{"id":"https://openalex.org/W3102383356","doi":"https://doi.org/10.1145/3337929","title":"Optimizing Bit-Serial Matrix Multiplication for Reconfigurable Computing","display_name":"Optimizing Bit-Serial Matrix Multiplication for Reconfigurable Computing","publication_year":2019,"publication_date":"2019-08-20","ids":{"openalex":"https://openalex.org/W3102383356","doi":"https://doi.org/10.1145/3337929","mag":"3102383356"},"language":"en","primary_location":{"id":"doi:10.1145/3337929","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3337929","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Reconfigurable Technology and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1901.00370","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001185686","display_name":"Yaman Umuroglu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210101362","display_name":"Xilinx (Ireland)","ror":"https://ror.org/00pahkj72","country_code":"IE","type":"company","lineage":["https://openalex.org/I32923980","https://openalex.org/I4210101362"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Yaman Umuroglu","raw_affiliation_strings":["Xilinx Research Labs, Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xilinx Research Labs, Dublin, Ireland","institution_ids":["https://openalex.org/I4210101362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031247318","display_name":"Davide Conficconi","orcid":"https://orcid.org/0000-0002-5834-0812"},"institutions":[{"id":"https://openalex.org/I4210101362","display_name":"Xilinx (Ireland)","ror":"https://ror.org/00pahkj72","country_code":"IE","type":"company","lineage":["https://openalex.org/I32923980","https://openalex.org/I4210101362"]},{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IE","IT"],"is_corresponding":false,"raw_author_name":"Davide Conficconi","raw_affiliation_strings":["Xilinx Research Labs, Ireland and Politecnico di Milano, Milano, Italy"],"raw_orcid":"https://orcid.org/0000-0002-5834-0812","affiliations":[{"raw_affiliation_string":"Xilinx Research Labs, Ireland and Politecnico di Milano, Milano, Italy","institution_ids":["https://openalex.org/I4210101362","https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081697483","display_name":"Lahiru Rasnayake","orcid":"https://orcid.org/0000-0001-9157-3207"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Lahiru Rasnayake","raw_affiliation_strings":["Norwegian University of Science and Technology, Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology, Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055093027","display_name":"Thomas B. Preu\u00dfer","orcid":"https://orcid.org/0000-0003-3998-7896"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas B. Preusser","raw_affiliation_strings":["Accemic Technologies GmbH, Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Accemic Technologies GmbH, Dresden, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024358692","display_name":"Magnus Sj\u00e4lander","orcid":"https://orcid.org/0000-0003-4232-6976"},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]},{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO","SE"],"is_corresponding":false,"raw_author_name":"Magnus Sj\u00e4lander","raw_affiliation_strings":["Uppsala University, Sweden and Norwegian University of Science and Technology, Trondheim, Norway"],"raw_orcid":"https://orcid.org/0000-0003-4232-6976","affiliations":[{"raw_affiliation_string":"Uppsala University, Sweden and Norwegian University of Science and Technology, Trondheim, Norway","institution_ids":["https://openalex.org/I123387679","https://openalex.org/I204778367"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7318,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.69899742,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"12","issue":"3","first_page":"1","last_page":"24"},"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":0.9998999834060669,"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":0.9998999834060669,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8277528285980225},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.7290993928909302},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6930969953536987},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.559077262878418},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5524385571479797},{"id":"https://openalex.org/keywords/mpsoc","display_name":"MPSoC","score":0.4885183572769165},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.43716636300086975},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.42607322335243225},{"id":"https://openalex.org/keywords/single-precision-floating-point-format","display_name":"Single-precision floating-point format","score":0.4188401401042938},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.29661089181900024},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2586471438407898},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.2374109923839569},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22214198112487793},{"id":"https://openalex.org/keywords/multiprocessing","display_name":"Multiprocessing","score":0.1373923420906067},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08902233839035034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8277528285980225},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.7290993928909302},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6930969953536987},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.559077262878418},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5524385571479797},{"id":"https://openalex.org/C2777187653","wikidata":"https://www.wikidata.org/wiki/Q975106","display_name":"MPSoC","level":3,"score":0.4885183572769165},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.43716636300086975},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.42607322335243225},{"id":"https://openalex.org/C133095886","wikidata":"https://www.wikidata.org/wiki/Q1307173","display_name":"Single-precision floating-point format","level":3,"score":0.4188401401042938},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.29661089181900024},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2586471438407898},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.2374109923839569},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22214198112487793},{"id":"https://openalex.org/C4822641","wikidata":"https://www.wikidata.org/wiki/Q846651","display_name":"Multiprocessing","level":2,"score":0.1373923420906067},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08902233839035034},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","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},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3337929","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3337929","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Reconfigurable Technology and Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1901.00370","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.00370","pdf_url":"https://arxiv.org/pdf/1901.00370","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:ntnuopen.ntnu.no:11250/2650745","is_oa":true,"landing_page_url":"https://hdl.handle.net/11250/2650745","pdf_url":null,"source":{"id":"https://openalex.org/S4306401716","display_name":"Duo Research Archive (University of Oslo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184942183","host_organization_name":"University of Oslo","host_organization_lineage":["https://openalex.org/I184942183"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"12","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:re.public.polimi.it:11311/1107414","is_oa":false,"landing_page_url":"http://hdl.handle.net/11311/1107414","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1901.00370","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1901.00370","pdf_url":"https://arxiv.org/pdf/1901.00370","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"score":0.8999999761581421,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G3784559673","display_name":"Leveraging Multi-Value Logic to Modulate Approximation for Future Nano Devices","funder_award_id":"2015-05159","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"}],"funders":[{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1534157463","https://openalex.org/W1983394510","https://openalex.org/W2017369466","https://openalex.org/W2022881857","https://openalex.org/W2120474114","https://openalex.org/W2121082877","https://openalex.org/W2126779549","https://openalex.org/W2265166184","https://openalex.org/W2524428287","https://openalex.org/W2563587242","https://openalex.org/W2565125333","https://openalex.org/W2618591429","https://openalex.org/W2748818695","https://openalex.org/W2755741562","https://openalex.org/W2761398658","https://openalex.org/W2785117529","https://openalex.org/W2788007484","https://openalex.org/W2810704618","https://openalex.org/W2900694899","https://openalex.org/W2951465358","https://openalex.org/W3100596846","https://openalex.org/W3102169921"],"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":{"Matrix-matrix":[0],"multiplication":[1,75,92],"is":[2],"a":[3,71,90,125,137],"key":[4],"computational":[5],"kernel":[6],"for":[7,77],"numerous":[8],"applications":[9,30],"in":[10],"science":[11],"and":[12,17,42,99],"engineering,":[13],"with":[14,96,136],"ample":[15],"parallelism":[16],"data":[18],"locality":[19],"that":[20,94,116],"lends":[21],"itself":[22],"well":[23],"to":[24,38,88],"high-performance":[25],"implementations.":[26],"Many":[27],"matrix":[28,74,91],"multiplication-dependent":[29],"can":[31,105],"use":[32],"reduced-precision":[33],"integer":[34],"or":[35,61],"fixed-point":[36],"representations":[37],"increase":[39],"their":[40],"performance":[41,85,93,127],"energy":[43],"efficiency":[44],"while":[45],"still":[46],"offering":[47],"adequate":[48],"quality":[49],"of":[50,86,128],"results.":[51],"However,":[52],"precision":[53,98],"requirements":[54],"may":[55],"vary":[56],"between":[57],"different":[58],"application":[59],"phases":[60],"depend":[62],"on":[63,109,132],"input":[64],"data,":[65],"rendering":[66],"constant-precision":[67],"solutions":[68],"ineffective.":[69],"BISMO,":[70],"vectorized":[72],"bit-serial":[73],"overlay":[76],"reconfigurable":[78],"computing,":[79],"previously":[80],"utilized":[81],"the":[82,133],"excellent":[83],"binary-operation":[84],"FPGAs":[87,111],"offer":[89],"scales":[95],"required":[97],"parallelism.":[100],"We":[101],"show":[102],"how":[103],"BISMO":[104,123],"be":[106],"scaled":[107],"up":[108],"Xilinx":[110,138],"using":[112],"an":[113],"arithmetic":[114],"architecture":[115],"better":[117],"utilizes":[118],"six-input":[119],"LUTs.":[120],"The":[121],"improved":[122],"achieves":[124],"peak":[126],"15.4":[129],"binary":[130],"TOPS":[131],"Ultra96":[134],"board":[135],"UltraScale+":[139],"MPSoC.":[140]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}
