{"id":"https://openalex.org/W4416750545","doi":"https://doi.org/10.1109/sips66314.2025.11261266","title":"Scalable Low-latency Systolic Arrays using Toroidal and Bi-Directional Dataflows","display_name":"Scalable Low-latency Systolic Arrays using Toroidal and Bi-Directional Dataflows","publication_year":2025,"publication_date":"2025-11-01","ids":{"openalex":"https://openalex.org/W4416750545","doi":"https://doi.org/10.1109/sips66314.2025.11261266"},"language":null,"primary_location":{"id":"doi:10.1109/sips66314.2025.11261266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sips66314.2025.11261266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Signal Processing Systems (SiPS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5113846792","display_name":"Linus Svensson","orcid":null},"institutions":[{"id":"https://openalex.org/I187531555","display_name":"Lund University","ror":"https://ror.org/012a77v79","country_code":"SE","type":"education","lineage":["https://openalex.org/I187531555"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Linus Svensson","raw_affiliation_strings":["Lund University,Dept. of Electrical and Information Technology,Lund,Sweden,SE-221 00"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lund University,Dept. of Electrical and Information Technology,Lund,Sweden,SE-221 00","institution_ids":["https://openalex.org/I187531555"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028423819","display_name":"Oscar Gustafsson","orcid":"https://orcid.org/0000-0003-3470-3911"},"institutions":[{"id":"https://openalex.org/I102134673","display_name":"Link\u00f6ping University","ror":"https://ror.org/05ynxx418","country_code":"SE","type":"education","lineage":["https://openalex.org/I102134673"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Oscar Gustafsson","raw_affiliation_strings":["Link&#x00F6;ping University,Dept. of Electrical Engineering,Link&#x00F6;ping,Sweden,SE-581 83"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Link&#x00F6;ping University,Dept. of Electrical Engineering,Link&#x00F6;ping,Sweden,SE-581 83","institution_ids":["https://openalex.org/I102134673"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104061156","display_name":"Joachim Rodrigues","orcid":null},"institutions":[{"id":"https://openalex.org/I187531555","display_name":"Lund University","ror":"https://ror.org/012a77v79","country_code":"SE","type":"education","lineage":["https://openalex.org/I187531555"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Joachim Rodrigues","raw_affiliation_strings":["Lund University,Dept. of Electrical and Information Technology,Lund,Sweden,SE-221 00"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lund University,Dept. of Electrical and Information Technology,Lund,Sweden,SE-221 00","institution_ids":["https://openalex.org/I187531555"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43247158,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.6284999847412109,"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"}},"topics":[{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.6284999847412109,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.2922999858856201,"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":0.039900001138448715,"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/toroid","display_name":"Toroid","score":0.553600013256073},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5353000164031982},{"id":"https://openalex.org/keywords/cmos","display_name":"CMOS","score":0.5320000052452087},{"id":"https://openalex.org/keywords/systolic-array","display_name":"Systolic array","score":0.5205000042915344},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5041999816894531},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.4487000107765198},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.44449999928474426},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.44029998779296875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.570900022983551},{"id":"https://openalex.org/C15001198","wikidata":"https://www.wikidata.org/wiki/Q3241394","display_name":"Toroid","level":3,"score":0.553600013256073},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5353000164031982},{"id":"https://openalex.org/C46362747","wikidata":"https://www.wikidata.org/wiki/Q173431","display_name":"CMOS","level":2,"score":0.5320000052452087},{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.5205000042915344},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5041999816894531},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.453900009393692},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.4487000107765198},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.44449999928474426},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.44029998779296875},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.3294999897480011},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.32109999656677246},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3109999895095825},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.2736000120639801},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.27309998869895935},{"id":"https://openalex.org/C29984679","wikidata":"https://www.wikidata.org/wiki/Q1929149","display_name":"Crossbar switch","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.27070000767707825},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C544956773","wikidata":"https://www.wikidata.org/wiki/Q670","display_name":"Silicon","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sips66314.2025.11261266","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sips66314.2025.11261266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Signal Processing Systems (SiPS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1493164714","https://openalex.org/W1963853729","https://openalex.org/W2017369466","https://openalex.org/W2945146780","https://openalex.org/W2953212265","https://openalex.org/W3116917247","https://openalex.org/W3213528054","https://openalex.org/W4404386171","https://openalex.org/W4409641128","https://openalex.org/W4410583693","https://openalex.org/W4412987431"],"related_works":[],"abstract_inverted_index":{"Systolic":[0],"arrays":[1,69,80],"(SAs)":[2],"for":[3,29,95],"matrix":[4,100],"multiplication":[5],"are":[6,27,124],"commonly":[7],"used":[8],"in":[9,37,126],"machine":[10],"learning":[11],"(ML),":[12],"wireless":[13],"communication,":[14],"and":[15,34,84,132],"signal":[16],"processing.":[17],"Inherently":[18],"offering":[19],"high":[20],"throughput":[21],"with":[22,70],"good":[23],"data":[24],"reuse,":[25],"they":[26],"well-positioned":[28],"both":[30],"low-power":[31],"edge":[32],"devices":[33],"accelerator":[35],"applications":[36],"high-performance":[38],"computing.":[39],"Current":[40],"realizations":[41],"suffer":[42],"from":[43,87],"startup":[44],"latency,":[45],"defined":[46],"as":[47],"the":[48,137],"time":[49],"required":[50],"to":[51,90,110,114],"fully":[52],"utilize":[53],"all":[54],"processing":[55],"elements":[56],"(PEs).":[57],"In":[58],"this":[59,61],"work,":[60],"issue":[62],"is":[63,134],"addressed":[64],"by":[65,108],"introducing":[66],"bidirectional":[67],"systolic":[68,79],"connected":[71],"edges":[72],"that":[73,136],"form":[74],"toroidal":[75,138],"dataflows.":[76],"The":[77],"proposed":[78],"significantly":[81],"reduce":[82],"computational":[83],"readout":[85],"latency":[86],"$4":[88],"n-2$":[89],"$2.5":[91],"n-1$":[92],"clock":[93],"cycles":[94],"an":[96],"$n":[97],"\\times":[98],"n$":[99],"multiplication,":[101],"while":[102],"simultaneously":[103],"reducing":[104],"energy":[105],"per":[106],"operation":[107],"up":[109],"$43":[111],"\\%$":[112,144],"compared":[113],"conventional":[115],"SAs.":[116],"Moreover,":[117],"a":[118,127,141],"variety":[119],"of":[120],"differently":[121],"shaped":[122],"SAs":[123],"synthesized":[125],"22":[128],"nm":[129],"CMOS":[130],"technology,":[131],"it":[133],"shown":[135],"designs":[139],"offer":[140],"$5":[142],"\\%-12":[143],"lower":[145],"silicon":[146],"area":[147],"cost.":[148]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-28T00:00:00"}
