{"id":"https://openalex.org/W2138690674","doi":"https://doi.org/10.1109/icpp.2008.83","title":"Optimization of All-to-All Communication on the Blue Gene/L Supercomputer","display_name":"Optimization of All-to-All Communication on the Blue Gene/L Supercomputer","publication_year":2008,"publication_date":"2008-09-01","ids":{"openalex":"https://openalex.org/W2138690674","doi":"https://doi.org/10.1109/icpp.2008.83","mag":"2138690674"},"language":"en","primary_location":{"id":"doi:10.1109/icpp.2008.83","doi":"https://doi.org/10.1109/icpp.2008.83","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpp.2008.83","pdf_url":null,"source":{"id":"https://openalex.org/S4210174133","display_name":"Proceedings of the International Conference on Parallel Processing","issn_l":"0190-3918","issn":["0190-3918","2332-5690"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 37th International Conference on Parallel Processing","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W2138690674"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"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/A5070117771","display_name":"Sameer Kumar","orcid":"https://orcid.org/0000-0001-8697-7370","observed_orcids":["https://orcid.org/0000-0001-8697-7370"]},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sameer Kumar","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","lBM T.J. Watson Res. Center, Yorktown Heights, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"lBM T.J. Watson Res. Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033885850","display_name":"Yogish Sabharwal","orcid":"https://orcid.org/0009-0002-5053-2059","observed_orcids":["https://orcid.org/0009-0002-5053-2059"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yogish Sabharwal","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","IBM (United States), Armonk, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024268264","display_name":"Rahul Dev Garg","orcid":"https://orcid.org/0000-0003-3684-8962","observed_orcids":["https://orcid.org/0000-0003-3684-8962"]},"institutions":[{"id":"https://openalex.org/I1321826891","display_name":"eBay (Ireland)","ror":"https://ror.org/02b00s810","country_code":"IE","type":"company","lineage":["https://openalex.org/I1321826891","https://openalex.org/I4210150719"]},{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]},{"id":"https://openalex.org/I4210129961","display_name":"IBM (India)","ror":"https://ror.org/034ahpr11","country_code":"IN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210129961"]}],"countries":["IE","IN"],"is_corresponding":false,"raw_author_name":"Rahul Garg","raw_affiliation_strings":["IBM India Research Laboratory, New Delhi, India","eBay (Ireland), Dublin, Ireland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM India Research Laboratory, New Delhi, India","institution_ids":["https://openalex.org/I4210103279","https://openalex.org/I4210129961"]},{"raw_affiliation_string":"eBay (Ireland), Dublin, Ireland","institution_ids":["https://openalex.org/I1321826891"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062754428","display_name":"Philip Heidelberger","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]},{"id":"https://openalex.org/I4210129961","display_name":"IBM (India)","ror":"https://ror.org/034ahpr11","country_code":"IN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210129961"]}],"countries":["IN","US"],"is_corresponding":false,"raw_author_name":"Philip Heidelberger","raw_affiliation_strings":["IBM India Research Laboratory, New Delhi, India","IBM (United States), Armonk, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM India Research Laboratory, New Delhi, India","institution_ids":["https://openalex.org/I4210103279","https://openalex.org/I4210129961"]},{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8464,"has_fulltext":false,"cited_by_count":67,"citation_normalized_percentile":{"value":0.91541079,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":87,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"320","last_page":"329"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9657999873161316,"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":0.9657999873161316,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.027799999341368675,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.004699999932199717,"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/all-to-all-communication","display_name":"all-to-all communication","score":0.9990000128746033},{"id":"https://openalex.org/keywords/blue-gene-l","display_name":"Blue Gene/L","score":0.9819999933242798},{"id":"https://openalex.org/keywords/link-contention","display_name":"link contention","score":0.9670000076293945},{"id":"https://openalex.org/keywords/processor-partitioning","display_name":"processor partitioning","score":0.828000009059906},{"id":"https://openalex.org/keywords/communication-optimization","display_name":"communication optimization","score":0.5249999761581421},{"id":"https://openalex.org/keywords/short-messages","display_name":"short messages","score":0.4429999887943268},{"id":"https://openalex.org/keywords/supercomputing-performance","display_name":"supercomputer performance","score":0.5659999847412109}],"concepts":[{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.8954118490219116},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.809171736240387},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.8074941635131836},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7718265056610107},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7384453415870667},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6534647345542908},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.53049635887146},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.46678221225738525},{"id":"https://openalex.org/C123745756","wikidata":"https://www.wikidata.org/wiki/Q1665949","display_name":"Interconnection","level":2,"score":0.4461110532283783},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.43496304750442505},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.41648373007774353},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.4148171544075012},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23629158735275269},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.1379890739917755},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12954258918762207},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12879231572151184},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08668601512908936},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08505189418792725},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpp.2008.83","doi":"https://doi.org/10.1109/icpp.2008.83","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpp.2008.83","pdf_url":null,"source":{"id":"https://openalex.org/S4210174133","display_name":"Proceedings of the International Conference on Parallel Processing","issn_l":"0190-3918","issn":["0190-3918","2332-5690"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 37th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338286","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1497413785","https://openalex.org/W1591532709","https://openalex.org/W1813030236","https://openalex.org/W1831614234","https://openalex.org/W1967295467","https://openalex.org/W1981763187","https://openalex.org/W1985832618","https://openalex.org/W2056879607","https://openalex.org/W2061388644","https://openalex.org/W2099952176","https://openalex.org/W2108244650","https://openalex.org/W2110338379","https://openalex.org/W2123287621","https://openalex.org/W2150606521","https://openalex.org/W2157664430","https://openalex.org/W2164945803","https://openalex.org/W2169135424"],"related_works":["https://openalex.org/W4239145072","https://openalex.org/W7098166179","https://openalex.org/W2357655446","https://openalex.org/W2032484463","https://openalex.org/W7098029929","https://openalex.org/W4416004143","https://openalex.org/W4402044182","https://openalex.org/W4396790354","https://openalex.org/W7097795214","https://openalex.org/W2893158683"],"abstract_inverted_index":{"All-to-all":[0],"communication":[1,27],"is":[2],"a":[3,61,133],"well":[4],"known":[5],"performance":[6,24,48,62,80,123,134],"bottleneck":[7],"for":[8,38,139],"many":[9],"applications,":[10],"such":[11],"as":[12],"the":[13,17,23,29,47,53,56,79,99,111,118,121,140],"ones":[14],"that":[15,33,46,76],"use":[16],"Fast-Fourier-transform":[18],"(FFT)":[19],"algorithm.":[20],"We":[21,44,59,71,116,131],"analyze":[22],"of":[25,49,55,64,68,81,96,120,135],"all-to-all":[26,39,50,65,82,122],"on":[28,52,66,98],"BlueGene/L":[30],"torus":[31],"interconnect":[32],"has":[34],"link":[35],"contention":[36],"even":[37],"operations":[40],"with":[41,83,146],"short":[42,84],"messages.":[43],"observed":[45],"depends":[51],"shape":[54],"processor":[57],"partition.":[58],"present":[60,73],"analysis":[63],"partitions":[67],"various":[69],"shapes.":[70],"then":[72],"optimization":[74],"schemes":[75],"substantially":[77],"improve":[78],"and":[85,127],"large":[86],"messages.In":[87],"particular,":[88],"throughput":[89],"improved":[90],"from":[91],"64%":[92],"to":[93],"over":[94,136],"99%":[95],"peak":[97],"65,536":[100],"(64":[101],"times":[102,104],"32":[103],"32)":[105],"node":[106],"Blue":[107],"Gene/L":[108],"machine":[109],"at":[110],"Lawrence":[112],"Livermore":[113],"National":[114],"Lab.":[115],"show":[117],"impact":[119],"optimizations":[124],"in":[125],"1-D":[126],"3-D":[128],"FFT":[129,144],"benchmarks.":[130],"achieved":[132],"2.8":[137],"TF":[138],"HPC":[141],"Challenge":[142],"1D":[143],"benchmark":[145],"our":[147],"optimized":[148],"all-to-all.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":11}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2016-06-24T00:00:00"}
