{"id":"https://openalex.org/W3208116483","doi":"https://doi.org/10.1145/3458817.3476190","title":"Hardware acceleration of tensor-structured multilevel ewald summation method on MDGRAPE-4A, a special-purpose computer system for molecular dynamics simulations","display_name":"Hardware acceleration of tensor-structured multilevel ewald summation method on MDGRAPE-4A, a special-purpose computer system for molecular dynamics simulations","publication_year":2021,"publication_date":"2021-10-21","ids":{"openalex":"https://openalex.org/W3208116483","doi":"https://doi.org/10.1145/3458817.3476190","mag":"3208116483"},"language":"en","primary_location":{"id":"doi:10.1145/3458817.3476190","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3458817.3476190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"article","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/A5002582881","display_name":"Gentaro Morimoto","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gentaro Morimoto","raw_affiliation_strings":["RIKEN BDR, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN BDR, Osaka, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070471763","display_name":"Yohei M. Koyama","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yohei M. Koyama","raw_affiliation_strings":["RIKEN BDR, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN BDR, Osaka, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100396935","display_name":"Hao Zhang","orcid":"https://orcid.org/0000-0002-6129-6410"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Zhang","raw_affiliation_strings":["RIKEN BDR, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN BDR, Osaka, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033102678","display_name":"Teruhisa Komatsu","orcid":"https://orcid.org/0000-0001-9124-8666"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Teruhisa S. Komatsu","raw_affiliation_strings":["RIKEN BDR, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN BDR, Osaka, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053954660","display_name":"Yousuke Ohno","orcid":"https://orcid.org/0000-0002-8124-4941"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yousuke Ohno","raw_affiliation_strings":["RIKEN BDR, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN BDR, Osaka, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110502003","display_name":"Keigo Nishida","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keigo Nishida","raw_affiliation_strings":["RIKEN BDR, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN BDR, Osaka, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013649780","display_name":"Itta Ohmura","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Itta Ohmura","raw_affiliation_strings":["RIKEN BDR, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN BDR, Osaka, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078350766","display_name":"Hiroshi Koyama","orcid":"https://orcid.org/0000-0002-1217-6754"},"institutions":[{"id":"https://openalex.org/I4210150921","display_name":"RIKEN Center for Integrative Medical Sciences","ror":"https://ror.org/04mb6s476","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210150921"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Koyama","raw_affiliation_strings":["RIKEN BDR, Yokohama, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN BDR, Yokohama, Japan","institution_ids":["https://openalex.org/I4210150921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033083222","display_name":"Makoto Taiji","orcid":"https://orcid.org/0000-0002-5317-0500"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Makoto Taiji","raw_affiliation_strings":["RIKEN BDR, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN BDR, Osaka, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5002582881"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.787,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.68831839,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"15"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11809","display_name":"Advanced NMR Techniques and Applications","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11809","display_name":"Advanced NMR Techniques and Applications","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9850999712944031,"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/T11247","display_name":"Plant nutrient uptake and metabolism","score":0.9682999849319458,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7078421115875244},{"id":"https://openalex.org/keywords/ewald-summation","display_name":"Ewald summation","score":0.6916506886482239},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.6552101969718933},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5977140665054321},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5792167782783508},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5626792311668396},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5572595000267029},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5288755893707275},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5281774401664734},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.5021758079528809},{"id":"https://openalex.org/keywords/emulation","display_name":"Emulation","score":0.44534650444984436},{"id":"https://openalex.org/keywords/coulomb","display_name":"Coulomb","score":0.445341557264328},{"id":"https://openalex.org/keywords/octree","display_name":"Octree","score":0.4423184394836426},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.4170282483100891},{"id":"https://openalex.org/keywords/topology","display_name":"Topology (electrical circuits)","score":0.32608237862586975},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26876354217529297},{"id":"https://openalex.org/keywords/molecular-dynamics","display_name":"Molecular dynamics","score":0.23447510600090027},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.21638664603233337},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1501508355140686},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13829249143600464},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12462460994720459},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11684563755989075},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10654732584953308},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09127840399742126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7078421115875244},{"id":"https://openalex.org/C143551052","wikidata":"https://www.wikidata.org/wiki/Q2426155","display_name":"Ewald summation","level":3,"score":0.6916506886482239},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.6552101969718933},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5977140665054321},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5792167782783508},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5626792311668396},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5572595000267029},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5288755893707275},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5281774401664734},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.5021758079528809},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.44534650444984436},{"id":"https://openalex.org/C9342510","wikidata":"https://www.wikidata.org/wiki/Q25406","display_name":"Coulomb","level":3,"score":0.445341557264328},{"id":"https://openalex.org/C141297171","wikidata":"https://www.wikidata.org/wiki/Q1143237","display_name":"Octree","level":2,"score":0.4423184394836426},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.4170282483100891},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.32608237862586975},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26876354217529297},{"id":"https://openalex.org/C59593255","wikidata":"https://www.wikidata.org/wiki/Q901663","display_name":"Molecular dynamics","level":2,"score":0.23447510600090027},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.21638664603233337},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1501508355140686},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13829249143600464},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12462460994720459},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11684563755989075},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10654732584953308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09127840399742126},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C147120987","wikidata":"https://www.wikidata.org/wiki/Q2225","display_name":"Electron","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3458817.3476190","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3458817.3476190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","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":41,"referenced_works":["https://openalex.org/W400726568","https://openalex.org/W1031578623","https://openalex.org/W1565282391","https://openalex.org/W1644459459","https://openalex.org/W1966130600","https://openalex.org/W1978281521","https://openalex.org/W1988609333","https://openalex.org/W1989786408","https://openalex.org/W1991939674","https://openalex.org/W2001676859","https://openalex.org/W2002506550","https://openalex.org/W2027109368","https://openalex.org/W2028263411","https://openalex.org/W2028621953","https://openalex.org/W2035687084","https://openalex.org/W2037549127","https://openalex.org/W2055564206","https://openalex.org/W2058874255","https://openalex.org/W2066345080","https://openalex.org/W2069496487","https://openalex.org/W2069734606","https://openalex.org/W2083206954","https://openalex.org/W2084800760","https://openalex.org/W2088187609","https://openalex.org/W2103945336","https://openalex.org/W2105536200","https://openalex.org/W2105662699","https://openalex.org/W2107879241","https://openalex.org/W2130190210","https://openalex.org/W2162186524","https://openalex.org/W2163112106","https://openalex.org/W2328012222","https://openalex.org/W2328939769","https://openalex.org/W2334862469","https://openalex.org/W2762515459","https://openalex.org/W2983971024","https://openalex.org/W2989374524","https://openalex.org/W3098444613","https://openalex.org/W3098993911","https://openalex.org/W4210426676","https://openalex.org/W4238684711"],"related_works":["https://openalex.org/W2154523322","https://openalex.org/W2083200807","https://openalex.org/W2921135940","https://openalex.org/W2028479167","https://openalex.org/W1987487955","https://openalex.org/W2079102984","https://openalex.org/W2032231896","https://openalex.org/W1966710686","https://openalex.org/W2015590052","https://openalex.org/W1973594099"],"abstract_inverted_index":{"We":[0,84],"developed":[1],"MDGRAPE-4A,":[2],"a":[3,47,80,143],"special-purpose":[4],"computer":[5],"system":[6],"for":[7,30,39,71,75,88,113,128],"molecular":[8],"dynamics":[9],"simulations,":[10],"consisting":[11],"of":[12,15,42,49,117],"512":[13],"nodes":[14],"custom":[16,68],"system-on-a-chip":[17],"LSIs":[18],"with":[19,101,126],"dedicated":[20],"processor":[21],"cores":[22],"and":[23,52,74,132],"interconnects":[24],"designed":[25],"to":[26,106],"achieve":[27],"strong":[28],"scalability":[29],"biomolecular":[31],"simulations.":[32],"To":[33],"reduce":[34],"the":[35,40,50,53,67,86,89,114,129,133],"global":[36],"communications":[37],"required":[38],"evaluation":[41],"Coulomb":[43,118],"interactions,":[44],"we":[45],"conducted":[46],"co-design":[48],"MDGRAPE-4A":[51],"novel":[54],"algorithm,":[55],"tensor-structured":[56],"multilevel":[57],"Ewald":[58],"summation":[59],"method":[60],"(TME),":[61],"which":[62,122,140],"produced":[63],"hardware":[64],"modules":[65],"on":[66,79,97],"LSI":[69],"circuit":[70],"particle-grid":[72],"operations":[73],"grid-grid":[76],"separable":[77],"convolutions":[78],"3D":[81,95],"torus":[82],"network.":[83],"implemented":[85],"convolution":[87],"top-level":[90],"grid":[91,108],"potentials":[92],"by":[93],"using":[94],"FFTs":[96],"an":[98,102],"FPGA,":[99],"along":[100],"FPGA-based":[103],"octree":[104],"network":[105],"gather":[107],"charges.":[109],"The":[110],"elapsed":[111],"time":[112],"long-range":[115],"part":[116],"is":[119,136,141],"50":[120],"\u03bcs,":[121],"can":[123],"mostly":[124],"overlap":[125],"those":[127],"short-range":[130],"part,":[131],"additional":[134],"cost":[135],"approximately":[137],"10":[138],"\u03bcs/step,":[139],"only":[142],"5%":[144],"performance":[145],"loss.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}