{"id":"https://openalex.org/W2104028289","doi":"https://doi.org/10.1145/2723772.2723776","title":"Hardware-Aware Automatic Code-Transformation to Support Compilers in Exploiting the Multi-Level Parallel Potential of Modern CPUs","display_name":"Hardware-Aware Automatic Code-Transformation to Support Compilers in Exploiting the Multi-Level Parallel Potential of Modern CPUs","publication_year":2015,"publication_date":"2015-02-08","ids":{"openalex":"https://openalex.org/W2104028289","doi":"https://doi.org/10.1145/2723772.2723776","mag":"2104028289"},"language":"en","primary_location":{"id":"doi:10.1145/2723772.2723776","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2723772.2723776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 International Workshop on Code Optimisation for Multi and Many Cores","raw_type":"proceedings-article"},"type":"conference-paper","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/A5078683331","display_name":"Dustin Feld","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098248","display_name":"Fraunhofer Institute for Algorithms and Scientific Computing","ror":"https://ror.org/00trw9c49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210098248","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dustin Feld","raw_affiliation_strings":["Fraunhofer SCAI, Schloss Birlinghoven, 53754 Sankt Augustin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer SCAI, Schloss Birlinghoven, 53754 Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210098248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110527152","display_name":"Thomas Soddemann","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098248","display_name":"Fraunhofer Institute for Algorithms and Scientific Computing","ror":"https://ror.org/00trw9c49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210098248","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Soddemann","raw_affiliation_strings":["Fraunhofer SCAI, Schloss Birlinghoven, 53754 Sankt Augustin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer SCAI, Schloss Birlinghoven, 53754 Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210098248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016595075","display_name":"Michael J\u00fcnger","orcid":"https://orcid.org/0000-0002-7574-6646"},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael J\u00fcnger","raw_affiliation_strings":["Institut f\u00fcr Informatik, Universit\u00e4t zu K\u00f6ln, Weyertal 121, 50931 K\u00f6ln, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Informatik, Universit\u00e4t zu K\u00f6ln, Weyertal 121, 50931 K\u00f6ln, Germany","institution_ids":["https://openalex.org/I180923762"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025296970","display_name":"Sven Mallach","orcid":"https://orcid.org/0000-0001-5335-0678"},"institutions":[{"id":"https://openalex.org/I180923762","display_name":"University of Cologne","ror":"https://ror.org/00rcxh774","country_code":"DE","type":"education","lineage":["https://openalex.org/I180923762"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sven Mallach","raw_affiliation_strings":["Institut f\u00fcr Informatik, Universit\u00e4t zu K\u00f6ln, Weyertal 121, 50931 K\u00f6ln, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Informatik, Universit\u00e4t zu K\u00f6ln, Weyertal 121, 50931 K\u00f6ln, Germany","institution_ids":["https://openalex.org/I180923762"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6328,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.83606878,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"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":0.9993000030517578,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9991000294685364,"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/computer-science","display_name":"Computer science","score":0.8997900485992432},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8686351776123047},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8218777179718018},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.6578347086906433},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6428192853927612},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5807695984840393},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.5034112334251404},{"id":"https://openalex.org/keywords/automatic-parallelization","display_name":"Automatic parallelization","score":0.48529690504074097},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.44851094484329224},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4286673069000244},{"id":"https://openalex.org/keywords/compile-time","display_name":"Compile time","score":0.41707879304885864},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.27399003505706787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8997900485992432},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8686351776123047},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8218777179718018},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.6578347086906433},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6428192853927612},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5807695984840393},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.5034112334251404},{"id":"https://openalex.org/C164833996","wikidata":"https://www.wikidata.org/wiki/Q2323839","display_name":"Automatic parallelization","level":3,"score":0.48529690504074097},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.44851094484329224},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4286673069000244},{"id":"https://openalex.org/C200833197","wikidata":"https://www.wikidata.org/wiki/Q333707","display_name":"Compile time","level":3,"score":0.41707879304885864},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.27399003505706787},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/2723772.2723776","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2723772.2723776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 International Workshop on Code Optimisation for Multi and Many Cores","raw_type":"proceedings-article"},{"id":"pmh:oai:USBKOELN.ub.uni-koeln.de:64078","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400371","display_name":"K\u00f6lner Universit\u00e4ts PublikationsServer (Universit\u00e4t zu K\u00f6ln)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210115942","host_organization_name":"Rhenish Institute for Environmental Research","host_organization_lineage":["https://openalex.org/I4210115942"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:bookPart"},{"id":"pmh:oai:e-archive.informatik.uni-koeln.de:796","is_oa":false,"landing_page_url":"http://e-archive.informatik.uni-koeln.de/796/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401304","display_name":"Computer Science Publication Server (University of Cologne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I180923762","host_organization_name":"University of Cologne","host_organization_lineage":["https://openalex.org/I180923762"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Proceedings article"},{"id":"pmh:oai:fraunhofer.de:N-367132","is_oa":false,"landing_page_url":"http://publica.fraunhofer.de/documents/N-367132.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer SCAI","raw_type":"Conference Paper"},{"id":"pmh:oai:publica.fraunhofer.de:publica/389917","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/389917","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W38784877","https://openalex.org/W1503700136","https://openalex.org/W1656664476","https://openalex.org/W1758912474","https://openalex.org/W1970141743","https://openalex.org/W1991009705","https://openalex.org/W2020505145","https://openalex.org/W2071110673","https://openalex.org/W2078845975","https://openalex.org/W2079737233","https://openalex.org/W2082352135","https://openalex.org/W2108737583","https://openalex.org/W2112391112","https://openalex.org/W2119691711","https://openalex.org/W2123680107","https://openalex.org/W2126464777","https://openalex.org/W2142655718","https://openalex.org/W2153993495","https://openalex.org/W2157273783","https://openalex.org/W2158158791","https://openalex.org/W2158958889","https://openalex.org/W2172191698","https://openalex.org/W2332864379","https://openalex.org/W2615583977","https://openalex.org/W2616606052","https://openalex.org/W3140469843","https://openalex.org/W4231265208"],"related_works":["https://openalex.org/W2566637483","https://openalex.org/W2127324789","https://openalex.org/W3024308452","https://openalex.org/W4244894488","https://openalex.org/W4285390450","https://openalex.org/W2366442643","https://openalex.org/W2090268225","https://openalex.org/W2021715972","https://openalex.org/W75461624","https://openalex.org/W2766828645"],"abstract_inverted_index":{"Modern":[0],"compilers":[1,45,96],"offer":[2],"more":[3,5,99],"and":[4,65,90,100,116,126,158,178],"capabilities":[6],"to":[7,31,94,107,129,136],"automatically":[8,105],"parallelize":[9],"code-regions":[10],"if":[11],"these":[12,35],"match":[13,34],"certain":[14],"properties.":[15],"However,":[16],"there":[17],"are":[18,37,84,135],"several":[19],"application":[20,165],"kernels":[21],"that,":[22],"although":[23],"rather":[24],"simple":[25],"transformations":[26,82],"would":[27],"suffice":[28],"in":[29,97,149],"order":[30],"make":[32],"them":[33],"properties,":[36],"either":[38],"not":[39],"at":[40,48],"all":[41],"parallelized":[42],"by":[43,139],"state-of-the-art":[44],"or":[46],"could":[47],"least":[49],"be":[50,137],"improved":[51],"w.r.t.":[52],"their":[53],"performance.":[54],"This":[55],"paper":[56],"proposes":[57],"a":[58,71,87,162],"loop-tiling":[59],"approach":[60],"focusing":[61],"on":[62,70,79],"automatic":[63],"vectorization":[64],"multi-core":[66],"parallelization,":[67],"with":[68],"emphasis":[69],"smart":[72],"cache":[73,117,155],"exploitation.":[74],"The":[75,167],"method":[76,168],"is":[77,92,127],"based":[78],"polyhedral":[80],"code":[81],"that":[83,134],"applied":[85],"as":[86,111],"pre-compilation":[88],"step":[89],"it":[91,120],"shown":[93],"help":[95],"generating":[98],"better":[101],"parallel":[102],"code-regions.":[103],"It":[104],"adapts":[106],"hardware":[108],"parameters":[109],"such":[110],"the":[112,150,171],"SIMD":[113],"register":[114],"width":[115],"sizes.":[118],"Further,":[119],"takes":[121],"memory-access":[122],"patterns":[123],"into":[124,176],"account":[125],"capable":[128],"minimize":[130],"communication":[131],"among":[132],"tiles":[133],"processed":[138],"different":[140],"cores.":[141],"An":[142],"extensive":[143],"computational":[144],"study":[145],"shows":[146],"significant":[147],"improvements":[148],"number":[151],"of":[152,164],"instructions":[153],"vectorized,":[154],"miss":[156],"rates,":[157],"running":[159],"times":[160],"for":[161],"range":[163],"kernels.":[166],"often":[169],"outperforms":[170],"internal":[172],"auto-parallelization":[173],"techniques":[174],"implemented":[175],"gcc":[177],"icc.":[179]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
