{"id":"https://openalex.org/W4415817370","doi":"https://doi.org/10.1177/10943420251363711","title":"Analytic roofline modeling and energy analysis of the LULESH proxy application on multi-core clusters","display_name":"Analytic roofline modeling and energy analysis of the LULESH proxy application on multi-core clusters","publication_year":2025,"publication_date":"2025-11-03","ids":{"openalex":"https://openalex.org/W4415817370","doi":"https://doi.org/10.1177/10943420251363711"},"language":"en","primary_location":{"id":"doi:10.1177/10943420251363711","is_oa":true,"landing_page_url":"https://doi.org/10.1177/10943420251363711","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1177/10943420251363711","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079056246","display_name":"Ayesha Afzal","orcid":"https://orcid.org/0000-0001-5061-0438"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Ayesha Afzal","raw_affiliation_strings":["Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg"],"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082552227","display_name":"Georg Hager","orcid":"https://orcid.org/0000-0002-8723-2781"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Georg Hager","raw_affiliation_strings":["Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg"],"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070209050","display_name":"Gerhard Wellein","orcid":"https://orcid.org/0000-0001-7371-3026"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Wellein","raw_affiliation_strings":["Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg"],"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079056246"],"corresponding_institution_ids":["https://openalex.org/I181369854"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3618636,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"2","first_page":"123","last_page":"141"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.694599986076355,"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":0.694599986076355,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.12870000302791595,"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"}},{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.05389999970793724,"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/concurrency","display_name":"Concurrency","score":0.5677000284194946},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.5152999758720398},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.46880000829696655},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4174000024795532},{"id":"https://openalex.org/keywords/power-consumption","display_name":"Power consumption","score":0.3977000117301941},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.3521000146865845},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.34929999709129333},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.3483000099658966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7170000076293945},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5795999765396118},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.5677000284194946},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.5152999758720398},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.46880000829696655},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C2984118289","wikidata":"https://www.wikidata.org/wiki/Q29954","display_name":"Power consumption","level":3,"score":0.3977000117301941},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C157742956","wikidata":"https://www.wikidata.org/wiki/Q3237776","display_name":"Frequency scaling","level":3,"score":0.3449000120162964},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3197999894618988},{"id":"https://openalex.org/C22684755","wikidata":"https://www.wikidata.org/wiki/Q847526","display_name":"Queueing theory","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/10943420251363711","is_oa":true,"landing_page_url":"https://doi.org/10.1177/10943420251363711","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1177/10943420251363711","is_oa":true,"landing_page_url":"https://doi.org/10.1177/10943420251363711","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1942400916","https://openalex.org/W1961751213","https://openalex.org/W2130604611","https://openalex.org/W2293076069","https://openalex.org/W2397792450","https://openalex.org/W2492540006","https://openalex.org/W2615801313","https://openalex.org/W2754695535","https://openalex.org/W2765505246","https://openalex.org/W2931103071","https://openalex.org/W2950444855","https://openalex.org/W2986407468","https://openalex.org/W3012831841","https://openalex.org/W3023224941","https://openalex.org/W3131125225","https://openalex.org/W3154810849","https://openalex.org/W4313417883","https://openalex.org/W4388581254","https://openalex.org/W4400798725","https://openalex.org/W6968076877"],"related_works":[],"abstract_inverted_index":{"We":[0,35,66,91,155],"present":[1],"a":[2,59,73],"thorough":[3],"performance":[4,76,88,124],"and":[5,17,30,41,102,127,143,167,182,186],"energy":[6,164,195],"consumption":[7,43],"analysis":[8,159],"of":[9,45,72,109,116,118,125,160,171,178,188,237],"the":[10,38,46,52,55,70,95,99,103,107,110,114,119,123,135,161,172,176,212,220],"LULESH":[11],"proxy":[12],"application":[13],"in":[14,51,146],"its":[15],"OpenMP":[16,126],"MPI":[18,128],"variants":[19],"on":[20,25,54,62,94,130,226,241],"two":[21],"different":[22],"clusters":[23],"based":[24,129],"Intel":[26],"Ice":[27,251],"Lake":[28],"(ICL)":[29],"Sapphire":[31],"Rapids":[32],"(SPR)":[33],"CPUs.":[34],"first":[36],"study":[37],"strong":[39],"scaling":[40],"power":[42,162,225],"characteristics":[44],"six":[47],"hot":[48,81,173],"spot":[49],"functions":[50,202],"code":[53],"node":[56],"level,":[57],"with":[58,69],"special":[60],"focus":[61],"memory":[63],"bandwidth":[64],"utilization.":[65],"then":[67],"proceed":[68],"construction":[71],"detailed":[74],"Roofline":[75],"model":[77,101,112],"for":[78,140,200],"each":[79],"memory-bound":[80,201,244],"spot,":[82],"which":[83,229],"we":[84,121],"validate":[85],"using":[86,204],"hardware":[87],"counter":[89],"measurements.":[90],"also":[92,156],"comment":[93],"observed":[96],"discrepancies":[97],"between":[98],"analytical":[100],"observations.":[104],"To":[105],"discern":[106],"influence":[108,115,177],"programming":[111],"from":[113],"implementation":[117,137],"code,":[120],"compare":[122],"problem":[131,153,179],"size,":[132,180],"examining":[133],"if":[134,144],"underlying":[136],"is":[138,219],"equivalent":[139],"large":[141],"problems,":[142],"differences":[145],"overheads":[147],"are":[148,197],"more":[149],"significant":[150],"at":[151],"smaller":[152],"sizes.":[154],"conduct":[157],"an":[158],"dissipation,":[163],"to":[165,250],"solution,":[166],"energy-delay":[168,238],"product":[169,239],"(EDP)":[170],"spots,":[174],"quantifying":[175],"core":[181,213],"uncore":[183],"clock":[184,214],"frequency,":[185],"number":[187],"active":[189],"cores":[190,206],"per":[191,207],"ccNUMA":[192,208],"domain.":[193],"Relevant":[194],"savings":[196],"only":[198,243],"possible":[199],"by":[203],"fewer":[205],"domain":[209],"and/or":[210],"reducing":[211],"speed.":[215],"A":[216],"major":[217],"issue":[218],"very":[221],"high":[222],"extrapolated":[223],"baseline":[224],"both":[227],"chips,":[228],"makes":[230],"concurrency":[231],"throttling":[232],"less":[233],"effective.":[234],"In":[235],"terms":[236],"(EDP),":[240],"SPR":[242],"workloads":[245],"offer":[246],"lower":[247],"EDP":[248],"compared":[249],"Lake.":[252]},"counts_by_year":[],"updated_date":"2026-03-13T14:20:09.374765","created_date":"2025-11-03T00:00:00"}