{"id":"https://openalex.org/W2105221648","doi":"https://doi.org/10.1177/1094342014524807","title":"Evaluating multi-core and many-core architectures through accelerating the three-dimensional Lax\u2013Wendroff correction stencil","display_name":"Evaluating multi-core and many-core architectures through accelerating the three-dimensional Lax\u2013Wendroff correction stencil","publication_year":2014,"publication_date":"2014-03-05","ids":{"openalex":"https://openalex.org/W2105221648","doi":"https://doi.org/10.1177/1094342014524807","mag":"2105221648"},"language":"en","primary_location":{"id":"doi:10.1177/1094342014524807","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342014524807","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/A5100658705","display_name":"Yang You","orcid":"https://orcid.org/0000-0003-2816-4384"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang You","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031545295","display_name":"Haohuan Fu","orcid":"https://orcid.org/0000-0002-6982-2235"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haohuan Fu","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, China","Ministry of Education Key Laboratory for Earth System Modeling, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Ministry of Education Key Laboratory for Earth System Modeling, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043209884","display_name":"Shuaiwen Leon Song","orcid":"https://orcid.org/0000-0002-8402-1436"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuaiwen Leon Song","raw_affiliation_strings":["Pacific Northwest National Laboratory, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003682451","display_name":"Maryam Mehri Dehnavi","orcid":"https://orcid.org/0000-0002-2719-8788"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maryam Mehri Dehnavi","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038750675","display_name":"Lin Gan","orcid":"https://orcid.org/0000-0003-1297-4462"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Gan","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, China","Ministry of Education Key Laboratory for Earth System Modeling, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Ministry of Education Key Laboratory for Earth System Modeling, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052865881","display_name":"Xiaomeng Huang","orcid":"https://orcid.org/0000-0002-4158-1089"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaomeng Huang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, China","Ministry of Education Key Laboratory for Earth System Modeling, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Ministry of Education Key Laboratory for Earth System Modeling, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115591592","display_name":"Guangwen Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangwen Yang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, China","Ministry of Education Key Laboratory for Earth System Modeling, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Ministry of Education Key Laboratory for Earth System Modeling, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1562,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.87925424,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"28","issue":"3","first_page":"301","last_page":"318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9925000071525574,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9878000020980835,"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/stencil","display_name":"Stencil","score":0.9684163928031921},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.8558759689331055},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8000245690345764},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7176492214202881},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.6936064958572388},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5296081304550171},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.49535953998565674},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.49366816878318787},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4896302819252014},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.48471665382385254},{"id":"https://openalex.org/keywords/terabyte","display_name":"Terabyte","score":0.4751945734024048},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.47198396921157837},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.42837467789649963},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11783665418624878},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09597879648208618}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.9684163928031921},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.8558759689331055},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8000245690345764},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7176492214202881},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.6936064958572388},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5296081304550171},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.49535953998565674},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.49366816878318787},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4896302819252014},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.48471665382385254},{"id":"https://openalex.org/C199683683","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Terabyte","level":2,"score":0.4751945734024048},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.47198396921157837},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.42837467789649963},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11783665418624878},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09597879648208618},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342014524807","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342014524807","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":[{"display_name":"Affordable and clean energy","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321940","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W74712455","https://openalex.org/W1483717008","https://openalex.org/W1499890669","https://openalex.org/W1965351873","https://openalex.org/W1967264375","https://openalex.org/W1984654389","https://openalex.org/W1987588924","https://openalex.org/W1990075242","https://openalex.org/W1994869533","https://openalex.org/W2000335122","https://openalex.org/W2001153911","https://openalex.org/W2011652244","https://openalex.org/W2016618963","https://openalex.org/W2028798345","https://openalex.org/W2034601083","https://openalex.org/W2049200548","https://openalex.org/W2065208324","https://openalex.org/W2068829602","https://openalex.org/W2080064193","https://openalex.org/W2097572763","https://openalex.org/W2104238795","https://openalex.org/W2113190809","https://openalex.org/W2120432001","https://openalex.org/W2131231747","https://openalex.org/W2149743155","https://openalex.org/W2160943542","https://openalex.org/W2353255992","https://openalex.org/W3145971282","https://openalex.org/W4214593133"],"related_works":["https://openalex.org/W2739740241","https://openalex.org/W1974923383","https://openalex.org/W2085105049","https://openalex.org/W2475524688","https://openalex.org/W2522739246","https://openalex.org/W2526069705","https://openalex.org/W1998641004","https://openalex.org/W2024016913","https://openalex.org/W2019153376","https://openalex.org/W2269110805"],"abstract_inverted_index":{"Wave":[0],"propagation":[1],"forward":[2],"modeling":[3],"is":[4,141],"a":[5],"widely":[6],"used":[7],"computational":[8],"method":[9],"in":[10,19,25,110],"oil":[11],"and":[12,41,56,73,102,131,138,172,179,181],"gas":[13],"exploration.":[14],"The":[15],"iterative":[16],"stencil":[17,96,119,134],"loops":[18,31],"such":[20,30,59],"problems":[21],"have":[22],"broad":[23],"applications":[24],"scientific":[26],"computing.":[27],"However,":[28],"executing":[29],"can":[32],"be":[33],"highly":[34],"time-consuming,":[35],"which":[36],"greatly":[37],"limits":[38],"their":[39,196],"performance":[40,91,129,156,171],"power":[42,173],"efficiency.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47,83,104,152],"accelerate":[48],"the":[49,53,74,80,90,114,132,164,182,191],"forward-modeling":[50],"technique":[51],"on":[52,176],"latest":[54],"multi-core":[55],"many-core":[57],"architectures":[58],"as":[60,186],"Intel\u00ae":[61,75],"Sandy":[62,99],"Bridge":[63,100],"CPUs,":[64],"NVIDIA":[65,69],"Fermi":[66],"C2070":[67],"GPUs,":[68,72],"Kepler":[70,177],"K20\u00d7":[71],"Xeon":[76],"Phi":[77],"co-processor.":[78],"For":[79,98],"GPU":[81,178],"platforms,":[82],"propose":[84],"two":[85],"parallel":[86],"strategies":[87],"to":[88,112,144,154,161],"explore":[89],"optimization":[92,108],"opportunities":[93],"for":[94,128,188,195],"our":[95,118,149],"kernels.":[97],"CPUs":[101],"MIC,":[103],"also":[105,168],"employ":[106],"various":[107],"techniques":[109],"order":[111],"achieve":[113,155],"best":[115],"performance.":[116],"Although":[117],"with":[120],"114":[121],"component":[122],"variables":[123],"poses":[124],"several":[125],"great":[126],"challenges":[127],"optimization,":[130],"low":[133],"ratio":[135],"between":[136],"computation":[137],"memory":[139],"access":[140],"too":[142],"inefficient":[143],"fully":[145],"take":[146],"advantage":[147],"of":[148,163],"evaluated":[150],"architectures,":[151],"manage":[153],"efficiencies":[157],"ranging":[158],"from":[159],"4.730%":[160],"20.02%":[162],"theoretical":[165],"peak.":[166],"We":[167],"conduct":[169],"cross-platform":[170],"analysis":[174],"(focusing":[175],"MIC)":[180],"results":[183],"could":[184],"serve":[185],"insights":[187],"users":[189],"selecting":[190],"most":[192],"suitable":[193],"accelerators":[194],"targeted":[197],"applications.":[198]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
