{"id":"https://openalex.org/W4319870564","doi":"https://doi.org/10.1145/3543622.3573152","title":"Graph-OPU: An FPGA-Based Overlay Processor for Graph Neural Networks","display_name":"Graph-OPU: An FPGA-Based Overlay Processor for Graph Neural Networks","publication_year":2023,"publication_date":"2023-02-10","ids":{"openalex":"https://openalex.org/W4319870564","doi":"https://doi.org/10.1145/3543622.3573152"},"language":"en","primary_location":{"id":"doi:10.1145/3543622.3573152","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543622.3573152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"},"type":"conference-abstract","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/A5100761386","display_name":"Ruiqi Chen","orcid":"https://orcid.org/0000-0001-6837-5675"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiqi Chen","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-6837-5675","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056063611","display_name":"Haoyang Zhang","orcid":"https://orcid.org/0000-0003-4496-4752"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyang Zhang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4496-4752","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053646739","display_name":"Yuhanxiao Ma","orcid":"https://orcid.org/0000-0003-0958-6397"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuhanxiao Ma","raw_affiliation_strings":["New York University, New York, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-0958-6397","affiliations":[{"raw_affiliation_string":"New York University, New York, NY, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056576567","display_name":"Enhao Tang","orcid":"https://orcid.org/0000-0002-0539-8885"},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enhao Tang","raw_affiliation_strings":["Fuzhou University, Fuzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0539-8885","affiliations":[{"raw_affiliation_string":"Fuzhou University, Fuzhou, China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442626","display_name":"Shun Li","orcid":"https://orcid.org/0000-0001-9003-8966"},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shun Li","raw_affiliation_strings":["Fuzhou University, Fuzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9003-8966","affiliations":[{"raw_affiliation_string":"Fuzhou University, Fuzhou, China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055272142","display_name":"Yanxiang Zhu","orcid":"https://orcid.org/0000-0002-5014-3419"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanxiang Zhu","raw_affiliation_strings":["VeriMake Innovation Lab, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-5014-3419","affiliations":[{"raw_affiliation_string":"VeriMake Innovation Lab, Nanjing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103098516","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0003-4286-9292"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4286-9292","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015932760","display_name":"Kun Wang","orcid":"https://orcid.org/0000-0002-7288-1789"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Wang","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7288-1789","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"49","last_page":"49"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9950000047683716,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9950000047683716,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9939000010490417,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9778000116348267,"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/computer-science","display_name":"Computer science","score":0.8472598791122437},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7169903516769409},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6146562695503235},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.600462019443512},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5430381894111633},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5132872462272644},{"id":"https://openalex.org/keywords/control-reconfiguration","display_name":"Control reconfiguration","score":0.48667222261428833},{"id":"https://openalex.org/keywords/datapath","display_name":"Datapath","score":0.43034934997558594},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3806348443031311},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3053845167160034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8472598791122437},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7169903516769409},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6146562695503235},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.600462019443512},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5430381894111633},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5132872462272644},{"id":"https://openalex.org/C119701452","wikidata":"https://www.wikidata.org/wiki/Q5165881","display_name":"Control reconfiguration","level":2,"score":0.48667222261428833},{"id":"https://openalex.org/C2781198647","wikidata":"https://www.wikidata.org/wiki/Q1633673","display_name":"Datapath","level":2,"score":0.43034934997558594},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3806348443031311},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3053845167160034},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3543622.3573152","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3543622.3573152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 ACM/SIGDA International Symposium on Field Programmable Gate Arrays","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8999999761581421,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G397489182","display_name":null,"funder_award_id":"2021YFA100-3602","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2109699519","https://openalex.org/W2006568360","https://openalex.org/W102726818","https://openalex.org/W4233616027","https://openalex.org/W2059591361","https://openalex.org/W970262775","https://openalex.org/W2170506987","https://openalex.org/W1580755070","https://openalex.org/W2532502681","https://openalex.org/W2537803004"],"abstract_inverted_index":{"Graph":[0],"Neural":[1],"Networks":[2],"(GNNs)":[3],"have":[4,11],"outstanding":[5],"performance":[6],"on":[7,167,220],"graph-structured":[8],"data":[9,78,108],"and":[10,49,80,105,132,140,171,187,192,203,230],"been":[12],"extensively":[13],"accelerated":[14],"by":[15],"field-programmable":[16],"gate":[17],"array":[18],"(FPGA)":[19],"in":[20,30,93,110],"various":[21],"ways.":[22],"However,":[23],"existing":[24],"accelerators":[25,38],"significantly":[26],"lack":[27],"flexibility,":[28],"especially":[29],"the":[31,77,85,94,107,111,125,148,157,164,173,199,209,216],"following":[32],"two":[33],"aspects:":[34],"1)":[35],"Many":[36],"FPGA-based":[37,67,221],"only":[39],"support":[40,89],"one":[41],"GNN":[42,57,72,98,160,175,225],"model.":[43],"2)":[44],"The":[45],"processes":[46],"of":[47,97,117,135,150,185,211],"re-synthesizing":[48],"bitstream":[50],"re-generating":[51],"are":[52],"very":[53],"time-consuming":[54],"for":[55,70,156,224],"new":[56],"models.":[58,99,161],"To":[59,208],"this":[60],"end,":[61],"we":[62,83,101,123],"propose":[63],"a":[64,130],"highly":[65],"integrated":[66],"overlay":[68],"processor":[69,202],"general":[71,141,222],"accelerations":[73],"named":[74],"Graph-OPU.":[75],"Regarding":[76],"structure":[79],"operation":[81,91],"irregularity,":[82],"customize":[84,102],"instruction":[86],"sets":[87],"to":[88,113,128],"irregular":[90],"patterns":[92],"inference":[95],"process":[96,134,149],"Then,":[100],"our":[103,212],"datapath":[104],"optimize":[106],"format":[109],"microarchitecture":[112],"take":[114],"full":[115],"advantage":[116],"high":[118,228],"bandwidth":[119],"memory":[120],"(HBM).":[121],"Moreover,":[122],"design":[124],"computation":[126],"module":[127],"ensure":[129],"unified":[131],"fully-pipelined":[133],"sparse":[136],"matrix":[137,142],"multiplication":[138,143],"(SpMM)":[139],"(GEMM).":[144],"Users":[145],"can":[146,181],"avoid":[147],"FPGA":[151],"reconfiguration":[152],"or":[153],"RTL":[154],"regeneration":[155],"newly":[158],"invented":[159],"We":[162],"implement":[163],"hardware":[165],"prototype":[166],"Xilinx":[168],"Alveo":[169],"U50":[170],"test":[172],"mainstream":[174],"models":[176],"with":[177,198,227],"9":[178],"datasets.":[179],"Graph-OPU":[180,214],"achieve":[182],"an":[183],"average":[184],"435\u00d7":[186],"18\u00d7":[188],"speedup,":[189],"while":[190],"2013\u00d7":[191],"109\u00d7":[193],"better":[194],"energy":[195,231],"efficiency,":[196],"compared":[197],"Intel":[200],"I7-12700KF":[201],"NVIDIA":[204],"RTX3090":[205],"GPU,":[206],"respectively.":[207],"best":[210],"knowledge,":[213],"is":[215],"first":[217],"in-depth":[218],"study":[219],"processors":[223],"acceleration":[226],"speedup":[229],"efficiency.":[232]},"counts_by_year":[{"year":2023,"cited_by_count":3}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}