{"id":"https://openalex.org/W2154422485","doi":"https://doi.org/10.1145/2020373.2020380","title":"Performance modeling for multilevel communication in SHMEM+","display_name":"Performance modeling for multilevel communication in SHMEM+","publication_year":2010,"publication_date":"2010-10-12","ids":{"openalex":"https://openalex.org/W2154422485","doi":"https://doi.org/10.1145/2020373.2020380","mag":"2154422485"},"language":"en","primary_location":{"id":"doi:10.1145/2020373.2020380","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2020373.2020380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth Conference on Partitioned Global Address Space Programming Model","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/A5043985825","display_name":"Vikas A. Aggarwal","orcid":"https://orcid.org/0000-0002-2040-6767"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"V. Aggarwal","raw_affiliation_strings":["University of Florida, Gainesville, FL"],"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063537978","display_name":"Changil Yoon","orcid":null},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Yoon","raw_affiliation_strings":["University of Florida, Gainesville, FL"],"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082898376","display_name":"Alan D. George","orcid":"https://orcid.org/0000-0001-9665-2879"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. George","raw_affiliation_strings":["University of Florida, Gainesville, FL"],"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020976710","display_name":"Herman Lam","orcid":"https://orcid.org/0000-0002-2388-0819"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"H. Lam","raw_affiliation_strings":["University of Florida, Gainesville, FL"],"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088031457","display_name":"Greg Stitt","orcid":"https://orcid.org/0000-0001-7159-7439"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G. Stitt","raw_affiliation_strings":["University of Florida, Gainesville, FL"],"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5043985825"],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.17847162,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"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":1.0,"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":1.0,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9995999932289124,"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":0.8197447061538696},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.7771910429000854},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.5179068446159363},{"id":"https://openalex.org/keywords/communications-system","display_name":"Communications system","score":0.48264867067337036},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4700556993484497},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4614158570766449},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4537709653377533},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.45261579751968384},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.44502002000808716},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.44315770268440247},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4257696270942688},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.42405465245246887},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4154886305332184},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.41192081570625305},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3809356987476349},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.2852572202682495},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21744218468666077}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8197447061538696},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.7771910429000854},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.5179068446159363},{"id":"https://openalex.org/C101765175","wikidata":"https://www.wikidata.org/wiki/Q577764","display_name":"Communications system","level":2,"score":0.48264867067337036},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4700556993484497},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4614158570766449},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4537709653377533},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.45261579751968384},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.44502002000808716},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.44315770268440247},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4257696270942688},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.42405465245246887},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4154886305332184},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.41192081570625305},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3809356987476349},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2852572202682495},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21744218468666077},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2020373.2020380","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2020373.2020380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fourth Conference on Partitioned Global Address Space Programming Model","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8500000238418579,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G818933388","display_name":null,"funder_award_id":"EEC-0642422","funder_id":"https://openalex.org/F4320337394","funder_display_name":"Division of Engineering Education and Centers"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320337394","display_name":"Division of Engineering Education and Centers","ror":"https://ror.org/050rnw378"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W53188351","https://openalex.org/W1922017469","https://openalex.org/W2004618348","https://openalex.org/W2041351581","https://openalex.org/W2045271686","https://openalex.org/W2053738729","https://openalex.org/W2059113806","https://openalex.org/W2076186064","https://openalex.org/W2102061396","https://openalex.org/W2127495498","https://openalex.org/W2135922703","https://openalex.org/W2146142633","https://openalex.org/W2159997088","https://openalex.org/W2165231728","https://openalex.org/W4251681643"],"related_works":["https://openalex.org/W2432304421","https://openalex.org/W4301139505","https://openalex.org/W1497179374","https://openalex.org/W4298442907","https://openalex.org/W3150983477","https://openalex.org/W2039401562","https://openalex.org/W2591741338","https://openalex.org/W2109608899","https://openalex.org/W2122155038","https://openalex.org/W2120739641"],"abstract_inverted_index":{"The":[0,50],"field":[1],"of":[2,17,52,58,70,103,111,123,172,185,202,229],"high-performance":[3],"computing":[4,87],"(HPC)":[5],"is":[6,128],"currently":[7],"undergoing":[8],"a":[9,15,100,120,136,214],"major":[10],"transformation":[11],"brought":[12],"upon":[13],"by":[14,232],"variety":[16],"new":[18,137,215],"processor":[19,104],"device":[20],"technologies.":[21],"Accelerator":[22],"devices":[23,54],"(e.g.":[24],"FPGA,":[25],"GPU)":[26],"are":[27,157],"becoming":[28],"increasingly":[29],"popular":[30],"as":[31,89,208,223],"coprocessors":[32],"in":[33,43,63,147,175,250],"HPC,":[34],"embedded,":[35],"and":[36,60,80,85,97,116,150,159,182,190,253],"other":[37],"systems,":[38],"improving":[39],"application":[40,114,165],"performance":[41,115,189,201,228],"while":[42],"some":[44],"cases":[45,156,246],"also":[46],"reducing":[47],"energy":[48],"consumption.":[49],"presence":[51],"such":[53,88,207,222],"introduces":[55],"additional":[56],"levels":[57],"communication":[59,96,112,126,139,173],"memory":[61],"hierarchy":[62],"the":[64,109,124,162,180,193,218],"system,":[65],"which":[66],"warrants":[67],"an":[68],"expansion":[69],"conventional":[71],"parallel-programming":[72],"practices":[73],"to":[74,94,107,167,198,213,225,236],"address":[75],"these":[76,148,244],"differences.":[77],"Programming":[78],"models":[79],"libraries":[81],"for":[82,141,151],"heterogeneous,":[83],"parallel,":[84],"reconfigurable":[86],"SHMEM+":[90,209,224],"have":[91],"been":[92],"developed":[93],"support":[95],"coordination":[98],"involving":[99],"diverse":[101],"mix":[102],"devices.":[105],"However,":[106],"evaluate":[108],"impact":[110],"on":[113],"obtain":[117],"optimal":[118],"performance,":[119,251],"concrete":[121],"understanding":[122],"underlying":[125],"infrastructure":[127],"often":[129],"imperative.":[130],"In":[131],"this":[132],"paper,":[133],"we":[134],"introduce":[135],"multilevel":[138],"model":[140,163,194,219],"representing":[142],"various":[143],"data":[144,230],"transfers":[145,231],"encountered":[146],"systems":[149],"predicting":[152],"performance.":[153],"Three":[154],"use":[155,245],"presented":[158],"evaluated.":[160],"First,":[161],"enables":[164,195],"developers":[166,197],"perform":[168],"early":[169],"design-space":[170],"exploration":[171],"patterns":[174],"their":[176],"applications":[177],"before":[178],"undertaking":[179],"laborious":[181],"expensive":[183],"process":[184],"implementation,":[186],"yielding":[187],"improved":[188],"productivity.":[191],"Second,":[192],"system":[196],"quickly":[199],"optimize":[200],"data-transfer":[203],"routines":[204],"within":[205],"tools":[206,221],"when":[210],"being":[211],"ported":[212],"platform.":[216],"Third,":[217],"augments":[220],"automatically":[226],"improve":[227],"self-tuning":[233],"internal":[234],"parameters":[235],"match":[237],"platform":[238],"capabilities.":[239],"Results":[240],"from":[241],"experiments":[242],"with":[243],"suggest":[247],"marked":[248],"improvement":[249],"productivity,":[252],"portability.":[254]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
