"vector":[123],"reusability":[124],"on-chip":[126],"utilization.":[128],"The":[129],"evaluation":[130],"12":[132],"large":[133],"matrices":[134],"shows":[135,163],"that":[136],"Cuper's":[137],"geomean":[138,160,172],"throughput":[139,187],"outperforms":[140],"four":[142],"latest":[143],"accelerators":[145],"HiSparse,":[146],"GraphLily,":[147],"Sextans,":[148],"Serpens,":[150],"3.28\u00d7,":[152,164],"1.99\u00d7,":[153],"1.75\u00d7,":[154],"1.44\u00d7,":[156],"respectively.":[157,182],"efficiency":[162,174,191],"2.20\u00d7,":[165],"2.82\u00d7,":[166],"1.31x":[168],"improvements,":[169],"while":[170],"energy":[173,190],"has":[175],"3.59\u00d7,":[176],"2.08\u00d7,":[177],"2.21\u00d7,":[178],"1.44\u00d7":[180],"optimizations,":[181],"Cuper":[183],"also":[184],"demonstrates":[185],"2.51\u00d7":[186],"7.97\u00d7":[189],"improvement":[193],"over":[194],"K80":[196],"GPU":[197],"2,757":[199],"SuiteSparse":[200],"matrices.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5}],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2025-10-10T00:00:00"}