{"id":"https://openalex.org/W7163328868","doi":"https://doi.org/10.1145/3818618","title":"<scp>MoonPoly</scp> : Bridging Code Generation and Adaptive Execution via Micro-Kernel Polymerization for Optimizing Dynamic-Shape Tensor Operators","display_name":"<scp>MoonPoly</scp> : Bridging Code Generation and Adaptive Execution via Micro-Kernel Polymerization for Optimizing Dynamic-Shape Tensor Operators","publication_year":2026,"publication_date":"2026-06-03","ids":{"openalex":"https://openalex.org/W7163328868","doi":"https://doi.org/10.1145/3818618"},"language":"en","primary_location":{"id":"doi:10.1145/3818618","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3818618","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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/10.1145/3818618","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054761925","display_name":"Yangyu Zhang","orcid":"https://orcid.org/0000-0001-7579-1888"},"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"]},{"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":"Yangyu Zhang","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences","University of Chinese Academy of Sciences"],"raw_orcid":"https://orcid.org/0000-0001-9582-6953","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137739722","display_name":"Guangli Li","orcid":"https://orcid.org/0000-0002-9738-261X"},"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/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"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":["AU","CN"],"is_corresponding":false,"raw_author_name":"Guangli Li","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences","University of Chinese Academy of Sciences","University of New South Wales"],"raw_orcid":"https://orcid.org/0000-0002-9738-261X","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"University of New South Wales","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137741700","display_name":"Feng Yu","orcid":"https://orcid.org/0009-0004-0974-0512"},"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"]},{"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":"Feng Yu","raw_affiliation_strings":["State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences","University of Chinese Academy of Sciences"],"raw_orcid":"https://orcid.org/0009-0004-0974-0512","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087358575","display_name":"Fan Luo","orcid":null},"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"]},{"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":"Fan Luo","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences","University of Chinese Academy of Sciences"],"raw_orcid":"https://orcid.org/0009-0003-1602-3549","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137725988","display_name":"Qianqi Sun","orcid":"https://orcid.org/0009-0009-8939-7721"},"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"]},{"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":"Qianqi Sun","raw_affiliation_strings":["Institute of Computing Technology Chinese Academy of Sciences","University of the Chinese Academy of Sciences"],"raw_orcid":"https://orcid.org/0009-0009-8939-7721","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of the Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087578136","display_name":"XM. Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueying Wang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications"],"raw_orcid":"https://orcid.org/0000-0002-7835-113X","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137764430","display_name":"Jiacheng Zhao","orcid":"https://orcid.org/0000-0001-5228-8972"},"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"]},{"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":"Jiacheng Zhao","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences","School of Computer and Control Engineering, University of Chinese Academy of Sciences"],"raw_orcid":"https://orcid.org/0000-0001-5228-8972","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Computer and Control Engineering, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137724851","display_name":"Huimin Cui","orcid":"https://orcid.org/0000-0002-2491-7679"},"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"]},{"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":"Huimin Cui","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences","University of Chinese Academy of Sciences"],"raw_orcid":"https://orcid.org/0000-0002-2491-7679","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109715374","display_name":"X N Feng","orcid":null},"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"]},{"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":"Xiaobing Feng","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences","University of Chinese Academy of Sciences"],"raw_orcid":"https://orcid.org/0000-0003-2909-7750","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5137785725","display_name":"Jingling Xue","orcid":"https://orcid.org/0000-0003-0380-3506"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jingling Xue","raw_affiliation_strings":["School of Computer Science and Engieering, University of New South Wales"],"raw_orcid":"https://orcid.org/0000-0003-0380-3506","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engieering, University of New South Wales","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"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":0.69490703,"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":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.19840000569820404,"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":0.19840000569820404,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.18709999322891235,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.18080000579357147,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6632999777793884},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6352999806404114},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5335000157356262},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.5019000172615051},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.49950000643730164},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4580000042915344},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.39570000767707825},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.3779999911785126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8671000003814697},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6632999777793884},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6352999806404114},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5335000157356262},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5019000172615051},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.49950000643730164},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4580000042915344},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.39730000495910645},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.39570000767707825},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.3779999911785126},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.37630000710487366},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.37400001287460327},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.34689998626708984},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.33070001006126404},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3276999890804291},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.29980000853538513},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2976999878883362},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29739999771118164},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C115168132","wikidata":"https://www.wikidata.org/wiki/Q55813","display_name":"Machine code","level":3,"score":0.27889999747276306},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.2786000072956085},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.267300009727478},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3818618","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3818618","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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:10.1145/3818618","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3818618","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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/G1989434931","display_name":null,"funder_award_id":"2023M733566","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G3454282639","display_name":"Enhancing Compiler Techniques for Dynamic-Shape Deep Learning Models","funder_award_id":"DP250104934","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"},{"id":"https://openalex.org/G4834427860","display_name":null,"funder_award_id":"62302479, 62232015, 62090024","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/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2780077279","https://openalex.org/W2949967139","https://openalex.org/W2963563691","https://openalex.org/W2979826702","https://openalex.org/W2981758446","https://openalex.org/W3118616291","https://openalex.org/W3123054690","https://openalex.org/W3130716829","https://openalex.org/W3161395920","https://openalex.org/W3177452048","https://openalex.org/W4212986322","https://openalex.org/W4214512541","https://openalex.org/W4308083739","https://openalex.org/W4381785750","https://openalex.org/W4387321091","https://openalex.org/W4388620366","https://openalex.org/W4407319523","https://openalex.org/W4408521258"],"related_works":[],"abstract_inverted_index":{"The":[0,160],"prevalence":[1],"of":[2,21,70,154,192,202,217],"dynamic":[3],"tensor":[4,55,80,125,171],"shapes,":[5,72],"driven":[6],"by":[7,84,175],"applications":[8],"like":[9],"language":[10,226],"model":[11],"serving":[12],"with":[13,44],"varying":[14],"sequence":[15],"lengths,":[16],"is":[17],"a":[18,29,68,123,139,152,169,176,199,215],"defining":[19],"characteristic":[20],"modern":[22],"deep":[23],"neural":[24],"networks.":[25],"This":[26],"dynamism":[27],"poses":[28],"fundamental":[30],"challenge:":[31],"reconciling":[32],"the":[33,45,143,195,221],"need":[34],"for":[35,47,67,89,214],"intensive,":[36],"offline":[37,144],"code":[38],"generation":[39],"to":[40,51,150],"achieve":[41],"peak":[42],"performance":[43,74,158],"demand":[46],"low-latency,":[48],"adaptive":[49,165],"execution":[50],"handle":[52],"unpredictable":[53],"runtime":[54],"shapes.":[56],"Consequently,":[57],"mainstream":[58],"strategies":[59],"are":[60,82],"ineffective.":[61],"Vendor-provided":[62],"libraries,":[63],"while":[64],"highly":[65],"optimized":[66],"subset":[69],"common":[71],"suffer":[73],"degradation":[75],"on":[76,102,181],"unconventional":[77],"ones.":[78],"Static":[79],"compilers":[81,96],"hamstrung":[83],"prohibitive":[85],"just-in-time":[86],"compilation":[87],"overheads":[88],"each":[90],"new":[91],"shape.":[92],"While":[93],"recent":[94],"dynamic-shape":[95,124],"offer":[97],"an":[98,182,188],"alternative,":[99],"they":[100],"rely":[101],"predefined":[103],"shape":[104],"ranges,":[105],"making":[106],"them":[107],"brittle":[108],"when":[109],"inputs":[110],"fall":[111],"outside":[112],"these":[113,135],"bounds.":[114],"To":[115],"resolve":[116],"this":[117],"tension,":[118],"we":[119],"present":[120],"MoonPoly":[121,186],",":[122],"compiler":[126],"that":[127],"introduces":[128],"micro-kernel":[129],"polymerization":[130],".":[131],"Our":[132],"approach":[133],"decouples":[134],"conflicting":[136],"requirements":[137],"through":[138],"two-stage":[140],"process.":[141],"In":[142],"stage,":[145],"it":[146],"performs":[147,164],"intensive":[148],"auto-tuning":[149],"generate":[151],"set":[153,201],"micro-kernels":[155],"and":[156,204,224],"corresponding":[157],"models.":[159,227],"online":[161],"stage":[162],"then":[163],"execution,":[166],"rapidly":[167],"assembling":[168],"near-optimal":[170],"operator":[172],"on-the-fly,":[173],"guided":[174],"lightweight":[177],"cost":[178],"model.":[179],"Evaluated":[180],"NVIDIA":[183],"A100":[184],"GPU,":[185],"achieves":[187],"average":[189],"operator-level":[190],"speedup":[191],"1.27\u00d7":[193],"over":[194],"cuBLAS":[196],"library":[197],"across":[198],"diverse":[200],"operators":[203],"data":[205],"types,":[206],"which":[207],"in":[208],"turn":[209],"yields":[210],"end-to-end":[211],"inference":[212],"acceleration":[213],"variety":[216],"models,":[218],"including":[219],"BERT,":[220],"Vision":[222],"Transformer,":[223],"large":[225]},"counts_by_year":[],"updated_date":"2026-06-27T06:13:17.587685","created_date":"2026-06-04T00:00:00"}
