{"id":"https://openalex.org/W4416133914","doi":"https://doi.org/10.1145/3757348.3757363","title":"Fine-Grained Application Energy and Power Measurements on the Frontier Exascale System","display_name":"Fine-Grained Application Energy and Power Measurements on the Frontier Exascale System","publication_year":2025,"publication_date":"2025-05-04","ids":{"openalex":"https://openalex.org/W4416133914","doi":"https://doi.org/10.1145/3757348.3757363"},"language":null,"primary_location":{"id":"doi:10.1145/3757348.3757363","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3757348.3757363","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3757348.3757363","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Cray User Group","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3757348.3757363","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071822072","display_name":"\u00d3scar Hern\u00e1ndez","orcid":"https://orcid.org/0000-0002-5380-6951"},"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":true,"raw_author_name":"Oscar Hernandez","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"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041347658","display_name":"Wael Elwasif","orcid":"https://orcid.org/0000-0003-0554-1036"},"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":"Wael Elwasif","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":2,"corresponding_author_ids":["https://openalex.org/A5071822072"],"corresponding_institution_ids":["https://openalex.org/I1289243028"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3900988,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"135","last_page":"146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9437999725341797,"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":0.9437999725341797,"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/T12238","display_name":"Green IT and Sustainability","score":0.01720000058412552,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.009200000204145908,"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/power","display_name":"Power (physics)","score":0.6302000284194946},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.567300021648407},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5472000241279602},{"id":"https://openalex.org/keywords/transient","display_name":"Transient (computer programming)","score":0.5379999876022339},{"id":"https://openalex.org/keywords/electricity-meter","display_name":"Electricity meter","score":0.5223000049591064},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.4499000012874603},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.43529999256134033},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.42320001125335693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7412999868392944},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.6302000284194946},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.567300021648407},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5472000241279602},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.5379999876022339},{"id":"https://openalex.org/C67172668","wikidata":"https://www.wikidata.org/wiki/Q622756","display_name":"Electricity meter","level":3,"score":0.5223000049591064},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.4499000012874603},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.43529999256134033},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.42320001125335693},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C2778837361","wikidata":"https://www.wikidata.org/wiki/Q2450880","display_name":"Exascale computing","level":3,"score":0.38429999351501465},{"id":"https://openalex.org/C4924752","wikidata":"https://www.wikidata.org/wiki/Q184148","display_name":"Plug-in","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3668999969959259},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3160000145435333},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.3109999895095825},{"id":"https://openalex.org/C89227174","wikidata":"https://www.wikidata.org/wiki/Q2388981","display_name":"Electric power system","level":3,"score":0.29829999804496765},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C149768029","wikidata":"https://www.wikidata.org/wiki/Q1509342","display_name":"Power budget","level":4,"score":0.2822999954223633},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C512564126","wikidata":"https://www.wikidata.org/wiki/Q7257959","display_name":"Public records","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3757348.3757363","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3757348.3757363","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3757348.3757363","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Cray User Group","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3757348.3757363","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3757348.3757363","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3757348.3757363","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Cray User Group","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4416133914.pdf"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W762259487","https://openalex.org/W1545880915","https://openalex.org/W2022513979","https://openalex.org/W2136434791","https://openalex.org/W2284372221","https://openalex.org/W2400128401","https://openalex.org/W2401404692","https://openalex.org/W2613252961","https://openalex.org/W2793320545","https://openalex.org/W2903928222","https://openalex.org/W2941102881","https://openalex.org/W3097861169","https://openalex.org/W3206285609","https://openalex.org/W4252521241","https://openalex.org/W4312580880","https://openalex.org/W4319287677","https://openalex.org/W4321636620","https://openalex.org/W4362469997","https://openalex.org/W4388581281","https://openalex.org/W4405003697","https://openalex.org/W4405755146","https://openalex.org/W4405755738"],"related_works":[],"abstract_inverted_index":{"The":[0],"increasing":[1],"complexity":[2],"and":[3,20,36,82,96,108,125,143,156,166,188,213,221],"power/energy":[4],"demands":[5],"of":[6,199,218,224],"heterogeneous":[7],"exascale":[8],"systems,":[9],"such":[10,207],"as":[11,208],"the":[12,30,102,197,216,219,222],"Frontier":[13],"supercomputer,":[14],"present":[15],"significant":[16],"challenges":[17],"for":[18,93,111],"measuring":[19],"optimizing":[21],"power":[22,35,46,81,90,107,151,158,226],"consumption":[23],"in":[24,57,184],"applications.":[25],"Current":[26],"tools":[27],"either":[28],"lack":[29],"resolution":[31],"to":[32,40,77,104,117,152,173],"capture":[33,153],"fine-grained":[34,80],"energy":[37,83,109,149,180],"measurements,":[38,84],"fail":[39],"validate":[41,189],"in-band":[42,190],"measurements":[43,92,110,134,191,220],"against":[44,192],"out-of-band":[45,165],"sensors,":[47],"or":[48],"cannot":[49],"integrate":[50],"this":[51,200],"information":[52],"with":[53,74,138],"application":[54,118,175],"performance":[55,67,119],"events":[56,120],"a":[58,64,122,160],"scalable":[59],"manner.":[60],"This":[61],"paper":[62],"introduces":[63],"novel":[65],"open-source":[66],"toolkit":[68,131],"that":[69,128],"integrates":[70],"extended":[71],"PAPI":[72],"components":[73],"Score-P":[75],"plugins":[76],"enable":[78],"in-band,":[79],"while":[85],"also":[86],"supporting":[87],"validation":[88],"using":[89,205],"meter":[91],"both":[94,154],"CPUs":[95],"GPUs.":[97],"One":[98],"key":[99],"contribution":[100],"is":[101],"ability":[103],"perform":[105],"millisecond-level":[106],"AMD":[112],"MI250X":[113],"GPUs,":[114],"mapping":[115,170],"them":[116],"within":[121],"single":[123],"trace":[124],"measurement":[126],"system":[127],"scales.":[129],"Our":[130],"combines":[132],"coarse-grained":[133],"from":[135,141],"cray_pm":[136],"counters":[137],"high-resolution":[139],"metrics":[140,172],"rocm_smi":[142],"RAPL,":[144],"converting":[145],"GPU":[146,185,209],"instantaneous":[147],"accumulated":[148],"into":[150],"transient":[155,225],"steady-state":[157],"behavior,":[159],"capability":[161],"often":[162],"missed":[163],"by":[164],"monitoring":[167],"tools.":[168],"By":[169],"these":[171],"specific":[174],"regions,":[176],"developers":[177],"can":[178],"identify":[179],"hotspots,":[181],"address":[182],"inefficiencies":[183],"kernel":[186],"execution,":[187],"external":[193],"measurements.":[194],"We":[195],"demonstrate":[196],"effectiveness":[198],"approach":[201],"through":[202],"case":[203],"studies":[204],"benchmarks":[206],"rocblas_sgemm,":[210],"BLIS":[211],"c_blas_dgemm,":[212],"rocHPL,":[214],"highlighting":[215],"variability":[217],"impact":[223],"spikes":[227],"on":[228],"kernel-level":[229],"efficiency.":[230]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-11T00:00:00"}
