{"id":"https://openalex.org/W2968147299","doi":"https://doi.org/10.1145/3341069.3341071","title":"Optimization of Jacobi Iteration on the Intel Xeon Phi","display_name":"Optimization of Jacobi Iteration on the Intel Xeon Phi","publication_year":2019,"publication_date":"2019-06-22","ids":{"openalex":"https://openalex.org/W2968147299","doi":"https://doi.org/10.1145/3341069.3341071","mag":"2968147299"},"language":"en","primary_location":{"id":"doi:10.1145/3341069.3341071","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3341069.3341071","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","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/A5016964586","display_name":"Wenxiang Yang","orcid":"https://orcid.org/0000-0002-7912-0181"},"institutions":[{"id":"https://openalex.org/I2802505932","display_name":"China Aerodynamics Research and Development Center","ror":"https://ror.org/00jma8s40","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802505932"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenxiang Yang","raw_affiliation_strings":["China Aerodynamics Research and Development Center, Mianyang, China"],"affiliations":[{"raw_affiliation_string":"China Aerodynamics Research and Development Center, Mianyang, China","institution_ids":["https://openalex.org/I2802505932"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110264109","display_name":"Jiming Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I2802505932","display_name":"China Aerodynamics Research and Development Center","ror":"https://ror.org/00jma8s40","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802505932"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiming Zou","raw_affiliation_strings":["China Aerodynamics Research and Development Center, Mianyang, China"],"affiliations":[{"raw_affiliation_string":"China Aerodynamics Research and Development Center, Mianyang, China","institution_ids":["https://openalex.org/I2802505932"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023992845","display_name":"Liang Deng","orcid":"https://orcid.org/0000-0003-1444-4588"},"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"]},{"id":"https://openalex.org/I2802505932","display_name":"China Aerodynamics Research and Development Center","ror":"https://ror.org/00jma8s40","country_code":"CN","type":"facility","lineage":["https://openalex.org/I2802505932"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Deng","raw_affiliation_strings":["China Aerodynamics Research and Development Center, Mianyang, China, School of Computer Science, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"China Aerodynamics Research and Development Center, Mianyang, China, School of Computer Science, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I2802505932","https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016964586"],"corresponding_institution_ids":["https://openalex.org/I2802505932"],"apc_list":null,"apc_paid":null,"fwci":0.2408,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.48760762,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9988999962806702,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9941999912261963,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8151392936706543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7870268821716309},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.7487791180610657},{"id":"https://openalex.org/keywords/loop-unrolling","display_name":"Loop unrolling","score":0.6616946458816528},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.6454416513442993},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5542548894882202},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.4860863983631134},{"id":"https://openalex.org/keywords/jacobi-method","display_name":"Jacobi method","score":0.45485615730285645},{"id":"https://openalex.org/keywords/subroutine","display_name":"Subroutine","score":0.43749773502349854},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4300975799560547},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.39019283652305603},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.17474475502967834},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.1384904384613037},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11567452549934387},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11481583118438721}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8151392936706543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7870268821716309},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.7487791180610657},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.6616946458816528},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.6454416513442993},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5542548894882202},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.4860863983631134},{"id":"https://openalex.org/C67923128","wikidata":"https://www.wikidata.org/wiki/Q1481893","display_name":"Jacobi method","level":2,"score":0.45485615730285645},{"id":"https://openalex.org/C96147967","wikidata":"https://www.wikidata.org/wiki/Q190686","display_name":"Subroutine","level":2,"score":0.43749773502349854},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4300975799560547},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.39019283652305603},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.17474475502967834},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.1384904384613037},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11567452549934387},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11481583118438721}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3341069.3341071","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3341069.3341071","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","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":6,"referenced_works":["https://openalex.org/W1961751213","https://openalex.org/W1997147891","https://openalex.org/W2039378765","https://openalex.org/W2154786353","https://openalex.org/W3103104567","https://openalex.org/W3152199537"],"related_works":["https://openalex.org/W3008658471","https://openalex.org/W1908180445","https://openalex.org/W3092174096","https://openalex.org/W2035419609","https://openalex.org/W3205799311","https://openalex.org/W2269110805","https://openalex.org/W4300860486","https://openalex.org/W1766386015","https://openalex.org/W2597386847","https://openalex.org/W2963706620"],"abstract_inverted_index":{"Jacobi":[0,30,110],"iteration":[1,31,111],"based":[2],"on":[3,37,91,97],"finite":[4,7],"difference":[5],"and":[6,44,56,61,86,117],"element":[8],"discrete":[9],"scheme":[10],"is":[11],"a":[12,124],"kind":[13],"of":[14,29,121],"typical":[15],"stencil":[16],"computation":[17],"in":[18,32,66,82,102],"scientific":[19],"computing.":[20],"In":[21],"this":[22],"paper,":[23],"we":[24],"analyze":[25],"the":[26,33,38,76,88,92,103],"parallel":[27,115],"optimization":[28,64,90],"real":[34],"CFD":[35],"codes":[36],"Intel":[39,98],"Many":[40],"Integrated":[41],"Core":[42],"architecture,":[43],"get":[45],"high":[46],"performance.":[47],"We":[48,69],"use":[49],"loop":[50,57],"fusion,":[51],"data":[52],"structure":[53],"transformation,":[54],"subroutine":[55],"unrolling,":[58],"cache":[59],"blocking":[60],"some":[62],"other":[63],"techniques":[65],"our":[67,109],"implementation.":[68],"also":[70],"collect":[71],"hardware":[72],"performance":[73,79,89],"indicators":[74],"through":[75],"open":[77],"source":[78],"analysis":[80],"tools,":[81],"order":[83],"to":[84],"guide":[85],"verify":[87],"many-core":[93],"architectures.":[94],"Experimental":[95],"results":[96],"Xeon":[99],"Phi":[100],"working":[101],"native":[104],"execution":[105],"mode":[106],"show":[107],"that":[108],"can":[112],"achieve":[113],"83.47%":[114],"efficiency":[116],"4.73":[118],"speed":[119],"ratio":[120],"vectorization":[122],"with":[123],"128":[125,127],"\u00d7":[126,128],"256":[129],"grid.":[130]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
