{"id":"https://openalex.org/W2996303834","doi":"https://doi.org/10.1145/3368474.3368484","title":"Scalable Direct-Iterative Hybrid Solver for Sparse Matrices on Multi-Core and Vector Architectures","display_name":"Scalable Direct-Iterative Hybrid Solver for Sparse Matrices on Multi-Core and Vector Architectures","publication_year":2019,"publication_date":"2019-12-17","ids":{"openalex":"https://openalex.org/W2996303834","doi":"https://doi.org/10.1145/3368474.3368484","mag":"2996303834"},"language":"en","primary_location":{"id":"doi:10.1145/3368474.3368484","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3368474.3368484","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3368474.3368484","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on High Performance Computing in Asia-Pacific Region","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/10.1145/3368474.3368484","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043279624","display_name":"Kenji Ono","orcid":"https://orcid.org/0000-0003-2679-7196"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kenji Ono","raw_affiliation_strings":["Kyushu University, Fukuoka, Japan"],"affiliations":[{"raw_affiliation_string":"Kyushu University, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077342395","display_name":"Toshihiro Kato","orcid":"https://orcid.org/0000-0002-1468-5405"},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshihiro Kato","raw_affiliation_strings":["NEC Corporation, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NEC Corporation, Tokyo, Japan","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080142917","display_name":"Satoshi Ohshima","orcid":"https://orcid.org/0000-0003-4073-5688"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Ohshima","raw_affiliation_strings":["Nagoya University, Nagoya, Japan"],"affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015306862","display_name":"Takeshi Nanri","orcid":null},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeshi Nanri","raw_affiliation_strings":["Kyushu University, Fukuoka, Japan"],"affiliations":[{"raw_affiliation_string":"Kyushu University, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5043279624"],"corresponding_institution_ids":["https://openalex.org/I135598925"],"apc_list":null,"apc_paid":null,"fwci":0.582,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.71742477,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"11","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9998999834060669,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9943000078201294,"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/T11416","display_name":"Numerical methods for differential equations","score":0.9861000180244446,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8383849859237671},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8366902470588684},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6875357627868652},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.613886833190918},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.611270010471344},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5747313499450684},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5455403923988342},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.42743057012557983},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.41336360573768616}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8383849859237671},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8366902470588684},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6875357627868652},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.613886833190918},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.611270010471344},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5747313499450684},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5455403923988342},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.42743057012557983},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.41336360573768616},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"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:10.1145/3368474.3368484","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3368474.3368484","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3368474.3368484","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on High Performance Computing in Asia-Pacific Region","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3368474.3368484","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3368474.3368484","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3368474.3368484","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on High Performance Computing in Asia-Pacific Region","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"},{"id":"https://openalex.org/F4320336976","display_name":"Research Institute for Information Technology, Kyushu University","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2996303834.pdf","grobid_xml":"https://content.openalex.org/works/W2996303834.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1493749856","https://openalex.org/W1876992439","https://openalex.org/W1990523337","https://openalex.org/W2006850990","https://openalex.org/W2017838066","https://openalex.org/W2027063888","https://openalex.org/W2045992017","https://openalex.org/W2051797821","https://openalex.org/W2079810565","https://openalex.org/W2112185810","https://openalex.org/W2136791882","https://openalex.org/W2170802276","https://openalex.org/W2312813920","https://openalex.org/W2321653420","https://openalex.org/W2906792484","https://openalex.org/W4239609053"],"related_works":["https://openalex.org/W2099629705","https://openalex.org/W1992352827","https://openalex.org/W3012895752","https://openalex.org/W1509422975","https://openalex.org/W4376647684","https://openalex.org/W2031026393","https://openalex.org/W2063611263","https://openalex.org/W2030992542","https://openalex.org/W1541167181","https://openalex.org/W4389888442"],"abstract_inverted_index":{"In":[0,138],"the":[1,17,20,29,33,44,62,84,88,97,108,112,120,135,140,155],"present":[2,39],"paper,":[3],"we":[4],"propose":[5],"an":[6,40],"efficient":[7,41,81],"direct-iterative":[8],"hybrid":[9,66],"solver":[10,99],"for":[11,47,75],"sparse":[12],"matrices":[13],"that":[14,53,96,118],"can":[15,86],"derive":[16],"scalability":[18,102],"of":[19,32,43,83,119,130,152],"latest":[21],"multi-core,":[22],"many-core,":[23],"and":[24,27,49,111,123],"vector":[25,50],"architectures":[26,51],"examine":[28],"execution":[30],"performance":[31,94,114],"proposed":[34,65],"SLOR-PCR":[35,98],"method.":[36],"We":[37],"also":[38],"implementation":[42],"PCR":[45],"algorithm":[46],"SIMD":[48,136],"so":[52],"it":[54],"is":[55,73],"easy":[56],"to":[57,104,132,148],"output":[58],"instructions":[59],"optimized":[60],"by":[61,127],"compiler.":[63],"The":[64,92],"method":[67,126],"has":[68],"high":[69],"cache":[70,85],"reusability,":[71],"which":[72],"favorable":[74],"modern":[76],"low":[77],"B/F":[78],"architecture":[79,157],"because":[80],"use":[82],"mitigate":[87],"memory":[89],"bandwidth":[90],"limitation.":[91],"measured":[93],"revealed":[95],"showed":[100],"excellent":[101],"up":[103],"352":[105,159],"cores":[106],"on":[107,134,154],"cc-NUMA":[109,156],"environment,":[110],"achieved":[113],"was":[115,146],"higher":[116],"than":[117],"conventional":[121],"Jacobi":[122],"Red-Black":[124],"ordering":[125],"a":[128,150],"factor":[129,151],"3.6":[131],"8.3":[133],"architecture.":[137],"addition,":[139],"maximum":[141],"speedup":[142],"in":[143],"computation":[144],"time":[145],"observed":[147],"be":[149],"6.3":[153],"with":[158],"cores.":[160]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}