{"id":"https://openalex.org/W4390993807","doi":"https://doi.org/10.1145/3630138.3630456","title":"CD-Sched: An Automated Scheduling Framework for Accelerating Neural Network Training on Shared Memory CPU-DSP Platforms","display_name":"CD-Sched: An Automated Scheduling Framework for Accelerating Neural Network Training on Shared Memory CPU-DSP Platforms","publication_year":2023,"publication_date":"2023-09-24","ids":{"openalex":"https://openalex.org/W4390993807","doi":"https://doi.org/10.1145/3630138.3630456"},"language":"en","primary_location":{"id":"doi:10.1145/3630138.3630456","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3630138.3630456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Power Communication Computing and Networking Technologies","raw_type":"proceedings-article"},"type":"article","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/A5072269195","display_name":"Yuanyuan Xiao","orcid":"https://orcid.org/0009-0001-5178-5472"},"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":"Yuanyuan Xiao","raw_affiliation_strings":["National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055426388","display_name":"Zhiquan Lai","orcid":"https://orcid.org/0000-0002-3458-4732"},"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":"Zhiquan Lai","raw_affiliation_strings":["National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100440903","display_name":"Dongsheng Li","orcid":"https://orcid.org/0000-0001-9743-2034"},"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 Processing, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Parallel and Distributed Processing, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5072269195"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18779741,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7823065519332886},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.7550462484359741},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5999180674552917},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5941882133483887},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5326138734817505},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4847821593284607},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4672033190727234},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.37992286682128906},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2094414234161377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16737064719200134},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07814785838127136}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7823065519332886},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.7550462484359741},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5999180674552917},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5941882133483887},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5326138734817505},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4847821593284607},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4672033190727234},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.37992286682128906},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2094414234161377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16737064719200134},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07814785838127136},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3630138.3630456","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3630138.3630456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Power Communication Computing and Networking Technologies","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2106562406","https://openalex.org/W2618530766","https://openalex.org/W2921704024","https://openalex.org/W3147109109","https://openalex.org/W4306178406","https://openalex.org/W6675771560"],"related_works":["https://openalex.org/W2390348052","https://openalex.org/W2065566231","https://openalex.org/W2390600871","https://openalex.org/W2363399630","https://openalex.org/W4231775656","https://openalex.org/W2148867666","https://openalex.org/W2074772664","https://openalex.org/W2046435967","https://openalex.org/W2319687164","https://openalex.org/W2379188611"],"abstract_inverted_index":{"DSP":[0],"holds":[1],"significant":[2],"potential":[3],"for":[4],"important":[5],"applications":[6],"in":[7],"Deep":[8],"Neural":[9],"Networks.":[10],"However,":[11],"there":[12],"is":[13],"currently":[14],"a":[15],"lack":[16],"of":[17,43,55,68,78,97],"research":[18],"focused":[19],"on":[20,45],"shared-memory":[21],"CPU-DSP":[22],"heterogeneous":[23],"chips.":[24],"This":[25,62],"paper":[26],"proposes":[27],"CD-Sched,":[28],"an":[29,94],"automated":[30],"scheduling":[31,63],"framework":[32],"that":[33],"aims":[34],"to":[35,57],"address":[36],"this":[37],"gap.":[38],"By":[39],"predicting":[40],"the":[41,53,58,66,74,89],"latency":[42],"operators":[44,56,70],"both":[46],"CPU":[47],"and":[48,71],"DSP,":[49],"CD-Sched":[50,85],"automatically":[51],"schedules":[52],"computation":[54,67],"appropriate":[59],"computing":[60],"device.":[61],"optimization":[64],"accelerates":[65],"individual":[69],"ultimately":[72],"improves":[73],"overall":[75,90],"training":[76,83,91],"time":[77],"neural":[79],"networks.":[80],"In":[81],"end-to-end":[82],"tasks,":[84],"can":[86],"significantly":[87],"reduce":[88],"time,":[92],"with":[93],"average":[95],"reduction":[96],"approximately":[98],"10.77%.":[99]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}