{"id":"https://openalex.org/W4413146919","doi":"https://doi.org/10.1109/ipdpsw66978.2025.00216","title":"Parallel Scan on Ascend AI Accelerators","display_name":"Parallel Scan on Ascend AI Accelerators","publication_year":2025,"publication_date":"2025-06-03","ids":{"openalex":"https://openalex.org/W4413146919","doi":"https://doi.org/10.1109/ipdpsw66978.2025.00216"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw66978.2025.00216","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw66978.2025.00216","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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.15112","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119282103","display_name":"Bart\u0142omiej Wr\u00f3blewski","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bart\u0142omiej Wr\u00f3blewski","raw_affiliation_strings":["Huawei Zurich Research Center,Computing Systems Lab,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Zurich Research Center,Computing Systems Lab,Zurich,Switzerland","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119282104","display_name":"Gioele Gottardo","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gioele Gottardo","raw_affiliation_strings":["Huawei Zurich Research Center,Computing Systems Lab,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Zurich Research Center,Computing Systems Lab,Zurich,Switzerland","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5119282105","display_name":"Anastasios Zouzias","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anastasios Zouzias","raw_affiliation_strings":["Huawei Zurich Research Center,Computing Systems Lab,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Zurich Research Center,Computing Systems Lab,Zurich,Switzerland","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5119282103"],"corresponding_institution_ids":["https://openalex.org/I2250955327"],"apc_list":null,"apc_paid":null,"fwci":4.2605,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.94030004,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1290","last_page":"1292"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.5928000211715698,"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":0.5928000211715698,"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":0.7281349897384644},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3807601034641266}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7281349897384644},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3807601034641266}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ipdpsw66978.2025.00216","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw66978.2025.00216","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:arXiv.org:2505.15112","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15112","pdf_url":"https://arxiv.org/pdf/2505.15112","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.15112","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15112","pdf_url":"https://arxiv.org/pdf/2505.15112","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"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":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413146919.pdf","grobid_xml":"https://content.openalex.org/works/W4413146919.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"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],"design":[1],"and":[2,25,48,66],"implement":[3],"parallel":[4,92],"prefix":[5],"sum":[6],"(scan)":[7],"algorithms":[8,40],"using":[9],"Ascend":[10,13],"AI":[11],"accelerators.":[12],"accelerators":[14],"feature":[15,35],"specialized":[16],"computing":[17],"units\u2014the":[18],"cube":[19,53,65],"units":[20,28,68],"for":[21,29,90],"efficient":[22],"matrix":[23,46,88,98],"multiplication":[24],"the":[26,37,52,64,76,95,107],"vector":[27,31,67],"optimized":[30],"operations.":[32],"A":[33],"key":[34],"of":[36,45,69,75,97],"proposed":[38],"scan":[39,58],"is":[41],"their":[42],"extensive":[43],"use":[44],"multiplications":[47,89],"accumulations":[49],"enabled":[50],"by":[51],"unit.We":[54],"present":[55],"a":[56],"multi-core":[57],"algorithm":[59],"that":[60],"fully":[61],"utilizes":[62,87],"both":[63],"Ascend,":[70],"reaching":[71],"up":[72],"to":[73],"37.5%":[74],"theoretical":[77],"memory":[78],"bandwidth.":[79],"In":[80],"addition,":[81],"our":[82],"radix":[83],"sort":[84],"implementation,":[85],"which":[86],"its":[91],"splits,":[93],"highlights":[94],"potential":[96],"engines":[99],"in":[100],"enhancing":[101],"complex":[102],"operations":[103],"(3.3\u00d7":[104],"speedup":[105],"over":[106],"vector-only":[108],"baseline).":[109]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}
