{"id":"https://openalex.org/W2916280107","doi":"https://doi.org/10.1177/1094342019828153","title":"Performance portable parallel programming of heterogeneous stencils across shared-memory platforms with modern Intel processors","display_name":"Performance portable parallel programming of heterogeneous stencils across shared-memory platforms with modern Intel processors","publication_year":2019,"publication_date":"2019-02-24","ids":{"openalex":"https://openalex.org/W2916280107","doi":"https://doi.org/10.1177/1094342019828153","mag":"2916280107"},"language":"en","primary_location":{"id":"doi:10.1177/1094342019828153","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342019828153","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-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/A5033643387","display_name":"\u0141ukasz Szustak","orcid":"https://orcid.org/0000-0001-7429-6981"},"institutions":[{"id":"https://openalex.org/I130294970","display_name":"Cz\u0119stochowa University of Technology","ror":"https://ror.org/046awyn59","country_code":"PL","type":"education","lineage":["https://openalex.org/I130294970"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Lukasz Szustak","raw_affiliation_strings":["Institute of Computer and Information Science, Faculty of Mechanical Engineering and Computer Science, Czestochowa University of Technology, Czestochowa, Poland"],"affiliations":[{"raw_affiliation_string":"Institute of Computer and Information Science, Faculty of Mechanical Engineering and Computer Science, Czestochowa University of Technology, Czestochowa, Poland","institution_ids":["https://openalex.org/I130294970"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054380674","display_name":"Pawe\u0142 Bratek","orcid":"https://orcid.org/0000-0003-4615-063X"},"institutions":[{"id":"https://openalex.org/I130294970","display_name":"Cz\u0119stochowa University of Technology","ror":"https://ror.org/046awyn59","country_code":"PL","type":"education","lineage":["https://openalex.org/I130294970"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Pawel Bratek","raw_affiliation_strings":["Institute of Computer and Information Science, Faculty of Mechanical Engineering and Computer Science, Czestochowa University of Technology, Czestochowa, Poland"],"affiliations":[{"raw_affiliation_string":"Institute of Computer and Information Science, Faculty of Mechanical Engineering and Computer Science, Czestochowa University of Technology, Czestochowa, Poland","institution_ids":["https://openalex.org/I130294970"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5033643387"],"corresponding_institution_ids":["https://openalex.org/I130294970"],"apc_list":null,"apc_paid":null,"fwci":1.3034,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.81731691,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"33","issue":"3","first_page":"534","last_page":"553"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9977999925613403,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9977999925613403,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9955999851226807,"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":0.9902999997138977,"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":0.81858229637146},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8106634616851807},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.6686398386955261},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.6389208436012268},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5926520824432373},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.49331942200660706},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.4726404547691345},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.46262145042419434},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43606802821159363},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.42055752873420715},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.414531946182251},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.3249056935310364},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.26376473903656006},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.20914265513420105},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.12787815928459167},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12456446886062622},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10262799263000488}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.81858229637146},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8106634616851807},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.6686398386955261},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.6389208436012268},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5926520824432373},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49331942200660706},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.4726404547691345},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.46262145042419434},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43606802821159363},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.42055752873420715},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.414531946182251},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3249056935310364},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.26376473903656006},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.20914265513420105},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.12787815928459167},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12456446886062622},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10262799263000488},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342019828153","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342019828153","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7035430154","display_name":null,"funder_award_id":"UMO-2017/26/D/ST6/00687","funder_id":"https://openalex.org/F4320322511","funder_display_name":"Narodowe Centrum Nauki"}],"funders":[{"id":"https://openalex.org/F4320322511","display_name":"Narodowe Centrum Nauki","ror":"https://ror.org/03ha2q922"},{"id":"https://openalex.org/F4320322691","display_name":"Politechnika Czestochowska","ror":"https://ror.org/046awyn59"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W37300632","https://openalex.org/W597802218","https://openalex.org/W1559264847","https://openalex.org/W1790519466","https://openalex.org/W1888553388","https://openalex.org/W1972883104","https://openalex.org/W1972922682","https://openalex.org/W1975539849","https://openalex.org/W1984884576","https://openalex.org/W1997147891","https://openalex.org/W2013917929","https://openalex.org/W2035430533","https://openalex.org/W2055722407","https://openalex.org/W2066139250","https://openalex.org/W2075022716","https://openalex.org/W2088907061","https://openalex.org/W2097757554","https://openalex.org/W2128438553","https://openalex.org/W2143161696","https://openalex.org/W2204773283","https://openalex.org/W2286735113","https://openalex.org/W2304365713","https://openalex.org/W2401247912","https://openalex.org/W2466690044","https://openalex.org/W2468778256","https://openalex.org/W2508492666","https://openalex.org/W2524741702","https://openalex.org/W2526069705","https://openalex.org/W2556150493","https://openalex.org/W2556888804","https://openalex.org/W2625627861","https://openalex.org/W2730364998","https://openalex.org/W2739885786","https://openalex.org/W2767127698","https://openalex.org/W2777139487","https://openalex.org/W2782482897","https://openalex.org/W2889034910","https://openalex.org/W2963242393","https://openalex.org/W3102336280","https://openalex.org/W3105204543","https://openalex.org/W4248486648"],"related_works":["https://openalex.org/W2031026366","https://openalex.org/W2717174904","https://openalex.org/W2066653375","https://openalex.org/W4255694249","https://openalex.org/W3184765594","https://openalex.org/W1998641004","https://openalex.org/W2548545698","https://openalex.org/W2482815832","https://openalex.org/W2294358097","https://openalex.org/W2189498595"],"abstract_inverted_index":{"In":[0],"this":[1,53],"work,":[2],"we":[3,55],"take":[4],"up":[5],"the":[6,31,39,44,48,69,99,103,130,134,145,157,169,182,185,192,206],"challenge":[7],"of":[8,12,20,27,43,47,59,68,102,120,133,144,153,156,168,196,205],"performance":[9,111,132,150,195],"portable":[10],"programming":[11],"heterogeneous":[13],"stencil":[14],"computations":[15,29],"across":[16],"a":[17,57,127,140],"wide":[18],"range":[19],"modern":[21],"shared-memory":[22],"systems.":[23],"An":[24],"important":[25],"example":[26],"such":[28],"is":[30,137,164],"Multidimensional":[32],"Positive":[33],"Definite":[34],"Advection":[35],"Transport":[36],"Algorithm":[37],"(MPDATA),":[38],"second":[40],"major":[41],"part":[42],"dynamic":[45],"core":[46],"EULAG":[49],"geophysical":[50],"model.":[51],"For":[52],"aim,":[54],"develop":[56,98],"set":[58],"parametric":[60],"optimization":[61],"techniques":[62,74],"and":[63,83,89,177],"four-step":[64],"procedure":[65],"for":[66,112,126,161,166],"customization":[67],"MPDATA":[70,104],"code.":[71],"Among":[72],"these":[73],"are:":[75],"islands-of-cores":[76],"strategy,":[77],"(3+1)D":[78],"decomposition,":[79],"exploiting":[80],"data":[81,86],"parallelism":[82],"simultaneous":[84],"multithreading,":[85],"flow":[87],"synchronization,":[88],"vectorization.":[90],"The":[91,148],"proposed":[92],"adaptation":[93],"methodology":[94],"helps":[95],"us":[96],"to":[97,106,202],"automatic":[100],"transformation":[101],"code":[105,136],"achieve":[107],"high":[108],"sustained":[109,131,194],"scalable":[110],"all":[113,162],"tested":[114],"ccNUMA":[115],"platforms":[116],"with":[117,188],"Intel":[118],"processors":[119,190],"last":[121],"generations.":[122],"This":[123],"means":[124],"that":[125,200],"given":[128],"platform,":[129],"new":[135],"kept":[138],"at":[139],"similar":[141],"level,":[142],"independently":[143],"problem":[146],"size.":[147],"highest":[149,193],"utilization":[151],"rate":[152],"about":[154,203],"41\u201346%":[155],"theoretical":[158],"peak,":[159],"measured":[160],"benchmarks,":[163],"provided":[165],"any":[167],"two-socket":[170],"servers":[171],"based":[172],"on":[173],"Skylake-SP":[174],"(SKL-SP),":[175],"Broadwell,":[176],"Haswell":[178],"CPU":[179],"architectures.":[180],"At":[181],"same":[183],"time,":[184],"four-socket":[186],"server":[187],"SKL-SP":[189],"achieves":[191],"around":[197],"1.0\u20131.1":[198],"Tflop/s":[199],"corresponds":[201],"33%":[204],"peak.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}
