{"id":"https://openalex.org/W2122395763","doi":"https://doi.org/10.1109/clustr.2003.1253341","title":"Improving the performance of MPI derived datatypes by optimizing memory-access cost","display_name":"Improving the performance of MPI derived datatypes by optimizing memory-access cost","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2122395763","doi":"https://doi.org/10.1109/clustr.2003.1253341","mag":"2122395763"},"language":"en","primary_location":{"id":"doi:10.1109/clustr.2003.1253341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/clustr.2003.1253341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings IEEE International Conference on Cluster Computing CLUSTR-03","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/A5062233562","display_name":"Suren Byna","orcid":"https://orcid.org/0000-0003-3048-3448"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Byna","raw_affiliation_strings":["Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA","Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA","institution_ids":["https://openalex.org/I180949307"]},{"raw_affiliation_string":"Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA#TAB#","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"middle","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":false,"raw_author_name":"Gropp","raw_affiliation_strings":["Math. and Computer Science Division, Argonne National Laboratory, Argonne, IL, USA","argonne national laboratory"],"affiliations":[{"raw_affiliation_string":"Math. and Computer Science Division, Argonne National Laboratory, Argonne, IL, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"argonne national laboratory","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057665558","display_name":"Xian\u2010He Sun","orcid":"https://orcid.org/0000-0002-1093-0792"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xian-He Sun","raw_affiliation_strings":["Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA","Illinois Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA","institution_ids":["https://openalex.org/I180949307"]},{"raw_affiliation_string":"Illinois Institute of Technology","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"last","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":false,"raw_author_name":"Thakur","raw_affiliation_strings":["Math. and Computer Science Division, Argonne National Laboratory, Argonne, IL, USA","argonne national laboratory"],"affiliations":[{"raw_affiliation_string":"Math. and Computer Science Division, Argonne National Laboratory, Argonne, IL, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"argonne national laboratory","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5062233562"],"corresponding_institution_ids":["https://openalex.org/I180949307"],"apc_list":null,"apc_paid":null,"fwci":2.767,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.90618607,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"1697","issue":null,"first_page":"412","last_page":"419"},"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":0.9998999834060669,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9997000098228455,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9250618815422058},{"id":"https://openalex.org/keywords/transpose","display_name":"Transpose","score":0.6068561673164368},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5955398678779602},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5343574285507202},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4992992877960205},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4778137505054474},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4287464916706085}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9250618815422058},{"id":"https://openalex.org/C200106649","wikidata":"https://www.wikidata.org/wiki/Q223683","display_name":"Transpose","level":3,"score":0.6068561673164368},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5955398678779602},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5343574285507202},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4992992877960205},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4778137505054474},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4287464916706085},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/clustr.2003.1253341","is_oa":false,"landing_page_url":"https://doi.org/10.1109/clustr.2003.1253341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings IEEE International Conference on Cluster Computing CLUSTR-03","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.104.3971","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.104.3971","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-unix.mcs.anl.gov/~thakur/papers/mpi-datatype.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.129.6547","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.129.6547","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.iit.edu/~scs/psfiles/135_byna_s.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.13.9267","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.13.9267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-unix.mcs.anl.gov/~gropp/bib/papers/2003/memcon-final.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.576.6090","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.576.6090","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/uploads/cels/papers/P1045.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W77050994","https://openalex.org/W1510543252","https://openalex.org/W1555194772","https://openalex.org/W1964031104","https://openalex.org/W1975053024","https://openalex.org/W2098220211","https://openalex.org/W2102061396","https://openalex.org/W2128145051","https://openalex.org/W2132548611","https://openalex.org/W2153806645","https://openalex.org/W2166346826","https://openalex.org/W2728600909","https://openalex.org/W4246367117","https://openalex.org/W6603165862","https://openalex.org/W6684519919"],"related_works":["https://openalex.org/W2003786218","https://openalex.org/W4313549635","https://openalex.org/W2376104713","https://openalex.org/W2356636683","https://openalex.org/W4205331489","https://openalex.org/W4385493077","https://openalex.org/W2009510026","https://openalex.org/W2176391467","https://openalex.org/W2311164424","https://openalex.org/W2056396287"],"abstract_inverted_index":{"The":[0,96],"MPI":[1,27,40,69,146],"Standard":[2],"supports":[3],"derived":[4,43,83,129],"datatypes,":[5],"which":[6],"allow":[7],"users":[8],"to":[9,29],"describe":[10],"noncontiguous":[11,16,34],"memory":[12,113],"layout":[13],"and":[14,65,139],"communicate":[15],"data":[17,60],"with":[18],"a":[19,46,62,76,120],"single":[20],"communication":[21],"function.":[22,70],"This":[23],"feature":[24],"enables":[25],"an":[26,68],"implementation":[28,127,147],"optimize":[30],"the":[31,53,80,103,112,137,140,145],"transfer":[32],"of":[33,82,111,128],"data.":[35],"In":[36,71],"practice,":[37],"however,":[38],"few":[39],"implementations":[41],"implement":[42],"datatypes":[44,84,130],"in":[45,144],"way":[47],"that":[48,90,102,123,125],"performs":[49],"better":[50],"than":[51],"what":[52],"user":[54,104,138],"can":[55],"achieve":[56],"by":[57,85,136],"manually":[58],"packing":[59,88,97,135],"into":[61],"contiguous":[63],"buffer":[64],"then":[66],"calling":[67],"this":[72],"paper,":[73],"we":[74],"present":[75,116],"technique":[77],"for":[78,93,119],"improving":[79],"performance":[81,117],"automatically":[86],"using":[87],"algorithms":[89,98],"are":[91],"optimized":[92],"memory-access":[94],"cost.":[95],"use":[99],"memory-optimization":[100],"techniques":[101],"cannot":[105],"apply":[106],"easily":[107],"without":[108],"advanced":[109],"knowledge":[110],"architecture.":[114],"We":[115],"results":[118],"matrix-transpose":[121],"example":[122],"demonstrate":[124],"our":[126],"significantly":[131],"outperforms":[132],"both":[133],"manual":[134],"existing":[141],"derived-datatype":[142],"code":[143],"(MPICH).":[148]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
