{"id":"https://openalex.org/W4403211238","doi":"https://doi.org/10.1109/ispdc62236.2024.10705404","title":"Short Paper: Evaluation of stdpar Compilers on a Kernel Matrix Assembly and a BLAS Level 3 SYMM Kernel","display_name":"Short Paper: Evaluation of stdpar Compilers on a Kernel Matrix Assembly and a BLAS Level 3 SYMM Kernel","publication_year":2024,"publication_date":"2024-07-08","ids":{"openalex":"https://openalex.org/W4403211238","doi":"https://doi.org/10.1109/ispdc62236.2024.10705404"},"language":"en","primary_location":{"id":"doi:10.1109/ispdc62236.2024.10705404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispdc62236.2024.10705404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 23rd International Symposium on Parallel and Distributed Computing (ISPDC)","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/A5016040832","display_name":"Marcel Breyer","orcid":"https://orcid.org/0000-0003-3574-0650"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Marcel Breyer","raw_affiliation_strings":["IPVS University of Stuttgart Stuttgart,Germany"],"affiliations":[{"raw_affiliation_string":"IPVS University of Stuttgart Stuttgart,Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081910883","display_name":"Alexander Van Craen","orcid":"https://orcid.org/0000-0002-3336-7226"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Van Craen","raw_affiliation_strings":["IPVS University of Stuttgart Stuttgart,Germany"],"affiliations":[{"raw_affiliation_string":"IPVS University of Stuttgart Stuttgart,Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041326099","display_name":"Dirk Pfl\u00fcger","orcid":"https://orcid.org/0000-0002-4360-0212"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dirk Pfl\u00fcger","raw_affiliation_strings":["IPVS University of Stuttgart Stuttgart,Germany"],"affiliations":[{"raw_affiliation_string":"IPVS University of Stuttgart Stuttgart,Germany","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016040832"],"corresponding_institution_ids":["https://openalex.org/I100066346"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1780245,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9850999712944031,"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":0.9850999712944031,"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/kernel","display_name":"Kernel (algebra)","score":0.8092000484466553},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6559963226318359},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6409502029418945},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4349665641784668},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4309951961040497},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2678947448730469},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1605968177318573},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.08835354447364807},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07448503375053406},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.056279897689819336}],"concepts":[{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.8092000484466553},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6559963226318359},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6409502029418945},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4349665641784668},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4309951961040497},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2678947448730469},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1605968177318573},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.08835354447364807},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07448503375053406},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.056279897689819336}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ispdc62236.2024.10705404","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ispdc62236.2024.10705404","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 23rd International Symposium on Parallel and Distributed Computing (ISPDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1596717185","https://openalex.org/W2112294207","https://openalex.org/W4225271295","https://openalex.org/W4283813583","https://openalex.org/W4289827856","https://openalex.org/W4318602897","https://openalex.org/W4362675219","https://openalex.org/W4394006036","https://openalex.org/W6860410504"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4240253816","https://openalex.org/W3096456556","https://openalex.org/W2169584677","https://openalex.org/W2979513934","https://openalex.org/W4232954277","https://openalex.org/W2020341030","https://openalex.org/W2749133591","https://openalex.org/W2367473450"],"abstract_inverted_index":{"The":[0,100],"introduction":[1],"of":[2,21,60,179],"stdpar":[3,61,69,147,172],"in":[4,23,37,51,90],"C++":[5],"introduces":[6],"parallel":[7],"algorithms":[8],"into":[9],"the":[10,19,49,58,64,91,118,145,154,184],"standard":[11],"library,":[12],"which":[13],"allows":[14],"developers":[15],"to":[16,27,150,161,181],"easily":[17],"harness":[18],"power":[20],"parallelism":[22],"their":[24],"applications,":[25],"leading":[26],"potential":[28],"performance":[29,46],"improvements,":[30],"scalability,":[31],"increased":[32],"productivity,":[33],"and":[34,62,81,113,129,158,196],"improved":[35],"reproducibility":[36],"scientific":[38],"computing":[39],"tasks.":[40],"At":[41],"least":[42],"theoretically,":[43],"as":[44],"its":[45],"depends":[47],"on":[48,120,153,163,201],"compiler":[50],"use.":[52],"In":[53],"this":[54,72],"paper,":[55],"we":[56,74,138,169],"examine":[57],"usability":[59],"demonstrate":[63],"significant":[65],"differences":[66,143],"between":[67,144],"different":[68,146,190],"compilers.":[70],"To":[71],"end,":[73],"study":[75],"a":[76,82,130,177],"kernel":[77],"matrix":[78],"assembly":[79],"algorithm":[80],"BLAS":[83],"level":[84],"3":[85],"SYMM":[86],"function,":[87],"both":[88],"implemented":[89],"Parallel":[92],"Least":[93],"Squares":[94],"Support":[95],"Vector":[96],"Machine":[97],"(PLSSVM)":[98],"library.":[99],"same":[101,186],"code":[102,119],"is":[103],"compiled":[104],"with":[105,183],"an":[106,121,125],"NVIDIA":[107,122,155],"nvc++,":[108],"gcc,":[109],"Intel":[110],"oneAPI":[111],"icpx,":[112],"AdaptiveCpp":[114],"compiler.":[115],"We":[116],"analyzed":[117],"A30":[123,156],"GPU,":[124,128],"AMD":[126,132,165],"MI210":[127],"dual-socket":[131],"EPYC":[133,166],"9274F":[134],"CPU":[135],"machine.":[136],"First,":[137],"report":[139],"surprisingly":[140],"large":[141],"runtime":[142],"compilers:":[148],"up":[149,160,180],"11":[151],"percent":[152],"GPU":[157],"even":[159],"335%":[162],"two":[164],"9274F.":[167],"Second,":[168],"show":[170],"how":[171],"enables":[173],"energy":[174],"reduction":[175],"by":[176,188],"factor":[178],"20.7":[182],"very":[185],"implementation":[187],"utilizing":[189],"hardware":[191],"platforms.The":[192],"code,":[193],"utility":[194],"scripts,":[195],"documentation":[197],"are":[198],"all":[199],"available":[200],"GitHub:":[202],"https://github.com/SC-SGS/PLSSVM":[203]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}