{"id":"https://openalex.org/W2131613942","doi":"https://doi.org/10.1177/1094342005051521","title":"Optimization of Collective Communication Operations in MPICH","display_name":"Optimization of Collective Communication Operations in MPICH","publication_year":2005,"publication_date":"2005-02-01","ids":{"openalex":"https://openalex.org/W2131613942","doi":"https://doi.org/10.1177/1094342005051521","mag":"2131613942"},"language":"en","primary_location":{"id":"doi:10.1177/1094342005051521","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342005051521","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-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/A5014920685","display_name":"Rajeev Thakur","orcid":"https://orcid.org/0000-0002-5532-3048"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rajeev Thakur","raw_affiliation_strings":["MATHEMATICS AND COMPUTER SCIENCE DIVISION ARGONNE NATIONAL LABORATORY\r                        ARGONNE, IL 60439, USA","Mathematics and Computer Science Division Argonne National Laboratory#R# Argonne, IL 60439, USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MATHEMATICS AND COMPUTER SCIENCE DIVISION ARGONNE NATIONAL LABORATORY\r                        ARGONNE, IL 60439, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"Mathematics and Computer Science Division Argonne National Laboratory#R# Argonne, IL 60439, USA,","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011618020","display_name":"Rolf Rabenseifner","orcid":null},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]},{"id":"https://openalex.org/I31582689","display_name":"Stuttgart Technical University of Applied Sciences","ror":"https://ror.org/039gdg280","country_code":"DE","type":"education","lineage":["https://openalex.org/I31582689"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rolf Rabenseifner","raw_affiliation_strings":["RECHENZENTRUM UNIVERSITAT STUTTGART (RUS) HIGH PERFORMANCE COMPUTING\r                        CENTER (HLRS) UNIVERSITY OF STUTTGART D-70550 STUTTGART, GERMANY","RECHENZENTRUM UNIVERSITAT STUTTGART (RUS) HIGH PERFORMANCE COMPUTING#R# CENTER (HLRS) UNIVERSITY OF STUTTGART D-70550 STUTTGART, GERMANY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RECHENZENTRUM UNIVERSITAT STUTTGART (RUS) HIGH PERFORMANCE COMPUTING\r                        CENTER (HLRS) UNIVERSITY OF STUTTGART D-70550 STUTTGART, GERMANY","institution_ids":["https://openalex.org/I100066346","https://openalex.org/I31582689"]},{"raw_affiliation_string":"RECHENZENTRUM UNIVERSITAT STUTTGART (RUS) HIGH PERFORMANCE COMPUTING#R# CENTER (HLRS) UNIVERSITY OF STUTTGART D-70550 STUTTGART, GERMANY","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017241944","display_name":"William Gropp","orcid":"https://orcid.org/0000-0003-2905-3029"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"William Gropp","raw_affiliation_strings":["MATHEMATICS AND COMPUTER SCIENCE DIVISION ARGONNE NATIONAL LABORATORY\r                        ARGONNE, IL 60439, USA","Mathematics and Computer Science Division Argonne National Laboratory#R# Argonne, IL 60439, USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MATHEMATICS AND COMPUTER SCIENCE DIVISION ARGONNE NATIONAL LABORATORY\r                        ARGONNE, IL 60439, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"Mathematics and Computer Science Division Argonne National Laboratory#R# Argonne, IL 60439, USA,","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014920685","https://openalex.org/A5017241944"],"corresponding_institution_ids":["https://openalex.org/I1282105669"],"apc_list":null,"apc_paid":null,"fwci":27.2422,"has_fulltext":false,"cited_by_count":917,"citation_normalized_percentile":{"value":0.99757976,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"19","issue":"1","first_page":"49","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9995999932289124,"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":0.9991999864578247,"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/myrinet","display_name":"Myrinet","score":0.9937722682952881},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.878389835357666},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.7562404870986938},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.6525394320487976},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6154862642288208},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.599327802658081},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.570170521736145},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.5066469311714172},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.4905926287174225},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.47485044598579407},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4133950471878052},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3876674771308899}],"concepts":[{"id":"https://openalex.org/C2780601250","wikidata":"https://www.wikidata.org/wiki/Q1863181","display_name":"Myrinet","level":3,"score":0.9937722682952881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.878389835357666},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.7562404870986938},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.6525394320487976},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6154862642288208},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.599327802658081},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.570170521736145},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.5066469311714172},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.4905926287174225},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.47485044598579407},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4133950471878052},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3876674771308899},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1177/1094342005051521","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342005051521","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.121.1852","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.121.1852","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hpc.sagepub.com/cgi/reprint/19/1/49.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.129.647","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.129.647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mcs.anl.gov/~thakur/papers/ijhpca-coll.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.157.494","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hpc.sagepub.com/cgi/reprint/19/1/49.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.71.4548","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.71.4548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.hlrs.de/people/rabenseifner/publ/HPCA_collectives.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.72.4368","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.72.4368","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.hlrs.de/people/rabenseifner/publ/HPCA_collectives.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W112345847","https://openalex.org/W246536198","https://openalex.org/W1497413785","https://openalex.org/W1524594851","https://openalex.org/W1578322035","https://openalex.org/W1584094055","https://openalex.org/W1591532709","https://openalex.org/W1598227005","https://openalex.org/W1654174318","https://openalex.org/W1814428676","https://openalex.org/W1858204095","https://openalex.org/W1860827079","https://openalex.org/W1937799376","https://openalex.org/W2037604385","https://openalex.org/W2041351581","https://openalex.org/W2049585661","https://openalex.org/W2059300917","https://openalex.org/W2078443819","https://openalex.org/W2084557272","https://openalex.org/W2102061396","https://openalex.org/W2105549957","https://openalex.org/W2105908643","https://openalex.org/W2117163917","https://openalex.org/W2128543830","https://openalex.org/W2133557963","https://openalex.org/W2133994512","https://openalex.org/W2142763683","https://openalex.org/W2149658259","https://openalex.org/W2168281730","https://openalex.org/W2914788591","https://openalex.org/W2988891856","https://openalex.org/W4230426658","https://openalex.org/W4237651079","https://openalex.org/W4241904697","https://openalex.org/W4245503759","https://openalex.org/W4250518453","https://openalex.org/W4285719527","https://openalex.org/W4301447929"],"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/W2099337421","https://openalex.org/W2161210471","https://openalex.org/W2131613942","https://openalex.org/W2411226825"],"abstract_inverted_index":{"We":[0,126],"describe":[1,68],"our":[2],"work":[3],"on":[4,29,82,107,123,169],"improving":[5],"the":[6,30,34,70,96,101,108,117,124,132,137,166,184,203],"performance":[7,186],"of":[8,36,64,134,136,153,198,213],"collective":[9,22,61,141,189],"communication":[10,190],"operations":[11,160],"in":[12,93,105,112,120,129],"MPICH":[13,106],"for":[14,39,46,55,72,147,158,187,206],"clusters":[15],"connected":[16],"by":[17],"switched":[18],"networks.":[19],"For":[20],"each":[21],"operation,":[23,191],"we":[24,50,67],"use":[25,45,195],"multiple":[26],"algorithms":[27,54,71,98,103,118,157,168,200],"depending":[28],"message":[31,209],"size,":[32],"with":[33],"goal":[35],"minimizing":[37,43],"latency":[38],"short":[40],"messages":[41,149],"and":[42,78,87,144,150,175,201,211],"bandwidth":[44],"long":[47,148],"messages.":[48],"Although":[49],"have":[51],"implemented":[52],"new":[53,97],"all":[56,94],"MPI":[57,122],"(Message":[58],"Passing":[59],"Interface)":[60],"operations,":[62,142],"because":[63],"limited":[65],"space":[66],"only":[69],"allgather,":[73],"broadcast,":[74],"all-to-all,":[75],"reduce-scatter,":[76],"reduce,":[77,145],"allreduce.":[79],"Performance":[80],"results":[81,179],"a":[83,170,188,196,207],"Myrinet-connected":[84],"Linux":[85],"cluster":[86],"an":[88],"IBM":[89,173],"SP":[90],"indicate":[91,180],"that,":[92],"cases,":[95,114],"significantly":[99],"outperform":[100,116],"old":[102],"used":[104,119,140],"Myrinet":[109,171],"cluster,":[110,172],"and,":[111],"many":[113],"they":[115],"IBM's":[121],"SP.":[125],"also":[127],"explore":[128],"further":[130],"detail":[131],"optimization":[133],"two":[135],"most":[138],"commonly":[139],"allreduce":[143],"particularly":[146],"nonpower-of-two":[151],"numbers":[152],"processes.":[154,214],"The":[155],"optimized":[156],"these":[159],"perform":[161],"several":[162],"times":[163],"better":[164],"than":[165],"native":[167],"SP,":[174],"Cray":[176],"T3E.":[177],"Our":[178],"that":[181],"to":[182,194],"achieve":[183],"best":[185],"one":[192],"needs":[193],"number":[197,212],"different":[199],"select":[202],"right":[204],"algorithm":[205],"particular":[208],"size":[210]},"counts_by_year":[{"year":2026,"cited_by_count":15},{"year":2025,"cited_by_count":76},{"year":2024,"cited_by_count":50},{"year":2023,"cited_by_count":59},{"year":2022,"cited_by_count":45},{"year":2021,"cited_by_count":71},{"year":2020,"cited_by_count":90},{"year":2019,"cited_by_count":68},{"year":2018,"cited_by_count":67},{"year":2017,"cited_by_count":39},{"year":2016,"cited_by_count":42},{"year":2015,"cited_by_count":29},{"year":2014,"cited_by_count":43},{"year":2013,"cited_by_count":36},{"year":2012,"cited_by_count":34}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}