{"id":"https://openalex.org/W2109608899","doi":"https://doi.org/10.1177/1094342012468180","title":"Modeling and predicting performance of high performance computing applications on hardware accelerators","display_name":"Modeling and predicting performance of high performance computing applications on hardware accelerators","publication_year":2012,"publication_date":"2012-12-28","ids":{"openalex":"https://openalex.org/W2109608899","doi":"https://doi.org/10.1177/1094342012468180","mag":"2109608899"},"language":"en","primary_location":{"id":"doi:10.1177/1094342012468180","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342012468180","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-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/A5009884317","display_name":"Mitesh R. Meswani","orcid":null},"institutions":[{"id":"https://openalex.org/I181653535","display_name":"San Diego Supercomputer Center","ror":"https://ror.org/04mg3nk07","country_code":"US","type":"facility","lineage":["https://openalex.org/I181653535","https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mitesh R. Meswani","raw_affiliation_strings":["San Diego Supercomputer Center, La Jolla, CA, USA","[San Diego Supercomputer Center, La Jolla, CA, USA]"],"affiliations":[{"raw_affiliation_string":"San Diego Supercomputer Center, La Jolla, CA, USA","institution_ids":["https://openalex.org/I181653535"]},{"raw_affiliation_string":"[San Diego Supercomputer Center, La Jolla, CA, USA]","institution_ids":["https://openalex.org/I181653535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021474358","display_name":"Laura Carrington","orcid":null},"institutions":[{"id":"https://openalex.org/I181653535","display_name":"San Diego Supercomputer Center","ror":"https://ror.org/04mg3nk07","country_code":"US","type":"facility","lineage":["https://openalex.org/I181653535","https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Laura Carrington","raw_affiliation_strings":["San Diego Supercomputer Center, La Jolla, CA, USA","[San Diego Supercomputer Center, La Jolla, CA, USA]"],"affiliations":[{"raw_affiliation_string":"San Diego Supercomputer Center, La Jolla, CA, USA","institution_ids":["https://openalex.org/I181653535"]},{"raw_affiliation_string":"[San Diego Supercomputer Center, La Jolla, CA, USA]","institution_ids":["https://openalex.org/I181653535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040713791","display_name":"Didem Unat","orcid":"https://orcid.org/0000-0002-2351-0770"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Didem Unat","raw_affiliation_strings":["University of California at San Diego, San Diego, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California at San Diego, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110725059","display_name":"Allan Snavely","orcid":null},"institutions":[{"id":"https://openalex.org/I181653535","display_name":"San Diego Supercomputer Center","ror":"https://ror.org/04mg3nk07","country_code":"US","type":"facility","lineage":["https://openalex.org/I181653535","https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Allan Snavely","raw_affiliation_strings":["San Diego Supercomputer Center, La Jolla, CA, USA","[San Diego Supercomputer Center, La Jolla, CA, USA]"],"affiliations":[{"raw_affiliation_string":"San Diego Supercomputer Center, La Jolla, CA, USA","institution_ids":["https://openalex.org/I181653535"]},{"raw_affiliation_string":"[San Diego Supercomputer Center, La Jolla, CA, USA]","institution_ids":["https://openalex.org/I181653535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043777072","display_name":"Scott B. Baden","orcid":"https://orcid.org/0000-0002-5479-8199"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott Baden","raw_affiliation_strings":["University of California at San Diego, San Diego, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of California at San Diego, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043234330","display_name":"Stephen Poole","orcid":"https://orcid.org/0000-0002-4531-7453"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen Poole","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5009884317"],"corresponding_institution_ids":["https://openalex.org/I181653535"],"apc_list":null,"apc_paid":null,"fwci":2.6747,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.9021987,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"27","issue":"2","first_page":"89","last_page":"108"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9997000098228455,"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":0.9994000196456909,"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/porting","display_name":"Porting","score":0.9177262783050537},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.9106154441833496},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8186930418014526},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.6480333805084229},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5892748832702637},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5595410466194153},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5425221920013428},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.5144332051277161},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.49982213973999023},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4521397352218628},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.42523714900016785},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.4131515622138977},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2697463929653168},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.1801425814628601}],"concepts":[{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.9177262783050537},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.9106154441833496},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8186930418014526},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.6480333805084229},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5892748832702637},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5595410466194153},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5425221920013428},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.5144332051277161},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.49982213973999023},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4521397352218628},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.42523714900016785},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.4131515622138977},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2697463929653168},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.1801425814628601},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342012468180","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342012468180","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320327572","display_name":"Promotion and Mutual Aid Corporation for Private Schools of Japan","ror":"https://ror.org/05h2t6865"},{"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":40,"referenced_works":["https://openalex.org/W207051584","https://openalex.org/W309890564","https://openalex.org/W354184832","https://openalex.org/W1522478627","https://openalex.org/W1965214876","https://openalex.org/W1975243974","https://openalex.org/W1979527452","https://openalex.org/W1980257390","https://openalex.org/W2002555321","https://openalex.org/W2014956284","https://openalex.org/W2015691124","https://openalex.org/W2019436626","https://openalex.org/W2032094184","https://openalex.org/W2041351581","https://openalex.org/W2052897520","https://openalex.org/W2054882590","https://openalex.org/W2058733701","https://openalex.org/W2064757275","https://openalex.org/W2083928586","https://openalex.org/W2089841364","https://openalex.org/W2099084006","https://openalex.org/W2100415730","https://openalex.org/W2107896023","https://openalex.org/W2108792719","https://openalex.org/W2109811664","https://openalex.org/W2112121929","https://openalex.org/W2115283682","https://openalex.org/W2117184662","https://openalex.org/W2120635877","https://openalex.org/W2121082877","https://openalex.org/W2138039790","https://openalex.org/W2147657366","https://openalex.org/W2159065635","https://openalex.org/W2165752568","https://openalex.org/W2167334577","https://openalex.org/W2537949677","https://openalex.org/W2764743921","https://openalex.org/W4239829442","https://openalex.org/W4243412784","https://openalex.org/W4245779115"],"related_works":["https://openalex.org/W2717174904","https://openalex.org/W2548545698","https://openalex.org/W2092936829","https://openalex.org/W2265963950","https://openalex.org/W1989157207","https://openalex.org/W2956082141","https://openalex.org/W2109608899","https://openalex.org/W2955328870","https://openalex.org/W2151741062","https://openalex.org/W2166713816"],"abstract_inverted_index":{"Hybrid-core":[0],"systems":[1,18],"speedup":[2,97],"applications":[3],"by":[4,98,115],"offloading":[5],"certain":[6],"compute":[7,108],"operations":[8,95],"that":[9,61,91,123],"can":[10,96],"run":[11],"faster":[12],"on":[13],"hardware":[14],"accelerators.":[15,32],"However,":[16],"such":[17],"require":[19],"significant":[20],"programming":[21],"and":[22,67,80,88,93,106,112,117,142],"porting":[23,36],"effort":[24],"to":[25,35,40,126,146],"gain":[26],"a":[27,49,58,102],"performance":[28,44,65],"benefit":[29,45,127],"from":[30,128],"the":[31,42,63,129,133,140,143],"Therefore,":[33],"prior":[34],"it":[37],"is":[38],"prudent":[39],"investigate":[41],"predicted":[43],"of":[46,104,110,132,135],"accelerators":[47,86,144],"for":[48,69,75,84],"given":[50],"workload.":[51],"To":[52],"address":[53],"this":[54],"problem":[55],"we":[56],"present":[57,73],"performance-modeling":[59],"framework":[60],"predicts":[62],"application":[64],"rapidly":[66],"accurately":[68],"hybrid-core":[70],"systems.":[71],"We":[72,120],"predictions":[74],"two":[76,85],"full-scale":[77],"HPC":[78],"applications\u2014HYCOM":[79],"Milc.":[81],"Our":[82],"results":[83],"(GPU":[87],"FPGA)":[89],"show":[90,122],"gather/scatter":[92],"stream":[94],"as":[99,101],"much":[100],"factor":[103],"15":[105],"overall":[107],"time":[109,138],"Milc":[111],"HYCOM":[113],"improve":[114],"3.4%":[116],"20%,":[118],"respectively.":[119],"also":[121],"in":[124],"order":[125],"accelerators,":[130],"70%":[131],"latency":[134],"data":[136],"transfer":[137],"between":[139],"CPU":[141],"needs":[145],"be":[147],"overcome.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}