{"id":"https://openalex.org/W7163559042","doi":"https://doi.org/10.23919/date69613.2026.11539577","title":"Dolphium: Co-Optimizing Quantization Dataflow and Paradigms on Poly-Hierarchical NPUs","display_name":"Dolphium: Co-Optimizing Quantization Dataflow and Paradigms on Poly-Hierarchical NPUs","publication_year":2026,"publication_date":"2026-04-20","ids":{"openalex":"https://openalex.org/W7163559042","doi":"https://doi.org/10.23919/date69613.2026.11539577"},"language":null,"primary_location":{"id":"doi:10.23919/date69613.2026.11539577","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date69613.2026.11539577","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 Design, Automation & Test in Europe Conference (DATE)","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/A5025127147","display_name":"Xiuping Cui","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiuping Cui","raw_affiliation_strings":["Peking University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101928924","display_name":"Chengrui Zhang","orcid":"https://orcid.org/0009-0002-5424-4898"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengrui Zhang","raw_affiliation_strings":["Peking University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137866137","display_name":"Xiang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Chen","raw_affiliation_strings":["Peking University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136397214","display_name":"Y Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Eric Liang","raw_affiliation_strings":["Peking University,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.3301999866962433,"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":0.3301999866962433,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.08079999685287476,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.0544000007212162,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.46129998564720154},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4291999936103821},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.24889999628067017},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.2362000048160553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6248999834060669},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.46129998564720154},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4291999936103821},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42489999532699585},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35429999232292175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3172999918460846},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.24889999628067017},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24050000309944153},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2362000048160553},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.2345999926328659}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date69613.2026.11539577","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date69613.2026.11539577","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 Design, Automation & Test in Europe Conference (DATE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2783538964","https://openalex.org/W2940862705","https://openalex.org/W2980104813","https://openalex.org/W2980200167","https://openalex.org/W2998617917","https://openalex.org/W3012249773","https://openalex.org/W3157657667","https://openalex.org/W3187788856","https://openalex.org/W4253012315","https://openalex.org/W4281932226","https://openalex.org/W4360831828","https://openalex.org/W4380874786","https://openalex.org/W4380881063","https://openalex.org/W4389491877","https://openalex.org/W4395106477","https://openalex.org/W4404133524","https://openalex.org/W4408902671","https://openalex.org/W4410553236","https://openalex.org/W4410582506"],"related_works":[],"abstract_inverted_index":{"Poly-hierarchical":[0],"NPUs":[1,112],"integrate":[2],"distributed":[3],"memory":[4,28],"modules":[5],"with":[6,89],"heterogeneous":[7],"computation":[8,37,60],"units,":[9],"posing":[10],"significant":[11],"challenges":[12],"for":[13],"mapping":[14,46,95],"quantized":[15],"operators.":[16],"The":[17],"difficulty":[18],"arises":[19],"from":[20,48],"the":[21,45,83,90,101],"need":[22],"to":[23,31,35,50,81],"coordinate":[24],"data":[25],"transfers":[26],"across":[27],"hierarchies":[29],"and":[30,65,70],"assign":[32],"diverse":[33],"operations":[34],"suitable":[36],"units.":[38],"In":[39],"this":[40,74],"work,":[41],"we":[42,76],"systematically":[43],"construct":[44],"space":[47],"quantization":[49,79,86,92,103],"dataflows":[51,80],"by":[52],"addressing":[53],"three":[54],"key":[55],"aspects:":[56],"generation":[57],"of":[58,67,85],"NPU-friendly":[59],"flows,":[61],"integrated":[62],"operation\u2013data":[63],"co-mapping,":[64],"determination":[66],"transfer":[68],"granularity":[69],"frequency.":[71],"Building":[72],"on":[73,111],"foundation,":[75],"further":[77],"exploit":[78],"guide":[82],"selection":[84],"paradigms.":[87],"Compared":[88],"state-of-the-art":[91],"compiler,":[93],"our":[94],"achieves":[96],"a":[97],"1.67\u20132.03\u00d7":[98],"speedup.":[99],"Moreover,":[100],"selected":[102],"paradigms":[104],"deliver":[105],"an":[106],"average":[107],"2.18\u00d7":[108],"efficiency":[109],"improvement":[110],"without":[113],"accuracy":[114],"loss.":[115]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-06-05T00:00:00"}