{"id":"https://openalex.org/W2208965674","doi":"https://doi.org/10.1145/2832087.2832092","title":"Automatic loop kernel analysis and performance modeling with Kerncraft","display_name":"Automatic loop kernel analysis and performance modeling with Kerncraft","publication_year":2015,"publication_date":"2015-11-11","ids":{"openalex":"https://openalex.org/W2208965674","doi":"https://doi.org/10.1145/2832087.2832092","mag":"2208965674"},"language":"en","primary_location":{"id":"doi:10.1145/2832087.2832092","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2832087.2832092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th International Workshop on Performance Modeling, Benchmarking, and Simulation of High Performance Computing Systems","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1509.03778","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034271822","display_name":"Julian Hammer","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Julian Hammer","raw_affiliation_strings":["University of Erlangen-Nuremberg"],"affiliations":[{"raw_affiliation_string":"University of Erlangen-Nuremberg","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082552227","display_name":"Georg Hager","orcid":"https://orcid.org/0000-0002-8723-2781"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Georg Hager","raw_affiliation_strings":["University of Erlangen-Nuremberg"],"affiliations":[{"raw_affiliation_string":"University of Erlangen-Nuremberg","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011822473","display_name":"Jan Eitzinger","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Eitzinger","raw_affiliation_strings":["University of Erlangen-Nuremberg"],"affiliations":[{"raw_affiliation_string":"University of Erlangen-Nuremberg","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070209050","display_name":"Gerhard Wellein","orcid":"https://orcid.org/0000-0001-7371-3026"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Wellein","raw_affiliation_strings":["University of Erlangen-Nuremberg"],"affiliations":[{"raw_affiliation_string":"University of Erlangen-Nuremberg","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034271822"],"corresponding_institution_ids":["https://openalex.org/I181369854"],"apc_list":null,"apc_paid":null,"fwci":3.3125,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.92514865,"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":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9997000098228455,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8470206260681152},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.656686007976532},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.6368148922920227},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5852935314178467},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.557778000831604},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5311362147331238},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5207931399345398},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4906729459762573},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.490204393863678},{"id":"https://openalex.org/keywords/loop-fission","display_name":"Loop fission","score":0.44275084137916565},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4219841957092285},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.41163739562034607},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3967611789703369},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.21642756462097168},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17565539479255676},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12323734164237976}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8470206260681152},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.656686007976532},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.6368148922920227},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5852935314178467},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.557778000831604},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5311362147331238},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5207931399345398},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4906729459762573},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.490204393863678},{"id":"https://openalex.org/C134718785","wikidata":"https://www.wikidata.org/wiki/Q6675821","display_name":"Loop fission","level":3,"score":0.44275084137916565},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4219841957092285},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.41163739562034607},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3967611789703369},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.21642756462097168},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17565539479255676},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12323734164237976},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2832087.2832092","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2832087.2832092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th International Workshop on Performance Modeling, Benchmarking, and Simulation of High Performance Computing Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1509.03778","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1509.03778","pdf_url":"https://arxiv.org/pdf/1509.03778","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1509.03778","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1509.03778","pdf_url":"https://arxiv.org/pdf/1509.03778","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W35088483","https://openalex.org/W842872497","https://openalex.org/W1535111405","https://openalex.org/W1549155553","https://openalex.org/W1628605343","https://openalex.org/W1961751213","https://openalex.org/W1986624837","https://openalex.org/W1997147891","https://openalex.org/W2002555321","https://openalex.org/W2026212799","https://openalex.org/W2038454316","https://openalex.org/W2057577013","https://openalex.org/W2059882081","https://openalex.org/W2078636996","https://openalex.org/W2096642134","https://openalex.org/W2134495056","https://openalex.org/W2227014377","https://openalex.org/W2963799023","https://openalex.org/W3099131631","https://openalex.org/W3103104567","https://openalex.org/W3106055984","https://openalex.org/W3125983777","https://openalex.org/W3128129736","https://openalex.org/W4298168968"],"related_works":["https://openalex.org/W3105129168","https://openalex.org/W2804920739","https://openalex.org/W4316371992","https://openalex.org/W2186216222","https://openalex.org/W2392765154","https://openalex.org/W2008005532","https://openalex.org/W1971603802","https://openalex.org/W2564509292","https://openalex.org/W2183878227","https://openalex.org/W4255540064"],"abstract_inverted_index":{"Analytic":[0],"performance":[1,8,28,43,78,109],"models":[2,79],"are":[3],"essential":[4],"for":[5,49,80],"understanding":[6],"the":[7,33,58,65,69,74,89,93,100,107,119,122,128],"characteristics":[9],"of":[10,18,76,99,113,131],"loop":[11,85,90],"kernels,":[12],"which":[13,72],"consume":[14],"a":[15,26,97],"major":[16],"part":[17],"CPU":[19],"cycles":[20],"in":[21],"computational":[22],"science.":[23],"Starting":[24,87],"from":[25,88],"validated":[27],"model":[29],"one":[30],"can":[31,104],"infer":[32],"relevant":[34],"hardware":[35,59],"bottlenecks":[36],"and":[37,60,83,96,110,136,138],"promising":[38],"optimization":[39],"opportunities.":[40],"Unfortunately,":[41],"analytic":[42,77,152],"modeling":[44],"is":[45],"often":[46],"tedious":[47],"even":[48],"experienced":[50],"developers":[51],"since":[52],"it":[53,62,142],"requires":[54],"in-depth":[55],"knowledge":[56],"about":[57],"how":[61,141],"interacts":[63],"with":[64,133],"software.":[66],"We":[67,126],"present":[68],"\"Kerncraft\"":[70],"tool,":[71],"eases":[73],"construction":[75],"streaming":[81],"kernels":[82],"stencil":[84],"nests.":[86],"source":[91],"code,":[92],"problem":[94],"size,":[95],"description":[98],"underlying":[101],"hardware,":[102],"Kerncraft":[103,132],"ideally":[105],"predict":[106],"single-core":[108],"scaling":[111],"behavior":[112],"loops":[114],"on":[115],"multicore":[116],"processors":[117],"using":[118],"Roofline":[120],"or":[121],"Execution-Cache-Memory":[123],"(ECM)":[124],"model.":[125],"describe":[127],"operating":[129],"principles":[130],"its":[134],"capabilities":[135],"limitations,":[137],"we":[139],"show":[140],"may":[143],"be":[144],"used":[145],"to":[146],"quickly":[147],"gain":[148],"insights":[149],"by":[150],"accelerated":[151],"modeling.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":2}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}
