{"id":"https://openalex.org/W2626469804","doi":"https://doi.org/10.1109/aiccsa.2016.7945637","title":"Auto-tuning TRSM with an asynchronous task assignment model on multicore, multi-GPU and coprocessor systems","display_name":"Auto-tuning TRSM with an asynchronous task assignment model on multicore, multi-GPU and coprocessor systems","publication_year":2016,"publication_date":"2016-11-01","ids":{"openalex":"https://openalex.org/W2626469804","doi":"https://doi.org/10.1109/aiccsa.2016.7945637","mag":"2626469804"},"language":"en","primary_location":{"id":"doi:10.1109/aiccsa.2016.7945637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiccsa.2016.7945637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA)","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/A5072907443","display_name":"Cl\u00edcia Pinto","orcid":null},"institutions":[{"id":"https://openalex.org/I126158947","display_name":"Universidade Federal da Bahia","ror":"https://ror.org/03k3p7647","country_code":"BR","type":"education","lineage":["https://openalex.org/I126158947"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Clicia Pinto","raw_affiliation_strings":["Laborat\u00f3rio de Sistemas Distribu\u00eddos, Universidade Federal da Bahia (UFBA), Salvador, Bahia, Brazil"],"affiliations":[{"raw_affiliation_string":"Laborat\u00f3rio de Sistemas Distribu\u00eddos, Universidade Federal da Bahia (UFBA), Salvador, Bahia, Brazil","institution_ids":["https://openalex.org/I126158947"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000123273","display_name":"Marcos Barreto","orcid":"https://orcid.org/0000-0002-7818-1855"},"institutions":[{"id":"https://openalex.org/I126158947","display_name":"Universidade Federal da Bahia","ror":"https://ror.org/03k3p7647","country_code":"BR","type":"education","lineage":["https://openalex.org/I126158947"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Marcos Barreto","raw_affiliation_strings":["Laborat\u00f3rio de Sistemas Distribu\u00eddos, Universidade Federal da Bahia (UFBA), Salvador, Bahia, Brazil"],"affiliations":[{"raw_affiliation_string":"Laborat\u00f3rio de Sistemas Distribu\u00eddos, Universidade Federal da Bahia (UFBA), Salvador, Bahia, Brazil","institution_ids":["https://openalex.org/I126158947"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007351831","display_name":"Murilo Boratto","orcid":"https://orcid.org/0000-0003-3908-4451"},"institutions":[{"id":"https://openalex.org/I1316675753","display_name":"Universidade do Estado da Bahia","ror":"https://ror.org/015n1m812","country_code":"BR","type":"education","lineage":["https://openalex.org/I1316675753"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Murilo Boratto","raw_affiliation_strings":["N\u00facleo de Arquitetura de Computadores e Sistemas Operacionais, Universidade do Estado da Bahia (UNEB), Salvador, Bahia, Brazil"],"affiliations":[{"raw_affiliation_string":"N\u00facleo de Arquitetura de Computadores e Sistemas Operacionais, Universidade do Estado da Bahia (UNEB), Salvador, Bahia, Brazil","institution_ids":["https://openalex.org/I1316675753"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5072907443"],"corresponding_institution_ids":["https://openalex.org/I126158947"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22418657,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":null,"first_page":"1","last_page":"8"},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9998000264167786,"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":0.9991999864578247,"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":0.8660711050033569},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.7830748558044434},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.7514088153839111},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.7437362670898438},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.7039854526519775},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6985042095184326},{"id":"https://openalex.org/keywords/multiprocessing","display_name":"Multiprocessing","score":0.5649617314338684},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5096666812896729},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45618051290512085},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4371337592601776},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.43531233072280884},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.16478285193443298},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09838521480560303}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8660711050033569},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.7830748558044434},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.7514088153839111},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7437362670898438},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.7039854526519775},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6985042095184326},{"id":"https://openalex.org/C4822641","wikidata":"https://www.wikidata.org/wiki/Q846651","display_name":"Multiprocessing","level":2,"score":0.5649617314338684},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5096666812896729},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45618051290512085},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4371337592601776},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.43531233072280884},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.16478285193443298},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09838521480560303},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aiccsa.2016.7945637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiccsa.2016.7945637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W182691100","https://openalex.org/W1509342228","https://openalex.org/W1598123014","https://openalex.org/W1964031104","https://openalex.org/W1986334759","https://openalex.org/W2014244478","https://openalex.org/W2045295714","https://openalex.org/W2050927566","https://openalex.org/W2064959534","https://openalex.org/W2096070062","https://openalex.org/W2099021415","https://openalex.org/W2109031898","https://openalex.org/W2122202371","https://openalex.org/W2124480634","https://openalex.org/W2134453244","https://openalex.org/W2183604634","https://openalex.org/W2592062615","https://openalex.org/W2995041159","https://openalex.org/W6635460668","https://openalex.org/W6641237240","https://openalex.org/W6685833736"],"related_works":["https://openalex.org/W2374902472","https://openalex.org/W2482815832","https://openalex.org/W2170132667","https://openalex.org/W2326041751","https://openalex.org/W2294358097","https://openalex.org/W2189498595","https://openalex.org/W1993191611","https://openalex.org/W2731059981","https://openalex.org/W1999755551","https://openalex.org/W2150820374"],"abstract_inverted_index":{"The":[0],"increasing":[1],"need":[2],"for":[3,11,80],"computing":[4],"power":[5],"today":[6],"justifies":[7],"the":[8,15,40,51],"continuous":[9],"search":[10],"techniques":[12],"that":[13,48],"decrease":[14],"time":[16],"to":[17,65],"answer":[18],"usual":[19],"computational":[20],"problems.":[21],"To":[22],"take":[23],"advantage":[24],"of":[25,44,53,77],"new":[26],"hybrid":[27],"parallel":[28,46],"architectures":[29],"composed":[30],"by":[31],"multithreading":[32],"and":[33,42,70,89,93],"multiprocessor":[34],"hardware,":[35],"our":[36],"current":[37],"efforts":[38],"involve":[39],"design":[41],"validation":[43],"highly":[45],"algorithms":[47],"efficiently":[49],"explore":[50],"characteristics":[52],"such":[54],"architectures.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59],"propose":[60],"an":[61,75,78],"automatic":[62],"tuning":[63],"methodology":[64],"easily":[66],"exploit":[67],"multicore,":[68],"multi-GPU":[69],"coprocessor":[71],"systems.":[72],"We":[73],"present":[74],"optimization":[76],"algorithm":[79],"solving":[81],"triangular":[82],"systems":[83],"(TRSM),":[84],"based":[85],"on":[86],"block":[87],"decomposition":[88],"asynchronous":[90],"task":[91],"assignment,":[92],"discuss":[94],"some":[95],"results.":[96]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}