{"id":"https://openalex.org/W3216064418","doi":"https://doi.org/10.1145/3491235","title":"The Strong Scaling Advantage of FPGAs in HPC for N-body Simulations","display_name":"The Strong Scaling Advantage of FPGAs in HPC for N-body Simulations","publication_year":2021,"publication_date":"2021-11-29","ids":{"openalex":"https://openalex.org/W3216064418","doi":"https://doi.org/10.1145/3491235","mag":"3216064418"},"language":"en","primary_location":{"id":"doi:10.1145/3491235","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3491235","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3491235","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/10.1145/3491235","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036734397","display_name":"J. Menzel","orcid":"https://orcid.org/0000-0002-2414-9809"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Johannes Menzel","raw_affiliation_strings":["Paderborn University, Department of Computer Science and Paderborn Center for Parallel Computing, Paderborn, North Rhine-Westphalia, Germany"],"affiliations":[{"raw_affiliation_string":"Paderborn University, Department of Computer Science and Paderborn Center for Parallel Computing, Paderborn, North Rhine-Westphalia, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039484700","display_name":"Christian Plessl","orcid":"https://orcid.org/0000-0001-5728-9982"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Plessl","raw_affiliation_strings":["Paderborn University, Department of Computer Science and Paderborn Center for Parallel Computing, Paderborn, North Rhine-Westphalia, Germany"],"affiliations":[{"raw_affiliation_string":"Paderborn University, Department of Computer Science and Paderborn Center for Parallel Computing, Paderborn, North Rhine-Westphalia, Germany","institution_ids":["https://openalex.org/I206945453"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009852288","display_name":"Tobias Kenter","orcid":"https://orcid.org/0000-0002-5088-0267"},"institutions":[{"id":"https://openalex.org/I206945453","display_name":"Paderborn University","ror":"https://ror.org/058kzsd48","country_code":"DE","type":"education","lineage":["https://openalex.org/I206945453"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Kenter","raw_affiliation_strings":["Paderborn University, Department of Computer Science and Paderborn Center for Parallel Computing, Paderborn, North Rhine-Westphalia, Germany"],"affiliations":[{"raw_affiliation_string":"Paderborn University, Department of Computer Science and Paderborn Center for Parallel Computing, Paderborn, North Rhine-Westphalia, Germany","institution_ids":["https://openalex.org/I206945453"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5036734397"],"corresponding_institution_ids":["https://openalex.org/I206945453"],"apc_list":null,"apc_paid":null,"fwci":2.348,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.89104639,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"15","issue":"1","first_page":"1","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T13126","display_name":"Scientific Research and Discoveries","score":0.9829000234603882,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9818000197410583,"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/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.8341606855392456},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8269346952438354},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.7665252685546875},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6495095491409302},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6205924153327942},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5971977710723877},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5092710256576538},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4988398551940918},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.4753420352935791},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.46310776472091675},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.43227308988571167},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.35319745540618896},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2831880450248718},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.238193541765213},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09644883871078491},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.083595871925354},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07204526662826538}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.8341606855392456},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8269346952438354},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.7665252685546875},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6495095491409302},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6205924153327942},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5971977710723877},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5092710256576538},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4988398551940918},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.4753420352935791},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.46310776472091675},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.43227308988571167},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.35319745540618896},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2831880450248718},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.238193541765213},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09644883871078491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.083595871925354},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07204526662826538},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3491235","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3491235","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3491235","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"}],"best_oa_location":{"id":"doi:10.1145/3491235","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3491235","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3491235","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":[{"display_name":"Affordable and clean energy","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G352791218","display_name":null,"funder_award_id":"(BMBF)","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3216064418.pdf","grobid_xml":"https://content.openalex.org/works/W3216064418.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1629396682","https://openalex.org/W1988915042","https://openalex.org/W2025347051","https://openalex.org/W2026836289","https://openalex.org/W2035687084","https://openalex.org/W2042195538","https://openalex.org/W2046771168","https://openalex.org/W2067174909","https://openalex.org/W2068306188","https://openalex.org/W2068764986","https://openalex.org/W2069452308","https://openalex.org/W2083206954","https://openalex.org/W2121082877","https://openalex.org/W2133156997","https://openalex.org/W2151868168","https://openalex.org/W2156938143","https://openalex.org/W2163257413","https://openalex.org/W2175477959","https://openalex.org/W2542189141","https://openalex.org/W2763326469","https://openalex.org/W2783189126","https://openalex.org/W2785874054","https://openalex.org/W2790575093","https://openalex.org/W2889517658","https://openalex.org/W2962513952","https://openalex.org/W2983971024","https://openalex.org/W3003605879","https://openalex.org/W3088376793","https://openalex.org/W3092054218","https://openalex.org/W3093571597","https://openalex.org/W3094076646","https://openalex.org/W3098221464","https://openalex.org/W3099104326","https://openalex.org/W3100822741","https://openalex.org/W3173206215","https://openalex.org/W3175441319","https://openalex.org/W3198027315","https://openalex.org/W4205715945","https://openalex.org/W4237473260","https://openalex.org/W6785493151"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W1582436825","https://openalex.org/W1996803181","https://openalex.org/W2979588510","https://openalex.org/W2074129693","https://openalex.org/W2548716681","https://openalex.org/W2149770606","https://openalex.org/W4250377101","https://openalex.org/W4301095421","https://openalex.org/W2949390274"],"abstract_inverted_index":{"N-body":[0],"methods":[1],"are":[2],"one":[3],"of":[4,10,47,55,67,69,166],"the":[5,41,56,78,162,167,179],"essential":[6],"algorithmic":[7],"building":[8],"blocks":[9],"high-performance":[11],"and":[12,37,101,105,130,185],"parallel":[13,171],"computing.":[14],"Previous":[15],"research":[16],"has":[17],"shown":[18],"promising":[19],"performance":[20,115,157,184],"for":[21,80,117,150],"implementing":[22],"n-body":[23],"simulations":[24],"with":[25,35,51,65,173],"pairwise":[26],"force":[27,53,99],"calculations":[28],"on":[29],"FPGAs.":[30,136],"However,":[31],"to":[32,71,112],"avoid":[33],"challenges":[34],"accumulation":[36],"memory":[38],"access":[39],"patterns,":[40],"presented":[42],"designs":[43],"calculate":[44],"each":[45,97],"pair":[46],"forces":[48],"twice,":[49],"along":[50],"both":[52,87],"sums":[54],"involved":[57],"particles.":[58],"Also,":[59],"they":[60],"require":[61],"large":[62,151],"problem":[63,119],"instances":[64],"hundreds":[66],"thousands":[68],"particles":[70,176],"reach":[72,113],"their":[73],"respective":[74],"peak":[75,114,156],"performance,":[76],"limiting":[77],"applicability":[79],"strong":[81,163],"scaling":[82,131,164],"scenarios.":[83],"This":[84],"work":[85],"addresses":[86],"issues":[88],"by":[89],"presenting":[90],"a":[91,108,138],"novel":[92],"FPGA":[93,168,180],"design":[94],"that":[95,110],"uses":[96],"calculated":[98],"twice":[100],"overlaps":[102],"data":[103],"transfers":[104],"computations":[106],"in":[107,127,170],"way":[109],"allows":[111],"even":[116,126],"small":[118],"instances,":[120],"outperforming":[121],"previous":[122],"single":[123],"precision":[124],"results":[125],"double":[128],"precision,":[129],"linearly":[132],"over":[133],"multiple":[134],"interconnected":[135],"For":[137],"comparison":[139],"across":[140],"architectures,":[141],"we":[142],"provide":[143],"an":[144],"equally":[145],"optimized":[146],"CPU":[147],"reference,":[148],"which":[149],"problems":[152],"actually":[153],"achieves":[154,182],"higher":[155],"per":[158,177],"device,":[159,178],"however,":[160],"given":[161],"advantages":[165],"design,":[169],"setups":[172],"few":[174],"thousand":[175],"platform":[181],"highest":[183],"power":[186],"efficiency.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}