{"id":"https://openalex.org/W4411203142","doi":"https://doi.org/10.1109/tpds.2025.3578630","title":"A Learned Performance Model With Transfer Learning Across GPUs on Tensorized Instructions","display_name":"A Learned Performance Model With Transfer Learning Across GPUs on Tensorized Instructions","publication_year":2025,"publication_date":"2025-06-11","ids":{"openalex":"https://openalex.org/W4411203142","doi":"https://doi.org/10.1109/tpds.2025.3578630"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2025.3578630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2025.3578630","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","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/A5020529992","display_name":"Yang Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yang Bai","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China","Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong SAR"],"raw_orcid":"https://orcid.org/0000-0002-5337-1783","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong SAR","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086203449","display_name":"Mingjun Li","orcid":"https://orcid.org/0009-0007-6740-8413"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Mingjun Li","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China","Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong SAR"],"raw_orcid":"https://orcid.org/0009-0007-6740-8413","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong SAR","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wendong Xu","orcid":"https://orcid.org/0000-0002-5857-7393"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wendong Xu","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong, SAR, China","Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong SAR"],"raw_orcid":"https://orcid.org/0000-0002-5857-7393","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong Kong SAR","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051340429","display_name":"Bei Yu","orcid":"https://orcid.org/0000-0001-6406-4810"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bei Yu","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China","Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong SAR"],"raw_orcid":"https://orcid.org/0000-0001-6406-4810","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong SAR","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7588,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86928705,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"36","issue":"9","first_page":"1904","last_page":"1919"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.8956999778747559,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12676","display_name":"Machine Learning and ELM","score":0.8956999778747559,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11122","display_name":"Online Learning and Analytics","score":0.8835999965667725,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10320","display_name":"Neural Networks and Applications","score":0.814300000667572,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8217123746871948},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4439389407634735},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.42031747102737427},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3954683840274811},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34085899591445923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27793246507644653}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8217123746871948},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4439389407634735},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.42031747102737427},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3954683840274811},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34085899591445923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27793246507644653}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2025.3578630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2025.3578630","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2108862644","https://openalex.org/W2194775991","https://openalex.org/W2225887246","https://openalex.org/W2295598076","https://openalex.org/W2590246587","https://openalex.org/W2606722458","https://openalex.org/W2805566098","https://openalex.org/W2896457183","https://openalex.org/W2949967139","https://openalex.org/W2954698171","https://openalex.org/W2961619211","https://openalex.org/W2963163009","https://openalex.org/W2963355447","https://openalex.org/W2967733054","https://openalex.org/W2981413347","https://openalex.org/W2988326850","https://openalex.org/W3004659153","https://openalex.org/W3162018314","https://openalex.org/W3174086521","https://openalex.org/W3176663407","https://openalex.org/W3204229702","https://openalex.org/W4200122815","https://openalex.org/W4293024135","https://openalex.org/W4318541538","https://openalex.org/W4319459088","https://openalex.org/W4386858078","https://openalex.org/W4389523770"],"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":{"The":[0],"training":[1],"and":[2,70,114,151,180,187,205],"inference":[3,178],"efficiency":[4],"of":[5,15,110,144,170],"ever-larger":[6],"deep":[7],"neural":[8],"networks":[9],"highly":[10],"rely":[11],"on":[12,18,189,207],"the":[13,46,96,100,108,122,142,167],"performance":[14,24,85,97,143,163,198],"tensor":[16,33,146],"operators":[17],"specific":[19],"hardware":[20,78],"accelerators.":[21],"Therefore,":[22],"a":[23,61,83,131,155],"tuning":[25],"framework":[26],"with":[27,45,66,76,91,112,136,160,173,194],"tensorized":[28,42,92,128,174,208],"instruction":[29,111,175,209],"compilation":[30],"for":[31,37,87],"automatic":[32,88],"generation":[34],"is":[35,99],"necessary":[36],"efficient":[38,134],"deployment.":[39],"These":[40],"novel":[41,84],"instruction,":[43],"along":[44],"emerging":[47],"machine":[48],"learning":[49],"models,":[50],"bring":[51],"tremendous":[52],"engineering":[53],"challenges":[54],"in":[55],"compilation-based":[56],"methods.":[57],"They":[58],"suffer":[59],"from":[60,125],"large":[62],"design":[63,135],"space":[64],"exploration":[65],"rough":[67],"measurement":[68],"accuracy":[69],"poor":[71],"transferability":[72],"among":[73],"specialized":[74],"instructions":[75],"certain":[77],"constraints.":[79],"This":[80],"paper":[81],"presents":[82],"model":[86,98,164],"code":[89,171],"optimization":[90],"instruction.":[93],"Central":[94],"to":[95,127,139,176,185,202],"assignment":[101],"feature":[102],"that":[103],"not":[104],"only":[105],"clearly":[106],"specifies":[107],"behaviour":[109],"computation":[113],"data":[115],"movement":[116],"abstraction,":[117],"but":[118],"also":[119],"formally":[120],"defines":[121],"matching":[123],"problem":[124],"algorithm":[126],"instructions.":[129],"Meanwhile,":[130],"simple":[132],"yet":[133],"attention-inspired":[137],"modules":[138],"accurately":[140],"predict":[141,166],"optimized":[145],"program":[147],"by":[148,183],"capturing":[149],"global":[150],"long-range":[152],"dependencies":[153],"within":[154],"complete":[156],"scheduling":[157],"space.":[158],"Compared":[159],"state-of-the-arts,":[161],"our":[162,197],"can":[165,199],"optimal":[168],"implementation":[169],"configurations":[172],"reduce":[177],"latency":[179],"search":[181],"time":[182],"up":[184],"1.21\u00d7":[186],"3.41\u00d7":[188],"modern":[190],"DNN":[191],"benchmarks.":[192],"Furthermore,":[193],"pre-trained":[195],"parameters,":[196],"quickly":[200],"adapt":[201],"different":[203],"workloads":[204],"platforms":[206],"via":[210],"transfer":[211],"learning.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}