{"id":"https://openalex.org/W7168020020","doi":"https://doi.org/10.1145/3806645.3816123","title":"Robust I/O Characterization of Machine Learning Workloads Across Performance Analysis Tools","display_name":"Robust I/O Characterization of Machine Learning Workloads Across Performance Analysis Tools","publication_year":2026,"publication_date":"2026-07-11","ids":{"openalex":"https://openalex.org/W7168020020","doi":"https://doi.org/10.1145/3806645.3816123"},"language":null,"primary_location":{"id":"doi:10.1145/3806645.3816123","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3806645.3816123","pdf_url":null,"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 35th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3806645.3816123","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140481812","display_name":"Zoya Masih","orcid":"https://orcid.org/0009-0004-1484-229X"},"institutions":[{"id":"https://openalex.org/I4210116730","display_name":"Universit\u00e4tsmedizin G\u00f6ttingen","ror":"https://ror.org/021ft0n22","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210116730"]},{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zoya Masih","raw_affiliation_strings":["Georg-August Universit\u00e4t G\u00f6ttingen / GWDG, G\u00f6ttingen, Germany"],"raw_orcid":"https://orcid.org/0009-0004-1484-229X","affiliations":[{"raw_affiliation_string":"Georg-August Universit\u00e4t G\u00f6ttingen / GWDG, G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I4210116730","https://openalex.org/I74656192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048579889","display_name":"Radita Liem","orcid":"https://orcid.org/0000-0002-2506-1841"},"institutions":[{"id":"https://openalex.org/I197323543","display_name":"Johannes Gutenberg University Mainz","ror":"https://ror.org/023b0x485","country_code":"DE","type":"education","lineage":["https://openalex.org/I197323543"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Radita Liem","raw_affiliation_strings":["Johannes Gutenberg University Mainz, Mainz, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2506-1841","affiliations":[{"raw_affiliation_string":"Johannes Gutenberg University Mainz, Mainz, Germany","institution_ids":["https://openalex.org/I197323543"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028731194","display_name":"Julian Kunkel","orcid":"https://orcid.org/0000-0002-6915-1179"},"institutions":[{"id":"https://openalex.org/I4210116730","display_name":"Universit\u00e4tsmedizin G\u00f6ttingen","ror":"https://ror.org/021ft0n22","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I4210116730"]},{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Julian Kunkel","raw_affiliation_strings":["Georg-August Universit\u00e4t G\u00f6ttingen / GWDG, G\u00f6ttingen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-6915-1179","affiliations":[{"raw_affiliation_string":"Georg-August Universit\u00e4t G\u00f6ttingen / GWDG, G\u00f6ttingen, Germany","institution_ids":["https://openalex.org/I4210116730","https://openalex.org/I74656192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.95983152,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"766","last_page":"773"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.6381000280380249,"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"}},"topics":[{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.6381000280380249,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.13699999451637268,"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":0.06430000066757202,"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/profiling","display_name":"Profiling (computer programming)","score":0.72079998254776},{"id":"https://openalex.org/keywords/tracing","display_name":"Tracing","score":0.6222000122070312},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.5236999988555908},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4390000104904175},{"id":"https://openalex.org/keywords/predictive-modelling","display_name":"Predictive modelling","score":0.4383000135421753},{"id":"https://openalex.org/keywords/instrumentation","display_name":"Instrumentation (computer programming)","score":0.4009000062942505},{"id":"https://openalex.org/keywords/execution-time","display_name":"Execution time","score":0.3928000032901764}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7623999714851379},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.72079998254776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6789000034332275},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.6222000122070312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5529000163078308},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.5236999988555908},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4390000104904175},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.4383000135421753},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4198000133037567},{"id":"https://openalex.org/C118530786","wikidata":"https://www.wikidata.org/wiki/Q1134732","display_name":"Instrumentation (computer programming)","level":2,"score":0.4009000062942505},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C141571065","wikidata":"https://www.wikidata.org/wiki/Q1771949","display_name":"Performance measurement","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2964000105857849},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.28619998693466187}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3806645.3816123","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3806645.3816123","pdf_url":null,"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 35th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3806645.3816123","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3806645.3816123","pdf_url":null,"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 35th International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1545880915","https://openalex.org/W2010628428","https://openalex.org/W2142812297","https://openalex.org/W2767346922","https://openalex.org/W3216700135","https://openalex.org/W4297957988","https://openalex.org/W4362505433","https://openalex.org/W4405755678","https://openalex.org/W4408232726","https://openalex.org/W4414210498"],"related_works":[],"abstract_inverted_index":{"Data-driven":[0],"models":[1,105],"can":[2,106],"predict":[3],"filesystem":[4,89],"I/O":[5,13,44,76,90,108],"time":[6,91,109],"proportion,":[7],"a":[8],"key":[9],"metric":[10],"for":[11,115],"guiding":[12],"tuning":[14],"in":[15,30,75,96,122],"HPC":[16],"applications,":[17],"from":[18],"performance":[19,126],"data.":[20],"This":[21],"work":[22,33],"evaluates":[23],"whether":[24],"the":[25,38,80,86,100],"XGBoost-based":[26],"model":[27],"we":[28,51],"proposed":[29],"our":[31],"prior":[32],"[13],":[34],"remains":[35,66],"effective":[36],"when":[37],"underlying":[39],"profiling":[40,69],"tool":[41],"changes.":[42],"Using":[43],"metrics":[45],"collected":[46],"with":[47],"Score-P":[48],"and":[49,57,85],"DFTracer,":[50],"analyze":[52],"two":[53],"video":[54],"processing":[55],"workloads":[56],"train":[58],"predictive":[59,64],"models.":[60],"Results":[61],"show":[62],"that":[63,79,103],"accuracy":[65],"stable":[67],"across":[68],"tools":[70],"while":[71],"revealing":[72],"workload-specific":[73],"differences":[74],"behavior,":[77],"suggesting":[78],"relationship":[81],"between":[82],"configuration":[83],"parameters":[84],"proportion":[87,110],"of":[88],"is":[92],"preserved":[93],"despite":[94],"variations":[95],"measurement":[97],"methodology.":[98],"Furthermore,":[99],"findings":[101],"indicate":[102],"configuration-driven":[104],"approximate":[107],"without":[111],"requiring":[112],"runtime":[113],"tracing":[114],"every":[116],"execution,":[117],"reducing":[118],"dependence":[119],"on":[120],"instrumentation":[121],"future":[123],"machine":[124],"learning-driven":[125],"analysis":[127],"workflows.":[128]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-12T00:00:00"}