{"id":"https://openalex.org/W3124796511","doi":"https://doi.org/10.1109/ccgrid51090.2021.00037","title":"Efficient MPI-based Communication for GPU-Accelerated Dask Applications","display_name":"Efficient MPI-based Communication for GPU-Accelerated Dask Applications","publication_year":2021,"publication_date":"2021-05-01","ids":{"openalex":"https://openalex.org/W3124796511","doi":"https://doi.org/10.1109/ccgrid51090.2021.00037","mag":"3124796511"},"language":"en","primary_location":{"id":"doi:10.1109/ccgrid51090.2021.00037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccgrid51090.2021.00037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/ACM 21st International Symposium on Cluster, Cloud and Internet Computing (CCGrid)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2101.08878","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Aamir Shafi","raw_affiliation_strings":["The Ohio State University","the Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"the Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008298485","display_name":"Jahanzeb Maqbool Hashmi","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":"Jahanzeb Maqbool Hashmi","raw_affiliation_strings":["The Ohio State University","the Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"the Ohio State University","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","the Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"the Ohio State University","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. DK Panda","raw_affiliation_strings":["The Ohio State University","Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078128277"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01527071,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"277","last_page":"286"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9990000128746033,"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":0.9986000061035156,"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":0.880588173866272},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6573910713195801},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6572626233100891},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6476128101348877},{"id":"https://openalex.org/keywords/infiniband","display_name":"InfiniBand","score":0.5064164400100708},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4600195288658142},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.45541831851005554},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.4527937173843384},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.3880537748336792},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3365759253501892},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11267244815826416},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1054641604423523}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.880588173866272},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6573910713195801},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6572626233100891},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6476128101348877},{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.5064164400100708},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4600195288658142},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.45541831851005554},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.4527937173843384},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.3880537748336792},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3365759253501892},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11267244815826416},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1054641604423523}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ccgrid51090.2021.00037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccgrid51090.2021.00037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/ACM 21st International Symposium on Cluster, Cloud and Internet Computing (CCGrid)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2101.08878","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.08878","pdf_url":"https://arxiv.org/pdf/2101.08878","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"","raw_type":"text"},{"id":"mag:3124796511","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2101.08878.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2101.08878","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2101.08878","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2101.08878","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2101.08878","pdf_url":"https://arxiv.org/pdf/2101.08878","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G202197749","display_name":null,"funder_award_id":"1818253","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4196433103","display_name":"OAC Core: Small: Next-Generation Communication and I/O Middleware for HPC and Deep Learning with Smart NICs","funder_award_id":"2007991","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5271487896","display_name":null,"funder_award_id":"1854828","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5279863110","display_name":null,"funder_award_id":"1931537","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8585293727","display_name":null,"funder_award_id":"2018627","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3124796511.pdf","grobid_xml":"https://content.openalex.org/works/W3124796511.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1583449596","https://openalex.org/W1962931680","https://openalex.org/W1997009754","https://openalex.org/W2001032894","https://openalex.org/W2104266030","https://openalex.org/W2527672088","https://openalex.org/W2542459869","https://openalex.org/W2584830274","https://openalex.org/W2973846153","https://openalex.org/W3014988774","https://openalex.org/W3033308515","https://openalex.org/W3157530502","https://openalex.org/W3203992401","https://openalex.org/W6656594533"],"related_works":["https://openalex.org/W3188297669","https://openalex.org/W1564050344","https://openalex.org/W2532741327","https://openalex.org/W1485684178","https://openalex.org/W2962753821","https://openalex.org/W3020258350","https://openalex.org/W2405528883","https://openalex.org/W2096475745","https://openalex.org/W2935041335","https://openalex.org/W2740001873","https://openalex.org/W2538465729","https://openalex.org/W2519996712","https://openalex.org/W2013390839","https://openalex.org/W2024846470","https://openalex.org/W2407863217","https://openalex.org/W2111144707","https://openalex.org/W1592554907","https://openalex.org/W2024830919","https://openalex.org/W2965037703","https://openalex.org/W2950505437"],"abstract_inverted_index":{"Dask":[0,22,209,231,267],"is":[1,76,91],"a":[2,69,92],"popular":[3],"parallel":[4],"and":[5,32,49,66,126,140,147,172,192,240,252,260],"distributed":[6],"computing":[7,30],"framework,":[8],"which":[9,90,109],"rivals":[10],"Apache":[11],"Spark":[12],"to":[13,59],"enable":[14],"task-based":[15],"scalable":[16],"processing":[17],"of":[18,28,68,95,156,166,183,190,216,258],"big":[19],"data.":[20],"The":[21],"Distributed":[23],"library":[24],"forms":[25],"the":[26,50,64,96,116,120,179,184,247,270],"basis":[27],"this":[29],"engine":[31],"provides":[33,103],"support":[34],"for":[35,47,52,73,78,136,142,205,220,250,263],"adding":[36],"new":[37,70],"communication":[38,44,71,107],"devices.":[39],"It":[40],"currently":[41],"has":[42],"two":[43,161,185],"devices:":[45],"one":[46],"TCP":[48],"other":[51],"high-speed":[53],"networks":[54],"using":[55,115,160],"UCX-Py\u2014a":[56],"Cython":[57],"wrapper":[58],"UCX.":[60],"This":[61],"paper":[62],"presents":[63],"design":[65],"implementation":[67,94],"backend":[72],"Dask\u2014called":[74],"MPI4Dask\u2014that":[75],"targeted":[77],"modern":[79],"HPC":[80],"clusters":[81],"built":[82,199],"with":[83,158,169,200,228],"GPUs.":[84],"MPI4Dask":[85,102,131,157,176,217,244],"exploits":[86],"mpi4py":[87],"over":[88],"MVAPICH2-GDR,":[89],"GPU-aware":[93],"Message":[97],"Passing":[98],"Interface":[99],"(MPI)":[100],"standard.":[101],"point-to-point":[104],"asynchronous":[105],"I/O":[106],"coroutines,":[108],"are":[110],"non-blocking":[111],"concurrent":[112],"operations":[113],"defined":[114],"async/await":[117],"keywords":[118],"from":[119],"Python\u2019s":[121],"asyncio":[122],"framework.":[123],"Our":[124],"latency":[125],"throughput":[127],"comparisons":[128],"suggest":[129],"that":[130],"outperforms":[132],"UCX":[133,159,219],"by":[134,187,255],"6\u00d7":[135],"1":[137,206,264],"Byte":[138],"message":[139],"4\u00d7":[141],"large":[143],"messages":[144],"(2":[145],"MBytes":[146],"beyond)":[148],"respectively.":[149],"We":[150,211],"also":[151,212],"conduct":[152],"comparative":[153],"performance":[154],"evaluation":[155],"benchmark":[162],"applications:":[163],"1)":[164],"sum":[165],"cuPy":[167,251],"array":[168],"its":[170],"transpose,":[171],"2)":[173],"cuDF":[174,253],"merge.":[175],"speeds":[177,245],"up":[178,246],"overall":[180],"execution":[181,248],"time":[182,249],"applications":[186,222,254],"an":[188,196,256],"average":[189,257],"3.47\u00d7":[191],"3.11\u00d7":[193],"respectively":[194,262],"on":[195,223,233,269],"in-house":[197],"cluster":[198],"NVIDIA":[201,235],"Tesla":[202],"V100":[203],"GPUs":[204,239],"\u2013":[207],"6":[208],"workers.":[210],"perform":[213],"scalability":[214],"analysis":[215],"against":[218],"these":[221],"TACC\u2019s":[224],"Frontera":[225,271],"(GPU)":[226,272],"system":[227],"upto":[229],"32":[230,234,266],"workers":[232,268],"Quadro":[236],"RTX":[237],"5000":[238],"256":[241],"CPU":[242],"cores.":[243],"1.71\u00d7":[259],"2.91\u00d7":[261],"\u2212":[265],"system.":[273]},"counts_by_year":[],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}