{"id":"https://openalex.org/W4403210793","doi":"https://doi.org/10.1109/tc.2024.3475575","title":"Efficient and Fast High-Performance Library Generation for Deep Learning Accelerators","display_name":"Efficient and Fast High-Performance Library Generation for Deep Learning Accelerators","publication_year":2024,"publication_date":"2024-10-08","ids":{"openalex":"https://openalex.org/W4403210793","doi":"https://doi.org/10.1109/tc.2024.3475575"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2024.3475575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2024.3475575","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-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/A5115444883","display_name":"Jun Bi","orcid":"https://orcid.org/0000-0001-9956-7039"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":"Jun Bi","raw_affiliation_strings":["State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9956-7039","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012591589","display_name":"Yuanbo Wen","orcid":"https://orcid.org/0000-0002-7775-2724"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":"Yuanbo Wen","raw_affiliation_strings":["State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7775-2724","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063860382","display_name":"Xiaqing Li","orcid":"https://orcid.org/0000-0002-7748-7967"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":"Xiaqing Li","raw_affiliation_strings":["State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7748-7967","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110580984","display_name":"Yongwei Zhao","orcid":"https://orcid.org/0000-0002-5503-4457"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":"Yongwei Zhao","raw_affiliation_strings":["State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5503-4457","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115444895","display_name":"Yuxuan Guo","orcid":"https://orcid.org/0000-0003-1462-8336"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxuan Guo","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0003-1462-8336","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000779411","display_name":"Enshuai Zhou","orcid":"https://orcid.org/0000-0001-6434-8602"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enshuai Zhou","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0001-6434-8602","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101964036","display_name":"Xing Hu","orcid":"https://orcid.org/0000-0002-9979-0561"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":"Xing Hu","raw_affiliation_strings":["State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9979-0561","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056949827","display_name":"Zidong Du","orcid":"https://orcid.org/0000-0002-7603-4210"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":"Zidong Du","raw_affiliation_strings":["State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7603-4210","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100435321","display_name":"Ling Li","orcid":"https://orcid.org/0000-0001-8877-9052"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling Li","raw_affiliation_strings":["Intelligent Software Research Center, Institute of Software, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8877-9052","affiliations":[{"raw_affiliation_string":"Intelligent Software Research Center, Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040104068","display_name":"Huaping Chen","orcid":"https://orcid.org/0000-0002-2058-7086"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaping Chen","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, China"],"raw_orcid":"https://orcid.org/0000-0002-2058-7086","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115444894","display_name":"Tianshi Chen","orcid":"https://orcid.org/0000-0002-7601-0753"},"institutions":[{"id":"https://openalex.org/I4401726770","display_name":"Cambricon (China)","ror":"https://ror.org/00r2rga43","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726770"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianshi Chen","raw_affiliation_strings":["Cambricon Technologies, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7601-0753","affiliations":[{"raw_affiliation_string":"Cambricon Technologies, Beijing, China","institution_ids":["https://openalex.org/I4401726770"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103063161","display_name":"Qi Guo","orcid":"https://orcid.org/0000-0003-2530-5874"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":"Qi Guo","raw_affiliation_strings":["State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2530-5874","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.395,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57875215,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"74","issue":"1","first_page":"155","last_page":"169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.963100016117096,"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":0.963100016117096,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.647436261177063},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5157632827758789},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3913155198097229},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3802621364593506},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3620138466358185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.647436261177063},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5157632827758789},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3913155198097229},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3802621364593506},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3620138466358185}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2024.3475575","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2024.3475575","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G160736790","display_name":null,"funder_award_id":"2021ZD0110102","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3584456257","display_name":null,"funder_award_id":"62372436","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5585668992","display_name":null,"funder_award_id":"62102398","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7537392905","display_name":null,"funder_award_id":"62222214","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8014835415","display_name":null,"funder_award_id":"U22A2028","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8462447369","display_name":null,"funder_award_id":"62302483","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/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1639032689","https://openalex.org/W2000967104","https://openalex.org/W2126891684","https://openalex.org/W2129710305","https://openalex.org/W2151339633","https://openalex.org/W2152839228","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2295598076","https://openalex.org/W2540279855","https://openalex.org/W2605347906","https://openalex.org/W2606722458","https://openalex.org/W2785369415","https://openalex.org/W2896457183","https://openalex.org/W2961619211","https://openalex.org/W2963114857","https://openalex.org/W2998993395","https://openalex.org/W3023540311","https://openalex.org/W3042725081","https://openalex.org/W3101788429","https://openalex.org/W3123639931","https://openalex.org/W4221062244","https://openalex.org/W4230989867","https://openalex.org/W4254672563","https://openalex.org/W4281932226","https://openalex.org/W4285805543","https://openalex.org/W4318541538","https://openalex.org/W4384918448","https://openalex.org/W6637373629","https://openalex.org/W6751349269","https://openalex.org/W6752057402","https://openalex.org/W6754777574","https://openalex.org/W6779728309","https://openalex.org/W6792155083","https://openalex.org/W6802856854","https://openalex.org/W6846258107","https://openalex.org/W6850579089","https://openalex.org/W6854866820"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W3215138031","https://openalex.org/W3009238340","https://openalex.org/W4321369474","https://openalex.org/W4360585206","https://openalex.org/W4285208911","https://openalex.org/W3082895349","https://openalex.org/W4213079790","https://openalex.org/W2248239756","https://openalex.org/W4323565446"],"abstract_inverted_index":{"The":[0,79,137],"widespread":[1],"adoption":[2],"of":[3,19,27,71,125],"deep":[4],"learning":[5],"accelerators":[6],"(DLAs)":[7],"underscores":[8],"their":[9],"pivotal":[10],"role":[11],"in":[12,73,145],"improving":[13],"the":[14,25,87,94,104,115,119,122,126,133,141],"performance":[15],"and":[16,57,76,92,113],"energy":[17],"efficiency":[18],"neural":[20],"networks.":[21],"To":[22],"fully":[23],"leverage":[24],"capabilities":[26],"these":[28,45],"accelerators,":[29],"exploration-based":[30],"library":[31],"generation":[32,90,169],"approaches":[33,46],"have":[34,47],"been":[35,48],"widely":[36],"used":[37],"to":[38,53,67,143,173],"substantially":[39],"reduce":[40],"software":[41],"development":[42],"overhead.":[43],"However,":[44],"challenged":[49],"by":[50],"issues":[51],"related":[52],"sub-optimal":[54],"optimization":[55,59],"results":[56,156],"excessive":[58],"overheads.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64],"propose":[65],"<small>Heron</small>":[66,102,159,177,190],"generate":[68],"high-performance":[69],"libraries":[70],"DLAs":[72],"an":[74,97],"efficient":[75],"fast":[77],"way.":[78],"key":[80],"is":[81],"automatically":[82],"enforcing":[83],"massive":[84],"constraints":[85,124],"through":[86],"entire":[88,134],"program":[89],"process":[91],"guiding":[93],"exploration":[95,135,138,147],"with":[96],"accurate":[98],"pre-trained":[99,153,188],"cost":[100],"model.":[101],"represents":[103],"search":[105,127],"space":[106,116,128,146],"as":[107],"a":[108,179,187,198],"constrained":[109],"satisfaction":[110],"problem":[111],"(CSP)":[112],"explores":[114],"via":[117],"evolving":[118],"CSPs.":[120],"Thus,":[121],"sophisticated":[123],"are":[129],"strictly":[130],"preserved":[131],"during":[132],"process.":[136],"algorithm":[139],"has":[140],"flexibility":[142],"engage":[144],"using":[148],"either":[149],"online-trained":[150],"models":[151],"or":[152],"models.":[154],"Experimental":[155],"demonstrate":[157],"that":[158],"averagely":[160],"achieves":[161,178,191],"2.71<inline-formula><tex-math":[162],"notation=\"LaTeX\">$\\times$</tex-math></inline-formula>":[163,181,193],"speedup":[164,182],"over":[165],"three":[166],"state-of-the-art":[167],"automatic":[168],"approaches.":[170],"Also,":[171],"compared":[172],"vendor-provided":[174],"hand-tuned":[175],"libraries,":[176],"2.00<inline-formula><tex-math":[180],"on":[183,201],"average.":[184],"When":[185],"employing":[186],"model,":[189],"11.6<inline-formula><tex-math":[192],"compilation":[194],"time":[195],"speedup,":[196],"incurring":[197],"minor":[199],"impact":[200],"execution":[202],"time.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}