{"id":"https://openalex.org/W3203437055","doi":"https://doi.org/10.1145/3472456.3473517","title":"Automatic Code Generation and Optimization of Large-scale Stencil Computation on Many-core Processors","display_name":"Automatic Code Generation and Optimization of Large-scale Stencil Computation on Many-core Processors","publication_year":2021,"publication_date":"2021-08-09","ids":{"openalex":"https://openalex.org/W3203437055","doi":"https://doi.org/10.1145/3472456.3473517","mag":"3203437055"},"language":"en","primary_location":{"id":"doi:10.1145/3472456.3473517","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3472456.3473517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"50th International Conference on Parallel Processing","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/A5046708261","display_name":"Mingzhen Li","orcid":"https://orcid.org/0000-0002-4115-9072"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingzhen Li","raw_affiliation_strings":["Beihang University, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330538","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0002-4911-1161"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Beihang University, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018705589","display_name":"Hailong Yang","orcid":"https://orcid.org/0000-0003-1101-7927"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hailong Yang","raw_affiliation_strings":["Beihang University, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011523353","display_name":"Yongmin Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongmin Hu","raw_affiliation_strings":["Beihang University, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060999547","display_name":"Qingxiao Sun","orcid":"https://orcid.org/0000-0003-2927-362X"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingxiao Sun","raw_affiliation_strings":["Beihang University, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049409043","display_name":"Bangduo Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bangduo Chen","raw_affiliation_strings":["Beihang University, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100683033","display_name":"Xin You","orcid":"https://orcid.org/0000-0002-5163-4607"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin You","raw_affiliation_strings":["Beihang University, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100324634","display_name":"Xiaoyan Liu","orcid":"https://orcid.org/0000-0002-1109-3869"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyan Liu","raw_affiliation_strings":["Beihang University, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074183877","display_name":"Zhongzhi Luan","orcid":"https://orcid.org/0000-0002-7186-0556"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongzhi Luan","raw_affiliation_strings":["Beihang University, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079362609","display_name":"Depei Qian","orcid":"https://orcid.org/0000-0002-5382-1473"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Depei Qian","raw_affiliation_strings":["Beihang University, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5046708261"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":3.4542,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.93010413,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9976999759674072,"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":0.9976999759674072,"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":0.9912999868392944,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9868999719619751,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.993526816368103},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8336578607559204},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.817095935344696},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5641939043998718},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.44102707505226135},{"id":"https://openalex.org/keywords/domain-specific-language","display_name":"Domain-specific language","score":0.4392687976360321},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.43204233050346375},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4309065639972687},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.41926640272140503},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.4175029397010803},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.2681490480899811},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21480095386505127},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10426673293113708},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06486356258392334}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.993526816368103},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8336578607559204},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.817095935344696},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5641939043998718},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.44102707505226135},{"id":"https://openalex.org/C135257023","wikidata":"https://www.wikidata.org/wiki/Q691358","display_name":"Domain-specific language","level":2,"score":0.4392687976360321},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.43204233050346375},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4309065639972687},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.41926640272140503},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.4175029397010803},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.2681490480899811},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21480095386505127},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10426673293113708},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06486356258392334},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3472456.3473517","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3472456.3473517","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"50th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1378380340","display_name":null,"funder_award_id":"2020YFB1506703","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4924613955","display_name":null,"funder_award_id":"SKLSDE-2021ZX-06","funder_id":"https://openalex.org/F4320326978","funder_display_name":"State Key Laboratory of Software Development Environment"},{"id":"https://openalex.org/G5774836301","display_name":null,"funder_award_id":"62072018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326978","display_name":"State Key Laboratory of Software Development Environment","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1506424797","https://openalex.org/W1965742121","https://openalex.org/W1968013322","https://openalex.org/W1973532523","https://openalex.org/W1975539849","https://openalex.org/W1979457157","https://openalex.org/W2039378765","https://openalex.org/W2074833026","https://openalex.org/W2090843874","https://openalex.org/W2100218206","https://openalex.org/W2104512032","https://openalex.org/W2119042753","https://openalex.org/W2127882405","https://openalex.org/W2154078685","https://openalex.org/W2475126267","https://openalex.org/W2562913534","https://openalex.org/W2608177516","https://openalex.org/W2728256789","https://openalex.org/W2767373187","https://openalex.org/W2772612468","https://openalex.org/W2946383579","https://openalex.org/W2990029213","https://openalex.org/W2996929894","https://openalex.org/W2997593252","https://openalex.org/W3020936970","https://openalex.org/W3031192821","https://openalex.org/W3091854778","https://openalex.org/W3099448935","https://openalex.org/W3099814709","https://openalex.org/W3105115110","https://openalex.org/W4231156094","https://openalex.org/W4232301837","https://openalex.org/W4251637954","https://openalex.org/W4251798485"],"related_works":["https://openalex.org/W3105129168","https://openalex.org/W2804920739","https://openalex.org/W4316371992","https://openalex.org/W2186216222","https://openalex.org/W2177020196","https://openalex.org/W2772612468","https://openalex.org/W4244512595","https://openalex.org/W1429949169","https://openalex.org/W3139770841","https://openalex.org/W153514170"],"abstract_inverted_index":{"Stencil":[0],"computation":[1,28,138],"is":[2,12],"an":[3],"indispensable":[4],"building":[5],"block":[6],"of":[7,19,30,85],"many":[8,41],"scientific":[9],"applications":[10],"and":[11,33,69,71,95,100,142,167,170],"widely":[13],"used":[14],"by":[15],"the":[16,26,34,59,194],"numerical":[17],"solvers":[18],"partial":[20],"differential":[21],"equations":[22],"(PDEs).":[23],"Due":[24],"to":[25,48,73,109,135,193],"complex":[27],"patterns":[29],"different":[31],"stencils":[32],"various":[35],"hardware":[36],"targets":[37],"(e.g.,":[38],"many-core":[39,64,77,156],"processors),":[40],"domain-specific":[42],"languages":[43],"(DSLs)":[44],"have":[45],"been":[46],"proposed":[47],"optimize":[49],"stencil":[50,54,90,105,132,137,149,196],"computation.":[51],"However,":[52],"existing":[53],"DSLs":[55,106],"mostly":[56],"focus":[57],"on":[58,62,154],"performance":[60,191],"optimizations":[61,96],"homogeneous":[63],"processors":[65,78],"such":[66,79],"as":[67,80],"CPUs":[68],"GPUs,":[70],"fail":[72],"embrace":[74],"emerging":[75,155],"heterogeneous":[76],"Sunway.":[81],"In":[82,124],"addition,":[83],"few":[84],"them":[86],"can":[87,113,146],"support":[88],"expressing":[89],"with":[91],"multiple":[92],"time":[93],"dependencies":[94],"from":[97],"both":[98,140],"spatial":[99,141],"temporal":[101,143],"dimensions.":[102,144],"Moreover,":[103],"most":[104],"are":[107],"unable":[108],"generate":[110,147],"codes":[111,150],"that":[112,186],"run":[114],"efficiently":[115],"in":[116,139,178],"large":[117,179],"scale,":[118],"which":[119],"limits":[120],"their":[121],"practical":[122],"applicability.":[123],"this":[125],"paper,":[126],"we":[127,159],"propose":[128],"MSC,":[129],"a":[130,171],"new":[131],"DSL":[133],"designed":[134],"express":[136],"It":[145],"high-performance":[148],"for":[151,164,174],"large-scale":[152],"execution":[153],"processors.":[157],"Specially,":[158],"design":[160],"several":[161],"optimization":[162],"primitives":[163],"improving":[165],"parallelism":[166],"data":[168],"locality,":[169],"communication":[172],"library":[173],"efficient":[175],"halo":[176],"exchange":[177],"scale":[180],"execution.":[181],"The":[182],"experiment":[183],"results":[184],"show":[185],"our":[187],"MSC":[188],"achieves":[189],"better":[190],"compared":[192],"state-of-the-art":[195],"DSLs.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
