{"id":"https://openalex.org/W4318685745","doi":"https://doi.org/10.1145/3566097.3567839","title":"Towards High-Bandwidth-Utilization SpMV on FPGAs via Partial Vector Duplication","display_name":"Towards High-Bandwidth-Utilization SpMV on FPGAs via Partial Vector Duplication","publication_year":2023,"publication_date":"2023-01-16","ids":{"openalex":"https://openalex.org/W4318685745","doi":"https://doi.org/10.1145/3566097.3567839"},"language":"en","primary_location":{"id":"doi:10.1145/3566097.3567839","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3566097.3567839","pdf_url":null,"source":{"id":"https://openalex.org/S4363608968","display_name":"Proceedings of the 28th Asia and South Pacific Design Automation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th Asia and South Pacific Design Automation Conference","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/A5053865422","display_name":"Bowen Liu","orcid":"https://orcid.org/0000-0001-5297-0795"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bowen Liu","raw_affiliation_strings":["Chongqing University"],"affiliations":[{"raw_affiliation_string":"Chongqing University","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102986560","display_name":"Dajiang Liu","orcid":"https://orcid.org/0000-0002-1591-0635"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dajiang Liu","raw_affiliation_strings":["Chongqing University"],"affiliations":[{"raw_affiliation_string":"Chongqing University","institution_ids":["https://openalex.org/I158842170"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053865422"],"corresponding_institution_ids":["https://openalex.org/I158842170"],"apc_list":null,"apc_paid":null,"fwci":3.9623,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.92753623,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"33","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9987999796867371,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9977999925613403,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8758094310760498},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6245601177215576},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5595265030860901},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5196762681007385},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4952303469181061},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.31944745779037476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8758094310760498},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6245601177215576},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5595265030860901},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5196762681007385},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4952303469181061},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.31944745779037476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3566097.3567839","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3566097.3567839","pdf_url":null,"source":{"id":"https://openalex.org/S4363608968","display_name":"Proceedings of the 28th Asia and South Pacific Design Automation Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th Asia and South Pacific Design Automation Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2004455575","https://openalex.org/W2955092019","https://openalex.org/W3043072009","https://openalex.org/W4200467342"],"related_works":["https://openalex.org/W2317245370","https://openalex.org/W1980160788","https://openalex.org/W198851386","https://openalex.org/W2030310580","https://openalex.org/W947442053","https://openalex.org/W2148915962","https://openalex.org/W4313433561","https://openalex.org/W2283866686","https://openalex.org/W4287182096","https://openalex.org/W27867058"],"abstract_inverted_index":{"Sparse":[0],"matrix-vector":[1],"multiplication":[2],"(SpMV)":[3],"is":[4,32,54,70],"widely":[5],"used":[6],"in":[7],"many":[8],"fields":[9],"and":[10,27,130],"usually":[11,47],"dominates":[12],"the":[13,82,93,143,156],"execution":[14],"time":[15],"of":[16,84,150],"a":[17,33,65,71,103,113],"task.":[18],"With":[19],"large":[20],"off-chip":[21],"memory":[22,50,79,99],"bandwidth,":[23],"customizable":[24],"on-chip":[25],"resources":[26],"high-performance":[28],"float-point":[29],"operation,":[30],"FPGA":[31,62,138],"potential":[34],"platform":[35],"to":[36,63,90,102,155],"accelerate":[37],"SpMV":[38,46,59,115],"tasks.":[39],"However,":[40],"as":[41],"compressed":[42],"data":[43,86],"formats":[44],"for":[45],"introduce":[48],"irregular":[49,78,98],"access":[51,80],"while":[52],"it":[53],"also":[55],"memory-intensive,":[56],"implementing":[57],"an":[58,148],"accelerator":[60,116],"on":[61,117],"achieve":[64,147],"high":[66],"bandwidth":[67],"utilization":[68],"(BU)":[69],"challenging":[72],"work.":[73,158],"Existing":[74],"works":[75],"either":[76],"eliminate":[77],"at":[81],"sacrifice":[83],"increasing":[85],"redundancy":[87],"or":[88],"try":[89],"locally":[91],"reduce":[92],"port":[94],"conflicts":[95],"introduced":[96],"by":[97],"access,":[100],"leading":[101],"limited":[104],"BU":[105],"improvement.":[106],"To":[107],"this":[108,110],"end,":[109],"paper":[111],"proposes":[112],"high-bandwidth-utilization":[114],"FPGAs":[118],"using":[119],"partial":[120],"vector":[121,125],"duplication,":[122],"where":[123],"read-conflict-free":[124],"buffer,":[126],"writing-conflict-free":[127],"adder":[128],"tree,":[129],"ping-pong-like":[131],"accumulator":[132],"registers":[133],"are":[134],"well":[135],"elaborated.":[136],"The":[137],"implementation":[139],"results":[140],"show":[141],"that":[142],"proposed":[144],"design":[145],"can":[146],"average":[149],"1.10x":[151],"performance":[152],"speedup":[153],"compared":[154],"state-of-the-art":[157]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
