{"id":"https://openalex.org/W4416004321","doi":"https://doi.org/10.1145/3731599.3767505","title":"DiOMP-Offloading: Toward Portable Distributed Heterogeneous OpenMP","display_name":"DiOMP-Offloading: Toward Portable Distributed Heterogeneous OpenMP","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416004321","doi":"https://doi.org/10.1145/3731599.3767505"},"language":null,"primary_location":{"id":"doi:10.1145/3731599.3767505","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731599.3767505","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 '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","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/A5083746071","display_name":"Baodi Shan","orcid":"https://orcid.org/0000-0002-1022-3801"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baodi Shan","raw_affiliation_strings":["Stony Brook University, Stony Brook, USA"],"raw_orcid":"https://orcid.org/0000-0002-1022-3801","affiliations":[{"raw_affiliation_string":"Stony Brook University, Stony Brook, USA","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027534318","display_name":"Mauricio Araya\u2013Polo","orcid":"https://orcid.org/0000-0002-5537-1840"},"institutions":[{"id":"https://openalex.org/I103084370","display_name":"Total (France)","ror":"https://ror.org/04sk34n56","country_code":"FR","type":"company","lineage":["https://openalex.org/I103084370"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mauricio Araya-Polo","raw_affiliation_strings":["TotalEnergies EP Research & Technology US, LLC, Houston, USA"],"raw_orcid":"https://orcid.org/0000-0002-5537-1840","affiliations":[{"raw_affiliation_string":"TotalEnergies EP Research & Technology US, LLC, Houston, USA","institution_ids":["https://openalex.org/I103084370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053733660","display_name":"Barbara Chapman","orcid":"https://orcid.org/0000-0001-8449-8579"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barbara Chapman","raw_affiliation_strings":["Stony Brook University, Stony Brook, USA"],"raw_orcid":"https://orcid.org/0000-0001-8449-8579","affiliations":[{"raw_affiliation_string":"Stony Brook University, Stony Brook, USA","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1289","last_page":"1301"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.2985000014305115,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.2985000014305115,"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"}},{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.23810000717639923,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.10830000042915344,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7754999995231628},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.46149998903274536},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.444599986076355},{"id":"https://openalex.org/keywords/vendor","display_name":"Vendor","score":0.42829999327659607},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.4075999855995178},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.40380001068115234},{"id":"https://openalex.org/keywords/physical-address","display_name":"Physical address","score":0.3837999999523163},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.3465999960899353}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8172000050544739},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7754999995231628},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5117999911308289},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.46149998903274536},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4569000005722046},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.444599986076355},{"id":"https://openalex.org/C2777338717","wikidata":"https://www.wikidata.org/wiki/Q1762621","display_name":"Vendor","level":2,"score":0.42829999327659607},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.4075999855995178},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.40380001068115234},{"id":"https://openalex.org/C41036726","wikidata":"https://www.wikidata.org/wiki/Q844824","display_name":"Physical address","level":3,"score":0.3837999999523163},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3564000129699707},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C39528615","wikidata":"https://www.wikidata.org/wiki/Q1229610","display_name":"Distributed shared memory","level":5,"score":0.34209999442100525},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.32989999651908875},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3197000026702881},{"id":"https://openalex.org/C144240696","wikidata":"https://www.wikidata.org/wiki/Q367204","display_name":"Address space","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2944999933242798},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.2890999913215637},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.2766000032424927},{"id":"https://openalex.org/C60832428","wikidata":"https://www.wikidata.org/wiki/Q945818","display_name":"Partitioned global address space","level":3,"score":0.27090001106262207},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.26759999990463257}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731599.3767505","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731599.3767505","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 '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324219","display_name":"Total","ror":"https://ror.org/04sk34n56"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2119148081","https://openalex.org/W2535374105","https://openalex.org/W2896801938","https://openalex.org/W2912650951","https://openalex.org/W2913135575","https://openalex.org/W2921746795","https://openalex.org/W3015737366","https://openalex.org/W3172565186","https://openalex.org/W4213291706","https://openalex.org/W4221061044","https://openalex.org/W4285214656","https://openalex.org/W4285429071","https://openalex.org/W4285504014","https://openalex.org/W4296338881","https://openalex.org/W4318604915","https://openalex.org/W4321782160","https://openalex.org/W4402622900"],"related_works":[],"abstract_inverted_index":{"High-performance":[0],"computing":[1],"faces":[2],"rising":[3],"core":[4],"counts,":[5],"increasing":[6],"heterogeneity,":[7],"and":[8,17,29,52,59,81,94,99,105,114,121,132],"growing":[9],"memory":[10,28,58,98],"bandwidth.":[11],"These":[12],"trends":[13],"complicate":[14],"programmability,":[15],"portability,":[16],"scalability,":[18],"while":[19],"traditional":[20],"MPI":[21,90],"+":[22,91],"OpenMP":[23,38],"struggles":[24],"with":[25,41],"distributed":[26],"GPU":[27,62],"portable":[30,73],"performance.":[31],"We":[32],"present":[33],"DiOMP-Offloading,":[34],"a":[35,42,72,128],"framework":[36],"unifying":[37],"target":[39],"offloading":[40],"Partitioned":[43],"Global":[44],"Address":[45],"Space":[46],"(PGAS)":[47],"model.":[48],"Built":[49],"on":[50,108],"LLVM-OpenMP":[51],"GASNet-EX,":[53],"it":[54],"centrally":[55],"manages":[56],"global":[57],"supports":[60],"symmetric/asymmetric":[61],"allocations,":[63],"enabling":[64],"remote":[65],"put/get":[66],"operations.":[67],"DiOMP":[68,102],"also":[69],"integrates":[70],"OMPCCL,":[71],"device-side":[74],"collective":[75],"layer":[76],"that":[77,125],"harmonizes":[78],"allocation":[79],"lifecycles":[80],"address":[82],"translation":[83],"across":[84],"vendor":[85],"backends.":[86],"By":[87],"eliminating":[88],"separate":[89],"X":[92],"stacks":[93],"abstracting":[95],"replicated":[96],"device":[97],"communication":[100],"logic,":[101],"improves":[103],"scalability":[104],"programmability.":[106],"Experiments":[107],"large-scale":[109],"NVIDIA":[110],"A100,":[111],"Grace":[112],"Hopper,":[113],"AMD":[115],"MI250X":[116],"platforms":[117],"show":[118],"superior":[119],"micro-benchmark":[120],"application":[122],"performance,":[123],"demonstrating":[124],"DiOMP-Offloading":[126],"offers":[127],"more":[129],"portable,":[130],"scalable,":[131],"efficient":[133],"path":[134],"for":[135],"heterogeneous":[136],"supercomputing.":[137]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-07T00:00:00"}