{"id":"https://openalex.org/W3096835151","doi":"https://doi.org/10.1109/cluster49012.2020.00023","title":"Dynamic Kernel Fusion for Bulk Non-contiguous Data Transfer on GPU Clusters","display_name":"Dynamic Kernel Fusion for Bulk Non-contiguous Data Transfer on GPU Clusters","publication_year":2020,"publication_date":"2020-09-01","ids":{"openalex":"https://openalex.org/W3096835151","doi":"https://doi.org/10.1109/cluster49012.2020.00023","mag":"3096835151"},"language":"en","primary_location":{"id":"doi:10.1109/cluster49012.2020.00023","doi":"https://doi.org/10.1109/cluster49012.2020.00023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster49012.2020.00023","pdf_url":null,"source":{"id":"https://openalex.org/S4210207155","display_name":"IEEE International Conference on Cluster Computing (CLUSTER)","issn_l":"1552-5244","issn":["1552-5244","2168-9253"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Cluster Computing (CLUSTER)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5076405830","display_name":"Ching-Hsiang Chu","orcid":"https://orcid.org/0000-0002-6752-3135","observed_orcids":["https://orcid.org/0000-0002-6752-3135"]},"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":"Ching-Hsiang Chu","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, 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","observed_orcids":["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":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028296912","display_name":"Qinghua Zhou","orcid":"https://orcid.org/0009-0001-8490-7990","observed_orcids":["https://orcid.org/0009-0001-8490-7990"]},"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":"Qinghua Zhou","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, 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","observed_orcids":["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":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, 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. DK Panda","orcid":"https://orcid.org/0000-0002-0356-1781","observed_orcids":["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":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, 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":0.9801,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.72469708,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"130","last_page":"141"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9984999895095825,"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":0.9984999895095825,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.000699999975040555,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/gpu-clusters","display_name":"GPU clusters","score":0.7870000004768372},{"id":"https://openalex.org/keywords/kernel-fusion","display_name":"kernel fusion","score":0.6859999895095825},{"id":"https://openalex.org/keywords/mpi","display_name":"MPI","score":0.7649999856948853},{"id":"https://openalex.org/keywords/communication-middleware","display_name":"communication middleware","score":0.4779999852180481},{"id":"https://openalex.org/keywords/lassen","display_name":"Lassen","score":0.4230000078678131}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8835148811340332},{"id":"https://openalex.org/C2777256151","wikidata":"https://www.wikidata.org/wiki/Q7897273","display_name":"Unpacking","level":2,"score":0.8555055856704712},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6566137671470642},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6191658973693848},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5527568459510803},{"id":"https://openalex.org/C169468491","wikidata":"https://www.wikidata.org/wiki/Q146923","display_name":"Middleware (distributed applications)","level":2,"score":0.5375063419342041},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5245280861854553},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.43871402740478516},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4239354133605957},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3201836943626404},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2229291796684265},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cluster49012.2020.00023","doi":"https://doi.org/10.1109/cluster49012.2020.00023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster49012.2020.00023","pdf_url":null,"source":{"id":"https://openalex.org/S4210207155","display_name":"IEEE International Conference on Cluster Computing (CLUSTER)","issn_l":"1552-5244","issn":["1552-5244","2168-9253"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Cluster Computing (CLUSTER)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W57243869","https://openalex.org/W1498400246","https://openalex.org/W1555194772","https://openalex.org/W1559860755","https://openalex.org/W1576599451","https://openalex.org/W1581386200","https://openalex.org/W1585237817","https://openalex.org/W1838493653","https://openalex.org/W1964981582","https://openalex.org/W1994531540","https://openalex.org/W2025388037","https://openalex.org/W2050297469","https://openalex.org/W2056687467","https://openalex.org/W2063057407","https://openalex.org/W2065208324","https://openalex.org/W2099034447","https://openalex.org/W2109977639","https://openalex.org/W2122395763","https://openalex.org/W2154082760","https://openalex.org/W2344706860","https://openalex.org/W2494507800","https://openalex.org/W2763018387","https://openalex.org/W2808274640","https://openalex.org/W2886814729","https://openalex.org/W2889463335","https://openalex.org/W2895512264","https://openalex.org/W2952046647","https://openalex.org/W2955454939","https://openalex.org/W2969804086","https://openalex.org/W2992165038","https://openalex.org/W3005695646","https://openalex.org/W3028644900","https://openalex.org/W3037565727","https://openalex.org/W4231763094"],"related_works":["https://openalex.org/W2056687467","https://openalex.org/W2109977639","https://openalex.org/W2494507800","https://openalex.org/W1994531540","https://openalex.org/W2344706860","https://openalex.org/W4319866449","https://openalex.org/W2025388037","https://openalex.org/W2063057407","https://openalex.org/W7058243112","https://openalex.org/W2070940137"],"abstract_inverted_index":{"In":[0,118],"the":[1,16,25,51,65,71,113,134,140,148,168,172,186,190,195],"last":[2],"decade,":[3],"many":[4,205],"scientific":[5],"applications":[6,32],"have":[7],"been":[8],"significantly":[9],"accelerated":[10],"by":[11,94,131,204],"large-scale":[12],"GPU":[13,92,136],"systems.":[14],"However,":[15,101],"movement":[17,47],"of":[18,24,29,40,67,147,207],"non-contiguous":[19,163],"GPU-resident":[20,79],"data":[21,46],"is":[22],"one":[23],"most":[26],"challenging":[27],"components":[28],"scaling":[30],"these":[31],"using":[33],"communication":[34,49],"middleware":[35],"like":[36],"MPI.":[37],"Although":[38],"plenty":[39],"research":[41],"has":[42],"discussed":[43],"improving":[44],"noncontiguous":[45],"within":[48],"middleware,":[50],"packing/unpacking":[52,88,114,135],"operations":[53,115],"on":[54,171,185],"GPUs":[55],"are":[56],"still":[57],"expensive.":[58],"They":[59],"cannot":[60,111],"be":[61],"hidden":[62],"due":[63],"to":[64,85,90,126,138,153,167,179],"limitation":[66],"MPI":[68,76,99],"standard":[69],"and":[70,129,155,161,202],"not-well-optimized":[72],"designs":[73,150],"in":[74,98],"existing":[75,183],"implementations":[77],"for":[78,159],"data.":[80],"Consequently,":[81],"application":[82],"developers":[83],"tend":[84],"implement":[86],"customized":[87],"kernels":[89,137],"improve":[91],"utilization":[93],"avoiding":[95],"unnecessary":[96],"synchronizations":[97],"routines.":[100],"this":[102,119],"reduces":[103],"productivity":[104],"as":[105,107,109,199],"well":[106],"performance":[108,157],"it":[110],"overlap":[112],"with":[116],"communication.":[117],"paper,":[120],"we":[121,176],"propose":[122],"a":[123],"novel":[124],"approach":[125],"achieve":[127],"low-latency":[128],"high-bandwidth":[130],"dynamically":[132],"fusing":[133],"reduce":[139],"expensive":[141],"kernel":[142],"launch":[143],"overhead.":[144],"The":[145],"evaluation":[146],"proposed":[149,191],"shows":[151],"up":[152,178],"8X":[154],"5X":[156],"improvement":[158,181],"sparse":[160],"dense":[162],"layout,":[164],"respectively,":[165],"compared":[166],"state-of-the-art":[169],"approaches":[170,184],"Lassen":[173],"system.":[174,188],"Similarly,":[175],"observe":[177],"19X":[180],"over":[182],"ABCI":[187],"Furthermore,":[189],"design":[192],"also":[193],"outperforms":[194],"production":[196],"libraries,":[197],"such":[198],"SpectrumMPI,":[200],"OpenMPI,":[201],"MVAPICH2,":[203],"orders":[206],"magnitude.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2020-11-09T00:00:00"}