{"id":"https://openalex.org/W4408029634","doi":"https://doi.org/10.1145/3710848.3710857","title":"Magneto: Accelerating Parallel Structures in DNNs via Co-Optimization of Operators","display_name":"Magneto: Accelerating Parallel Structures in DNNs via Co-Optimization of Operators","publication_year":2025,"publication_date":"2025-02-28","ids":{"openalex":"https://openalex.org/W4408029634","doi":"https://doi.org/10.1145/3710848.3710857"},"language":"en","primary_location":{"id":"doi:10.1145/3710848.3710857","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3710848.3710857","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3710848.3710857","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3710848.3710857","any_repository_has_fulltext":null},"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":false,"raw_author_name":"Zhanyuan Di","raw_affiliation_strings":["SKLP, Institute of Computing Technology, CAS, University of Chinese, Academy of Sciences"],"raw_orcid":"https://orcid.org/0000-0003-2716-5051","affiliations":[{"raw_affiliation_string":"SKLP, Institute of Computing Technology, CAS, University of Chinese, Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","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":["SKLP, Institute of Computing Technology, CAS"],"raw_orcid":"https://orcid.org/0009-0009-4940-5598","affiliations":[{"raw_affiliation_string":"SKLP, Institute of Computing Technology, CAS","institution_ids":["https://openalex.org/I4210090176"]}]},{"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"]},{"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":"Ziyi Ren","raw_affiliation_strings":["SKLP, Institute of Computing Technology, CAS, University of Chinese, Academy of Sciences"],"raw_orcid":"https://orcid.org/0009-0005-5821-1163","affiliations":[{"raw_affiliation_string":"SKLP, Institute of Computing Technology, CAS, University of Chinese, Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","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":["SKLP, Institute of Computing Technology, CAS, University of Chinese, Academy of Sciences"],"raw_orcid":"https://orcid.org/0000-0002-9678-7228","affiliations":[{"raw_affiliation_string":"SKLP, Institute of Computing Technology, CAS, University of Chinese, Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","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/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":["SKLP, Institute of Computing Technology, CAS"],"raw_orcid":"https://orcid.org/0000-0001-5422-4497","affiliations":[{"raw_affiliation_string":"SKLP, 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":["SKLP, Institute of Computing Technology, CAS"],"raw_orcid":"https://orcid.org/0000-0002-6361-5948","affiliations":[{"raw_affiliation_string":"SKLP, 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":["SKLP, Institute of Computing Technology, CAS"],"raw_orcid":"https://orcid.org/0000-0002-1953-1392","affiliations":[{"raw_affiliation_string":"SKLP, Institute of Computing Technology, CAS","institution_ids":["https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02546823,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"563","last_page":"565"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9929999709129333,"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":0.9929999709129333,"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.972000002861023,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.957099974155426,"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/magneto","display_name":"Magneto","score":0.6255922317504883},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5968607068061829},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5104490518569946},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.18891945481300354},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10237452387809753}],"concepts":[{"id":"https://openalex.org/C171636128","wikidata":"https://www.wikidata.org/wiki/Q1307177","display_name":"Magneto","level":3,"score":0.6255922317504883},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5968607068061829},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5104490518569946},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.18891945481300354},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10237452387809753},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3710848.3710857","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3710848.3710857","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3710848.3710857","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3710848.3710857","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3710848.3710857","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3710848.3710857","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G127019057","display_name":null,"funder_award_id":"Z211100002121143, 20220484217","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G6443105322","display_name":null,"funder_award_id":"2021YFB0300202","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G685717211","display_name":null,"funder_award_id":"62102396, 62032023, T2125013","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4408029634.pdf"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1689711448","https://openalex.org/W2183341477","https://openalex.org/W2549139847","https://openalex.org/W2809290718","https://openalex.org/W2964081807","https://openalex.org/W3119866685","https://openalex.org/W3170073102","https://openalex.org/W3184439416","https://openalex.org/W3191654415","https://openalex.org/W4220818654","https://openalex.org/W4287391717"],"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":{"Deep":[0],"neural":[1],"networks":[2],"(DNNs)":[3],"increasingly":[4],"rely":[5],"on":[6],"parallel":[7,29,48,56,63],"structures":[8,25,49],"to":[9,27,46],"enhance":[10],"performance":[11],"and":[12,32,66,86,93],"efficiency.":[13],"However,":[14],"existing":[15],"machine":[16],"learning":[17],"compilers":[18],"(MLCs)":[19],"face":[20],"challenges":[21],"in":[22,50],"optimizing":[23],"these":[24],"due":[26],"limited":[28],"fusion":[30,65],"scopes":[31],"insufficient":[33],"consideration":[34],"of":[35,55,62,91],"intra-operator":[36],"information.":[37],"This":[38],"paper":[39],"introduces":[40],"Magneto,":[41],"a":[42,68],"novel":[43],"framework":[44],"designed":[45],"accelerate":[47],"DNNs":[51],"through":[52],"the":[53,60],"co-optimization":[54],"operators.":[57],"By":[58],"expanding":[59],"scope":[61],"operator":[64],"introducing":[67],"dedicated":[69],"co-tuning":[70],"algorithm,":[71],"Magneto":[72,82],"unlocks":[73],"new":[74],"opportunities":[75],"for":[76],"co-optimization.":[77],"Experimental":[78],"results":[79],"demonstrate":[80],"that":[81],"outperforms":[83],"NVIDIA":[84],"TensorRT":[85],"AMD":[87],"MIGraphX,":[88],"achieving":[89],"speedups":[90],"3.02\u00d7":[92],"4.19\u00d7,":[94],"respectively.":[95]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
