{"id":"https://openalex.org/W4411350627","doi":"https://doi.org/10.1145/3744906","title":"Accelerating Parallel Structures in DNNs via Parallel Fusion and Operator Co-Optimization","display_name":"Accelerating Parallel Structures in DNNs via Parallel Fusion and Operator Co-Optimization","publication_year":2025,"publication_date":"2025-06-16","ids":{"openalex":"https://openalex.org/W4411350627","doi":"https://doi.org/10.1145/3744906"},"language":"en","primary_location":{"id":"doi:10.1145/3744906","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3744906","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1145/3744906","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072178581","display_name":"Zhanyuan Di","orcid":"https://orcid.org/0000-0003-2716-5051"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhanyuan Di","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, CAS","University of Chinese Academy of Sciences"],"raw_orcid":"https://orcid.org/0000-0003-2716-5051","affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, CAS","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035662158","display_name":"Leping Wang","orcid":"https://orcid.org/0009-0009-4940-5598"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leping Wang","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, CAS"],"raw_orcid":"https://orcid.org/0009-0009-4940-5598","affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, CAS","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103571446","display_name":"Zhaojia Ma","orcid":"https://orcid.org/0009-0000-3783-8964"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaojia Ma","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, CAS","University of Chinese Academy of Sciences"],"raw_orcid":"https://orcid.org/0009-0005-4824-9336","affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, CAS","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027464011","display_name":"En Shao","orcid":"https://orcid.org/0000-0002-9678-7228"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"En Shao","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, CAS","University of Chinese Academy of Sciences"],"raw_orcid":"https://orcid.org/0000-0002-9678-7228","affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, CAS","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000546902","display_name":"Jie Zhao","orcid":"https://orcid.org/0000-0003-2303-9736"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhao","raw_affiliation_strings":["Hunan University"],"raw_orcid":"https://orcid.org/0000-0003-2303-9736","affiliations":[{"raw_affiliation_string":"Hunan University","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114084654","display_name":"Ziyi Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyi Ren","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, CAS"],"raw_orcid":"https://orcid.org/0009-0005-5821-1163","affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, CAS","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110303119","display_name":"S.M. Feng","orcid":"https://orcid.org/0000-0002-4682-983X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Feng","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":"https://orcid.org/0000-0002-4682-983X","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063703614","display_name":"Dingwen Tao","orcid":"https://orcid.org/0000-0001-5422-4497"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dingwen Tao","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, CAS"],"raw_orcid":"https://orcid.org/0000-0001-5422-4497","affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, CAS","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006750799","display_name":"Guangming Tan","orcid":"https://orcid.org/0000-0002-6361-5948"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangming Tan","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, CAS"],"raw_orcid":"https://orcid.org/0000-0002-6361-5948","affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, CAS","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101738013","display_name":"Ninghui Sun","orcid":"https://orcid.org/0000-0002-1953-1392"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ninghui Sun","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, CAS"],"raw_orcid":"https://orcid.org/0000-0002-1953-1392","affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, CAS","institution_ids":["https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5072178581"],"corresponding_institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11113021,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"3","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9977999925613403,"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":0.9977999925613403,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9952999949455261,"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"}},{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7837152481079102},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6424819827079773},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.5222269296646118},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.46253159642219543}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7837152481079102},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6424819827079773},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.5222269296646118},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.46253159642219543},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3744906","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3744906","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3744906","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3744906","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2209159086","display_name":null,"funder_award_id":"24ZXKJGX00060","funder_id":"https://openalex.org/F4320336756","funder_display_name":"Tianjin Science and Technology Program"},{"id":"https://openalex.org/G3663037429","display_name":null,"funder_award_id":"62032023, T2125013, T2422007, 62225205, and U24A20235","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336756","display_name":"Tianjin Science and Technology Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1689711448","https://openalex.org/W2183341477","https://openalex.org/W2549139847","https://openalex.org/W2809290718","https://openalex.org/W2905135312","https://openalex.org/W2954698171","https://openalex.org/W2961619211","https://openalex.org/W2964081807","https://openalex.org/W2981758446","https://openalex.org/W3012249773","https://openalex.org/W3037749908","https://openalex.org/W3095319910","https://openalex.org/W3098625345","https://openalex.org/W3112101075","https://openalex.org/W3119866685","https://openalex.org/W3122286897","https://openalex.org/W3136585513","https://openalex.org/W3173358825","https://openalex.org/W3174529902","https://openalex.org/W3184439416","https://openalex.org/W4205983429","https://openalex.org/W4212986322","https://openalex.org/W4251637954","https://openalex.org/W4287391717","https://openalex.org/W4318541538","https://openalex.org/W4408049815","https://openalex.org/W6785429063"],"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":{"Parallel":[0],"structures":[1,28],"have":[2],"become":[3],"a":[4,45,63],"key":[5],"pattern":[6],"in":[7,25,78],"deep":[8],"neural":[9],"networks":[10],"(DNNs),":[11],"offering":[12],"improved":[13],"efficiency":[14],"and":[15,35,61,99,108],"scalability.":[16],"However,":[17],"existing":[18],"machine":[19],"learning":[20],"compilers":[21],"(MLCs)":[22],"face":[23],"challenges":[24,76],"optimizing":[26,79],"these":[27],"due":[29],"to":[30,48,67],"limited":[31],"parallel":[32,54,80],"fusion":[33,59],"scope":[34,60],"insufficient":[36],"analysis":[37],"of":[38,106],"intra-operator":[39],"characteristics.":[40],"This":[41],"article":[42],"introduces":[43],"Magneto,":[44],"framework":[46],"designed":[47],"accelerate":[49],"DNN":[50],"inference":[51],"by":[52],"co-optimizing":[53],"operators.":[55],"Magneto":[56,94],"broadens":[57],"the":[58,74],"incorporates":[62],"specialized":[64],"co-tuning":[65],"algorithm":[66],"optimize":[68],"operators":[69],"jointly.":[70],"Our":[71],"approach":[72],"addresses":[73],"unique":[75],"inherent":[77],"structures,":[81],"enabling":[82],"significant":[83],"performance":[84],"improvements":[85],"across":[86],"various":[87],"hardware":[88],"platforms.":[89],"Experimental":[90],"results":[91],"show":[92],"that":[93],"outperforms":[95],"state-of-the-art":[96],"NVIDIA":[97],"TensorRT":[98],"AMD":[100],"MIGraphX,":[101],"achieving":[102],"geometric":[103],"mean":[104],"speedups":[105],"2.27\u00d7":[107],"2.88\u00d7,":[109],"respectively.":[110]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
