{"id":"https://openalex.org/W1985660086","doi":"https://doi.org/10.1109/hpcsim.2012.6266960","title":"A method for communication efficient work distributions in stencil operation based applications on heterogeneous clusters","display_name":"A method for communication efficient work distributions in stencil operation based applications on heterogeneous clusters","publication_year":2012,"publication_date":"2012-07-01","ids":{"openalex":"https://openalex.org/W1985660086","doi":"https://doi.org/10.1109/hpcsim.2012.6266960","mag":"1985660086"},"language":"en","primary_location":{"id":"doi:10.1109/hpcsim.2012.6266960","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2012.6266960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 International Conference on High Performance Computing & Simulation (HPCS)","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/A5042192916","display_name":"Joseph Schneible","orcid":null},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Joseph Schneible","raw_affiliation_strings":["Department of Electrical and Computer Engineering, George Washington University, Washington DC, DC, USA","Dept. of Electrical and Computer Engineering,, The George Washington University,, Washington, DC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, George Washington University, Washington DC, DC, USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering,, The George Washington University,, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021447319","display_name":"Lubom\u0131\u0301r \u0158\u0131\u0301ha","orcid":"https://orcid.org/0000-0002-1017-5766"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lubomir Riha","raw_affiliation_strings":["Department of Electrical and Computer Engineering, George Washington University, Washington DC, DC, USA","Dept. of Electrical and Computer Engineering,, The George Washington University,, Washington, DC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, George Washington University, Washington DC, DC, USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering,, The George Washington University,, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010278061","display_name":"Maria Malik","orcid":"https://orcid.org/0000-0001-8425-2501"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maria Malik","raw_affiliation_strings":["Department of Electrical and Computer Engineering, George Washington University, Washington DC, DC, USA","Dept. of Electrical and Computer Engineering,, The George Washington University,, Washington, DC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, George Washington University, Washington DC, DC, USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering,, The George Washington University,, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001914825","display_name":"Tarek El\u2010Ghazawi","orcid":"https://orcid.org/0000-0001-9687-7939"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tarek El-Ghazawi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, George Washington University, Washington DC, DC, USA","Dept. of Electrical and Computer Engineering,, The George Washington University,, Washington, DC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, George Washington University, Washington DC, DC, USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering,, The George Washington University,, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013691364","display_name":"Andrei Alexandru","orcid":"https://orcid.org/0000-0003-4547-1554"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrei Alexandru","raw_affiliation_strings":["Department of Physics, George Washington University, Washington DC, DC, USA","Department of Physics, The George Washington University, Washington, DC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Physics, George Washington University, Washington DC, DC, USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"Department of Physics, The George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5042192916"],"corresponding_institution_ids":["https://openalex.org/I193531525"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0995513,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"468","last_page":"474"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9972000122070312,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9972000122070312,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9941999912261963,"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":0.9904999732971191,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/infiniband","display_name":"InfiniBand","score":0.9495076537132263},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.8497724533081055},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8109440207481384},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6905472278594971},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.6179215908050537},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5086005926132202},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5059570670127869},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.48855480551719666},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.48361244797706604},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.46718907356262207},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.4528326988220215},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4441555440425873},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4188888967037201},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3479403257369995},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16711193323135376},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08979946374893188}],"concepts":[{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.9495076537132263},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.8497724533081055},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8109440207481384},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6905472278594971},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.6179215908050537},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5086005926132202},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5059570670127869},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.48855480551719666},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.48361244797706604},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.46718907356262207},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.4528326988220215},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4441555440425873},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4188888967037201},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3479403257369995},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16711193323135376},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08979946374893188},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpcsim.2012.6266960","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2012.6266960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 International Conference on High Performance Computing & Simulation (HPCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1575160822","https://openalex.org/W1642444757","https://openalex.org/W1983144994","https://openalex.org/W1987779630","https://openalex.org/W2118001135","https://openalex.org/W2155967869","https://openalex.org/W4252458306"],"related_works":["https://openalex.org/W2406331183","https://openalex.org/W2363988059","https://openalex.org/W2792231649","https://openalex.org/W2053215237","https://openalex.org/W2526291892","https://openalex.org/W1936984751","https://openalex.org/W2270278874","https://openalex.org/W2767285788","https://openalex.org/W1525827451","https://openalex.org/W1998726389"],"abstract_inverted_index":{"In":[0,74,98],"recent":[1],"years,":[2],"the":[3,26,49,61,92,110,139,142],"use":[4,50,62],"of":[5,25,29,51,63,113,141,147,157],"accelerators":[6],"in":[7,57],"conjunction":[8],"with":[9,67,115,126],"CPUs,":[10],"known":[11],"as":[12,119],"heterogeneous":[13,65,123],"computing,":[14],"has":[15],"brought":[16],"about":[17],"significant":[18],"performance":[19,104,140],"increases":[20],"for":[21,108],"scientific":[22],"applications.":[23],"One":[24],"best":[27],"examples":[28],"this":[30,99],"is":[31,81,135],"Lattice":[32,120,148],"Quantum":[33],"Chromo-Dynamics":[34],"(QCD),":[35],"a":[36,44,64,103,127],"stencil":[37,116],"operation":[38],"based":[39,106],"simulation.":[40],"These":[41],"simulations":[42],"have":[43],"large":[45],"memory":[46],"footprint":[47],"necessitating":[48],"many":[52],"graphics":[53],"processing":[54],"units":[55],"(GPUs)":[56],"parallel.":[58],"This":[59],"requires":[60],"cluster":[66],"one":[68],"or":[69],"more":[70],"GPUs":[71,90],"per":[72],"node.":[73],"order":[75],"to":[76,83,137,154],"obtain":[77],"optimal":[78],"performance,":[79],"it":[80],"necessary":[82],"determine":[84],"an":[85],"efficient":[86],"communication":[87,111,158],"pattern":[88],"between":[89,96],"on":[91,122],"same":[93],"node":[94],"and":[95,159],"nodes.":[97],"paper":[100],"we":[101],"present":[102],"model":[105],"method":[107,134],"minimizing":[109],"time":[112],"applications":[114],"operations,":[117],"such":[118],"QCD,":[121],"computing":[124],"systems":[125],"non-blocking":[128],"Infiniband":[129],"interconnection":[130],"network.":[131],"The":[132],"proposed":[133],"able":[136],"increase":[138],"most":[143],"computationally":[144],"intensive":[145],"kernel":[146],"QCD":[149],"by":[150],"25":[151],"percent":[152],"due":[153],"improved":[155],"overlapping":[156],"computation.":[160]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}