{"id":"https://openalex.org/W2576167992","doi":"https://doi.org/10.3233/978-1-61499-621-7-647","title":"Towards Compiler-Agnostic Performance in Finite-Difference Codes","display_name":"Towards Compiler-Agnostic Performance in Finite-Difference Codes","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2576167992","doi":"https://doi.org/10.3233/978-1-61499-621-7-647","mag":"2576167992"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-621-7-647","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-621-7-647","pdf_url":null,"source":{"id":"https://openalex.org/S4210175178","display_name":"Advances in parallel computing","issn_l":"0927-5452","issn":["0927-5452","1879-808X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Parallel Computing","raw_type":"book-chapter"},"type":"book-chapter","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/A5026750900","display_name":"Andrew Porter","orcid":"https://orcid.org/0000-0003-3174-2114"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Porter A.R.","raw_affiliation_strings":["STFC Hartree Centre"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STFC Hartree Centre","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110246189","display_name":"Rupert Ford","orcid":"https://orcid.org/0000-0001-5483-4965"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ford R.W.","raw_affiliation_strings":["STFC Hartree Centre"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STFC Hartree Centre","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010519532","display_name":"Mike Ashworth","orcid":"https://orcid.org/0000-0002-4944-2200"},"institutions":[{"id":"https://openalex.org/I2802015276","display_name":"Daresbury Laboratory","ror":"https://ror.org/0089bg420","country_code":"GB","type":"facility","lineage":["https://openalex.org/I162524378","https://openalex.org/I2802015276","https://openalex.org/I4210087105"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ashworth M.","raw_affiliation_strings":["STFC Daresbury Laboratories"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STFC Daresbury Laboratories","institution_ids":["https://openalex.org/I2802015276"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087600309","display_name":"Graham Riley","orcid":"https://orcid.org/0000-0001-7023-517X"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Riley G.D.","raw_affiliation_strings":["University of Manchester, Manchester, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Manchester, Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090492507","display_name":"Manish Modani","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210167072","display_name":"IBM (Brazil)","ror":"https://ror.org/05thm6q88","country_code":"BR","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210167072"]}],"countries":["BR","US"],"is_corresponding":false,"raw_author_name":"Modani M.","raw_affiliation_strings":["IBM, Corp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM, Corp","institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210167072"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5026750900"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7921,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.85261194,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"647","last_page":"658"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9929999709129333,"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":0.9929999709129333,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11032","display_name":"VLSI and Analog Circuit Testing","score":0.98580002784729,"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/compiler","display_name":"Compiler","score":0.7687757015228271},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6394519805908203},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.46984758973121643},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.45382794737815857}],"concepts":[{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7687757015228271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6394519805908203},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.46984758973121643},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.45382794737815857}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3233/978-1-61499-621-7-647","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-621-7-647","pdf_url":null,"source":{"id":"https://openalex.org/S4210175178","display_name":"Advances in parallel computing","issn_l":"0927-5452","issn":["0927-5452","1879-808X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Parallel Computing","raw_type":"book-chapter"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/4bec40b5-d206-496c-8c3f-846e000dcac4","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/4bec40b5-d206-496c-8c3f-846e000dcac4","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Porter, A, Ford, R, Ashworth, M, Riley, G & Modani, M 2016, Towards Compiler-Agnostic Performance in Finite-Difference Codes. in G R Joubert, H Leather, M Parsons, F Peters & M Sawyer (eds), Parallel Computing 2015 (ParCo), Edinburgh 1-4 September, 2015 : Parallel Computing: On the Road to Exascale. vol. 27, Advances in Parallel Computing, IOS Press, pp. 647-658. https://doi.org/10.3233/978-1-61499-621-7-647","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"mag:2576167992","is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/parco/parco2015.html#PorterFARM15","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Parallel Computing","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4240253816","https://openalex.org/W3096456556","https://openalex.org/W1713081424","https://openalex.org/W2127315869","https://openalex.org/W1523769955","https://openalex.org/W2245390655","https://openalex.org/W4379536100"],"abstract_inverted_index":{"In":[0,21],"this":[1,203,225],"paper":[2],"we":[3,13,207],"evaluate":[4],"the":[5,23,27,54,73,81,97,107,110,119,130,140,148,162,170,185,212,236,246,251,257,272,289,305,310],"performance":[6,108,177,209,280,285],"implications":[7],"of":[8,44,53,80,109,136,173,184,304,309],"applying":[9],"a":[10,60,76,134,181],"technique":[11],"which":[12],"call":[14],"PSyKAl":[15,22,102,131,273],"to":[16,26,36,48,68,71,118,129,139,202,229,264,267,288],"finite":[17,85],"difference":[18,86],"Ocean":[19],"models.":[20],"code":[24,34,49,62,74,137,174,187,253,306],"related":[25,35],"underlying":[28,55],"science":[29,51,82],"is":[30,94,104,179,211,243,298],"formally":[31],"separated":[32],"from":[33],"parallelisation":[37],"and":[38,64,106,151,157,160,191,262,282],"single":[39,61,300],"core":[40],"optimisations.":[41],"This":[42],"separation":[43],"concerns":[45],"allows":[46],"scientists":[47],"their":[50],"independently":[52,79],"hardware":[56],"architecture":[57,192,234],"(thereby":[58],"keeping":[59],"base)":[63],"for":[65,75,91,147,161,188,217,232,307],"optimisation":[66,141],"specialists":[67],"be":[69,227,265,276],"able":[70],"tailor":[72],"particular":[77],"machine":[78],"code.":[83,270,292],"A":[84,100],"shallow":[87],"water":[88],"benchmark":[89,121],"optimised":[90,291],"cache-based":[92],"architectures":[93],"taken":[95],"as":[96,133],"starting":[98],"point.":[99],"vanilla":[101],"version":[103,132],"written":[105],"two":[111],"compared.":[112],"The":[113,199],"optimisations":[114],"that":[115,169,178,224,233,296],"were":[116],"applied":[117,128],"original":[120,186,252,290],"(loop":[122],"fusion":[123],"etc.)":[124],"are":[125,145],"then":[126],"manually":[127],"set":[135,172],"modifications":[138,175],"layer.":[142],"Performance":[143],"results":[144],"presented":[146],"Cray,":[149],"Intel":[150,155],"GNU":[152],"compilers":[153,311],"on":[154,165,194,215,245,260],"Ivybridge":[156],"Haswell":[158,216],"processors":[159],"IBM":[163,258],"compiler":[164,190,214,238,259],"Power8.":[166],"Results":[167],"show":[168],"combined":[171],"obtain":[176,268],"within":[180],"few":[182],"percent":[183],"all":[189,195,308],"combinations":[193],"tested":[196],"problem":[197,219,242],"sizes.":[198],"only":[200],"exception":[201],"(other":[204],"than":[205],"where":[206],"see":[208],"improvement)":[210],"Gnu":[213,237],"one":[218],"size.":[220],"Our":[221],"tests":[222],"indicate":[223],"may":[226],"due":[228],"immature":[230],"support":[231],"in":[235],"–":[239],"no":[240,299],"such":[241],"seen":[244],"Ivy":[247],"Bridge":[248],"system.":[249],"Further,":[250],"performed":[254],"poorly":[255],"using":[256],"Power8":[261],"needed":[263],"modified":[266],"performant":[269],"Therefore,":[271],"approach":[274],"can":[275],"used":[277],"with":[278],"negligible":[279],"loss":[281],"sometimes":[283],"small":[284],"gains":[286],"compared":[287],"We":[293],"also":[294],"find":[295],"there":[297],"best":[301],"hand-optimised":[302],"implementation":[303],"tested.":[312]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}