{"id":"https://openalex.org/W2070468128","doi":"https://doi.org/10.1145/2628071.2671423","title":"Design of a Hybrid MPI-CUDA Benchmark Suite for CPU-GPU Clusters","display_name":"Design of a Hybrid MPI-CUDA Benchmark Suite for CPU-GPU Clusters","publication_year":2014,"publication_date":"2014-08-24","ids":{"openalex":"https://openalex.org/W2070468128","doi":"https://doi.org/10.1145/2628071.2671423","mag":"2070468128"},"language":"en","primary_location":{"id":"doi:10.1145/2628071.2671423","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2628071.2671423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Parallel architectures and compilation","raw_type":"proceedings-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/A5052854393","display_name":"Tejaswi Agarwal","orcid":"https://orcid.org/0009-0000-7929-036X"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tejaswi Agarwal","raw_affiliation_strings":["University of Missouri-Columbia, Columbia, MO, USA","University of Missouri Columbia, Columbia, MO, USA"],"affiliations":[{"raw_affiliation_string":"University of Missouri-Columbia, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]},{"raw_affiliation_string":"University of Missouri Columbia, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041520129","display_name":"Michela Becchi","orcid":"https://orcid.org/0000-0001-8353-2915"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michela Becchi","raw_affiliation_strings":["University of Missouri-Columbia, Columbia, MO, USA","University of Missouri Columbia, Columbia, MO, USA"],"affiliations":[{"raw_affiliation_string":"University of Missouri-Columbia, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]},{"raw_affiliation_string":"University of Missouri Columbia, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5052854393"],"corresponding_institution_ids":["https://openalex.org/I76835614"],"apc_list":null,"apc_paid":null,"fwci":0.6896,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75070185,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"505","last_page":"506"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998000264167786,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9968000054359436,"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":0.862259030342102},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.80024254322052},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7679355144500732},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6754903793334961},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6590443849563599},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.6273728609085083},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4872254431247711},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4657759368419647},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.4583842158317566},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4226975440979004},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16069158911705017},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.0661957859992981}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.862259030342102},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.80024254322052},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7679355144500732},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6754903793334961},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6590443849563599},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.6273728609085083},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4872254431247711},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4657759368419647},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.4583842158317566},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4226975440979004},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16069158911705017},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0661957859992981},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2628071.2671423","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2628071.2671423","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Parallel architectures and compilation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8182433835","display_name":null,"funder_award_id":"CNS-1216756","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"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W2074231493","https://openalex.org/W2115345034"],"related_works":["https://openalex.org/W2056717482","https://openalex.org/W1966243865","https://openalex.org/W2017587301","https://openalex.org/W2030707850","https://openalex.org/W2170611190","https://openalex.org/W2566934642","https://openalex.org/W1582436825","https://openalex.org/W2548246577","https://openalex.org/W2092007952","https://openalex.org/W2096672917"],"abstract_inverted_index":{"In":[0],"the":[1,41,73,104,112,115,122,126],"last":[2],"few":[3],"years,":[4],"GPUs":[5],"have":[6],"become":[7],"an":[8],"integral":[9],"part":[10],"of":[11,29,49,106,114],"HPC":[12],"clusters.":[13,59],"To":[14],"test":[15],"these":[16,55],"heterogeneous":[17],"CPU-GPU":[18,58],"systems,":[19],"we":[20],"designed":[21,64],"a":[22],"hybrid":[23],"CUDA-MPI":[24],"benchmark":[25,61],"suite":[26],"that":[27,98,111],"consists":[28],"three":[30],"communication-":[31],"and":[32,40,89,125],"compute-intensive":[33],"applications:":[34],"Matrix":[35],"Multiplication":[36],"(MM),":[37],"Needleman-Wunsch":[38],"(NW)":[39],"ADFA":[42],"compression":[43],"algorithm":[44],"[1].":[45],"The":[46],"main":[47],"goal":[48],"this":[50],"work":[51],"is":[52],"to":[53,65,69,75,80,90],"characterize":[54],"workloads":[56],"on":[57,119],"Our":[60,95],"applications":[62,79,116,127],"are":[63],"allow":[66],"cluster":[67,123],"administrators":[68],"identify":[70],"bottlenecks":[71],"in":[72],"cluster,":[74],"decide":[76],"if":[77],"scaling":[78],"multiple":[81],"nodes":[82],"would":[83],"improve":[84],"or":[85],"decrease":[86],"overall":[87],"throughput":[88,105],"design":[91],"effective":[92],"scheduling":[93],"policies.":[94],"experiments":[96],"show":[97],"inter-node":[99],"communication":[100],"can":[101],"significantly":[102],"degrade":[103],"communication-intensive":[107],"applications.":[108],"We":[109],"conclude":[110],"scalability":[113],"depends":[117],"primarily":[118],"two":[120],"factors:":[121],"configuration":[124],"characteristics.":[128]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
