{"id":"https://openalex.org/W4321446141","doi":"https://doi.org/10.1145/3572848.3577517","title":"A Scalable Hybrid Total FETI Method for Massively Parallel FEM Simulations","display_name":"A Scalable Hybrid Total FETI Method for Massively Parallel FEM Simulations","publication_year":2023,"publication_date":"2023-02-21","ids":{"openalex":"https://openalex.org/W4321446141","doi":"https://doi.org/10.1145/3572848.3577517"},"language":"en","primary_location":{"id":"doi:10.1145/3572848.3577517","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3572848.3577517","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3572848.3577517","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3572848.3577517","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069261260","display_name":"Kehao Lin","orcid":"https://orcid.org/0000-0002-9651-3593"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]},{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kehao Lin","raw_affiliation_strings":["Hangzhou Dianzi University, Hangzhou, China and Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University, Hangzhou, China and Computer Network Information Center, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I50760025","https://openalex.org/I19820366","https://openalex.org/I4210108629"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103552831","display_name":"Chunbao Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunbao Zhou","raw_affiliation_strings":["Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210108629","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008416156","display_name":"Yan Zeng","orcid":"https://orcid.org/0000-0003-2026-417X"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Zeng","raw_affiliation_strings":["Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012495474","display_name":"Ningming Nie","orcid":"https://orcid.org/0000-0002-6254-0147"},"institutions":[{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ningming Nie","raw_affiliation_strings":["Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210108629","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440604","display_name":"Jue Wang","orcid":"https://orcid.org/0000-0002-3641-3136"},"institutions":[{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jue Wang","raw_affiliation_strings":["Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210108629","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088172355","display_name":"Shigang Li","orcid":"https://orcid.org/0000-0003-0022-7865"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shigang Li","raw_affiliation_strings":["School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026897600","display_name":"Yangde Feng","orcid":"https://orcid.org/0000-0002-0205-5561"},"institutions":[{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangde Feng","raw_affiliation_strings":["Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210108629","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100758518","display_name":"Yangang Wang","orcid":"https://orcid.org/0000-0002-1325-9252"},"institutions":[{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangang Wang","raw_affiliation_strings":["Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210108629","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044320341","display_name":"Kehan Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]},{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kehan Yao","raw_affiliation_strings":["Hangzhou Dianzi University, Hangzhou, China and Computer Network Information Center, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University, Hangzhou, China and Computer Network Information Center, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I50760025","https://openalex.org/I19820366","https://openalex.org/I4210108629"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006958929","display_name":"Tiechui Yao","orcid":"https://orcid.org/0000-0002-1928-0466"},"institutions":[{"id":"https://openalex.org/I4210108629","display_name":"Computer Network Information Center","ror":"https://ror.org/01s0wyf50","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210108629"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tiechui Yao","raw_affiliation_strings":["Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Network Information Center, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210108629","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100624320","display_name":"Jilin Zhang","orcid":"https://orcid.org/0000-0002-0423-9356"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jilin Zhang","raw_affiliation_strings":["Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082606335","display_name":"Jian Wan","orcid":"https://orcid.org/0000-0001-9882-3029"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Wan","raw_affiliation_strings":["Hangzhou Dianzi University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hangzhou Dianzi University, Hangzhou, China","institution_ids":["https://openalex.org/I50760025"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":12,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2883,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4469962,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"135","last_page":"147"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9972000122070312,"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":0.9972000122070312,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9904999732971191,"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"}},{"id":"https://openalex.org/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.9876999855041504,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7655370235443115},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7502462267875671},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7128913998603821},{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.5756250619888306},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5162580013275146},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.5076524019241333},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35507336258888245},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12292173504829407},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.11012953519821167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7655370235443115},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7502462267875671},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7128913998603821},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.5756250619888306},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5162580013275146},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.5076524019241333},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35507336258888245},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12292173504829407},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.11012953519821167},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3572848.3577517","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3572848.3577517","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3572848.3577517","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3572848.3577517","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3572848.3577517","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3572848.3577517","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1131598070","display_name":null,"funder_award_id":"2019YFB2102100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3541693721","display_name":"\u201c\u5b66\u4e60\u9a71\u52a8\u578b\u201d\u8fb9\u7f18\u667a\u80fd\u7cfb\u7edf\u6027\u80fd\u4f18\u5316\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"62072146","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3697398574","display_name":null,"funder_award_id":"2020YFB0204802","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4611520700","display_name":null,"funder_award_id":"2019YFB2102100","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6306364297","display_name":null,"funder_award_id":"2021C03187","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327480","display_name":"China Institute of Atomic Energy","ror":"https://ror.org/00v5gqm66"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4321446141.pdf","grobid_xml":"https://content.openalex.org/works/W4321446141.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1538076361","https://openalex.org/W1578616456","https://openalex.org/W1983220757","https://openalex.org/W2005390260","https://openalex.org/W2018190542","https://openalex.org/W2139172930","https://openalex.org/W2140639233","https://openalex.org/W2193930533","https://openalex.org/W2350868417","https://openalex.org/W2612209529","https://openalex.org/W2781038251","https://openalex.org/W2891492949","https://openalex.org/W2899066514","https://openalex.org/W2941348163","https://openalex.org/W2971023069","https://openalex.org/W2990407694","https://openalex.org/W3080244561","https://openalex.org/W3129903487","https://openalex.org/W3130670923","https://openalex.org/W3138259231","https://openalex.org/W3206504463","https://openalex.org/W4235209476"],"related_works":["https://openalex.org/W2380023786","https://openalex.org/W2503642292","https://openalex.org/W119040397","https://openalex.org/W2587522138","https://openalex.org/W2986192809","https://openalex.org/W2090121564","https://openalex.org/W1531488649","https://openalex.org/W1970172627","https://openalex.org/W2535500072","https://openalex.org/W3045060527"],"abstract_inverted_index":{"The":[0],"Hybrid":[1],"Total":[2],"Finite":[3],"Element":[4],"Tearing":[5],"and":[6,17,60,102,116,133,135,169,175,180,203],"Interconnecting":[7],"(HTFETI)":[8],"method":[9,22,153],"plays":[10],"an":[11],"important":[12],"role":[13],"in":[14,55,201],"solving":[15],"large-scale":[16,202],"complex":[18],"engineering":[19],"problems.":[20],"This":[21],"needs":[23],"to":[24,42,97,142,154],"handle":[25],"numerous":[26],"matrix-vector":[27,36],"multiplications.":[28],"Directly":[29],"calling":[30],"the":[31,76,82,85,90,98,136,150,156,170,193],"vendor-optimized":[32],"library":[33],"for":[34,51,73,166],"general":[35],"multiplication":[37],"(gemv)":[38],"on":[39,109,130,182],"GPU":[40],"leads":[41],"low":[43],"performance,":[44],"since":[45,75],"it":[46],"does":[47],"not":[48],"consider":[49],"optimizations":[50],"different":[52,58],"matrix":[53,77],"sizes":[54],"HTFETI,":[56,74],"i.e.":[57],"row":[59],"column":[61],"sizes.":[62],"In":[63],"addition,":[64],"state-of-the-art":[65],"graph":[66,131],"partitioning":[67],"methods":[68],"cannot":[69],"guarantee":[70],"load":[71,137],"balancing":[72],"size":[78],"is":[79,140,192],"determined":[80],"by":[81],"length":[83],"of":[84,160,172],"subdomain":[86],"boundary.":[87],"To":[88],"solve":[89],"problems":[91],"above,":[92],"we":[93,189],"first":[94,194],"port":[95],"gemv":[96],"multi-stream":[99],"pipeline":[100],"scheme":[101,128],"develop":[103],"a":[104,125],"new":[105],"batched":[106],"kernel":[107],"function":[108],"GPU,":[110],"which":[111],"brings":[112],"15%~30%":[113],"throughput":[114],"improvement":[115],"37%":[117],"average":[118],"GFLOPs":[119],"improvement,":[120],"respectively.":[121,185],"We":[122,146],"also":[123],"propose":[124],"multi-grained":[126],"load-balancing":[127],"based":[129],"repartitioning":[132],"work-stealing,":[134],"imbalance":[138],"ratio":[139],"down":[141],"1.05~1.09":[143],"from":[144],"1.5.":[145],"have":[147],"successfully":[148],"applied":[149],"scalable":[151],"HTFETI":[152,197],"simulate":[155],"whole":[157,205],"core":[158,206],"assembly":[159,207],"China":[161],"Experimental":[162],"Fast":[163],"Reactor":[164],"(CEFR)":[165],"steady-state":[167],"analysis,":[168],"efficiencies":[171],"weak":[173],"scalability":[174,177],"strong":[176],"reach":[178],"78%":[179],"72%":[181],"12,288":[183],"GPUs,":[184],"As":[186],"far":[187],"as":[188],"know,":[190],"this":[191],"time":[195],"that":[196],"has":[198],"been":[199],"used":[200],"high-fidelity":[204],"simulation.":[208]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
