{"id":"https://openalex.org/W2516291056","doi":"https://doi.org/10.1145/2949550.2949567","title":"Cross-Accelerator Performance Profiling","display_name":"Cross-Accelerator Performance Profiling","publication_year":2016,"publication_date":"2016-07-17","ids":{"openalex":"https://openalex.org/W2516291056","doi":"https://doi.org/10.1145/2949550.2949567","mag":"2516291056"},"language":"en","primary_location":{"id":"doi:10.1145/2949550.2949567","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2949550.2949567","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2949567&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the XSEDE16 Conference on Diversity, Big Data, and Science at Scale","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=2949567&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009654490","display_name":"Esthela Gallardo","orcid":null},"institutions":[{"id":"https://openalex.org/I164936912","display_name":"The University of Texas at El Paso","ror":"https://ror.org/04d5vba33","country_code":"US","type":"education","lineage":["https://openalex.org/I164936912"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Esthela Gallardo","raw_affiliation_strings":["University of Texas at El Paso, El Paso, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at El Paso, El Paso, TX","institution_ids":["https://openalex.org/I164936912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108516574","display_name":"Patricia J. Teller","orcid":null},"institutions":[{"id":"https://openalex.org/I164936912","display_name":"The University of Texas at El Paso","ror":"https://ror.org/04d5vba33","country_code":"US","type":"education","lineage":["https://openalex.org/I164936912"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patricia J. Teller","raw_affiliation_strings":["University of Texas at El Paso, El Paso, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at El Paso, El Paso, TX","institution_ids":["https://openalex.org/I164936912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013339281","display_name":"Arturo Argueta","orcid":null},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arturo Argueta","raw_affiliation_strings":["University of Notre Dame, Notre Dame, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame, Notre Dame, IN","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017546728","display_name":"Jaime Jaloma","orcid":null},"institutions":[{"id":"https://openalex.org/I164936912","display_name":"The University of Texas at El Paso","ror":"https://ror.org/04d5vba33","country_code":"US","type":"education","lineage":["https://openalex.org/I164936912"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaime Jaloma","raw_affiliation_strings":["University of Texas at El Paso, El Paso, TX"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at El Paso, El Paso, TX","institution_ids":["https://openalex.org/I164936912"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9993000030517578,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9976000189781189,"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/xeon-phi","display_name":"Xeon Phi","score":0.9001171588897705},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.846138060092926},{"id":"https://openalex.org/keywords/kepler","display_name":"Kepler","score":0.6497941017150879},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5890405774116516},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.5869462490081787},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5471276044845581},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.5176025629043579},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.46167728304862976},{"id":"https://openalex.org/keywords/power-consumption","display_name":"Power consumption","score":0.45949557423591614},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4344038963317871},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2856711745262146},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.2248782217502594}],"concepts":[{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.9001171588897705},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.846138060092926},{"id":"https://openalex.org/C207963374","wikidata":"https://www.wikidata.org/wiki/Q47592","display_name":"Kepler","level":3,"score":0.6497941017150879},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5890405774116516},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.5869462490081787},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5471276044845581},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.5176025629043579},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.46167728304862976},{"id":"https://openalex.org/C2984118289","wikidata":"https://www.wikidata.org/wiki/Q29954","display_name":"Power consumption","level":3,"score":0.45949557423591614},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4344038963317871},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2856711745262146},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2248782217502594},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C150846664","wikidata":"https://www.wikidata.org/wiki/Q7602306","display_name":"Stars","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2949550.2949567","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2949550.2949567","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2949567&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the XSEDE16 Conference on Diversity, Big Data, and Science at Scale","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2949550.2949567","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2949550.2949567","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2949567&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the XSEDE16 Conference on Diversity, Big Data, and Science at Scale","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.9100000262260437}],"awards":[{"id":"https://openalex.org/G3338714062","display_name":null,"funder_award_id":"60300261- 107307-B","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G5643650489","display_name":null,"funder_award_id":"UTA13-000072","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/F4320310620","display_name":"University of Texas at Austin","ror":"https://ror.org/00hj54h04"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2516291056.pdf","grobid_xml":"https://content.openalex.org/works/W2516291056.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W83535271","https://openalex.org/W348433680","https://openalex.org/W2023047131","https://openalex.org/W2036293628","https://openalex.org/W2080592089","https://openalex.org/W2149234156","https://openalex.org/W2175477959","https://openalex.org/W2271041116","https://openalex.org/W2407057568","https://openalex.org/W2470920449"],"related_works":["https://openalex.org/W32529763","https://openalex.org/W1908180445","https://openalex.org/W2475524688","https://openalex.org/W2739740241","https://openalex.org/W2597386847","https://openalex.org/W2035419609","https://openalex.org/W2912502764","https://openalex.org/W1766386015","https://openalex.org/W2895895456","https://openalex.org/W2963706620"],"abstract_inverted_index":{"The":[0],"computing":[1,25,44,60,115],"requirements":[2],"of":[3,17,36,42,58,114,133],"scientific":[4],"applications":[5],"have":[6,11],"influenced":[7],"processor":[8],"design,":[9],"and":[10,15,129,141,145,180,183,206,220,229,231],"motivated":[12],"the":[13,33,56,112,122,131,137,142,159,169,172,177,181,184,187,200,204,207],"introduction":[14],"use":[16,121],"many-core":[18],"processors,":[19],"i.e.,":[20],"accelerators,":[21,161],"for":[22,32],"high":[23],"performance":[24,57,70,132],"(HPC).":[26],"Consequently,":[27],"it":[28],"is":[29,90,100],"now":[30],"common":[31],"compute":[34],"nodes":[35],"HPC":[37],"clusters":[38],"to":[39,54,67,94,106,110,127,165,190,197],"be":[40,52],"comprised":[41],"multiple":[43],"devices,":[45,61],"including":[46],"accelerators.":[47],"Although":[48],"execution":[49],"time":[50],"can":[51],"used":[53,189],"compare":[55,128],"different":[59,75,135],"there":[62],"exists":[63],"no":[64],"standard":[65],"way":[66],"analyze":[68,130],"application":[69,97,126],"across":[71,158],"devices":[72],"with":[73],"very":[74],"architectural":[76,174],"designs":[77],"and,":[78],"thus,":[79],"understand":[80,107],"why":[81,199],"one":[82],"outperforms":[83,202],"another.":[84],"Without":[85],"this":[86,118],"knowledge,":[87],"a":[88,101],"developer":[89],"handicapped":[91],"when":[92,104],"attempting":[93],"effectively":[95],"tune":[96],"performance,":[98,193],"as":[99,223,225],"hardware":[102],"designer":[103],"trying":[105],"how":[108],"best":[109],"improve":[111],"design":[113],"devices.":[116],"In":[117],"paper,":[119],"we":[120,194,213],"LULESH":[123,152],"1.0":[124,153],"proxy":[125],"three":[134,160],"accelerators:":[136],"Intel\u00ae":[138],"Xeon":[139,178,208],"Phi\u2122":[140,179],"NVIDIA":[143],"Fermi":[144,205],"Kepler":[146,201],"GPUs.":[147],"Our":[148],"study":[149],"shows":[150],"that":[151],"exhibits":[154],"similar":[155],"execution-time":[156],"behavior":[157,228],"but":[162],"runs":[163],"up":[164],"7X":[166],"faster":[167],"on":[168],"Kepler.":[170],"Despite":[171],"significant":[173],"differences":[175,185],"between":[176],"GPUs,":[182],"in":[186],"metrics":[188],"characterize":[191],"their":[192,215,226],"were":[195],"able":[196],"quantify":[198],"both":[203],"Phi\u2122.":[209],"To":[210],"do":[211],"this,":[212],"compared":[214],"achieved":[216],"instructions":[217],"per":[218],"cycle":[219],"vectorization":[221],"usage,":[222],"well":[224],"memory":[227],"power":[230],"energy":[232],"consumption.":[233]},"counts_by_year":[{"year":2016,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}