{"id":"https://openalex.org/W4414909273","doi":"https://doi.org/10.1109/cluster59342.2025.11186477","title":"NSYS2PRV: Detailed and Quantitative Analysis of Large-Scale GPU Execution Traces with Paraver","display_name":"NSYS2PRV: Detailed and Quantitative Analysis of Large-Scale GPU Execution Traces with Paraver","publication_year":2025,"publication_date":"2025-09-02","ids":{"openalex":"https://openalex.org/W4414909273","doi":"https://doi.org/10.1109/cluster59342.2025.11186477"},"language":"en","primary_location":{"id":"doi:10.1109/cluster59342.2025.11186477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster59342.2025.11186477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Cluster Computing (CLUSTER)","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/A5092230963","display_name":"Marc Clasc\u00e0","orcid":"https://orcid.org/0000-0002-5963-6658"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Marc Clasc\u00e0","raw_affiliation_strings":["Barcelona Supercomputing Center,Barcelona,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center,Barcelona,Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035035680","display_name":"Jes\u00fas Labarta","orcid":"https://orcid.org/0000-0002-7489-4727"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jes\u00fas Labarta","raw_affiliation_strings":["Barcelona Supercomputing Center,Barcelona,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center,Barcelona,Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082933794","display_name":"Marta Garc\u00eda-Gasulla","orcid":"https://orcid.org/0000-0003-3682-9905"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Marta Garcia-Gasulla","raw_affiliation_strings":["Barcelona Supercomputing Center,Barcelona,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center,Barcelona,Spain","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7378,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86110829,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9850000143051147,"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":0.9850000143051147,"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":0.9725000262260437,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9722999930381775,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7120000123977661},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6258000135421753},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.620199978351593},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5641999840736389},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.536300003528595},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.49950000643730164},{"id":"https://openalex.org/keywords/quantitative-analysis","display_name":"Quantitative analysis (chemistry)","score":0.4406999945640564},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.37560001015663147}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8693000078201294},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7120000123977661},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6258000135421753},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.620199978351593},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5641999840736389},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.536300003528595},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.49950000643730164},{"id":"https://openalex.org/C95986675","wikidata":"https://www.wikidata.org/wiki/Q185168","display_name":"Quantitative analysis (chemistry)","level":2,"score":0.4406999945640564},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.37560001015663147},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.33379998803138733},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3303999900817871},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C98183937","wikidata":"https://www.wikidata.org/wiki/Q2112188","display_name":"Program analysis","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29260000586509705},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.28610000014305115},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.27059999108314514},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2685999870300293},{"id":"https://openalex.org/C2780977526","wikidata":"https://www.wikidata.org/wiki/Q42417149","display_name":"Data exploration","level":3,"score":0.26429998874664307},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C2777138346","wikidata":"https://www.wikidata.org/wiki/Q1714153","display_name":"Performance tuning","level":2,"score":0.25999999046325684}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cluster59342.2025.11186477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster59342.2025.11186477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Cluster Computing (CLUSTER)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1545880915","https://openalex.org/W2014579090","https://openalex.org/W2401404692","https://openalex.org/W3129831491","https://openalex.org/W4391993458","https://openalex.org/W4396921923","https://openalex.org/W4399282121","https://openalex.org/W4400680326"],"related_works":[],"abstract_inverted_index":{"This":[0,157],"work":[1,158],"presents":[2],"a":[3,5,7,29,57,160,181],"tool,":[4,62],"methodology,":[6],"set":[8,182],"of":[9,18,56,67,73,100,141,154,183],"metrics,":[10],"and":[11,21,70,91,139,163,191,204],"practical":[12],"examples":[13,194],"for":[14],"evaluating":[15],"the":[16,54,65,71,98,126,137,171,188],"performance":[17,49,60,102,145],"large-scale":[19,88,101],"AI":[20,92,203],"traditional":[22],"HPC":[23,59,205],"applications":[24,90],"using":[25],"GPUs.":[26],"NSYS2PRV":[27],"is":[28,109],"tool":[30],"that":[31,87,108,168,186],"converts":[32],"NVIDIA":[33],"Nsight":[34,176],"Systems":[35],"reports":[36],"into":[37],"traces":[38,69,119],"compatible":[39],"with":[40,136],"Paraver,":[41],"enabling":[42],"significantly":[43],"enhanced":[44],"insight":[45],"compared":[46],"to":[47,76,120,124,201],"current":[48],"analysis":[50,61,103,146,165,189],"practices.":[51],"By":[52],"leveraging":[53],"capabilities":[55],"well-established":[58],"we":[63,179,192],"enable":[64],"comparison":[66],"execution":[68,130],"quantification":[72],"microscopic-level":[74],"differences":[75],"explain":[77],"behaviors":[78],"across":[79],"hundreds":[80],"or":[81],"more":[82,161],"computing":[83],"devices.":[84],"We":[85],"argue":[86],"GPU":[89],"workloads":[93],"can":[94],"greatly":[95],"benefit":[96],"from":[97,133],"type":[99],"introduced":[104],"here,":[105],"an":[106,142],"approach":[107],"not":[110],"yet":[111],"widely":[112],"adopted":[113],"in":[114,175],"this":[115],"domain.":[116],"Translating":[117],"nsys-generated":[118],"Paraver":[121,148],"allows":[122],"analysts":[123],"combine":[125],"fine-grained,":[127],"highly":[128],"accurate":[129],"data":[131],"obtainable":[132],"proprietary":[134],"tools":[135,174],"flexibility":[138],"scalability":[140],"open-source,":[143],"parallel":[144],"environment.":[147],"also":[149],"enables":[150],"easy,":[151],"customizable":[152],"computation":[153],"efficiency":[155],"metrics.":[156],"demonstrates":[159],"effective":[162],"insightful":[164],"experience":[166],"than":[167],"offered":[169],"by":[170],"native":[172],"visualization":[173],"Systems.":[177],"Additionally,":[178],"introduce":[180],"Paravercompatible":[184],"metrics":[185,197],"guide":[187],"process,":[190],"showcase":[193],"where":[195],"these":[196],"were":[198],"successfully":[199],"applied":[200],"real-world":[202],"workloads.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}