{"id":"https://openalex.org/W2087124296","doi":"https://doi.org/10.1145/2488551.2488557","title":"Optimization of MPI_Allreduce on the blue Gene/Q supercomputer","display_name":"Optimization of MPI_Allreduce on the blue Gene/Q supercomputer","publication_year":2013,"publication_date":"2013-09-11","ids":{"openalex":"https://openalex.org/W2087124296","doi":"https://doi.org/10.1145/2488551.2488557","mag":"2087124296"},"language":"en","primary_location":{"id":"doi:10.1145/2488551.2488557","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2488551.2488557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th European MPI Users' Group Meeting","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/A5070117771","display_name":"Sameer Kumar","orcid":"https://orcid.org/0000-0001-8697-7370"},"institutions":[{"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"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sameer Kumar","raw_affiliation_strings":["IBM T.J. Watson Research Center, Yorktown Heights, NY and IBM Research India Lab, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Yorktown Heights, NY and IBM Research India Lab, Bangalore, India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062250655","display_name":"Daniel A. Faraj","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]},{"id":"https://openalex.org/I4210143979","display_name":"Systems Technology (United States)","ror":"https://ror.org/04cv8g472","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143979"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Faraj","raw_affiliation_strings":["IBM Systems Technology Group, Rochester, MN","IBM Systems Technology Group, Rochester, MN#TAB#"],"affiliations":[{"raw_affiliation_string":"IBM Systems Technology Group, Rochester, MN","institution_ids":["https://openalex.org/I4210143979"]},{"raw_affiliation_string":"IBM Systems Technology Group, Rochester, MN#TAB#","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5070117771"],"corresponding_institution_ids":["https://openalex.org/I4210103279"],"apc_list":null,"apc_paid":null,"fwci":1.96549609,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.88751691,"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":null,"last_page":null},"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9997000098228455,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9986000061035156,"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/supercomputer","display_name":"Supercomputer","score":0.8832975625991821},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7754732966423035},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7678744792938232},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.7446592450141907},{"id":"https://openalex.org/keywords/grid-network","display_name":"Grid network","score":0.6021273732185364},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5679284334182739},{"id":"https://openalex.org/keywords/network-packet","display_name":"Network packet","score":0.4857940673828125},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.45159316062927246},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.41952836513519287},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4181898236274719},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.41204512119293213},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4101622700691223},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.34065890312194824},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2275206446647644},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.19197821617126465},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11823326349258423},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.10332345962524414},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.09065374732017517},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07786807417869568}],"concepts":[{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.8832975625991821},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7754732966423035},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7678744792938232},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.7446592450141907},{"id":"https://openalex.org/C24337046","wikidata":"https://www.wikidata.org/wiki/Q4394138","display_name":"Grid network","level":3,"score":0.6021273732185364},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5679284334182739},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.4857940673828125},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.45159316062927246},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.41952836513519287},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4181898236274719},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.41204512119293213},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4101622700691223},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.34065890312194824},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2275206446647644},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.19197821617126465},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11823326349258423},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.10332345962524414},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.09065374732017517},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07786807417869568},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2488551.2488557","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2488551.2488557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th European MPI Users' Group Meeting","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2009852231","https://openalex.org/W2035079906","https://openalex.org/W2081612620","https://openalex.org/W2123859357","https://openalex.org/W2143425413","https://openalex.org/W4213379201"],"related_works":["https://openalex.org/W2124048060","https://openalex.org/W4386915331","https://openalex.org/W2378910916","https://openalex.org/W2116006827","https://openalex.org/W2361929291","https://openalex.org/W2086666199","https://openalex.org/W1997862718","https://openalex.org/W1511717675","https://openalex.org/W2185992486","https://openalex.org/W2146057962"],"abstract_inverted_index":{"The":[0,78],"IBM":[1],"Blue":[2],"Gene/Q":[3],"supercomputer":[4],"has":[5],"a":[6,84,99],"5D":[7],"torus":[8,42],"network":[9,48,106],"where":[10],"each":[11],"node":[12],"is":[13,83,98],"connected":[14],"to":[15,25],"ten":[16,33,41],"bi-directional":[17],"links.":[18,43],"In":[19],"this":[20],"paper":[21],"we":[22,81],"present":[23],"techniques":[24],"optimize":[26],"the":[27,40,54,62,67,75,104,110],"MPI_Allreduce":[28],"collective":[29,105],"operation":[30],"by":[31,53,74],"building":[32],"different":[34],"edge":[35],"disjoint":[36],"spanning":[37],"trees":[38],"on":[39,69,114],"We":[44],"accelerate":[45],"summing":[46],"of":[47,56,87,101],"packets":[49],"with":[50],"local":[51],"buffers":[52],"use":[55],"Quad":[57],"Processing":[58],"SIMD":[59],"unit":[60],"in":[61,109],"BG/Q":[63],"cores":[64],"and":[65],"executing":[66],"sums":[68],"multiple":[70],"communication":[71],"threads":[72],"created":[73],"PAMI":[76],"libraries.":[77],"net":[79],"gain":[80],"achieve":[82],"peak":[85],"throughput":[86],"6.3":[88],"GB/sec":[89],"for":[90],"double":[91],"precision":[92],"floating":[93],"point":[94],"sum":[95],"allreduce,":[96],"that":[97],"speedup":[100],"3.75x":[102],"over":[103],"based":[107],"algorithm":[108],"product":[111],"MPI":[112],"stack":[113],"BG/Q.":[115]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}