{"id":"https://openalex.org/W2729851701","doi":"https://doi.org/10.1145/3106341","title":"MATOG","display_name":"MATOG","publication_year":2017,"publication_date":"2017-08-30","ids":{"openalex":"https://openalex.org/W2729851701","doi":"https://doi.org/10.1145/3106341","mag":"2729851701"},"language":"en","primary_location":{"id":"doi:10.1145/3106341","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3106341","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3106341&type=pdf","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=3106341&type=pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110023001","display_name":"Nicolas Weber","orcid":"https://orcid.org/0000-0003-0032-9511"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Nicolas Weber","raw_affiliation_strings":["Graduate School of Computational Engineering, TU Darmstadt,Rundeturmst, Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Computational Engineering, TU Darmstadt,Rundeturmst, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066521879","display_name":"Michael Goesele","orcid":"https://orcid.org/0000-0002-0944-0980"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Goesele","raw_affiliation_strings":["TU Darmstadt, Rundeturmst, Darmstadt, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Darmstadt, Rundeturmst, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110023001"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":1.3866,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.82592166,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"14","issue":"3","first_page":"1","last_page":"26"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9993000030517578,"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":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.9045469760894775},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.681721568107605},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6815086007118225},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.6252419352531433},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.6086801290512085},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5892427563667297},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.5371812582015991},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.4739891588687897},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.41076621413230896},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3408007025718689},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15528997778892517},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1215025782585144}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9045469760894775},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.681721568107605},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6815086007118225},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.6252419352531433},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.6086801290512085},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5892427563667297},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.5371812582015991},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.4739891588687897},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.41076621413230896},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3408007025718689},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15528997778892517},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1215025782585144},{"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/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3106341","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3106341","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3106341&type=pdf","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:87760","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/87760/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Artikel"}],"best_oa_location":{"id":"doi:10.1145/3106341","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3106341","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=3106341&type=pdf","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323384","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2729851701.pdf","grobid_xml":"https://content.openalex.org/works/W2729851701.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W172770979","https://openalex.org/W1575955136","https://openalex.org/W1588915715","https://openalex.org/W1779740778","https://openalex.org/W1971367716","https://openalex.org/W1981896890","https://openalex.org/W1988307172","https://openalex.org/W1989562524","https://openalex.org/W1990090459","https://openalex.org/W2001258868","https://openalex.org/W2006295906","https://openalex.org/W2033088400","https://openalex.org/W2062368747","https://openalex.org/W2080592089","https://openalex.org/W2091599698","https://openalex.org/W2100218206","https://openalex.org/W2100409742","https://openalex.org/W2102394168","https://openalex.org/W2105937753","https://openalex.org/W2125833438","https://openalex.org/W2128539477","https://openalex.org/W2130597822","https://openalex.org/W2132147136","https://openalex.org/W2139935536","https://openalex.org/W2141389982","https://openalex.org/W2160786443","https://openalex.org/W2162404488","https://openalex.org/W2168559597","https://openalex.org/W2260757707","https://openalex.org/W2272866099","https://openalex.org/W2344642201","https://openalex.org/W2518567779","https://openalex.org/W2532040979","https://openalex.org/W2553626380","https://openalex.org/W2566880439","https://openalex.org/W2580538010","https://openalex.org/W3103983137"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W4245975140","https://openalex.org/W2062253548","https://openalex.org/W4225414539","https://openalex.org/W3122369893","https://openalex.org/W2407476586","https://openalex.org/W2750654225","https://openalex.org/W1977905671"],"abstract_inverted_index":{"Optimal":[0],"code":[1,43,77,94,142],"performance":[2,56,111],"is":[3,70,78],"(besides":[4],"correctness":[5],"and":[6,57,85,102,126,138,172],"accuracy)":[7],"the":[8,42,50,73,88,110,115,123,131,141,145,168,174,179],"most":[9],"important":[10],"objective":[11],"in":[12,135],"compute":[13,33],"intensive":[14],"applications.":[15],"In":[16,67,98,118],"many":[17],"of":[18,28,32,112,167],"these":[19],"applications,":[20,158],"Graphic":[21],"Processing":[22],"Units":[23],"(GPUs)":[24],"are":[25],"used":[26,146,169],"because":[27],"their":[29,38],"high":[30],"amount":[31],"power.":[34],"However,":[35],"caused":[36],"by":[37],"massively":[39],"parallel":[40],"architecture,":[41],"has":[44,59,87],"to":[45,49,53,60,90,95,144,154,176],"be":[46,61],"specifically":[47],"adjusted":[48],"underlying":[51,116],"hardware":[52],"achieve":[54],"optimal":[55],"therefore":[58],"reoptimized":[62],"for":[63],"each":[64],"new":[65,96],"generation.":[66],"reality,":[68],"this":[69,119],"usually":[71],"not":[72],"case":[74],"as":[75],"productive":[76],"normally":[79],"at":[80],"least":[81],"several":[82],"years":[83,100],"old":[84],"nobody":[86],"time":[89],"continuously":[91],"adjust":[92],"existing":[93],"hardware.":[97,117],"recent":[99],"more":[101,103],"approaches":[104],"have":[105],"emerged":[106],"that":[107],"automatically":[108,139],"tune":[109,178],"applications":[113,137],"toward":[114],"article,":[120],"we":[121],"present":[122],"MATOG":[124,148],"auto-tuner":[125],"its":[127],"concepts.":[128],"It":[129],"abstracts":[130],"array":[132],"memory":[133],"access":[134],"CUDA":[136],"optimizes":[140],"according":[143],"GPUs.":[147],"only":[149],"requires":[150],"few":[151],"profiling":[152],"runs":[153],"analyze":[155],"even":[156],"complex":[157],"while":[159],"achieving":[160],"significant":[161],"speedups":[162],"over":[163],"non-optimized":[164],"code,":[165],"independent":[166],"GPU":[170],"generation":[171],"without":[173],"need":[175],"manually":[177],"code.":[180]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2017-07-14T00:00:00"}