{"id":"https://openalex.org/W2019364330","doi":"https://doi.org/10.1109/cluster.2013.6702632","title":"Co-processing SPMD computation on CPUs and GPUs cluster","display_name":"Co-processing SPMD computation on CPUs and GPUs cluster","publication_year":2013,"publication_date":"2013-09-01","ids":{"openalex":"https://openalex.org/W2019364330","doi":"https://doi.org/10.1109/cluster.2013.6702632","mag":"2019364330"},"language":"en","primary_location":{"id":"doi:10.1109/cluster.2013.6702632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2013.6702632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Cluster Computing (CLUSTER)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5047113301","display_name":"Hui Li","orcid":"https://orcid.org/0000-0001-9223-264X"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hui Li","raw_affiliation_strings":["School of Informatics and Computing, Indiana University Bloomington","Sch. of Inf. & Comput., Indiana Univ. - Bloomington, Bloomington, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics and Computing, Indiana University Bloomington","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Sch. of Inf. & Comput., Indiana Univ. - Bloomington, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108016089","display_name":"Geoffrey Fox","orcid":"https://orcid.org/0000-0001-8198-4117"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Geoffrey Fox","raw_affiliation_strings":["School of Informatics and Computing, Indiana University Bloomington","Sch. of Inf. & Comput., Indiana Univ. - Bloomington, Bloomington, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics and Computing, Indiana University Bloomington","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Sch. of Inf. & Comput., Indiana Univ. - Bloomington, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006991539","display_name":"Gregor von Laszewski","orcid":"https://orcid.org/0000-0001-9558-179X"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gregor von Laszewski","raw_affiliation_strings":["School of Informatics and Computing, Indiana University Bloomington","Sch. of Inf. & Comput., Indiana Univ. - Bloomington, Bloomington, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics and Computing, Indiana University Bloomington","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Sch. of Inf. & Comput., Indiana Univ. - Bloomington, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102865110","display_name":"Arun Chauhan","orcid":"https://orcid.org/0000-0002-0327-7254"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arun Chauhan","raw_affiliation_strings":["School of Informatics and Computing, Indiana University Bloomington","Sch. of Inf. & Comput., Indiana Univ. - Bloomington, Bloomington, IN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics and Computing, Indiana University Bloomington","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Sch. of Inf. & Comput., Indiana Univ. - Bloomington, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9998999834060669,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/spmd","display_name":"SPMD","score":0.9896275997161865},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8734993934631348},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7559253573417664},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6653634309768677},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6189205646514893},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5206917524337769},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.4863603711128235},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.48346883058547974},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.43722784519195557},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42803120613098145},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41727960109710693},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.41190072894096375},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3901998698711395},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.14315059781074524},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11104026436805725},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10372641682624817}],"concepts":[{"id":"https://openalex.org/C7042729","wikidata":"https://www.wikidata.org/wiki/Q2289219","display_name":"SPMD","level":2,"score":0.9896275997161865},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8734993934631348},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7559253573417664},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6653634309768677},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6189205646514893},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5206917524337769},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.4863603711128235},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.48346883058547974},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.43722784519195557},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42803120613098145},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41727960109710693},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.41190072894096375},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3901998698711395},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.14315059781074524},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11104026436805725},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10372641682624817},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cluster.2013.6702632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2013.6702632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Cluster Computing (CLUSTER)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8999999761581421,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307769","display_name":"Astellas Pharma US","ror":"https://ror.org/05pw69n24"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1502554142","https://openalex.org/W1816932979","https://openalex.org/W1965307606","https://openalex.org/W1966031848","https://openalex.org/W1976860187","https://openalex.org/W1991126176","https://openalex.org/W2001347918","https://openalex.org/W2002555321","https://openalex.org/W2010459485","https://openalex.org/W2025560906","https://openalex.org/W2030977227","https://openalex.org/W2052715082","https://openalex.org/W2083221501","https://openalex.org/W2088222724","https://openalex.org/W2092464631","https://openalex.org/W2104958979","https://openalex.org/W2129817042","https://openalex.org/W2133288847","https://openalex.org/W2146703352","https://openalex.org/W2147865600","https://openalex.org/W2150476673","https://openalex.org/W2173213060","https://openalex.org/W2267061685","https://openalex.org/W4248767818","https://openalex.org/W6638416746","https://openalex.org/W6648192099"],"related_works":["https://openalex.org/W160207554","https://openalex.org/W2059556329","https://openalex.org/W2348578850","https://openalex.org/W2514049505","https://openalex.org/W1993048673","https://openalex.org/W2159570675","https://openalex.org/W2558536494","https://openalex.org/W2108703006","https://openalex.org/W2116671421","https://openalex.org/W4234791718"],"abstract_inverted_index":{"Heterogeneous":[0],"parallel":[1,58],"systems":[2],"with":[3],"multi":[4],"processors":[5],"and":[6,15,25,40,69,96,109,119],"accelerators":[7],"are":[8,26,74],"becoming":[9],"ubiquitous":[10],"due":[11],"to":[12,38,51,63,79,102],"better":[13],"cost-performance":[14],"energy-efficiency.":[16],"These":[17],"heterogeneous":[18,47,85,126],"processor":[19],"architectures":[20],"have":[21],"different":[22],"instruction":[23],"sets":[24],"optimized":[27],"for":[28],"either":[29],"task-latency":[30],"or":[31],"throughput":[32],"purposes.":[33],"Challenges":[34],"occur":[35],"in":[36,124],"regard":[37],"programmability":[39],"performance":[41],"when":[42],"running":[43],"SPMD":[44,65,82,107],"tasks":[45,83],"on":[46,67,84],"devices.":[48,111],"In":[49],"order":[50],"meet":[52],"these":[53],"challenges,":[54],"we":[55,73],"implemented":[56],"a":[57,103],"runtime":[59],"system":[60],"that":[61],"used":[62],"co-process":[64],"computation":[66],"CPUs":[68],"GPUs":[70],"clusters.":[71,86],"Furthermore,":[72],"proposing":[75],"an":[76],"analytic":[77,88],"model":[78,89],"automatically":[80],"schedule":[81],"Our":[87],"is":[90],"derived":[91],"from":[92],"the":[93,116],"roofline":[94],"model,":[95],"therefore":[97],"it":[98],"can":[99],"be":[100],"applied":[101],"wider":[104],"range":[105],"of":[106,115],"applications":[108],"hardware":[110],"The":[112],"experimental":[113],"results":[114],"C-means,":[117],"GMM,":[118],"GEMV":[120],"show":[121],"good":[122],"speedup":[123],"practical":[125],"cluster":[127],"environments.":[128]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}