{"id":"https://openalex.org/W7164026269","doi":"https://doi.org/10.1145/3820380","title":"NPUMeter: Automatic Operator Optimization for Ascend NPU with Accurate Analytical Performance Models","display_name":"NPUMeter: Automatic Operator Optimization for Ascend NPU with Accurate Analytical Performance Models","publication_year":2026,"publication_date":"2026-06-09","ids":{"openalex":"https://openalex.org/W7164026269","doi":"https://doi.org/10.1145/3820380"},"language":"en","primary_location":{"id":"doi:10.1145/3820380","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3820380","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/10.1145/3820380","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112958261","display_name":"Weichuang Zhang","orcid":null},"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":"Weichuang Zhang","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University"],"raw_orcid":"https://orcid.org/0009-0000-7928-6512","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138238467","display_name":"Yufei Shangguan","orcid":"https://orcid.org/0009-0006-1544-2356"},"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":"Yufei Shangguan","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University"],"raw_orcid":"https://orcid.org/0009-0006-1544-2356","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100554980","display_name":"Haibo Xu","orcid":"https://orcid.org/0009-0001-1678-6592"},"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":"Haibo Xu","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University"],"raw_orcid":"https://orcid.org/0009-0004-7111-5574","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070566200","display_name":"Yuting Mai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuting Mai","raw_affiliation_strings":["Huawei Technologies Co Ltd"],"raw_orcid":"https://orcid.org/0009-0005-0142-6366","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075720732","display_name":"Qiuliang Wang","orcid":"https://orcid.org/0000-0001-5987-4069"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qiuliang Wang","raw_affiliation_strings":["Huawei Technologies Co Ltd"],"raw_orcid":"https://orcid.org/0009-0006-9808-1380","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418393","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0001-9480-5632"},"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":"Chen Chen","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University"],"raw_orcid":"https://orcid.org/0000-0001-9480-5632","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138222417","display_name":"Yi Li","orcid":"https://orcid.org/0009-0009-0748-8452"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yi Li","raw_affiliation_strings":["Huawei Technologies Co Ltd"],"raw_orcid":"https://orcid.org/0009-0009-0748-8452","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138241005","display_name":"Quan Chen","orcid":"https://orcid.org/0000-0001-5832-0347"},"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":"Quan Chen","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University"],"raw_orcid":"https://orcid.org/0000-0001-5832-0347","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102769588","display_name":"Wenchao Ding","orcid":"https://orcid.org/0000-0003-4249-526X"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenchao Ding","raw_affiliation_strings":["College of Intelligent Robotics and Advanced Manufacturing, Fudan University"],"raw_orcid":"https://orcid.org/0000-0003-4249-526X","affiliations":[{"raw_affiliation_string":"College of Intelligent Robotics and Advanced Manufacturing, Fudan University","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047571832","display_name":"Jieru Zhao","orcid":"https://orcid.org/0000-0001-8211-2812"},"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":"Jieru Zhao","raw_affiliation_strings":["School of Computer Science, Shanghai Jiao Tong University"],"raw_orcid":"https://orcid.org/0000-0001-8211-2812","affiliations":[{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5138221914","display_name":"Minyi Guo","orcid":"https://orcid.org/0000-0003-0034-2302"},"institutions":[{"id":"https://openalex.org/I178232147","display_name":"Guizhou University","ror":"https://ror.org/02wmsc916","country_code":"CN","type":"education","lineage":["https://openalex.org/I178232147"]},{"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":"Minyi Guo","raw_affiliation_strings":["College of Computer Science and Technology, Guizhou University","School of Computer Science, Shanghai Jiao Tong University"],"raw_orcid":"https://orcid.org/0000-0003-0034-2302","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Guizhou University","institution_ids":["https://openalex.org/I178232147"]},{"raw_affiliation_string":"School of Computer Science, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":3,"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":0.73739173,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":"2","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":0.4336000084877014,"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":0.4336000084877014,"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":0.2515000104904175,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.033799998462200165,"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/speedup","display_name":"Speedup","score":0.7228999733924866},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.5760999917984009},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5005999803543091},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.45840001106262207},{"id":"https://openalex.org/keywords/parameter-space","display_name":"Parameter space","score":0.43230000138282776},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42149999737739563},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.3822000026702881},{"id":"https://openalex.org/keywords/development","display_name":"Development (topology)","score":0.3479999899864197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.888700008392334},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7228999733924866},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.5760999917984009},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5005999803543091},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.45840001106262207},{"id":"https://openalex.org/C73586568","wikidata":"https://www.wikidata.org/wiki/Q2600211","display_name":"Parameter space","level":2,"score":0.43230000138282776},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42149999737739563},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.3822000026702881},{"id":"https://openalex.org/C2776542497","wikidata":"https://www.wikidata.org/wiki/Q5266672","display_name":"Development (topology)","level":2,"score":0.3479999899864197},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3449999988079071},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3384000062942505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33719998598098755},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3125999867916107},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.3059000074863434},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C131675550","wikidata":"https://www.wikidata.org/wiki/Q7646884","display_name":"Surrogate model","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2540000081062317},{"id":"https://openalex.org/C164752517","wikidata":"https://www.wikidata.org/wiki/Q5570875","display_name":"Global optimization","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C2987595161","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Optimization algorithm","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3820380","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3820380","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:10.1145/3820380","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3820380","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":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.9022963047027588}],"awards":[{"id":"https://openalex.org/G6643119303","display_name":null,"funder_award_id":"62472273 and 62232015","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2798956872","https://openalex.org/W2901073342","https://openalex.org/W2940862705","https://openalex.org/W2961619211","https://openalex.org/W2963989532","https://openalex.org/W3012526378","https://openalex.org/W3094260441","https://openalex.org/W3136358373","https://openalex.org/W3192336523","https://openalex.org/W4231332361","https://openalex.org/W4239766522","https://openalex.org/W4318773891","https://openalex.org/W4393949386","https://openalex.org/W4407319928"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,40,53,135,178,182,188],"rapid":[2],"development":[3,58],"of":[4,25,120],"AI":[5],"and":[6,29,68,75,96],"deep":[7,46],"learning,":[8],"computational":[9],"demands":[10],"are":[11],"increasing":[12],"significantly.":[13],"While":[14],"GPUs":[15],"excel":[16],"in":[17,23,139],"parallel":[18],"computing,":[19],"they":[20],"fall":[21],"short":[22],"terms":[24],"energy":[26],"efficiency,":[27],"specialization,":[28],"processing":[30],"latency.":[31],"In":[32],"contrast,":[33],"Neural":[34],"Processing":[35],"Units":[36],"(NPUs),":[37],"such":[38],"as":[39],"Ascend":[41,91,183],"NPUs,":[42],"designed":[43],"specifically":[44],"for":[45,90,134,166],"learning":[47],"tasks,":[48],"demonstrate":[49,148],"superior":[50],"performance.":[51],"However,":[52],"architecture":[54],"specialization":[55],"makes":[56],"operator":[57,87,113],"more":[59],"challenging,":[60],"leading":[61],"to":[62,171,177,193],"a":[63,140,172],"reliance":[64],"on":[65,115],"manual":[66],"tuning":[67],"optimization,":[69],"which":[70],"incurs":[71],"significant":[72],"time":[73,190],"cost":[74],"developing":[76],"effort.":[77],"To":[78],"address":[79],"this":[80],"issue,":[81],"we":[82],"propose":[83],"NPUMeter,":[84],"an":[85,106,124,156],"automatic":[86],"optimization":[88,121],"framework":[89],"NPUs":[92],"built":[93],"upon":[94],"accurate":[95],"comprehensive":[97],"analytical":[98,107],"performance":[99,108,174],"models.":[100],"NPUMeter":[101,150],"comprises":[102],"two":[103],"components:":[104],"(1)":[105],"model":[109],"that":[110,131,149],"accurately":[111],"estimates":[112],"latency":[114],"NPU":[116],"given":[117],"different":[118],"configurations":[119,165],"parameters;":[122],"(2)":[123],"efficient":[125],"design":[126,142],"space":[127,143],"exploration":[128],"(DSE)":[129],"algorithm":[130],"automatically":[132],"searches":[133],"optimal":[136],"parameter":[137],"configuration":[138,179],"large":[141],"within":[144],"minutes.":[145,194],"Experimental":[146],"results":[147],"achieves":[151],"high":[152],"estimation":[153],"accuracy,":[154],"with":[155],"average":[157],"error":[158],"below":[159],"5%.":[160],"It":[161],"effectively":[162],"generates":[163],"near-optimal":[164],"various":[167],"operators,":[168],"achieving":[169],"up":[170],"1.46\u00d7":[173],"speedup":[175],"compared":[176],"generated":[180],"by":[181],"C":[184],"compiler":[185],"while":[186],"reducing":[187],"DSE":[189],"from":[191],"hours":[192]},"counts_by_year":[],"updated_date":"2026-06-27T06:13:17.587685","created_date":"2026-06-10T00:00:00"}
