{"id":"https://openalex.org/W4388561279","doi":"https://doi.org/10.1145/3624062.3624136","title":"Maximizing Data Utility for HPC Python Workflow Execution","display_name":"Maximizing Data Utility for HPC Python Workflow Execution","publication_year":2023,"publication_date":"2023-11-10","ids":{"openalex":"https://openalex.org/W4388561279","doi":"https://doi.org/10.1145/3624062.3624136"},"language":"en","primary_location":{"id":"doi:10.1145/3624062.3624136","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3624062.3624136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","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/A5010192079","display_name":"Thanh Son Phung","orcid":"https://orcid.org/0000-0001-5382-938X"},"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":true,"raw_author_name":"Thanh Son Phung","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Notre Dame, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Notre Dame, United States","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084849440","display_name":"Ben Clifford","orcid":"https://orcid.org/0000-0001-6397-7239"},"institutions":[{"id":"https://openalex.org/I4210114455","display_name":"Cambridge Quantum Computing (United Kingdom)","ror":"https://ror.org/024779x77","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210114455"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ben Clifford","raw_affiliation_strings":["CQX Limited, United Kingdom"],"affiliations":[{"raw_affiliation_string":"CQX Limited, United Kingdom","institution_ids":["https://openalex.org/I4210114455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065464552","display_name":"Kyle Chard","orcid":"https://orcid.org/0000-0002-7370-4805"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle Chard","raw_affiliation_strings":["University of Chicago, United States of America"],"affiliations":[{"raw_affiliation_string":"University of Chicago, United States of America","institution_ids":["https://openalex.org/I40347166"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007301255","display_name":"Douglas Thain","orcid":"https://orcid.org/0000-0001-5218-1956"},"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":"Douglas Thain","raw_affiliation_strings":["University of Notre Dame, USA"],"affiliations":[{"raw_affiliation_string":"University of Notre Dame, USA","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010192079"],"corresponding_institution_ids":["https://openalex.org/I107639228"],"apc_list":null,"apc_paid":null,"fwci":2.7588,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.93029982,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"637","last_page":"640"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9997000098228455,"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":0.9975000023841858,"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/computer-science","display_name":"Computer science","score":0.8847624063491821},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.8535848259925842},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8394120931625366},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.7269585728645325},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4710695147514343},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.44202297925949097},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3719050884246826},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3520579934120178},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.32080864906311035},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.24125677347183228}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8847624063491821},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8535848259925842},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8394120931625366},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7269585728645325},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4710695147514343},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.44202297925949097},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3719050884246826},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3520579934120178},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.32080864906311035},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.24125677347183228}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3624062.3624136","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3624062.3624136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SC '23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2078962046","https://openalex.org/W2084078215","https://openalex.org/W2527672088","https://openalex.org/W2898657440","https://openalex.org/W2943761765","https://openalex.org/W3011735680","https://openalex.org/W3092704488","https://openalex.org/W3100544306","https://openalex.org/W3104388511","https://openalex.org/W3138589548","https://openalex.org/W4205290699"],"related_works":["https://openalex.org/W2317245370","https://openalex.org/W4249323025","https://openalex.org/W198851386","https://openalex.org/W1980160788","https://openalex.org/W2030310580","https://openalex.org/W947442053","https://openalex.org/W2148915962","https://openalex.org/W4313433561","https://openalex.org/W2283866686","https://openalex.org/W2948365806"],"abstract_inverted_index":{"Large-scale":[0],"HPC":[1],"workflows":[2],"are":[3],"increasingly":[4],"implemented":[5],"in":[6],"dynamic":[7],"languages":[8],"such":[9],"as":[10],"Python,":[11],"which":[12,108],"allow":[13],"for":[14],"more":[15],"rapid":[16],"development":[17],"than":[18],"traditional":[19],"techniques.":[20],"However,":[21],"the":[22,34,44,68,125,132],"cost":[23],"of":[24,36,70,85,122,128,142],"executing":[25],"Python":[26],"applications":[27],"at":[28,114],"scale":[29],"is":[30,99],"often":[31],"dominated":[32],"by":[33],"distribution":[35,49,113],"common":[37],"datasets":[38],"and":[39,147],"complex":[40],"software":[41],"dependencies.":[42],"As":[43],"application":[45],"scales":[46],"up,":[47],"data":[48,93,104,112],"becomes":[50],"a":[51,58,88,119],"limiting":[52],"factor":[53],"that":[54],"prevents":[55],"scaling":[56],"beyond":[57],"few":[59],"hundred":[60],"nodes.":[61,149],"To":[62],"address":[63],"this":[64],"problem,":[65],"we":[66],"present":[67],"integration":[69],"Parsl":[71,98],"(a":[72,79],"Python-native":[73],"parallel":[74],"programming":[75],"library)":[76],"with":[77,144],"TaskVine":[78],"data-intensive":[80],"workflow":[81],"execution":[82],"engine).":[83],"Instead":[84],"relying":[86],"on":[87,96],"shared":[89,133],"filesystem":[90],"to":[91,94,101,106],"provide":[92],"tasks":[95,146],"demand,":[97],"able":[100],"express":[102],"advance":[103],"needs":[105],"TaskVine,":[107],"then":[109],"performs":[110],"efficient":[111],"runtime.":[115],"This":[116],"combination":[117],"provides":[118],"performance":[120],"speedup":[121,141],"1.48x":[123],"over":[124],"typical":[126],"method":[127],"on-demand":[129],"paging":[130],"from":[131],"filesystem,":[134],"while":[135],"also":[136],"providing":[137],"an":[138],"average":[139],"task":[140],"1.79x":[143],"2048":[145],"256":[148]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
