{"id":"https://openalex.org/W4285100150","doi":"https://doi.org/10.1145/3539781.3539785","title":"Reducing communication in the conjugate gradient method","display_name":"Reducing communication in the conjugate gradient method","publication_year":2022,"publication_date":"2022-06-27","ids":{"openalex":"https://openalex.org/W4285100150","doi":"https://doi.org/10.1145/3539781.3539785"},"language":"en","primary_location":{"id":"doi:10.1145/3539781.3539785","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539781.3539785","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3539781.3539785","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Platform for Advanced Scientific Computing Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3539781.3539785","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033686530","display_name":"Martin Karp","orcid":"https://orcid.org/0000-0003-3374-8093"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Martin Karp","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060044772","display_name":"Niclas Jansson","orcid":"https://orcid.org/0000-0002-5020-1631"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Niclas Jansson","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035985391","display_name":"Artur Podobas","orcid":"https://orcid.org/0000-0001-5452-6794"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Artur Podobas","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001997189","display_name":"Philipp Schlatter","orcid":"https://orcid.org/0000-0001-9627-5903"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Philipp Schlatter","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085178088","display_name":"Stefano Markidis","orcid":"https://orcid.org/0000-0003-0639-0639"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Stefano Markidis","raw_affiliation_strings":["KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5033686530"],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":0.6035,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70213462,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9980000257492065,"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"}},"topics":[{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9980000257492065,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9955000281333923,"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"}},{"id":"https://openalex.org/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.8025529384613037},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7767131328582764},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.7294177412986755},{"id":"https://openalex.org/keywords/conjugate-gradient-method","display_name":"Conjugate gradient method","score":0.6818773746490479},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6742523908615112},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.590998649597168},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5356494784355164},{"id":"https://openalex.org/keywords/communications-system","display_name":"Communications system","score":0.49753525853157043},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4853990972042084},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.43728840351104736},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4261504113674164},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4124453365802765},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.37812870740890503},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.37764400243759155},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34388530254364014},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.1538074016571045},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14194709062576294},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10343948006629944}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8025529384613037},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7767131328582764},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.7294177412986755},{"id":"https://openalex.org/C81184566","wikidata":"https://www.wikidata.org/wiki/Q1191895","display_name":"Conjugate gradient method","level":2,"score":0.6818773746490479},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6742523908615112},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.590998649597168},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5356494784355164},{"id":"https://openalex.org/C101765175","wikidata":"https://www.wikidata.org/wiki/Q577764","display_name":"Communications system","level":2,"score":0.49753525853157043},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4853990972042084},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.43728840351104736},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4261504113674164},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4124453365802765},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.37812870740890503},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.37764400243759155},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34388530254364014},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.1538074016571045},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14194709062576294},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10343948006629944},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3539781.3539785","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539781.3539785","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3539781.3539785","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Platform for Advanced Scientific Computing Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3539781.3539785","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3539781.3539785","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3539781.3539785","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Platform for Advanced Scientific Computing Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7200000286102295,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1364868472","display_name":null,"funder_award_id":"2018-05973","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G2826949580","display_name":null,"funder_award_id":"SESSI","funder_id":"https://openalex.org/F4320317161","funder_display_name":"Swedish e-Science Research Centre"},{"id":"https://openalex.org/G3321450376","display_name":null,"funder_award_id":"05973","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G4417068407","display_name":null,"funder_award_id":"2019-04723","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G5356226767","display_name":null,"funder_award_id":"2018-0597","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G6533660618","display_name":null,"funder_award_id":"2018-05973","funder_id":"https://openalex.org/F4320317161","funder_display_name":"Swedish e-Science Research Centre"},{"id":"https://openalex.org/G712881263","display_name":null,"funder_award_id":"2018-","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"}],"funders":[{"id":"https://openalex.org/F4320317161","display_name":"Swedish e-Science Research Centre","ror":"https://ror.org/01e59yk92"},{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285100150.pdf","grobid_xml":"https://content.openalex.org/works/W4285100150.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1486449984","https://openalex.org/W1488942459","https://openalex.org/W1575701986","https://openalex.org/W1907157228","https://openalex.org/W1972501001","https://openalex.org/W2002555321","https://openalex.org/W2010747199","https://openalex.org/W2011467018","https://openalex.org/W2034692228","https://openalex.org/W2047352485","https://openalex.org/W2096714979","https://openalex.org/W2099611016","https://openalex.org/W2102061396","https://openalex.org/W2104736438","https://openalex.org/W2113338557","https://openalex.org/W2128249697","https://openalex.org/W2138266087","https://openalex.org/W2145194992","https://openalex.org/W2157237396","https://openalex.org/W2165439482","https://openalex.org/W2221817300","https://openalex.org/W2284994597","https://openalex.org/W2316564661","https://openalex.org/W2324384718","https://openalex.org/W2572292438","https://openalex.org/W2809001843","https://openalex.org/W2969262004","https://openalex.org/W2984305089","https://openalex.org/W3015998244","https://openalex.org/W3016268593","https://openalex.org/W3155036733","https://openalex.org/W4205715945","https://openalex.org/W4232006005","https://openalex.org/W6629335552"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W2597809628","https://openalex.org/W3012895752"],"abstract_inverted_index":{"Currently,":[0],"a":[1,35,72,89],"major":[2],"bottleneck":[3,30],"for":[4,107,177],"several":[5],"scientific":[6],"computations":[7],"is":[8,211],"communication,":[9,17],"both":[10,122],"communication":[11,20,55,145],"between":[12,21],"different":[13,22],"processors,":[14],"so-called":[15],"horizontal":[16,144],"and":[18,67,127,158,169],"vertical":[19,62],"levels":[23],"of":[24,42,137,173,175,200,209],"the":[25,40,47,54,61,95,108,117,124,130,197,201,207],"memory":[26],"hierarchy.":[27],"With":[28],"this":[29],"in":[31,65,93,193],"mind,":[32],"we":[33,56,83,104,114,149],"target":[34],"notoriously":[36],"communication-bound":[37],"solver":[38,74,87],"at":[39,188],"core":[41],"many":[43],"high-performance":[44,90],"applications,":[45],"namely":[46,156],"conjugate":[48],"gradient":[49],"method":[50,98],"(CG).":[51],"To":[52],"reduce":[53],"present":[57],"lower":[58],"bounds":[59],"on":[60,69,88,111,134,186],"data":[63,77],"movement":[64],"CG":[66,73,86,151,179,183],"go":[68],"to":[70,132,141,152,165,181,195],"make":[71],"with":[75],"reduced":[76],"movement.":[78],"Using":[79],"our":[80,85,102],"theoretical":[81],"analysis":[82],"apply":[84],"discretization":[91],"used":[92],"practice,":[94],"spectral":[96],"element":[97],"(SEM).":[99],"Guided":[100],"by":[101,119,121,128,214],"analysis,":[103],"show":[105,191],"that":[106,192,206],"Poisson":[109],"equation":[110],"modern":[112],"GPUs":[113],"can":[115,146],"improve":[116],"performance":[118,171],"30%":[120],"rematerializing":[123],"discrete":[125],"system":[126,131],"reformulating":[129],"work":[133],"unique":[135],"degrees":[136],"freedom.":[138],"In":[139],"order":[140],"investigate":[142],"how":[143],"be":[147],"reduced,":[148],"compare":[150],"two":[153],"communication-reducing":[154],"techniques,":[155],"communication-avoiding":[157],"pipelined":[159,178,215],"CG.":[160,216],"We":[161,190],"strong":[162],"scale":[163],"up":[164],"4096":[166],"CPU":[167],"cores":[168],"showcase":[170],"improvements":[172],"upwards":[174],"70%":[176],"compared":[180],"standard":[182],"when":[184],"applied":[185],"SEM":[187,210],"scale.":[189],"addition":[194],"improving":[196],"scaling":[198],"capabilities":[199],"solver,":[202],"initial":[203],"measurements":[204],"indicate":[205],"convergence":[208],"largely":[212],"unaffected":[213]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}