{"id":"https://openalex.org/W1966611485","doi":"https://doi.org/10.1145/1454115.1454134","title":"Runtime optimization of vector operations on large scale SMP clusters","display_name":"Runtime optimization of vector operations on large scale SMP clusters","publication_year":2008,"publication_date":"2008-10-25","ids":{"openalex":"https://openalex.org/W1966611485","doi":"https://doi.org/10.1145/1454115.1454134","mag":"1966611485"},"language":"en","primary_location":{"id":"doi:10.1145/1454115.1454134","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1454115.1454134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th international conference on Parallel architectures and compilation techniques","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/A5023233400","display_name":"Costin Iancu","orcid":"https://orcid.org/0000-0001-7845-2427"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Costin Iancu","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA, USA","Lawrence Berkeley National Laboratory, Berkeley, CA USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]},{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA USA#TAB#","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016671058","display_name":"Steven Hofmeyr","orcid":"https://orcid.org/0000-0002-3299-472X"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Hofmeyr","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA, USA","Lawrence Berkeley National Laboratory, Berkeley, CA USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]},{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA USA#TAB#","institution_ids":["https://openalex.org/I148283060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5023233400"],"corresponding_institution_ids":["https://openalex.org/I148283060"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04751832,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"122","last_page":"132"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9990000128746033,"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":0.9990000128746033,"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":0.8514261245727539},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.6272774338722229},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.6109366416931152},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6035430431365967},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.536325216293335},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5152173638343811},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.42005470395088196},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4153985381126404},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.40319550037384033},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2842079997062683},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13881346583366394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8514261245727539},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.6272774338722229},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.6109366416931152},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6035430431365967},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.536325216293335},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5152173638343811},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.42005470395088196},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4153985381126404},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40319550037384033},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2842079997062683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13881346583366394},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1454115.1454134","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1454115.1454134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th international conference on Parallel architectures and compilation techniques","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.392.8570","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.392.8570","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://crd.lbl.gov/assets/pubs_presos/pact120-iancu.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W179815580","https://openalex.org/W255796304","https://openalex.org/W1559860755","https://openalex.org/W1580435966","https://openalex.org/W1861151562","https://openalex.org/W1991591392","https://openalex.org/W2008654264","https://openalex.org/W2041351581","https://openalex.org/W2063400505","https://openalex.org/W2065413511","https://openalex.org/W2109982223","https://openalex.org/W2110102019","https://openalex.org/W2116823855","https://openalex.org/W2119094934","https://openalex.org/W2122395763","https://openalex.org/W2122814645","https://openalex.org/W2137192690","https://openalex.org/W2140300123","https://openalex.org/W2155066383","https://openalex.org/W2157203968","https://openalex.org/W2165575435","https://openalex.org/W2166521388","https://openalex.org/W2561675875","https://openalex.org/W2677178705","https://openalex.org/W2753574770","https://openalex.org/W4235939861"],"related_works":["https://openalex.org/W4256429076","https://openalex.org/W1971174658","https://openalex.org/W2120447654","https://openalex.org/W2977179488","https://openalex.org/W2099195351","https://openalex.org/W2144453115","https://openalex.org/W2128223750","https://openalex.org/W4238532390","https://openalex.org/W2188872161","https://openalex.org/W2961779879"],"abstract_inverted_index":{"\"Vector\"":[0],"style":[1],"communication":[2,111],"operations":[3,14],"transfer":[4],"multiple":[5,63],"disjoint":[6],"memory":[7],"regions":[8],"within":[9],"one":[10],"logical":[11],"step.":[12],"These":[13],"are":[15],"widely":[16],"used":[17],"in":[18,110],"applications,":[19],"they":[20],"do":[21],"improve":[22],"application":[23],"performance,":[24],"and":[25,31],"their":[26],"behavior":[27],"has":[28],"been":[29],"studied":[30],"optimized":[32],"using":[33],"different":[34],"implementation":[35,57],"techniques":[36,100],"across":[37],"a":[38,48,59],"large":[39],"variety":[40],"of":[41,53,58,94],"systems.":[42],"In":[43],"this":[44],"paper":[45],"we":[46,79,97],"present":[47],"methodology":[49],"for":[50,72,107],"the":[51,54,92],"selection":[52],"best":[55],"performing":[56],"vector":[60],"operation":[61],"from":[62],"alternative":[64],"implementations.":[65],"Our":[66],"approach":[67],"is":[68],"designed":[69],"to":[70,86,91,102],"work":[71],"systems":[73],"with":[74],"wide":[75],"SMP":[76],"nodes":[77],"where":[78],"believe":[80,98],"that":[81,99],"most":[82],"published":[83],"studies":[84],"fail":[85],"correctly":[87],"predict":[88],"performance.":[89],"Due":[90],"emergence":[93],"multi-core":[95],"processors":[96],"similar":[101],"ours":[103],"will":[104],"be":[105],"incorporated":[106],"performance":[108],"reasons":[109],"libraries":[112],"or":[113],"language":[114],"runtimes.":[115]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}