{"id":"https://openalex.org/W4412480901","doi":"https://doi.org/10.1145/3694906.3743326","title":"Decoupled Fallback: A Portable Single-Pass GPU Scan","display_name":"Decoupled Fallback: A Portable Single-Pass GPU Scan","publication_year":2025,"publication_date":"2025-07-16","ids":{"openalex":"https://openalex.org/W4412480901","doi":"https://doi.org/10.1145/3694906.3743326"},"language":"en","primary_location":{"id":"doi:10.1145/3694906.3743326","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3694906.3743326","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3694906.3743326","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th ACM Symposium on Parallelism in Algorithms and Architectures","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3694906.3743326","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060707561","display_name":"Tucker Smith","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Thomas Smith","raw_affiliation_strings":["Google, USA"],"raw_orcid":"https://orcid.org/0009-0005-3612-865X","affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026296435","display_name":"Raph Levien","orcid":"https://orcid.org/0000-0003-4592-3389"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raph Levien","raw_affiliation_strings":["Google, USA"],"raw_orcid":"https://orcid.org/0000-0003-4592-3389","affiliations":[{"raw_affiliation_string":"Google, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028662746","display_name":"John D. Owens","orcid":"https://orcid.org/0000-0001-6582-8237"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John D. Owens","raw_affiliation_strings":["University of California, Davis, USA and Google"],"raw_orcid":"https://orcid.org/0000-0001-6582-8237","affiliations":[{"raw_affiliation_string":"University of California, Davis, USA and Google","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5060707561"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":2.1546,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86724936,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"255","last_page":"268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9987000226974487,"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":0.6872041821479797},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4364226460456848},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3616945147514343}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6872041821479797},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4364226460456848},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3616945147514343}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3694906.3743326","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3694906.3743326","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3694906.3743326","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th ACM Symposium on Parallelism in Algorithms and Architectures","raw_type":"proceedings-article"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt0bk9z4bt","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/0bk9z4bt","pdf_url":"https://escholarship.org/content/qt0bk9z4bt/qt0bk9z4bt.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"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":"article"},{"id":"pmh:ark:/13030/qt0bk9z4bt","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1145/3694906.3743326","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3694906.3743326","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3694906.3743326","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 37th ACM Symposium on Parallelism in Algorithms and Architectures","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.75}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412480901.pdf","grobid_xml":"https://content.openalex.org/works/W4412480901.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1541061791","https://openalex.org/W1582324226","https://openalex.org/W1780333029","https://openalex.org/W1877513498","https://openalex.org/W1963965124","https://openalex.org/W1964704819","https://openalex.org/W1972418517","https://openalex.org/W1979306010","https://openalex.org/W1999655384","https://openalex.org/W2019708326","https://openalex.org/W2082248799","https://openalex.org/W2087977509","https://openalex.org/W2119588908","https://openalex.org/W2121843607","https://openalex.org/W2128853364","https://openalex.org/W2130931788","https://openalex.org/W2134427337","https://openalex.org/W2143462372","https://openalex.org/W2155503253","https://openalex.org/W2168543008","https://openalex.org/W2886199004","https://openalex.org/W3138798301","https://openalex.org/W3200544313","https://openalex.org/W3203575865","https://openalex.org/W4249127270","https://openalex.org/W4318541674","https://openalex.org/W6907659760","https://openalex.org/W6962870248"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"We":[0,88],"present":[1],"Decoupled":[2,94],"Fallback,":[3],"a":[4,26,47],"work-stealing":[5],"method":[6],"that":[7,33,109],"enables":[8],"single-pass":[9],"Chained":[10,31],"Scans":[11,32],"to":[12,106],"run":[13],"on":[14,37],"hardware":[15],"without":[16],"forward-progress":[17],"guarantees":[18],"(FPG)":[19],"while":[20],"avoiding":[21],"starvation.":[22],"Additionally,":[23],"we":[24],"introduce":[25],"tile":[27],"state":[28],"representation":[29],"for":[30,43,62],"does":[34],"not":[35],"rely":[36],"64-bit":[38],"atomics":[39],"or":[40],"memory":[41],"barriers":[42],"correctness,":[44],"along":[45],"with":[46],"subgroup-size-agnostic":[48],"intra-workgroup":[49],"implementation.":[50],"On":[51],"FPG-lacking":[52],"devices---Apple":[53],"M1":[54],"Max":[55],"and":[56,75],"M3---Decoupled":[57],"Fallback":[58,95],"achieves":[59],"near-Memcpy":[60],"speeds":[61],"inclusive":[63],"prefix":[64],"sum":[65],"using":[66],"the":[67,72,77,84,91],"native":[68],"Dawn":[69],"implementation":[70],"of":[71,93,104],"WebGPU":[73],"standard,":[74],"approaches":[76],"full":[78],"theoretically":[79],"expected":[80],"50%":[81],"speedup":[82],"over":[83,114],"slower":[85],"Reduce-then-Scan":[86,115],"approach.":[87],"further":[89],"demonstrate":[90],"resilience":[92],"against":[96],"unfair":[97],"schedulers":[98],"by":[99],"simulating":[100],"blocking":[101],"at":[102],"rates":[103],"up":[105],"50%,":[107],"showing":[108],"it":[110],"maintains":[111],"superior":[112],"performance":[113],"even":[116],"under":[117],"extreme":[118],"contention.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}