{"id":"https://openalex.org/W4395064757","doi":"https://doi.org/10.1145/3626203.3670561","title":"Automatic BLAS Offloading on Unified Memory Architecture: A Study on NVIDIA Grace-Hopper","display_name":"Automatic BLAS Offloading on Unified Memory Architecture: A Study on NVIDIA Grace-Hopper","publication_year":2024,"publication_date":"2024-07-17","ids":{"openalex":"https://openalex.org/W4395064757","doi":"https://doi.org/10.1145/3626203.3670561"},"language":"en","primary_location":{"id":"doi:10.1145/3626203.3670561","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626203.3670561","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing 2024: Human Powered Computing","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2404.13195","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Junjie Li","orcid":"https://orcid.org/0000-0002-1051-5927"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Junjie Li","raw_affiliation_strings":["Texas Advanced Computing Center, The University of Texas at Austin, USA"],"affiliations":[{"raw_affiliation_string":"Texas Advanced Computing Center, The University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018692017","display_name":"Yinzhi Wang","orcid":"https://orcid.org/0000-0001-8505-0223"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yinzhi Wang","raw_affiliation_strings":["Texas Advanced Computing Center, The University of Texas at Austin, USA"],"affiliations":[{"raw_affiliation_string":"Texas Advanced Computing Center, The University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiao Liang","orcid":"https://orcid.org/0000-0002-7882-3571"},"institutions":[{"id":"https://openalex.org/I35765314","display_name":"Pittsburgh Supercomputing Center","ror":"https://ror.org/04tac1482","country_code":"US","type":"facility","lineage":["https://openalex.org/I35765314"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Liang","raw_affiliation_strings":["Pittsburgh Supercomputing Center, Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Pittsburgh Supercomputing Center, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I35765314","https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":null,"display_name":"Hang Liu","orcid":"https://orcid.org/0000-0002-3486-7863"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hang Liu","raw_affiliation_strings":["Texas Advanced Computing Center, The University of Texas at Austin, USA"],"affiliations":[{"raw_affiliation_string":"Texas Advanced Computing Center, The University of Texas at Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":1.7149,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84539717,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.920799970626831,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.920799970626831,"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/T11478","display_name":"Caching and Content Delivery","score":0.914900004863739,"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/T14067","display_name":"Cloud Computing and Remote Desktop Technologies","score":0.9101999998092651,"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/computer-science","display_name":"Computer science","score":0.6660341024398804},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6414083242416382},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.5518426299095154},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4899448752403259},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4191584289073944},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.32265061140060425},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.07471340894699097}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6660341024398804},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6414083242416382},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.5518426299095154},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4899448752403259},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4191584289073944},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.32265061140060425},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.07471340894699097},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3626203.3670561","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3626203.3670561","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Practice and Experience in Advanced Research Computing 2024: Human Powered Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2404.13195","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.13195","pdf_url":"https://arxiv.org/pdf/2404.13195","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2404.13195","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.13195","pdf_url":"https://arxiv.org/pdf/2404.13195","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G2587327834","display_name":null,"funder_award_id":"OAC-1854828","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2738246091","display_name":null,"funder_award_id":"OAC-2139536","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3023375744","display_name":null,"funder_award_id":"2139536","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5271487896","display_name":null,"funder_award_id":"1854828","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6508124865","display_name":null,"funder_award_id":"OAC-2402542","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6598054934","display_name":"OAC Core: Cost-Adaptive Monitoring and Real-Time Tuning at Function-Level","funder_award_id":"2402542","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6755165505","display_name":null,"funder_award_id":"award","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4395064757.pdf","grobid_xml":"https://content.openalex.org/works/W4395064757.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W1985095956","https://openalex.org/W2006326929","https://openalex.org/W2160919049","https://openalex.org/W3023479823","https://openalex.org/W4388581248"],"related_works":["https://openalex.org/W2418291489","https://openalex.org/W2068121105","https://openalex.org/W3096519538","https://openalex.org/W2744747300","https://openalex.org/W4241166160","https://openalex.org/W2384826897","https://openalex.org/W1997466117","https://openalex.org/W2588198209","https://openalex.org/W1909006023","https://openalex.org/W2038503502"],"abstract_inverted_index":{"Porting":[0],"codes":[1],"to":[2,27],"GPU":[3,104],"often":[4,23],"requires":[5],"major":[6],"efforts.":[7],"While":[8],"several":[9],"tools":[10],"exist":[11],"for":[12,70,84,106],"automatically":[13],"offload":[14,105],"numerical":[15],"libraries":[16],"such":[17],"as":[18],"BLAS":[19,86,107],"and":[20,55,73,101],"LAPACK,":[21],"they":[22],"prove":[24],"impractical":[25],"due":[26],"the":[28,88,91],"high":[29,44,92],"cost":[30],"of":[31,49],"mandatory":[32],"data":[33],"transfer.":[34],"The":[35,116],"new":[36,68,82],"unified":[37],"memory":[38,47,51],"architecture":[39],"in":[40,61,99],"NVIDIA":[41],"Grace-Hopper":[42],"allows":[43],"bandwidth":[45],"cache-coherent":[46],"access":[48],"all":[50],"from":[52],"both":[53],"CPU":[54],"GPU,":[56],"potentially":[57],"eliminating":[58],"bottleneck":[59],"faced":[60],"conventional":[62],"architecture.":[63],"This":[64],"breakthrough":[65],"opens":[66],"up":[67],"avenues":[69],"application":[71],"development":[72],"porting":[74],"strategies.":[75],"In":[76],"this":[77],"study,":[78],"we":[79],"introduce":[80],"a":[81],"tool":[83,89,117],"automatic":[85],"offload,":[87],"leverages":[90],"speed":[93],"cache":[94],"coherent":[95],"NVLink":[96],"C2C":[97],"interconnect":[98],"Grace-Hopper,":[100],"enables":[102],"performant":[103],"heavy":[108],"applications":[109],"with":[110],"no":[111],"code":[112],"changes":[113],"or":[114,124],"recompilation.":[115],"was":[118],"tested":[119],"on":[120],"two":[121],"quantum":[122],"chemistry":[123],"physics":[125],"codes,":[126],"great":[127],"performance":[128],"benefits":[129],"were":[130],"observed.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
