{"id":"https://openalex.org/W4413145828","doi":"https://doi.org/10.1109/ipdpsw66978.2025.00217","title":"Performance and Portability in Multi-GPU Branch-and-Bound: Chapel Versus CUDA and HIP for Tree-Based Optimization","display_name":"Performance and Portability in Multi-GPU Branch-and-Bound: Chapel Versus CUDA and HIP for Tree-Based Optimization","publication_year":2025,"publication_date":"2025-06-03","ids":{"openalex":"https://openalex.org/W4413145828","doi":"https://doi.org/10.1109/ipdpsw66978.2025.00217"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw66978.2025.00217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw66978.2025.00217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://orbilu.uni.lu/handle/10993/66041","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119281985","display_name":"Ivan Tagliaferro","orcid":null},"institutions":[{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Ivan Tagliaferro","raw_affiliation_strings":["Université de Lille, CNRS/CRIStAL UMR 9189,Centre Inria de l’Université de Lille,Lille,France"],"affiliations":[{"raw_affiliation_string":"Université de Lille, CNRS/CRIStAL UMR 9189,Centre Inria de l’Université de Lille,Lille,France","institution_ids":["https://openalex.org/I2279609970","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013209190","display_name":"Guillaume Helbecque","orcid":"https://orcid.org/0000-0002-8697-3721"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Guillaume Helbecque","raw_affiliation_strings":["Université de Lille, CNRS/CRIStAL UMR 9189,Centre Inria de l’Université de Lille,Lille,France"],"affiliations":[{"raw_affiliation_string":"Université de Lille, CNRS/CRIStAL UMR 9189,Centre Inria de l’Université de Lille,Lille,France","institution_ids":["https://openalex.org/I2279609970","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033657134","display_name":"Ezhilmathi Krishnasamy","orcid":"https://orcid.org/0000-0002-1971-4973"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Ezhilmathi Krishnasamy","raw_affiliation_strings":["University of Luxembourg,DCS-FSTM/SnT,Belval,Luxembourg"],"affiliations":[{"raw_affiliation_string":"University of Luxembourg,DCS-FSTM/SnT,Belval,Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112866837","display_name":"Nouredine Melab","orcid":null},"institutions":[{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nouredine Melab","raw_affiliation_strings":["Université de Lille, CNRS/CRIStAL UMR 9189,Centre Inria de l’Université de Lille,Lille,France"],"affiliations":[{"raw_affiliation_string":"Université de Lille, CNRS/CRIStAL UMR 9189,Centre Inria de l’Université de Lille,Lille,France","institution_ids":["https://openalex.org/I2279609970","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107678280","display_name":"Gr\u00e9goire Danoy","orcid":"https://orcid.org/0000-0001-9419-4210"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Gr\u00e9goire Danoy","raw_affiliation_strings":["University of Luxembourg,DCS-FSTM/SnT,Belval,Luxembourg"],"affiliations":[{"raw_affiliation_string":"University of Luxembourg,DCS-FSTM/SnT,Belval,Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5119281985"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2279609970"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26479438,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1293","last_page":"1295"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9909999966621399,"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":0.9909999966621399,"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":0.9484999775886536,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9419000148773193,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/cuda","display_name":"CUDA","score":0.9486048221588135},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.8597440719604492},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7639043927192688},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6278451681137085},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5639833211898804},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5006656646728516},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3557882308959961},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.24451887607574463},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.2290131151676178},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14097875356674194},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08583581447601318}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.9486048221588135},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.8597440719604492},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7639043927192688},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6278451681137085},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5639833211898804},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5006656646728516},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3557882308959961},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.24451887607574463},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.2290131151676178},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14097875356674194},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08583581447601318},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ipdpsw66978.2025.00217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw66978.2025.00217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","raw_type":"proceedings-article"},{"id":"pmh:oai:orbilu.uni.lu:10993/66041","is_oa":true,"landing_page_url":"https://orbilu.uni.lu/handle/10993/66041","pdf_url":null,"source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Performance and Portability in Multi-GPU Branch-and-Bound: Chapel versus CUDA and HIP for Tree-Based Optimization, 1293-1295 (2025-08-13); 2025 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), Milan, Italy [IT], 03-06-2025 => 07-06-2025","raw_type":"peer reviewed"},{"id":"pmh:oai:HAL:hal-05263968v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05263968","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.ipdps.org/ipdps2025/","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:orbilu.uni.lu:10993/66041","is_oa":true,"landing_page_url":"https://orbilu.uni.lu/handle/10993/66041","pdf_url":null,"source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Performance and Portability in Multi-GPU Branch-and-Bound: Chapel versus CUDA and HIP for Tree-Based Optimization, 1293-1295 (2025-08-13); 2025 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), Milan, Italy [IT], 03-06-2025 => 07-06-2025","raw_type":"peer reviewed"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3020739840","https://openalex.org/W2913998709","https://openalex.org/W3177128669","https://openalex.org/W4386875822","https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538"],"abstract_inverted_index":{"Tree":[0],"search":[1,55],"algorithms,":[2,57],"such":[3],"as":[4],"the":[5,33,49,74,115,128],"Branch-and-Bound":[6],"(B&B)":[7],"method,":[8],"are":[9],"essential":[10],"tools":[11],"in":[12,21,48,94,134],"exact":[13,53],"combinatorial":[14],"optimization.":[15],"Parallel":[16],"B&B":[17,83],"presents":[18],"significant":[19],"challenges":[20],"achieving":[22],"scalability":[23],"arising":[24],"due":[25],"to":[26,120],"irregular":[27],"and":[28,32,67,76,103],"fine-grained":[29],"workload":[30],"associated":[31],"hardware":[34],"heterogeneity":[35,47],"of":[36,78,114],"modern":[37],"supercomputers":[38],"[1]":[39],".":[40],"This":[41,123],"work":[42],"focuses":[43],"on":[44],"leveraging":[45],"GPU":[46,90,105],"HPC":[50],"environment":[51],"within":[52],"tree":[54],"optimization":[56],"through":[58],"a":[59,62,68,79],"comparison":[60,124],"between":[61,130],"proposed":[63,108],"CUDA-based":[64],"low-level":[65,97,121],"implementation":[66,77],"high-level":[69],"PGAS-based":[70],"one.":[71],"We":[72],"revisit":[73],"design":[75],"pool-based":[80],"GPU-accelerated":[81],"parallel":[82],"algorithm":[84],"tailored":[85],"for":[86,101,109],"heterogeneous":[87,136],"CPU":[88],"/":[89],"systems":[91],"originally":[92],"developed":[93],"Chapel.":[95],"A":[96],"counterpart":[98],"implementation,":[99],"suited":[100],"Nvidia":[102],"AMD":[104],"architectures,":[106],"is":[107],"performance":[110],"gain,":[111],"appeasing":[112],"some":[113],"portability":[116],"issues":[117],"usually":[118],"related":[119],"implementations.":[122],"provides":[125],"insights":[126],"into":[127],"trade-offs":[129],"different":[131],"programming":[132],"paradigms":[133],"large-scale,":[135],"computing":[137],"environments.":[138]},"counts_by_year":[],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}