{"id":"https://openalex.org/W2043291549","doi":"https://doi.org/10.1145/1274971.1274986","title":"An operation stacking framework for large ensemble computations","display_name":"An operation stacking framework for large ensemble computations","publication_year":2007,"publication_date":"2007-06-17","ids":{"openalex":"https://openalex.org/W2043291549","doi":"https://doi.org/10.1145/1274971.1274986","mag":"2043291549"},"language":"en","primary_location":{"id":"doi:10.1145/1274971.1274986","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1274971.1274986","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st annual international conference on Supercomputing","raw_type":"proceedings-article"},"type":"conference-paper","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/A5078584378","display_name":"Mehmet Belgin","orcid":"https://orcid.org/0000-0001-8613-3485"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehmet Belgin","raw_affiliation_strings":["State University, Blacksburg, VA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State University, Blacksburg, VA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111678566","display_name":"Calvin J. Ribbens","orcid":null},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Calvin J. Ribbens","raw_affiliation_strings":["State University, Blacksburg, VA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State University, Blacksburg, VA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081080607","display_name":"Godmar Back","orcid":null},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Godmar Back","raw_affiliation_strings":["State University, Blacksburg, VA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State University, Blacksburg, VA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"00","issue":null,"first_page":"83","last_page":"92"},"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9983999729156494,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9973000288009644,"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":0.859143853187561},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7552899122238159},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.676912784576416},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6055842638015747},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.549885630607605},{"id":"https://openalex.org/keywords/generalized-minimal-residual-method","display_name":"Generalized minimal residual method","score":0.5449920296669006},{"id":"https://openalex.org/keywords/conjugate-gradient-method","display_name":"Conjugate gradient method","score":0.5320504903793335},{"id":"https://openalex.org/keywords/stacking","display_name":"Stacking","score":0.5114980936050415},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.47437554597854614},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.449513703584671},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4224022626876831},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3831101655960083}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.859143853187561},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7552899122238159},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.676912784576416},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6055842638015747},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.549885630607605},{"id":"https://openalex.org/C155332342","wikidata":"https://www.wikidata.org/wiki/Q1432976","display_name":"Generalized minimal residual method","level":3,"score":0.5449920296669006},{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.5320504903793335},{"id":"https://openalex.org/C33347731","wikidata":"https://www.wikidata.org/wiki/Q285210","display_name":"Stacking","level":2,"score":0.5114980936050415},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.47437554597854614},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.449513703584671},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4224022626876831},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3831101655960083},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C46141821","wikidata":"https://www.wikidata.org/wiki/Q209402","display_name":"Nuclear magnetic resonance","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1274971.1274986","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1274971.1274986","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st annual international conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W78547367","https://openalex.org/W336063547","https://openalex.org/W1506342804","https://openalex.org/W1509994495","https://openalex.org/W1518969538","https://openalex.org/W1545465591","https://openalex.org/W1552224009","https://openalex.org/W1884140786","https://openalex.org/W1964031104","https://openalex.org/W1964477602","https://openalex.org/W1965351873","https://openalex.org/W1965551736","https://openalex.org/W1981772986","https://openalex.org/W1982733412","https://openalex.org/W1987393840","https://openalex.org/W2002257715","https://openalex.org/W2007774531","https://openalex.org/W2012969549","https://openalex.org/W2045841536","https://openalex.org/W2049890071","https://openalex.org/W2099625934","https://openalex.org/W2111255560","https://openalex.org/W2114977680","https://openalex.org/W2115215129","https://openalex.org/W2117197583","https://openalex.org/W2130289795","https://openalex.org/W2138007781","https://openalex.org/W2154590891","https://openalex.org/W2533362133","https://openalex.org/W6630354094"],"related_works":["https://openalex.org/W2358905935","https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W3046241855","https://openalex.org/W2139875628","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W1976157534","https://openalex.org/W2369649360"],"abstract_inverted_index":{"Iterative":[0],"solutions":[1],"of":[2,11,45,57,66,203,214,221],"sparse":[3,25,47,137],"problems":[4,138],"often":[5],"achieve":[6],"only":[7,51,61],"a":[8,52,87,190,230],"small":[9,53],"fraction":[10],"the":[12,42,116,129,179,201],"peak":[13],"theoretical":[14],"performance":[15,98,212],"on":[16,120,229],"modern":[17],"architectures.":[18],"This":[19],"problem":[20,92],"is":[21],"highly":[22],"challenging":[23],"because":[24],"matrix":[26,48],"storage":[27],"schemes":[28],"require":[29],"data":[30,122,142],"to":[31,37,63,90,173,208,216],"be":[32,101],"accessed":[33],"irregularly,":[34],"which":[35,59,114,134],"leads":[36,62],"massive":[38],"cache":[39,151],"misses.":[40],"Furthermore,":[41],"inner":[43],"loop":[44],"typical":[46],"operations":[49],"accesses":[50],"and":[54,84,143,152,183,226],"variable":[55],"amount":[56],"data,":[58],"not":[60,94],"low":[64],"utilization":[65],"floating":[67],"point":[68],"registers,":[69],"but":[70],"also":[71],"prevents":[72],"optimization":[73],"techniques":[74],"that":[75,169,197],"improve":[76],"instruction":[77],"level":[78],"parallelism":[79],"(ILP),":[80],"such":[81,177],"as":[82,146,178],"unroll":[83],"jam.":[85],"Although":[86],"general":[88],"solution":[89],"this":[91,125],"has":[93],"been":[95],"found,":[96],"significant":[97],"improvements":[99,213],"can":[100,156,199],"made":[102],"for":[103,223],"at":[104],"least":[105],"one":[106],"important":[107],"special":[108],"case,":[109],"namely":[110],"large":[111],"ensemble":[112],"computations,":[113],"run":[115],"same":[117],"application":[118],"repeatedly":[119],"different":[121],"sets.":[123],"In":[124],"paper,":[126],"we":[127],"present":[128],"Operation":[130],"Stacking":[131],"Framework":[132],"(OSF),":[133],"runs":[135],"multiple":[136],"simultaneously,":[139],"stacking":[140,198],"their":[141,162],"solving":[144],"them":[145],"one,":[147],"thus":[148],"improving":[149],"both":[150],"ILP":[153],"utilization.":[154],"Programmers":[155],"use":[157],"stacked":[158,191,224],"solvers":[159,176],"transparently":[160],"in":[161,211],"applications.":[163],"Moreover,":[164],"OSF":[165],"provides":[166],"an":[167,219],"API":[168],"makes":[170],"it":[171],"simple":[172],"convert":[174],"existing":[175],"conjugate":[180],"gradient":[181],"(CG)":[182],"generalized":[184],"minimal":[185],"residual":[186],"(GMRES)":[187],"methods":[188],"into":[189],"form.":[192],"Our":[193],"experimental":[194],"results":[195],"show":[196],"reduce":[200],"number":[202],"L2":[204],"misses":[205],"by":[206],"25%":[207],"44%,":[209],"resulting":[210],"up":[215],"1.95x":[217],"with":[218],"average":[220],"1.60x":[222],"CG":[225],"GMRES":[227],"algorithms":[228],"single":[231],"CPU.":[232]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}