{"id":"https://openalex.org/W4409133366","doi":"https://doi.org/10.1109/hpec62836.2024.10938453","title":"JACC.shared: Leveraging HPC Metaprogramming and Performance Portability for Computations That Use Shared Memory GPUs","display_name":"JACC.shared: Leveraging HPC Metaprogramming and Performance Portability for Computations That Use Shared Memory GPUs","publication_year":2024,"publication_date":"2024-09-23","ids":{"openalex":"https://openalex.org/W4409133366","doi":"https://doi.org/10.1109/hpec62836.2024.10938453"},"language":"en","primary_location":{"id":"doi:10.1109/hpec62836.2024.10938453","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec62836.2024.10938453","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/servlets/purl/2561231","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083524237","display_name":"Pedro Valero\u2010Lara","orcid":"https://orcid.org/0000-0002-1479-4310"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pedro Valero-Lara","raw_affiliation_strings":["Advanced Computing Systems Research Section, Oak Ridge National Laboratory,Oak Ridge,Tennessee,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Computing Systems Research Section, Oak Ridge National Laboratory,Oak Ridge,Tennessee,USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107809692","display_name":"William F. Godoy","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William F. Godoy","raw_affiliation_strings":["Advanced Computing Systems Research Section, Oak Ridge National Laboratory,Oak Ridge,Tennessee,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Computing Systems Research Section, Oak Ridge National Laboratory,Oak Ridge,Tennessee,USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019745966","display_name":"Keita Teranishi","orcid":"https://orcid.org/0000-0001-6647-2690"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keita Teranishi","raw_affiliation_strings":["Advanced Computing Systems Research Section, Oak Ridge National Laboratory,Oak Ridge,Tennessee,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Computing Systems Research Section, Oak Ridge National Laboratory,Oak Ridge,Tennessee,USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112035225","display_name":"Jeffrey S. Vetter","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey S. Vetter","raw_affiliation_strings":["Advanced Computing Systems Research Section, Oak Ridge National Laboratory,Oak Ridge,Tennessee,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Computing Systems Research Section, Oak Ridge National Laboratory,Oak Ridge,Tennessee,USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1289243028"],"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":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9955000281333923,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9955000281333923,"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":0.9927999973297119,"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":0.9904999732971191,"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/software-portability","display_name":"Software portability","score":0.8970848321914673},{"id":"https://openalex.org/keywords/metaprogramming","display_name":"Metaprogramming","score":0.860115647315979},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8536931276321411},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.5717096328735352},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.48960691690444946},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.48325997591018677},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4520667493343353},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.42306947708129883},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.4227285087108612},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.40151774883270264},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.07198306918144226}],"concepts":[{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.8970848321914673},{"id":"https://openalex.org/C35390924","wikidata":"https://www.wikidata.org/wiki/Q661075","display_name":"Metaprogramming","level":2,"score":0.860115647315979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8536931276321411},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.5717096328735352},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.48960691690444946},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.48325997591018677},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4520667493343353},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.42306947708129883},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.4227285087108612},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.40151774883270264},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.07198306918144226}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hpec62836.2024.10938453","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec62836.2024.10938453","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:2561231","is_oa":true,"landing_page_url":"https://www.osti.gov/servlets/purl/2561231","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:2561231","is_oa":true,"landing_page_url":"https://www.osti.gov/servlets/purl/2561231","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2064645013","https://openalex.org/W2071542942","https://openalex.org/W2102959723","https://openalex.org/W2106783315","https://openalex.org/W2401246392","https://openalex.org/W2902409898","https://openalex.org/W2913063451","https://openalex.org/W2996807164","https://openalex.org/W3017059353","https://openalex.org/W3195293013","https://openalex.org/W3195830194","https://openalex.org/W3200743451","https://openalex.org/W4206841102","https://openalex.org/W4308610619","https://openalex.org/W4318711025","https://openalex.org/W6662677552","https://openalex.org/W6679034768","https://openalex.org/W6739575747","https://openalex.org/W6798705879","https://openalex.org/W6846468022","https://openalex.org/W6849463651","https://openalex.org/W6850663806","https://openalex.org/W6852185813","https://openalex.org/W6858373767"],"related_works":["https://openalex.org/W107105315","https://openalex.org/W1584537303","https://openalex.org/W2349791858","https://openalex.org/W4317765321","https://openalex.org/W1578381328","https://openalex.org/W2169907249","https://openalex.org/W254684032","https://openalex.org/W1824582190","https://openalex.org/W2388026393","https://openalex.org/W1848192231"],"abstract_inverted_index":{"In":[0],"this":[1,80],"work,":[2],"we":[3],"present":[4],"JACC.shared,":[5],"a":[6,54,70,159],"new":[7,29],"feature":[8,30],"of":[9,21,41,115,121,136,148],"Julia":[10,26],"for":[11,56,64,76,173],"ACCelerators":[12],"(JACC),":[13],"which":[14],"is":[15],"the":[16,22,36,65,116,151,167],"performanceportable":[17],"and":[18,24,73,82,91,98,127,162,165,170,177],"metaprogramming":[19],"model":[20],"just-in-time":[23],"LLVM-based":[25],"language.":[27],"This":[28],"allows":[31],"JACC":[32],"applications":[33],"to":[34,78,104,138,150],"leverage":[35],"high-performance":[37],"computing":[38],"(HPC)":[39],"capabilities":[40,172],"high-bandwidth,":[42,48],"on-chip":[43],"GPU":[44,110],"memory.":[45],"Historically,":[46],"exploiting":[47],"shared-memory":[49],"GPUs":[50],"has":[51],"not":[52],"been":[53,102],"priority":[55],"high-level":[57],"programming":[58,168],"solutions.":[59],"JACC.shared":[60,106],"covers":[61],"that":[62],"gap":[63],"first":[66],"time,":[67],"thereby":[68],"providing":[69,155],"highlevel,":[71],"portable,":[72,161],"easy-to-use":[74],"solution":[75],"programmers":[77],"exploit":[79],"memory":[81],"supporting":[83],"all":[84],"current":[85],"major":[86],"accelerator":[87],"architectures.":[88],"Well-known":[89],"HPC":[90],"AI":[92,99],"workloads,":[93],"such":[94],"as":[95],"multi/hyperspectral":[96],"imaging":[97],"convolutions,":[100],"have":[101],"used":[103],"evaluate":[105],"on":[107],"two":[108],"exascale":[109],"architectures":[111],"hosted":[112],"by":[113,143],"some":[114],"most":[117],"powerful":[118],"US":[119],"Department":[120],"Energy":[122],"supercomputers:":[123],"Perlmutter":[124],"(NVIDIA":[125],"A100)":[126],"Frontier":[128],"(AMD":[129],"MI250X).":[130],"The":[131],"performance":[132],"evaluation":[133],"reports":[134],"speedup":[135],"up":[137],"<tex":[139],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[140],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$3.5":[141],"\\times$</tex>":[142],"adding":[144],"only":[145],"one":[146],"line":[147],"code":[149],"base":[152],"codes,":[153],"thus":[154],"important":[156],"accelerators":[157],"in":[158],"simple,":[160],"transparent":[163],"way":[164],"elevating":[166],"productivity":[169],"performance-portability":[171],"Julia/JACC":[174],"HPC,":[175],"AI,":[176],"scientific":[178],"applications.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}