{"id":"https://openalex.org/W4319866449","doi":"https://doi.org/10.1109/mm.2023.3241133","title":"Network-Assisted Noncontiguous Transfers for GPU-Aware MPI Libraries","display_name":"Network-Assisted Noncontiguous Transfers for GPU-Aware MPI Libraries","publication_year":2023,"publication_date":"2023-01-31","ids":{"openalex":"https://openalex.org/W4319866449","doi":"https://doi.org/10.1109/mm.2023.3241133"},"language":"en","primary_location":{"id":"doi:10.1109/mm.2023.3241133","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mm.2023.3241133","pdf_url":null,"source":{"id":"https://openalex.org/S59697426","display_name":"IEEE Micro","issn_l":"0272-1732","issn":["0272-1732","1937-4143"],"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 Micro","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/A5055205226","display_name":"Kaushik Kandadi Suresh","orcid":"https://orcid.org/0000-0002-3705-2387"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaushik Kandadi Suresh","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0002-3705-2387","affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017245523","display_name":"Kawthar Shafie Khorassani","orcid":"https://orcid.org/0000-0001-5856-5483"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kawthar Shafie Khorassani","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112844643","display_name":"Chen Chun Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Chun Chen","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103171233","display_name":"Bharath Ramesh","orcid":"https://orcid.org/0000-0002-6430-8587"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bharath Ramesh","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032141491","display_name":"Mustafa Abduljabbar","orcid":"https://orcid.org/0000-0003-1280-130X"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mustafa Abduljabbar","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078128277","display_name":"Aamir Shafi","orcid":"https://orcid.org/0000-0002-1924-2769"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aamir Shafi","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034293705","display_name":"Hari Subramoni","orcid":"https://orcid.org/0000-0002-1200-2754"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hari Subramoni","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024879682","display_name":"Dhabaleswar K. Panda","orcid":"https://orcid.org/0000-0002-0356-1781"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhabaleswar K. Panda","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01002587,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"43","issue":"2","first_page":"131","last_page":"139"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9988999962806702,"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":0.9161898493766785},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.7598526477813721},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7325477600097656},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7229512929916382},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.6515293717384338},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.6341084241867065},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5912819504737854},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.5664528012275696},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5141015648841858},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5003523826599121},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.4932820200920105},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.4892880618572235},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4426463842391968},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4129224419593811},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.29298630356788635}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9161898493766785},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.7598526477813721},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7325477600097656},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7229512929916382},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.6515293717384338},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.6341084241867065},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5912819504737854},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.5664528012275696},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5141015648841858},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5003523826599121},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.4932820200920105},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.4892880618572235},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4426463842391968},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4129224419593811},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.29298630356788635},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mm.2023.3241133","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mm.2023.3241133","pdf_url":null,"source":{"id":"https://openalex.org/S59697426","display_name":"IEEE Micro","issn_l":"0272-1732","issn":["0272-1732","1937-4143"],"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 Micro","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1183959340","display_name":null,"funder_award_id":"1818253","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G1402606311","display_name":null,"funder_award_id":"2007991","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G225171624","display_name":null,"funder_award_id":"2018627","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G7300486580","display_name":null,"funder_award_id":"1854828","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G8279241996","display_name":null,"funder_award_id":"1931537","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"}],"funders":[{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1555194772","https://openalex.org/W2056687467","https://openalex.org/W2109977639","https://openalex.org/W2344706860","https://openalex.org/W2494507800","https://openalex.org/W2963955661","https://openalex.org/W3005695646","https://openalex.org/W3096835151","https://openalex.org/W4312647711","https://openalex.org/W6863920777"],"related_works":["https://openalex.org/W2124048060","https://openalex.org/W1902983110","https://openalex.org/W4386915331","https://openalex.org/W2378910916","https://openalex.org/W2086666199","https://openalex.org/W1511717675","https://openalex.org/W2116006827","https://openalex.org/W2062632752","https://openalex.org/W2375309128","https://openalex.org/W2030707850"],"abstract_inverted_index":{"The":[0],"importance":[1],"of":[2,20,27,76,94],"graphics":[3],"processing":[4],"units":[5],"(GPUs)":[6],"in":[7,49],"accelerating":[8],"HPC":[9,29],"applications":[10,30,42],"is":[11,47],"evident":[12],"by":[13],"the":[14,69,92,99,106,116,121,132],"fact":[15],"that":[16,46,105],"a":[17,86],"large":[18],"number":[19],"supercomputing":[21],"clusters":[22],"are":[23,74],"GPU":[24,50,81],"enabled.":[25],"Many":[26],"these":[28],"use":[31],"message":[32],"passing":[33],"interface":[34],"(MPI)":[35],"as":[36,141],"their":[37],"programming":[38],"model.":[39],"These":[40],"MPI":[41,52,138],"frequently":[43],"exchange":[44],"data":[45,78],"noncontiguous":[48,80,96],"memory.":[51],"provides":[53,109],"derived":[54],"datatypes":[55],"(DDTs)":[56],"to":[57,90,111,115,128,136],"represent":[58],"such":[59,140],"data.":[60],"Past":[61],"research":[62],"on":[63,67],"DDTs":[64],"mainly":[65],"focused":[66],"optimizing":[68],"pack\u2013unpack":[70,101],"kernels.":[71,102],"Modern":[72],"HCAs":[73],"capable":[75],"gathering/scattering":[77],"from/to":[79],"memory":[82],"regions.":[83],"We":[84,103],"propose":[85],"low-overhead":[87],"HCA-assisted":[88],"scheme":[89,108,119],"improve":[91],"performance":[93],"GPU-based":[95,100],"exchanges":[97],"without":[98],"show":[104,126],"proposed":[107],"up":[110,127],"2\u00d7":[112],"benefits":[113],"compared":[114,135],"existing":[117],"pack-based":[118],"at":[120],"benchmark":[122],"level.":[123],"Furthermore,":[124],"we":[125],"17%":[129],"improvement":[130],"with":[131],"SW4Lite":[133],"application":[134],"other":[137],"libraries,":[139],"MVAPICH2-GDR":[142],"and":[143],"OpenMPI+UCX.":[144]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}
