{"id":"https://openalex.org/W2013926070","doi":"https://doi.org/10.1080/17445760600568139","title":"Algorithmic optimizations of a conjugate gradient solver on shared memory architectures","display_name":"Algorithmic optimizations of a conjugate gradient solver on shared memory architectures","publication_year":2006,"publication_date":"2006-06-19","ids":{"openalex":"https://openalex.org/W2013926070","doi":"https://doi.org/10.1080/17445760600568139","mag":"2013926070"},"language":"en","primary_location":{"id":"doi:10.1080/17445760600568139","is_oa":false,"landing_page_url":"https://doi.org/10.1080/17445760600568139","pdf_url":null,"source":{"id":"https://openalex.org/S85375271","display_name":"International Journal of Parallel Emergent and Distributed Systems","issn_l":"1026-7689","issn":["1026-7689","1029-032X","1063-7192","1744-5760","1744-5779"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Parallel, Emergent and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-67891","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055315465","display_name":"Henrik L\u00f6f","orcid":null},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Henrik L\u00f6f","raw_affiliation_strings":["Uppsala University, Department of Information Technology, Box 337, Uppsala, 751 05, Sweden","Uppsala University, Department of Information Technology , Box 337, Uppsala, 751 05, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Uppsala University, Department of Information Technology, Box 337, Uppsala, 751 05, Sweden","institution_ids":["https://openalex.org/I123387679"]},{"raw_affiliation_string":"Uppsala University, Department of Information Technology , Box 337, Uppsala, 751 05, Sweden","institution_ids":["https://openalex.org/I123387679"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074772489","display_name":"Jarmo Rantakokko","orcid":null},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jarmo Rantakokko","raw_affiliation_strings":["Uppsala University, Department of Information Technology, Box 337, Uppsala, 751 05, Sweden","Uppsala University, Department of Information Technology , Box 337, Uppsala, 751 05, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Uppsala University, Department of Information Technology, Box 337, Uppsala, 751 05, Sweden","institution_ids":["https://openalex.org/I123387679"]},{"raw_affiliation_string":"Uppsala University, Department of Information Technology , Box 337, Uppsala, 751 05, Sweden","institution_ids":["https://openalex.org/I123387679"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5055315465"],"corresponding_institution_ids":["https://openalex.org/I123387679"],"apc_list":null,"apc_paid":null,"fwci":0.9498,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79258496,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"21","issue":"5","first_page":"345","last_page":"363"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9915000200271606,"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":0.9915000200271606,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.989799976348877,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9843000173568726,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/conjugate-gradient-method","display_name":"Conjugate gradient method","score":0.774814248085022},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6833699345588684},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6635891199111938},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5935614109039307},{"id":"https://openalex.org/keywords/conjugate","display_name":"Conjugate","score":0.5876087546348572},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3480835556983948},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19951856136322021},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17353641986846924},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15122464299201965}],"concepts":[{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.774814248085022},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6833699345588684},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6635891199111938},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5935614109039307},{"id":"https://openalex.org/C197336794","wikidata":"https://www.wikidata.org/wiki/Q5161150","display_name":"Conjugate","level":2,"score":0.5876087546348572},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3480835556983948},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19951856136322021},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17353641986846924},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15122464299201965},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1080/17445760600568139","is_oa":false,"landing_page_url":"https://doi.org/10.1080/17445760600568139","pdf_url":null,"source":{"id":"https://openalex.org/S85375271","display_name":"International Journal of Parallel Emergent and Distributed Systems","issn_l":"1026-7689","issn":["1026-7689","1029-032X","1063-7192","1744-5760","1744-5779"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Parallel, Emergent and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:DiVA.org:uu-67891","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-67891","pdf_url":null,"source":{"id":"https://openalex.org/S4306402042","display_name":"Uppsala University Publications (Uppsala University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123387679","host_organization_name":"Uppsala University","host_organization_lineage":["https://openalex.org/I123387679"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/report"}],"best_oa_location":{"id":"pmh:oai:DiVA.org:uu-67891","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-67891","pdf_url":null,"source":{"id":"https://openalex.org/S4306402042","display_name":"Uppsala University Publications (Uppsala University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123387679","host_organization_name":"Uppsala University","host_organization_lineage":["https://openalex.org/I123387679"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/report"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W173642856","https://openalex.org/W1235391856","https://openalex.org/W1503001724","https://openalex.org/W1552224009","https://openalex.org/W1575701986","https://openalex.org/W1598206477","https://openalex.org/W1766762903","https://openalex.org/W1971343078","https://openalex.org/W1986914969","https://openalex.org/W1987393840","https://openalex.org/W2037244283","https://openalex.org/W2040590908","https://openalex.org/W2066692739","https://openalex.org/W2070232376","https://openalex.org/W2089370129","https://openalex.org/W2093603593","https://openalex.org/W2095420020","https://openalex.org/W2100720297","https://openalex.org/W2101195691","https://openalex.org/W2104120668","https://openalex.org/W2114977680","https://openalex.org/W2133947540","https://openalex.org/W2135460498","https://openalex.org/W2153075575","https://openalex.org/W2155819987","https://openalex.org/W2165220841","https://openalex.org/W2912686856","https://openalex.org/W4300666158"],"related_works":["https://openalex.org/W1503783781","https://openalex.org/W1604758548","https://openalex.org/W4367553810","https://openalex.org/W2104142636","https://openalex.org/W1549048322","https://openalex.org/W2804126825","https://openalex.org/W2011940952","https://openalex.org/W2731831065","https://openalex.org/W4283162424","https://openalex.org/W2144429051"],"abstract_inverted_index":{"OpenMP":[0,12,91],"is":[1,13,39,132,160],"an":[2,45,82],"architecture-independent":[3,27],"language":[4],"for":[5,42,68],"programming":[6,23],"in":[7,20,90],"the":[8,26,32,79,110,133,158,164,168],"shared":[9,53,97],"memory":[10,54,98,124,143,148],"model.":[11],"designed":[14],"to":[15],"be":[16],"simple":[17],"and":[18,61,107,123,141],"powerful":[19],"terms":[21],"of":[22,34,77,81,96,109,120],"abstractions.":[24],"Unfortunately,":[25],"abstractions":[28],"sometimes":[29],"come":[30],"with":[31,44,163],"price":[33],"low":[35],"parallel":[36],"performance.":[37,69],"This":[38],"especially":[40],"true":[41],"applications":[43],"unstructured":[46],"data":[47,59],"access":[48],"pattern":[49],"running":[50,92],"on":[51,93],"distributed":[52],"systems":[55],"(DSM).":[56],"Here,":[57],"proper":[58],"distribution":[60],"algorithmic":[62,165],"optimizations":[63,166],"play":[64],"a":[65,117,146,155,175],"vital":[66],"role":[67],"In":[70],"this":[71],"article,":[72],"we":[73,127,150],"have":[74,101],"investigated":[75],"ways":[76],"improving":[78],"performance":[80,159],"industrial":[83],"class":[84],"conjugate":[85],"gradient":[86],"(CG)":[87],"solver,":[88],"implemented":[89],"two":[94],"types":[95],"systems.":[99],"We":[100],"evaluated":[102],"bandwidth":[103,130],"minimization,":[104],"graph":[105],"partitioning":[106],"reformulations":[108],"original":[111],"algorithm":[112],"reducing":[113,137],"global":[114,171],"barriers.":[115],"By":[116],"detailed":[118],"analysis":[119],"barrier":[121],"time":[122],"system":[125,169],"performance,":[126],"found":[128],"that":[129],"minimization":[131],"most":[134],"important":[135],"optimization":[136],"both":[138],"L2":[139],"misses":[140],"remote":[142],"accesses.":[144],"On":[145,154],"uniform":[147],"system,":[149,157],"get":[151],"perfect":[152],"scaling.":[153],"NUMA":[156],"significantly":[161],"improved":[162],"leaving":[167],"dependent":[170],"reduction":[172],"operations":[173],"as":[174],"bottleneck.":[176]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
