{"id":"https://openalex.org/W2766672944","doi":"https://doi.org/10.1109/tpds.2017.2768413","title":"Cache-Oblivious MPI All-to-All Communications Based on Morton Order","display_name":"Cache-Oblivious MPI All-to-All Communications Based on Morton Order","publication_year":2017,"publication_date":"2017-10-31","ids":{"openalex":"https://openalex.org/W2766672944","doi":"https://doi.org/10.1109/tpds.2017.2768413","mag":"2766672944"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2017.2768413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2017.2768413","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","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/A5088172355","display_name":"Shigang Li","orcid":"https://orcid.org/0000-0003-0022-7865"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shigang Li","raw_affiliation_strings":["State Key Laboratory of Computer Architecture, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Architecture, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001666028","display_name":"Yunquan Zhang","orcid":"https://orcid.org/0000-0002-2618-5088"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunquan Zhang","raw_affiliation_strings":["State Key Laboratory of Computer Architecture, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Architecture, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026990786","display_name":"Torsten Hoefler","orcid":"https://orcid.org/0000-0002-1333-9797"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Torsten Hoefler","raw_affiliation_strings":["Department of Computer Science, ETH Zurich, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088172355"],"corresponding_institution_ids":["https://openalex.org/I19820366"],"apc_list":null,"apc_paid":null,"fwci":2.9291,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.92903917,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"29","issue":"3","first_page":"542","last_page":"555"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization 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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9965000152587891,"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/computer-science","display_name":"Computer science","score":0.9011073112487793},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8355478048324585},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8316960334777832},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.6983215808868408},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.6880244016647339},{"id":"https://openalex.org/keywords/heap","display_name":"Heap (data structure)","score":0.6189563274383545},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5715099573135376},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.496102899312973},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.456174373626709},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4330081343650818},{"id":"https://openalex.org/keywords/locality-of-reference","display_name":"Locality of reference","score":0.42556142807006836},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4180441200733185},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25677138566970825},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.08735805749893188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9011073112487793},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8355478048324585},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8316960334777832},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.6983215808868408},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.6880244016647339},{"id":"https://openalex.org/C134757568","wikidata":"https://www.wikidata.org/wiki/Q274089","display_name":"Heap (data structure)","level":2,"score":0.6189563274383545},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5715099573135376},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.496102899312973},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.456174373626709},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4330081343650818},{"id":"https://openalex.org/C27602214","wikidata":"https://www.wikidata.org/wiki/Q1868547","display_name":"Locality of reference","level":3,"score":0.42556142807006836},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4180441200733185},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25677138566970825},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.08735805749893188},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2017.2768413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2017.2768413","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2849673663","display_name":null,"funder_award_id":"61432018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6244656024","display_name":null,"funder_award_id":"61502450","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8380396287","display_name":null,"funder_award_id":"61521092","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W7811966","https://openalex.org/W1498011047","https://openalex.org/W1498436796","https://openalex.org/W1551516195","https://openalex.org/W1552509329","https://openalex.org/W1581507139","https://openalex.org/W1912350778","https://openalex.org/W1965081941","https://openalex.org/W1968020161","https://openalex.org/W1986445598","https://openalex.org/W2016559894","https://openalex.org/W2017915001","https://openalex.org/W2023973086","https://openalex.org/W2029674034","https://openalex.org/W2038785086","https://openalex.org/W2042455990","https://openalex.org/W2043143850","https://openalex.org/W2052196304","https://openalex.org/W2053663473","https://openalex.org/W2056476515","https://openalex.org/W2059124748","https://openalex.org/W2089064856","https://openalex.org/W2106103789","https://openalex.org/W2112121929","https://openalex.org/W2117134475","https://openalex.org/W2127533540","https://openalex.org/W2131613942","https://openalex.org/W2133557963","https://openalex.org/W2136222095","https://openalex.org/W2149658259","https://openalex.org/W2161973644","https://openalex.org/W2469287745","https://openalex.org/W2988891856","https://openalex.org/W4229786028","https://openalex.org/W4229975587","https://openalex.org/W4242286475","https://openalex.org/W6633152989","https://openalex.org/W6640125768"],"related_works":["https://openalex.org/W1555349535","https://openalex.org/W2583128298","https://openalex.org/W2053359564","https://openalex.org/W2739740241","https://openalex.org/W1974923383","https://openalex.org/W2161159383","https://openalex.org/W1495260638","https://openalex.org/W2085105049","https://openalex.org/W2475524688","https://openalex.org/W1511204342"],"abstract_inverted_index":{"Many-core":[0],"systems":[1,113],"with":[2],"a":[3,10,35,76,168,180,192],"rapidly":[4],"increasing":[5],"number":[6],"of":[7],"cores":[8],"pose":[9],"significant":[11],"challenge":[12],"to":[13,16,58,83,103,106,130],"parallel":[14],"applications":[15,25],"use":[17,80],"their":[18],"complex":[19],"memory":[20,86],"hierarchies":[21],"efficiently.":[22],"Many":[23],"such":[24],"rely":[26],"on":[27,75,111,136,145,154,167,173,179,185,191],"collective":[28],"communications":[29],"in":[30],"performance-critical":[31],"phases,":[32],"which":[33],"become":[34],"bottleneck":[36],"if":[37],"they":[38],"are":[39,134],"not":[40],"optimized.":[41],"We":[42,99,120],"address":[43],"this":[44],"issue":[45],"by":[46],"proposing":[47],"cache-oblivious":[48,66,125],"algorithms":[49,105,126],"for":[50,94,157,197],"MPI_Alltoall,":[51,141],"MPI_Allgather,":[52],"and":[53,72,79,159,183],"the":[54,60,65,70,85,108,124,150],"MPI":[55],"neighborhood":[56],"collectives":[57],"exploit":[59],"data":[61],"locality.":[62],"To":[63],"implement":[64],"algorithms,":[67],"we":[68],"allocate":[69],"send":[71],"receive":[73],"buffers":[74],"shared":[77,155],"heap":[78,156],"Morton":[81],"order":[82],"guide":[84],"copies.":[87],"Our":[88],"analysis":[89],"shows":[90],"that":[91],"our":[92,104,142],"algorithm":[93],"MPI_Alltoall":[95],"is":[96],"asymptotically":[97],"optimal.":[98],"show":[100],"an":[101],"extension":[102],"minimize":[107],"communication":[109],"distance":[110],"NUMA":[112],"while":[114],"maintaining":[115],"optimality":[116],"within":[117],"each":[118],"socket.":[119],"further":[121],"demonstrate":[122],"how":[123],"can":[127],"be":[128],"applied":[129],"multi-node":[131],"machines.":[132],"Experiments":[133],"conducted":[135],"different":[137],"many-core":[138],"architectures.":[139],"For":[140],"implementation":[143,152],"achieves":[144,172,184],"average":[146,174,186],"1.40X":[147],"speedup":[148,176,188],"over":[149,177,189],"naive":[151],"based":[153],"small":[158],"medium":[160],"block":[161,198],"sizes":[162,199],"(less":[163],"than":[164,201],"16":[165],"KB)":[166],"Xeon":[169,181,194],"Phi":[170],"KNC,":[171],"3.03X":[175],"MVAPICH2":[178,190],"E7-8890,":[182],"2.23X":[187],"256-node":[193],"E5-2680":[195],"cluster":[196],"less":[200],"1":[202],"KB.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":2}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}