{"id":"https://openalex.org/W2061788314","doi":"https://doi.org/10.1145/2591635.2591656","title":"Author retrospective for optimizing matrix multiply using PHiPAC","display_name":"Author retrospective for optimizing matrix multiply using PHiPAC","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2061788314","doi":"https://doi.org/10.1145/2591635.2591656","mag":"2061788314"},"language":"en","primary_location":{"id":"doi:10.1145/2591635.2591656","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2591635.2591656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"25th Anniversary International Conference on Supercomputing Anniversary Volume -","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/A5113478221","display_name":"Jeff Bilmes","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jeff Bilmes","raw_affiliation_strings":["University of Washington, Seattle, WA, USA","University of Washington, Seattle WA, USA"],"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"University of Washington, Seattle WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035134864","display_name":"Krste Asanovi\u0107","orcid":"https://orcid.org/0000-0003-0754-3975"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krste Asanovic","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA","University of California, Berkeley, Berkeley, CA USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016822385","display_name":"CheeWhye Chin","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chee-Whye Chin","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109872442","display_name":"Jim Demmel","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jim Demmel","raw_affiliation_strings":["University of California, Berkeley, Berkeley, CA, USA","University of California, Berkeley, Berkeley, CA USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, Berkeley, CA USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5113478221"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":1.2259,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.79528118,"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":"42","last_page":"44"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/compiler","display_name":"Compiler","score":0.9272599220275879},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.822501540184021},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.7411915063858032},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6713401079177856},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.5182499885559082},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5116530060768127},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5058073997497559},{"id":"https://openalex.org/keywords/assembly-language","display_name":"Assembly language","score":0.4764459431171417},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.4602659046649933},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4522186517715454},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.4451175332069397},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.42584165930747986},{"id":"https://openalex.org/keywords/compile-time","display_name":"Compile time","score":0.42326849699020386},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3665541112422943},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1479179561138153},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.0750797688961029},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06730908155441284}],"concepts":[{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.9272599220275879},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.822501540184021},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.7411915063858032},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6713401079177856},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.5182499885559082},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5116530060768127},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5058073997497559},{"id":"https://openalex.org/C50831359","wikidata":"https://www.wikidata.org/wiki/Q165436","display_name":"Assembly language","level":3,"score":0.4764459431171417},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.4602659046649933},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4522186517715454},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.4451175332069397},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.42584165930747986},{"id":"https://openalex.org/C200833197","wikidata":"https://www.wikidata.org/wiki/Q333707","display_name":"Compile time","level":3,"score":0.42326849699020386},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3665541112422943},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1479179561138153},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0750797688961029},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06730908155441284},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2591635.2591656","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2591635.2591656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"25th Anniversary International Conference on Supercomputing Anniversary Volume -","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1566317540","https://openalex.org/W1576205104","https://openalex.org/W1577724162","https://openalex.org/W1972209410","https://openalex.org/W2014244478","https://openalex.org/W2044437287","https://openalex.org/W2074488431","https://openalex.org/W2136922672"],"related_works":["https://openalex.org/W2005635288","https://openalex.org/W2011669306","https://openalex.org/W2168850728","https://openalex.org/W2157117208","https://openalex.org/W2999906275","https://openalex.org/W4237382625","https://openalex.org/W1561018727","https://openalex.org/W2623604894","https://openalex.org/W3110545230","https://openalex.org/W2527038815"],"abstract_inverted_index":{"PHiPAC":[0],"was":[1,82,87,99,137],"an":[2,60,85],"early":[3,29],"attempt":[4],"to":[5,19,62,89,106,139],"improve":[6],"software":[7],"performance":[8],"by":[9],"searching":[10],"in":[11,27,51],"a":[12,66,114],"large":[13],"design":[14,121],"space":[15],"of":[16,59,65,117,131],"possible":[17,119],"implementations":[18],"find":[20],"the":[21,25,28,31,63,80,94,118,128,132,147],"best":[22],"one.":[23],"At":[24],"time,":[26],"1990s,":[30],"most":[32],"efficient":[33],"numerical":[34],"linear":[35],"algebra":[36],"libraries":[37],"were":[38,48],"carefully":[39],"hand":[40],"tuned":[41],"for":[42,73],"specific":[43],"microarchitectures":[44],"and":[45,47,69,101,111,134],"compilers,":[46],"often":[49],"written":[50],"assembly":[52],"language.":[53],"This":[54],"allowed":[55],"very":[56],"precise":[57],"tuning":[58],"algorithm":[61],"specifics":[64],"current":[67],"platform,":[68],"provided":[70],"great":[71,103],"opportunity":[72],"high":[74],"efficiency.":[75],"The":[76],"prevailing":[77],"thought":[78],"at":[79],"time":[81],"that":[83],"such":[84],"approach":[86,98],"necessary":[88],"produce":[90],"near-peak":[91],"performance.":[92],"On":[93],"other":[95],"hand,":[96],"this":[97],"brittle,":[100],"required":[102],"human":[104],"effort":[105],"try":[107],"each":[108],"code":[109,120,142],"variant,":[110],"so":[112],"only":[113],"tiny":[115],"subset":[116],"points":[122],"could":[123],"be":[124,145],"explored.":[125],"Worse,":[126],"given":[127],"combined":[129],"complexities":[130],"compiler":[133],"microarchitecture,":[135],"it":[136],"difficult":[138],"predict":[140],"which":[141],"variants":[143],"would":[144],"worth":[146],"implementation":[148],"effort.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
