{"id":"https://openalex.org/W3021133567","doi":"https://doi.org/10.1145/3375555.3383586","title":"Acceleration Opportunities in Linear Algebra Applications via Idiom Recognition","display_name":"Acceleration Opportunities in Linear Algebra Applications via Idiom Recognition","publication_year":2020,"publication_date":"2020-04-20","ids":{"openalex":"https://openalex.org/W3021133567","doi":"https://doi.org/10.1145/3375555.3383586","mag":"3021133567"},"language":"en","primary_location":{"id":"doi:10.1145/3375555.3383586","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3375555.3383586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the ACM/SPEC International Conference on Performance Engineering","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/A5090480187","display_name":"Jo\u00e3o P. L. de Carvalho","orcid":"https://orcid.org/0000-0002-3476-184X"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o P. L. de Carvalho","raw_affiliation_strings":["University of Campinas, Campinas, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Campinas, Campinas, Brazil","institution_ids":["https://openalex.org/I181391015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017764932","display_name":"Braedy Kuzma","orcid":"https://orcid.org/0000-0001-5819-1100"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Braedy Kuzma","raw_affiliation_strings":["University of Alberta, Edmonton, AB, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, AB, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067675731","display_name":"Guido Ara\u00fajo","orcid":"https://orcid.org/0000-0003-4869-5190"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Guido Araujo","raw_affiliation_strings":["University of Campinas, Campinas, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Campinas, Campinas, Brazil","institution_ids":["https://openalex.org/I181391015"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.236,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46499507,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"34","last_page":"35"},"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":0.9983000159263611,"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":0.9980999827384949,"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":0.8241851329803467},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.7808789014816284},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.7462854981422424},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.5801007151603699},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5618257522583008},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5265196561813354},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5253604650497437},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5143104791641235},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3439386487007141},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.30221447348594666},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.144250750541687},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07698136568069458}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8241851329803467},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.7808789014816284},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.7462854981422424},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.5801007151603699},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5618257522583008},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5265196561813354},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5253604650497437},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5143104791641235},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3439386487007141},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.30221447348594666},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.144250750541687},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07698136568069458},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3375555.3383586","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3375555.3383586","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion of the ACM/SPEC International Conference on Performance Engineering","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":3,"referenced_works":["https://openalex.org/W1992200374","https://openalex.org/W2084379367","https://openalex.org/W2412152731"],"related_works":["https://openalex.org/W3126131865","https://openalex.org/W4253186488","https://openalex.org/W2044344400","https://openalex.org/W1996938127","https://openalex.org/W2083611981","https://openalex.org/W3121314575","https://openalex.org/W3147497457","https://openalex.org/W4206336957","https://openalex.org/W4225552076","https://openalex.org/W3004823601"],"abstract_inverted_index":{"General":[0],"matrix-matrix":[1],"multiplication":[2],"(GEMM)":[3],"is":[4,14],"a":[5,15,105],"critical":[6],"operation":[7],"in":[8,43],"many":[9],"application":[10],"domains":[11],"[1].":[12],"It":[13],"central":[16],"building":[17],"block":[18],"of":[19,45,99,102,120],"deep":[20],"learning":[21],"algorithms,":[22],"computer":[23],"graphics":[24],"operations,":[25],"and":[26,40,52,61],"other":[27,53],"linear":[28],"algebra":[29],"dominated":[30],"applications.":[31],"Due":[32],"to":[33,72,95],"this,":[34],"GEMM":[35,103,121],"has":[36],"been":[37],"extensively":[38],"studied":[39],"optimized,":[41],"resulting":[42],"libraries":[44],"exceptional":[46],"quality":[47],"such":[48,57],"as":[49,58],"BLAS,":[50],"Eigen,":[51],"platform":[54],"specific":[55],"implementations":[56,101,119],"MKL":[59],"(Intel)":[60],"ESSL":[62],"(IBM)":[63],"[2,3].":[64],"Despite":[65],"these":[66],"successes,":[67],"the":[68,80,86,111],"GeMM":[69],"idiom":[70,115],"continues":[71],"be":[73],"re-implemented":[74],"by":[75,85,124],"programmers,":[76],"without":[77],"consideration":[78],"for":[79,84],"intricacies":[81],"already":[82],"accounted":[83],"aforementioned":[87],"libraries.":[88],"To":[89],"this":[90,92],"end,":[91],"project":[93],"aims":[94],"provide":[96],"transparent":[97],"adoption":[98],"high-performance":[100],"through":[104],"novel":[106],"optimization":[107],"pass":[108],"implemented":[109],"within":[110],"LLVM":[112],"framework":[113],"using":[114],"recognition":[116],"techniques[4].":[117],"Sub-optimal":[118],"are":[122],"replaced":[123],"equivalent":[125],"library":[126],"calls.":[127]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
