{"id":"https://openalex.org/W7204036558","doi":"https://doi.org/10.1007/978-981-92-4805-6_25","title":"DOA: Dataflow Optimization for Attention on Multi-core DSPs with Three-Level Memory Hierarchy","display_name":"DOA: Dataflow Optimization for Attention on Multi-core DSPs with Three-Level Memory Hierarchy","publication_year":2026,"publication_date":"2026-08-23","ids":{"openalex":"https://openalex.org/W7204036558","doi":"https://doi.org/10.1007/978-981-92-4805-6_25"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-92-4805-6_25","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-92-4805-6_25","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"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/A5147203170","display_name":"Shengwei Li","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengwei Li","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147882051","display_name":"Zhiquan Lai","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhiquan Lai","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059418859","display_name":"Shuai Xu","orcid":"https://orcid.org/0000-0002-4687-506X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Xu","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147905558","display_name":"Shun Ouyang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shun Ouyang","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147879239","display_name":"Han Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Xiao","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147880627","display_name":"Zhaoning Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoning Zhang","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101632859","display_name":"Menghan Jia","orcid":"https://orcid.org/0000-0002-5639-7882"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Menghan Jia","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070555846","display_name":"Huayou Su","orcid":"https://orcid.org/0000-0002-3587-0917"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huayou Su","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5147902634","display_name":"Dongsheng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongsheng Li","raw_affiliation_strings":["National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Computing, College of Computer Science and Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5147882051"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"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":"375","last_page":"389"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.9089000225067139},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6766999959945679},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.6064000129699707},{"id":"https://openalex.org/keywords/interleaved-memory","display_name":"Interleaved memory","score":0.5613999962806702},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5435000061988831},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4921000003814697},{"id":"https://openalex.org/keywords/flat-memory-model","display_name":"Flat memory model","score":0.48820000886917114},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.4262000024318695},{"id":"https://openalex.org/keywords/memory-map","display_name":"Memory map","score":0.413100004196167},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.4117000102996826}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9199000000953674},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.9089000225067139},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6773999929428101},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6766999959945679},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.6064000129699707},{"id":"https://openalex.org/C63511323","wikidata":"https://www.wikidata.org/wiki/Q908936","display_name":"Interleaved memory","level":4,"score":0.5613999962806702},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5435000061988831},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4921000003814697},{"id":"https://openalex.org/C57863822","wikidata":"https://www.wikidata.org/wiki/Q905488","display_name":"Flat memory model","level":4,"score":0.48820000886917114},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C74426580","wikidata":"https://www.wikidata.org/wiki/Q719484","display_name":"Memory map","level":3,"score":0.413100004196167},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.4117000102996826},{"id":"https://openalex.org/C3720319","wikidata":"https://www.wikidata.org/wiki/Q5015937","display_name":"Cache-only memory architecture","level":5,"score":0.40939998626708984},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4000999927520752},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C51290061","wikidata":"https://www.wikidata.org/wiki/Q1936765","display_name":"Uniform memory access","level":4,"score":0.35740000009536743},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.3357999920845032},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.3059999942779541},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C176727019","wikidata":"https://www.wikidata.org/wiki/Q1172415","display_name":"Dataflow architecture","level":3,"score":0.2867000102996826},{"id":"https://openalex.org/C153247305","wikidata":"https://www.wikidata.org/wiki/Q835713","display_name":"Memory address","level":3,"score":0.2815999984741211},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C201374245","wikidata":"https://www.wikidata.org/wiki/Q104534","display_name":"Digital subscriber line","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C93446704","wikidata":"https://www.wikidata.org/wiki/Q449328","display_name":"Registered memory","level":3,"score":0.2687999904155731},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C171675096","wikidata":"https://www.wikidata.org/wiki/Q1143380","display_name":"Extended memory","level":4,"score":0.26660001277923584},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.26420000195503235},{"id":"https://openalex.org/C82687282","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Auxiliary memory","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C2779602883","wikidata":"https://www.wikidata.org/wiki/Q15544750","display_name":"Memory architecture","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C123745756","wikidata":"https://www.wikidata.org/wiki/Q1665949","display_name":"Interconnection","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-92-4805-6_25","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-92-4805-6_25","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2005881934","https://openalex.org/W3012514909","https://openalex.org/W3204998121","https://openalex.org/W3205192296","https://openalex.org/W3205803342","https://openalex.org/W4214686755","https://openalex.org/W4289646389","https://openalex.org/W4318541578","https://openalex.org/W4327694855","https://openalex.org/W4385571616","https://openalex.org/W4389518760","https://openalex.org/W4399452094","https://openalex.org/W4400411561","https://openalex.org/W4401977362","https://openalex.org/W4405440297","https://openalex.org/W4407784164","https://openalex.org/W4414281281","https://openalex.org/W4415797154","https://openalex.org/W7128703968","https://openalex.org/W7133227460"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-08-24T07:32:12.397491","created_date":"2026-08-24T00:00:00"}
