{"id":"https://openalex.org/W3020221024","doi":"https://doi.org/10.1109/tpds.2020.2990924","title":"A Ubiquitous Machine Learning Accelerator With Automatic Parallelization on FPGA","display_name":"A Ubiquitous Machine Learning Accelerator With Automatic Parallelization on FPGA","publication_year":2020,"publication_date":"2020-04-27","ids":{"openalex":"https://openalex.org/W3020221024","doi":"https://doi.org/10.1109/tpds.2020.2990924","mag":"3020221024"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2020.2990924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2020.2990924","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed 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/A5011884768","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0002-9403-5575"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["School of Computer Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-9403-5575","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072915437","display_name":"Lei Gong","orcid":"https://orcid.org/0000-0002-8391-5526"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Gong","raw_affiliation_strings":["School of Computer Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-8391-5526","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747336","display_name":"Xi Li","orcid":"https://orcid.org/0000-0002-8582-5073"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Li","raw_affiliation_strings":["School of Computer Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077322091","display_name":"Xuehai Zhou","orcid":"https://orcid.org/0000-0002-8360-3143"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuehai Zhou","raw_affiliation_strings":["School of Computer Science, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-8360-3143","affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":2.3596,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.89384598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"31","issue":"10","first_page":"2346","last_page":"2359"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12029","display_name":"DNA and Biological Computing","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12029","display_name":"DNA and Biological Computing","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9965999722480774,"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/T11321","display_name":"Error Correcting Code Techniques","score":0.9959999918937683,"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":0.8771467804908752},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6136284470558167},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5826436281204224},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5696253776550293},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.5672906041145325},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.4677548408508301},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4335033893585205},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4268590807914734},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41139742732048035},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4079176187515259},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3907473683357239},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.26222625374794006}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8771467804908752},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6136284470558167},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5826436281204224},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5696253776550293},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.5672906041145325},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.4677548408508301},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4335033893585205},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4268590807914734},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41139742732048035},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4079176187515259},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3907473683357239},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.26222625374794006},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2020.2990924","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2020.2990924","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.5}],"awards":[{"id":"https://openalex.org/G354725111","display_name":null,"funder_award_id":"2017YFA0700900","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4451411784","display_name":null,"funder_award_id":"2017497","funder_id":"https://openalex.org/F4320322847","funder_display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences"},{"id":"https://openalex.org/G6823762549","display_name":null,"funder_award_id":"WK2150110003","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7639841928","display_name":null,"funder_award_id":"BK20181193","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G8758304440","display_name":null,"funder_award_id":"61976200","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"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1442374986","https://openalex.org/W1492347181","https://openalex.org/W1576445103","https://openalex.org/W1606347560","https://openalex.org/W1632742330","https://openalex.org/W1972648069","https://openalex.org/W1981943579","https://openalex.org/W2048266589","https://openalex.org/W2061680337","https://openalex.org/W2067523571","https://openalex.org/W2075919068","https://openalex.org/W2089572724","https://openalex.org/W2094756095","https://openalex.org/W2110726704","https://openalex.org/W2119180969","https://openalex.org/W2123608497","https://openalex.org/W2127590703","https://openalex.org/W2128928939","https://openalex.org/W2142801765","https://openalex.org/W2146496959","https://openalex.org/W2152839228","https://openalex.org/W2153287401","https://openalex.org/W2153543246","https://openalex.org/W2155893237","https://openalex.org/W2168231600","https://openalex.org/W2170585292","https://openalex.org/W2181607856","https://openalex.org/W2219888463","https://openalex.org/W2237922334","https://openalex.org/W2261808795","https://openalex.org/W2276486856","https://openalex.org/W2282294254","https://openalex.org/W2289891016","https://openalex.org/W2290132443","https://openalex.org/W2293282867","https://openalex.org/W2294282016","https://openalex.org/W2331737637","https://openalex.org/W2406293284","https://openalex.org/W2479514080","https://openalex.org/W2611709845","https://openalex.org/W2883927138","https://openalex.org/W2919115771","https://openalex.org/W2951135776","https://openalex.org/W2952075007","https://openalex.org/W3024621361","https://openalex.org/W4240168186","https://openalex.org/W4241632897","https://openalex.org/W4247053599","https://openalex.org/W4248707617","https://openalex.org/W6628377381","https://openalex.org/W6634343353","https://openalex.org/W6636358008","https://openalex.org/W6636832544","https://openalex.org/W6674479107","https://openalex.org/W6684859321","https://openalex.org/W6713184358"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2187181201","https://openalex.org/W2999668243","https://openalex.org/W2177838837","https://openalex.org/W2963831937","https://openalex.org/W2748614007","https://openalex.org/W2080419754","https://openalex.org/W2518118925","https://openalex.org/W2532502681","https://openalex.org/W3159273459"],"abstract_inverted_index":{"Machine":[0],"learning":[1,46,170],"has":[2,12],"been":[3,40],"widely":[4],"applied":[5],"in":[6,124],"various":[7],"emerging":[8],"data-intensive":[9,74],"applications,":[10,81,126,139,156,171],"and":[11,16,90,127,151,162,180,219],"to":[13,21,55,95,108,120,206],"be":[14,52],"optimized":[15],"accelerated":[17],"by":[18],"powerful":[19],"engines":[20],"process":[22,179],"very":[23],"large":[24],"scale":[25],"data.":[26],"Recently,":[27],"the":[28,97,101,122,125,133,140,193,200],"instruction":[29],"set":[30],"based":[31],"accelerators":[32,175],"on":[33,132],"Field":[34],"Progarmmable":[35],"Gate":[36],"Arrays":[37],"(FPGAs)":[38],"have":[39],"a":[41,65,129,189],"promising":[42],"topic":[43],"for":[44,72,176,184,192],"machine":[45],"applications.":[47,75],"The":[48,76],"customized":[49],"instructions":[50],"can":[51,142,203],"further":[53],"scheduled":[54],"achieve":[56],"higher":[57],"instruction-level":[58,99],"parallelism.":[59],"In":[60,93],"this":[61],"article,":[62],"we":[63,172,187],"design":[64,188],"ubiquitous":[66],"accelerator":[67,77,102,141,191,201],"with":[68,212],"out-of-order":[69,105],"automatic":[70],"parallelization":[71],"large-scale":[73],"accommodates":[78,158],"four":[79,144],"representative":[80],"including":[82,147],"clustering":[83],"algorithms,":[84,146],"deep":[85,169],"neural":[86],"networks,":[87],"genome":[88,185],"sequencing,":[89,186],"collaborative":[91,154],"filtering.":[92],"order":[94],"improve":[96],"coarse-grained":[98],"parallelism,":[100],"employs":[103],"an":[104],"scheduling":[106],"method":[107],"enable":[109],"parallel":[110],"dataflow":[111],"computation.":[112],"We":[113],"use":[114],"Colored":[115],"Petri":[116],"Net":[117],"(CPN)":[118],"tools":[119],"analyze":[121],"dependences":[123],"build":[128],"hardware":[130,174,190,214],"prototype":[131],"real":[134],"FPGA":[135],"platform.":[136],"For":[137,153,168],"cluster":[138],"support":[143],"different":[145],"K-Means,":[148],"SLINK,":[149],"PAM,":[150],"DBSCAN.":[152],"filtering":[155],"it":[157],"Tanimoto,":[159],"euclidean,":[160],"Cosine,":[161],"Pearson":[163],"Correlation":[164],"as":[165],"Similarity":[166],"metrics.":[167],"implement":[173],"both":[177],"training":[178],"inference":[181],"process.":[182],"Finally,":[183],"BWA-SW":[194],"algorithm.":[195],"Experimental":[196],"results":[197],"show":[198],"that":[199],"architecture":[202],"reach":[204],"up":[205],"25X":[207],"speedup":[208],"against":[209],"Intel":[210],"processors":[211],"affordable":[213],"cost,":[215],"insignificant":[216],"power":[217],"consumption,":[218],"high":[220],"flexibility.":[221]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}