{"id":"https://openalex.org/W4389140831","doi":"https://doi.org/10.1145/3634920","title":"Across Time and Space: <scp>Senju</scp> \u2019s Approach for Scaling Iterative Stencil Loop Accelerators on Single and Multiple FPGAs","display_name":"Across Time and Space: <scp>Senju</scp> \u2019s Approach for Scaling Iterative Stencil Loop Accelerators on Single and Multiple FPGAs","publication_year":2023,"publication_date":"2023-11-29","ids":{"openalex":"https://openalex.org/W4389140831","doi":"https://doi.org/10.1145/3634920"},"language":"en","primary_location":{"id":"doi:10.1145/3634920","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3634920","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3634920","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":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3634920","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083420180","display_name":"Emanuele Del Sozzo","orcid":"https://orcid.org/0000-0003-3101-8118"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Emanuele Del Sozzo","raw_affiliation_strings":["RIKEN Center for Computational Science, Kobe, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3101-8118","affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"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/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Davide Conficconi","raw_affiliation_strings":["Politecnico di Milano, Milan, Italy","Politecnico di Milano Dipartimento di Elettronica, Informazione e Bioingegneria, Italy"],"raw_orcid":"https://orcid.org/0000-0002-5834-0812","affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Politecnico di Milano Dipartimento di Elettronica, Informazione e Bioingegneria, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081752237","display_name":"Kentaro Sano","orcid":"https://orcid.org/0000-0002-6681-4192"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kentaro Sano","raw_affiliation_strings":["RIKEN Center for Computational Science, Kobe, Japan"],"raw_orcid":"https://orcid.org/0000-0002-6681-4192","affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5083420180"],"corresponding_institution_ids":["https://openalex.org/I4210129730"],"apc_list":null,"apc_paid":null,"fwci":1.4687,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.82074322,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"17","issue":"2","first_page":"1","last_page":"33"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9991000294685364,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9991000294685364,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9976000189781189,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/stencil","display_name":"Stencil","score":0.8690205812454224},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7348992824554443},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.5949364900588989},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5829128623008728},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5032421946525574},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.48237672448158264},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.45885685086250305},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.2704406976699829},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.2523288130760193},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17004933953285217},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.12836340069770813},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12388518452644348}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.8690205812454224},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7348992824554443},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.5949364900588989},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5829128623008728},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5032421946525574},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.48237672448158264},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.45885685086250305},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.2704406976699829},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2523288130760193},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17004933953285217},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.12836340069770813},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12388518452644348},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3634920","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3634920","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3634920","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:re.public.polimi.it:11311/1268644","is_oa":true,"landing_page_url":"https://hdl.handle.net/11311/1268644","pdf_url":"https://re.public.polimi.it/bitstream/11311/1268644/6/ISL_TRETS.pdf","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1145/3634920","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3634920","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3634920","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"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320335125","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389140831.pdf","grobid_xml":"https://content.openalex.org/works/W4389140831.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W1586293437","https://openalex.org/W1977937121","https://openalex.org/W1979457157","https://openalex.org/W1987588924","https://openalex.org/W2000331453","https://openalex.org/W2002555321","https://openalex.org/W2011073159","https://openalex.org/W2025347051","https://openalex.org/W2034761517","https://openalex.org/W2035701183","https://openalex.org/W2057313876","https://openalex.org/W2077195120","https://openalex.org/W2078874319","https://openalex.org/W2099011691","https://openalex.org/W2104512032","https://openalex.org/W2105042925","https://openalex.org/W2110902796","https://openalex.org/W2128120785","https://openalex.org/W2133027790","https://openalex.org/W2138680920","https://openalex.org/W2154078685","https://openalex.org/W2221279259","https://openalex.org/W2273440736","https://openalex.org/W2529513625","https://openalex.org/W2538589664","https://openalex.org/W2626476365","https://openalex.org/W2745429450","https://openalex.org/W2899691047","https://openalex.org/W2903012053","https://openalex.org/W2943018941","https://openalex.org/W2965571038","https://openalex.org/W3003676114","https://openalex.org/W3111765144","https://openalex.org/W3195130375","https://openalex.org/W3200558682","https://openalex.org/W4213408169","https://openalex.org/W4224924610","https://openalex.org/W4225647032","https://openalex.org/W4239385313","https://openalex.org/W4255560897","https://openalex.org/W4285009800","https://openalex.org/W4310551570","https://openalex.org/W4318618048","https://openalex.org/W4319870662","https://openalex.org/W4319918345"],"related_works":["https://openalex.org/W2039378765","https://openalex.org/W2003798513","https://openalex.org/W2151764765","https://openalex.org/W2890431355","https://openalex.org/W4376875029","https://openalex.org/W3149084271","https://openalex.org/W4247008888","https://openalex.org/W2150319905","https://openalex.org/W2962978274","https://openalex.org/W4298291099"],"abstract_inverted_index":{"Stencil-based":[0],"applications":[1],"play":[2],"an":[3,104,121,136],"essential":[4],"role":[5],"in":[6,12,179],"high-performance":[7],"systems":[8],"as":[9,17,84],"they":[10,85],"occur":[11],"numerous":[13],"computational":[14],"areas,":[15],"such":[16],"partial":[18],"differential":[19],"equation":[20],"solving.":[21],"In":[22],"this":[23,116],"context,":[24],"Iterative":[25],"Stencil":[26],"Loops":[27],"(ISLs)":[28],"represent":[29,79],"a":[30,49,80,170,180,188],"prominent":[31],"and":[32,63,92,110,145,155,160,175,183,190],"well-known":[33],"algorithmic":[34],"class":[35],"within":[36],"the":[37,45,87,97,125,141,196],"stencil":[38,47],"domain.":[39],"Specifically,":[40],"ISL-based":[41],"calculations":[42],"iteratively":[43],"apply":[44],"same":[46],"to":[48,60],"multi-dimensional":[50],"point":[51],"grid":[52],"multiple":[53],"times":[54],"or":[55],"until":[56],"convergence.":[57],"However,":[58],"due":[59],"their":[61],"iterative":[62],"intensive":[64],"nature,":[65],"ISLs":[66,101],"are":[67],"highly":[68,128],"performance-hungry,":[69],"demanding":[70],"specialized":[71,192],"solutions.":[72],"Here,":[73],"Field":[74],"Programmable":[75],"Gate":[76],"Arrays":[77],"(FPGAs)":[78],"valid":[81],"architectural":[82],"choice":[83],"enable":[86],"design":[88,126,143],"of":[89,100,127,173,195],"custom,":[90],"parallel,":[91],"scalable":[93,156],"ISL":[94,130],"accelerators.":[95],"Besides,":[96],"regular":[98],"structure":[99],"makes":[102],"them":[103],"ideal":[105],"candidate":[106],"for":[107,124],"automatic":[108],"optimization":[109],"generation":[111],"flows.":[112],"For":[113],"these":[114],"reasons,":[115],"article":[117],"introduces":[118],"Senju":[119,139],",":[120],"automation":[122],"framework":[123],"parallel":[129],"accelerators":[131],"targeting":[132],"single-/multi-FPGA":[133],"systems.":[134],"Given":[135],"input":[137],"description,":[138],"automates":[140],"entire":[142],"process":[144],"provides":[146],"accurate":[147],"performance":[148,186],"estimations.":[149],"The":[150],"experimental":[151],"evaluation":[152],"shows":[153],"remarkable":[154],"results,":[157],"outperforming":[158],"single-":[159,189],"multi-FPGA":[161,193],"literature":[162],"approaches":[163],"under":[164],"different":[165],"metrics.":[166],"Finally,":[167],"we":[168],"present":[169],"new":[171],"analysis":[172],"temporal":[174],"spatial":[176],"parallelism":[177],"trade-offs":[178],"real-case":[181],"scenario":[182],"discuss":[184],"our":[185],"through":[187],"novel":[191],"formulation":[194],"Roofline":[197],"Model.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2023-11-30T00:00:00"}
