{"id":"https://openalex.org/W3132763358","doi":"https://doi.org/10.1145/3437801.3441598","title":"Improving communication by optimizing on-node data movement with data layout","display_name":"Improving communication by optimizing on-node data movement with data layout","publication_year":2021,"publication_date":"2021-02-17","ids":{"openalex":"https://openalex.org/W3132763358","doi":"https://doi.org/10.1145/3437801.3441598","mag":"3132763358"},"language":"en","primary_location":{"id":"doi:10.1145/3437801.3441598","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3437801.3441598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://escholarship.org/uc/item/0qb7x6cq","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033875105","display_name":"Tuowen Zhao","orcid":"https://orcid.org/0000-0002-6347-7135"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tuowen Zhao","raw_affiliation_strings":["University of Utah"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030152493","display_name":"Mary Hall","orcid":"https://orcid.org/0000-0002-3058-7573"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mary Hall","raw_affiliation_strings":["University of Utah"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Utah","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082013692","display_name":"Hans Johansen","orcid":"https://orcid.org/0000-0002-9644-9982"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hans Johansen","raw_affiliation_strings":["Lawrence Berkeley National Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Lab","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102746800","display_name":"Samuel Williams","orcid":"https://orcid.org/0000-0002-8327-5717"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel Williams","raw_affiliation_strings":["Lawrence Berkeley National Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Lab","institution_ids":["https://openalex.org/I148283060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2337,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.88075881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"304","last_page":"317"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":1.0,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9987999796867371,"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/indirection","display_name":"Indirection","score":0.8450204133987427},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8146089315414429},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.7375893592834473},{"id":"https://openalex.org/keywords/unpacking","display_name":"Unpacking","score":0.6758235096931458},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.6389607191085815},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4421504735946655},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.42801228165626526},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.1248774528503418},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09960329532623291},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08920574188232422}],"concepts":[{"id":"https://openalex.org/C89377073","wikidata":"https://www.wikidata.org/wiki/Q1171224","display_name":"Indirection","level":2,"score":0.8450204133987427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8146089315414429},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.7375893592834473},{"id":"https://openalex.org/C2777256151","wikidata":"https://www.wikidata.org/wiki/Q7897273","display_name":"Unpacking","level":2,"score":0.6758235096931458},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.6389607191085815},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4421504735946655},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.42801228165626526},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.1248774528503418},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09960329532623291},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08920574188232422},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3437801.3441598","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3437801.3441598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},{"id":"pmh:ark:/13030/qt0qb7x6cq","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:escholarship.org:ark:/13030/qt0qb7x6cq","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/0qb7x6cq","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:escholarship.org:ark:/13030/qt0qb7x6cq","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/0qb7x6cq","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W47921549","https://openalex.org/W1493774699","https://openalex.org/W1553808293","https://openalex.org/W1921750833","https://openalex.org/W1955591353","https://openalex.org/W1965092590","https://openalex.org/W1973948156","https://openalex.org/W2002555321","https://openalex.org/W2026024102","https://openalex.org/W2048118924","https://openalex.org/W2108334595","https://openalex.org/W2145194992","https://openalex.org/W2160106616","https://openalex.org/W2165439482","https://openalex.org/W2167713801","https://openalex.org/W2340879669","https://openalex.org/W2561650451","https://openalex.org/W2750596392","https://openalex.org/W2903775786","https://openalex.org/W2913407901","https://openalex.org/W2944412207","https://openalex.org/W2971787243","https://openalex.org/W2984920043","https://openalex.org/W2985709405","https://openalex.org/W3033810518","https://openalex.org/W4232301837","https://openalex.org/W4376543064"],"related_works":["https://openalex.org/W2039378765","https://openalex.org/W2003798513","https://openalex.org/W2151764765","https://openalex.org/W2890431355","https://openalex.org/W4376875029","https://openalex.org/W2315600872","https://openalex.org/W2097757554","https://openalex.org/W3149084271","https://openalex.org/W4247008888","https://openalex.org/W2150319905"],"abstract_inverted_index":{"We":[0],"present":[1],"optimizations":[2,88,133],"to":[3,23,84,97,121,148],"improve":[4],"communication":[5,144],"performance":[6],"by":[7,146],"reducing":[8,47,143],"on-node":[9,52],"data":[10,26,36,49,53,66,93,123,127],"movement":[11,27,50,54,67,124],"for":[12,71],"a":[13,140],"class":[14],"of":[15,34,105,114,131],"distributed":[16],"memory":[17,106,108],"applications.":[18],"The":[19,87,129],"primary":[20],"concept":[21],"is":[22,68],"eliminate":[24],"the":[25,35,40,112],"associated":[28],"with":[29],"packing":[30],"and":[31,62,116],"unpacking":[32],"subsets":[33],"during":[37],"communication.":[38,64],"With":[39],"rapid":[41],"rise":[42],"in":[43,76,136],"network":[44,63],"injection":[45],"bandwidth":[46],"off-node":[48],"cost,":[51],"can":[55],"be":[56],"significantly":[57],"more":[58],"expensive":[59],"than":[60],"computation":[61],"This":[65],"especially":[69],"costly":[70],"small":[72],"domains":[73],"-":[74],"as":[75],"memory-intensive":[77],"multi-physics":[78],"codes":[79],"or":[80],"when":[81],"strong":[82],"scaling":[83],"reduce":[85],"time-to-solution.":[86],"presented":[89],"include":[90],"(1)":[91],"optimizing":[92],"layout":[94],"through":[95],"indirection":[96],"enable":[98],"pack-free":[99],"communication;":[100],"(2)":[101],"creating":[102],"contiguous":[103],"views":[104],"using":[107],"mapping":[109],"thus":[110],"minimizing":[111],"number":[113],"messages;":[115],"(3)":[117],"applying":[118],"these":[119,132],"techniques":[120],"intra-node":[122],"including":[125],"CPU-GPU":[126],"movement.":[128],"benefits":[130],"are":[134],"demonstrated":[135],"stencil":[137],"benchmarks":[138],"against":[139],"highly-optimized":[141],"baseline,":[142],"time":[145],"up":[147],"14.4\u00d7.":[149]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}
