{"id":"https://openalex.org/W2996351509","doi":"https://doi.org/10.1145/3373087.3375296","title":"Flexible Communication Avoiding Matrix Multiplication on FPGA with High-Level Synthesis","display_name":"Flexible Communication Avoiding Matrix Multiplication on FPGA with High-Level Synthesis","publication_year":2020,"publication_date":"2020-02-23","ids":{"openalex":"https://openalex.org/W2996351509","doi":"https://doi.org/10.1145/3373087.3375296","mag":"2996351509"},"language":"en","primary_location":{"id":"doi:10.1145/3373087.3375296","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3373087.3375296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1912.06526","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Johannes de Fine Licht","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Johannes de Fine Licht","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Grzegorz Kwasniewski","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Grzegorz Kwasniewski","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":null,"display_name":"Torsten Hoefler","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Torsten Hoefler","raw_affiliation_strings":["ETH Zurich, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":7.5433,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.97899337,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"244","last_page":"254"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9988999962806702,"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/software-portability","display_name":"Software portability","score":0.6717000007629395},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6660000085830688},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6241000294685364},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5907999873161316},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48410001397132874},{"id":"https://openalex.org/keywords/maintainability","display_name":"Maintainability","score":0.4690999984741211},{"id":"https://openalex.org/keywords/reconfigurable-computing","display_name":"Reconfigurable computing","score":0.4431000053882599},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43639999628067017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8007000088691711},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.6717000007629395},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6660000085830688},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6241000294685364},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5907999873161316},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4950000047683716},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48410001397132874},{"id":"https://openalex.org/C160713754","wikidata":"https://www.wikidata.org/wiki/Q1389965","display_name":"Maintainability","level":2,"score":0.4690999984741211},{"id":"https://openalex.org/C142962650","wikidata":"https://www.wikidata.org/wiki/Q240838","display_name":"Reconfigurable computing","level":3,"score":0.4431000053882599},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43639999628067017},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4115999937057495},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.38920000195503235},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.37549999356269836},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.36090001463890076},{"id":"https://openalex.org/C58013763","wikidata":"https://www.wikidata.org/wiki/Q5754574","display_name":"High-level synthesis","level":3,"score":0.34459999203681946},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.31619998812675476},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.28780001401901245},{"id":"https://openalex.org/C201290732","wikidata":"https://www.wikidata.org/wiki/Q130762","display_name":"Multiplication algorithm","level":3,"score":0.2741999924182892},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.26910001039505005},{"id":"https://openalex.org/C65232700","wikidata":"https://www.wikidata.org/wiki/Q5656403","display_name":"Hardware architecture","level":3,"score":0.2603999972343445},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3373087.3375296","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3373087.3375296","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2020 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1912.06526","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.06526","pdf_url":"https://arxiv.org/pdf/1912.06526","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1912.06526","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.06526","pdf_url":"https://arxiv.org/pdf/1912.06526","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[],"awards":[{"id":"https://openalex.org/G3971425494","display_name":null,"funder_award_id":"678880","funder_id":"https://openalex.org/F4320335254","funder_display_name":"Horizon 2020"}],"funders":[{"id":"https://openalex.org/F4320335254","display_name":"Horizon 2020","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1530803551","https://openalex.org/W1582059966","https://openalex.org/W1950718439","https://openalex.org/W1992935334","https://openalex.org/W2003804316","https://openalex.org/W2010747199","https://openalex.org/W2035476608","https://openalex.org/W2061624656","https://openalex.org/W2333659671","https://openalex.org/W2575866180","https://openalex.org/W2727238169","https://openalex.org/W2785452945","https://openalex.org/W2788183263","https://openalex.org/W2895305554","https://openalex.org/W2953128281","https://openalex.org/W2972087877","https://openalex.org/W2979482768","https://openalex.org/W2984305089","https://openalex.org/W4292169167"],"related_works":[],"abstract_inverted_index":{"Data":[0],"movement":[1],"is":[2,33],"the":[3,22,71,77,87,132,136,199],"dominating":[4],"factor":[5],"affecting":[6],"performance":[7,122,178],"and":[8,36,42,47,94,123,160,163,185,205],"energy":[9],"in":[10,76,179],"modern":[11],"computing":[12,29],"systems.":[13,50],"Consequently,":[14],"many":[15],"algorithms":[16,103,208],"have":[17,39],"been":[18,40],"developed":[19,75],"to":[20,70,84,101,112,138,155,175,197],"minimize":[21],"number":[23],"of":[24,67,79,91,151,202],"I/O":[25,59,206],"operations":[26],"for":[27,45,58,104,116],"common":[28],"patterns.":[30],"Matrix":[31],"multiplication":[32,115],"no":[34],"exception,":[35],"lower":[37],"bounds":[38,74],"proven":[41],"implemented":[43],"both":[44,183],"shared":[46],"distributed":[48,89],"memory":[49,68,95,186],"Reconfigurable":[51],"hardware":[52,106,211],"platforms":[53],"are":[54,173],"a":[55,98,110,139,143,148],"lucrative":[56],"target":[57],"minimizing":[60,207],"algorithms,":[61],"as":[62,192],"they":[63],"offer":[64,176,189],"full":[65],"control":[66],"accesses":[69],"programmer.":[72],"While":[73],"context":[78],"fixed":[80],"architectures":[81],"still":[82],"apply":[83],"these":[85],"platforms,":[86,118],"spatially":[88],"nature":[90],"their":[92],"computational":[93],"resources":[96],"requires":[97],"decentralized":[99],"approach":[100],"optimize":[102,113],"maximum":[105,121],"utilization.":[107],"We":[108,134,188],"present":[109],"model":[111,137],"matrix":[114],"FPGA":[117,166],"simultaneously":[119],"targeting":[120],"minimum":[124],"off-chip":[125],"data":[126,158],"movement,":[127],"within":[128],"constraints":[129],"set":[130],"by":[131],"hardware.":[133],"map":[135],"concrete":[140],"architecture":[141,172],"using":[142],"high-level":[144],"synthesis":[145],"tool,":[146],"maintaining":[147],"high":[149],"level":[150],"abstraction,":[152],"allowing":[153],"us":[154],"support":[156],"arbitrary":[157],"types,":[159],"enables":[161],"maintainability":[162],"portability":[164],"across":[165],"devices.":[167],"Kernels":[168],"generated":[169],"from":[170],"our":[171,190],"shown":[174],"competitive":[177],"practice,":[180],"scaling":[181],"with":[182],"compute":[184],"resources.":[187],"design":[191],"an":[193],"open":[194,200],"source":[195],"project":[196],"encourage":[198],"development":[201],"linear":[203],"algebra":[204],"on":[209],"reconfigurable":[210],"platforms.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2019-12-26T00:00:00"}