{"id":"https://openalex.org/W4381328331","doi":"https://doi.org/10.1145/3577193.3593726","title":"Optimizing Multi-grid Computation and Parallelization on Multi-cores","display_name":"Optimizing Multi-grid Computation and Parallelization on Multi-cores","publication_year":2023,"publication_date":"2023-06-20","ids":{"openalex":"https://openalex.org/W4381328331","doi":"https://doi.org/10.1145/3577193.3593726"},"language":"en","primary_location":{"id":"doi:10.1145/3577193.3593726","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577193.3593726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th International Conference on Supercomputing","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/A5101776727","display_name":"Xiaojian Yang","orcid":"https://orcid.org/0009-0007-9821-171X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaojian Yang","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087730416","display_name":"Shengguo Li","orcid":"https://orcid.org/0000-0001-7827-6304"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengguo Li","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038684857","display_name":"Y. X. Fan","orcid":"https://orcid.org/0009-0003-9022-0727"},"institutions":[{"id":"https://openalex.org/I4610292","display_name":"Xiangtan University","ror":"https://ror.org/00xsfaz62","country_code":"CN","type":"education","lineage":["https://openalex.org/I4610292"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yuan","raw_affiliation_strings":["Xiangtan University, Xiangtan, China"],"affiliations":[{"raw_affiliation_string":"Xiangtan University, Xiangtan, China","institution_ids":["https://openalex.org/I4610292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006729432","display_name":"Dezun Dong","orcid":"https://orcid.org/0000-0001-6243-8479"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dezun Dong","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101626850","display_name":"Chun Huang","orcid":"https://orcid.org/0000-0002-0317-8192"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Huang","raw_affiliation_strings":["National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100401045","display_name":"Zheng Wang","orcid":"https://orcid.org/0000-0001-6157-0662"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zheng Wang","raw_affiliation_strings":["University of Leeds, Leeds, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Leeds, Leeds, United Kingdom","institution_ids":["https://openalex.org/I130828816"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101776727"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":2.7269,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.90060976,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"227","last_page":"239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9994000196456909,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.992900013923645,"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/computer-science","display_name":"Computer science","score":0.8689140677452087},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8227793574333191},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6234225034713745},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.592627227306366},{"id":"https://openalex.org/keywords/x86","display_name":"x86","score":0.5310571193695068},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5036472678184509},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4134840965270996},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4117977023124695},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3349706828594208},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2515087127685547},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.1849336326122284},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.12364625930786133}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8689140677452087},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8227793574333191},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6234225034713745},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.592627227306366},{"id":"https://openalex.org/C170723468","wikidata":"https://www.wikidata.org/wiki/Q182933","display_name":"x86","level":3,"score":0.5310571193695068},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5036472678184509},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4134840965270996},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4117977023124695},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3349706828594208},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2515087127685547},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.1849336326122284},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.12364625930786133},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3577193.3593726","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3577193.3593726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th International Conference on Supercomputing","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:198955","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/12","display_name":"Responsible consumption and production"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W993511226","https://openalex.org/W1506342804","https://openalex.org/W1589783193","https://openalex.org/W1845641575","https://openalex.org/W1987896015","https://openalex.org/W1991173503","https://openalex.org/W1994104955","https://openalex.org/W1998373364","https://openalex.org/W2004951603","https://openalex.org/W2009196736","https://openalex.org/W2013029558","https://openalex.org/W2035080386","https://openalex.org/W2060803192","https://openalex.org/W2080090223","https://openalex.org/W2082146198","https://openalex.org/W2088866486","https://openalex.org/W2099611016","https://openalex.org/W2101511474","https://openalex.org/W2104373803","https://openalex.org/W2111784516","https://openalex.org/W2148497060","https://openalex.org/W2314577266","https://openalex.org/W2316564661","https://openalex.org/W2318393100","https://openalex.org/W2331164610","https://openalex.org/W2794424798","https://openalex.org/W2901426413","https://openalex.org/W2936463352","https://openalex.org/W3034899595","https://openalex.org/W3098281632","https://openalex.org/W3127904641","https://openalex.org/W3210190478","https://openalex.org/W4210809102","https://openalex.org/W4226064176","https://openalex.org/W4245743185","https://openalex.org/W4301491118"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W2216575582","https://openalex.org/W2096357811","https://openalex.org/W2072005592"],"abstract_inverted_index":{"Multigrid":[0],"algorithms":[1,51],"are":[2],"widely":[3],"used":[4],"to":[5,37,67,104],"solve":[6],"large-scale":[7],"sparse":[8],"linear":[9],"systems,":[10],"which":[11],"is":[12,23],"essential":[13],"for":[14,26],"many":[15],"high-performance":[16],"workloads.":[17],"The":[18],"symmetric":[19],"Gauss-Seidel":[20],"(SYMGS)":[21],"method":[22],"often":[24],"responsible":[25],"the":[27,41,47,69,86,106,114,123,147],"performance":[28,148],"bottleneck":[29],"of":[30,46,91,95,116,149],"MG.":[31,92],"This":[32],"paper":[33],"presents":[34],"new":[35,79,100],"methods":[36],"parallelize":[38],"and":[39,43,49,62,72,126,138,151,157],"enhance":[40],"computation":[42,65,70],"parallelization":[44,102],"efficiency":[45],"SYMGS":[48,80],"MG":[50],"on":[52,132],"multi-core":[53],"CPUs.":[54],"Our":[55],"solution":[56],"employs":[57],"a":[58,63,99],"matrix":[59],"splitting":[60],"strategy":[61],"revised":[64],"formula":[66],"decrease":[68],"operations":[71],"memory":[73],"accesses":[74],"in":[75],"SYMGS.":[76,111],"With":[77],"this":[78],"strategy,":[81],"we":[82,97],"can":[83],"then":[84],"merge":[85],"two":[87,127],"most":[88],"time-consuming":[89],"components":[90],"On":[93],"top":[94],"these,":[96],"propose":[98],"asynchronous":[101],"scheme":[103],"reduce":[105],"synchronization":[107],"overhead":[108],"when":[109],"parallelizing":[110],"We":[112],"demonstrate":[113],"benefit":[115],"our":[117,143],"techniques":[118,144],"by":[119],"integrating":[120],"them":[121],"with":[122],"HPCG":[124],"benchmark":[125],"real-life":[128],"applications.":[129],"Evaluation":[130],"conducted":[131],"four":[133],"architectures,":[134],"including":[135],"three":[136],"ARMv8":[137],"one":[139],"x86,":[140],"shows":[141],"that":[142],"greatly":[145],"surpass":[146],"engineer-":[150],"vendor-tuned":[152],"implementations":[153],"across":[154],"various":[155],"workloads":[156],"platforms.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
