{"id":"https://openalex.org/W7204137916","doi":"https://doi.org/10.48550/arxiv.2608.20711","title":"AsmEvo: Agentic Assembly-Level Optimization of AMD GPU Kernels with Functional Equivalence Verification","display_name":"AsmEvo: Agentic Assembly-Level Optimization of AMD GPU Kernels with Functional Equivalence Verification","publication_year":2026,"publication_date":"2026-08-21","ids":{"openalex":"https://openalex.org/W7204137916","doi":"https://doi.org/10.48550/arxiv.2608.20711"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.20711","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20711","pdf_url":"https://arxiv.org/pdf/2608.20711","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.20711","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147998320","display_name":"Ji Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Ji","raw_affiliation_strings":["Advanced Micro Devices , Inc. (AMD)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices , Inc. (AMD)","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121954616","display_name":"Puyuan Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang, Puyuan","raw_affiliation_strings":["Advanced Micro Devices , Inc. (AMD)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices , Inc. (AMD)","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101820519","display_name":"Rongzhang Zheng","orcid":"https://orcid.org/0009-0000-9988-4712","observed_orcids":["https://orcid.org/0009-0000-9988-4712"]},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheng, Rongzhang","raw_affiliation_strings":["Advanced Micro Devices , Inc. (AMD)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices , Inc. (AMD)","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147978039","display_name":"Fan Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Fan","raw_affiliation_strings":["Advanced Micro Devices , Inc. (AMD)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices , Inc. (AMD)","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5145958665","display_name":"Jinglin Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]},{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Wang, Jinglin","raw_affiliation_strings":["Advanced Micro Devices , Inc. (AMD)","Southern University of Science and Technology , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices , Inc. (AMD)","institution_ids":["https://openalex.org/I4210137977"]},{"raw_affiliation_string":"Southern University of Science and Technology , Shenzhen , China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057601049","display_name":"Muhammad A. Awad","orcid":"https://orcid.org/0000-0002-6914-493X","observed_orcids":["https://orcid.org/0000-0002-6914-493X"]},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Awad, Muhammad A.","raw_affiliation_strings":["Advanced Micro Devices , Inc. (AMD)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices , Inc. (AMD)","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147976629","display_name":"Mortis Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huang, Mortis","raw_affiliation_strings":["Advanced Micro Devices , Inc. (AMD)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices , Inc. (AMD)","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147977283","display_name":"Andy Chang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chang, Andy","raw_affiliation_strings":["Advanced Micro Devices , Inc. (AMD)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices , Inc. (AMD)","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106482041","display_name":"Zekai Li","orcid":"https://orcid.org/0009-0008-3962-6074","observed_orcids":["https://orcid.org/0009-0008-3962-6074"]},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Zekai","raw_affiliation_strings":["Advanced Micro Devices , Inc. (AMD)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices , Inc. (AMD)","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101787835","display_name":"Zeping Li","orcid":"https://orcid.org/0009-0007-0099-5879","observed_orcids":["https://orcid.org/0009-0007-0099-5879","https://orcid.org/0000-0001-8260-4278"]},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Zeping","raw_affiliation_strings":["Advanced Micro Devices , Inc. (AMD)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices , Inc. (AMD)","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148042369","display_name":"Zihao An","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"An, Zihao","raw_affiliation_strings":["Advanced Micro Devices , Inc. (AMD)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices , Inc. (AMD)","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147958269","display_name":"Yue Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Yue","raw_affiliation_strings":["Advanced Micro Devices , Inc. (AMD)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices , Inc. (AMD)","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136556995","display_name":"Yuchen Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang, Yuchen","raw_affiliation_strings":["Advanced Micro Devices , Inc. (AMD)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices , Inc. (AMD)","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147925966","display_name":"Jianghui Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]},{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Wang, Jianghui","raw_affiliation_strings":["Advanced Micro Devices , Inc. (AMD)","Southern University of Science and Technology , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices , Inc. (AMD)","institution_ids":["https://openalex.org/I4210137977"]},{"raw_affiliation_string":"Southern University of Science and Technology , Shenzhen , China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075814697","display_name":"\u8655\u4e16 \u9673","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Chushi","raw_affiliation_strings":["Advanced Micro Devices , Inc. (AMD)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices , Inc. (AMD)","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079691252","display_name":"Ziqiong Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Ziqiong","raw_affiliation_strings":["Advanced Micro Devices , Inc. (AMD)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices , Inc. (AMD)","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147953535","display_name":"Fuwei Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang, Fuwei","raw_affiliation_strings":["Advanced Micro Devices , Inc. (AMD)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices , Inc. (AMD)","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147941882","display_name":"Dong Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Dong","raw_affiliation_strings":["Advanced Micro Devices , Inc. (AMD)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices , Inc. (AMD)","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148012282","display_name":"Wen Heng Chung","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chung, Wen Heng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148038219","display_name":"Shengcai Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Shengcai","raw_affiliation_strings":["Southern University of Science and Technology , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology , Shenzhen , China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027115167","display_name":"Emad Barsoum","orcid":"https://orcid.org/0000-0002-4097-8690","observed_orcids":["https://orcid.org/0000-0002-4097-8690"]},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barsoum, Emad","raw_affiliation_strings":["Advanced Micro Devices , Inc. (AMD)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Micro Devices , Inc. (AMD)","institution_ids":["https://openalex.org/I4210137977"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9976000189781189,"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":0.9976000189781189,"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":0.0010000000474974513,"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/T10260","display_name":"Software Engineering Research","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/triton-kernels","display_name":"Triton kernels","score":0.7110000252723694},{"id":"https://openalex.org/keywords/vllm","display_name":"vLLM","score":0.5400000214576721},{"id":"https://openalex.org/keywords/sglang","display_name":"SGLang","score":0.8069999814033508}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8253999948501587},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6654999852180481},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6215000152587891},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5881999731063843},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.492900013923645},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.48809999227523804},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.4830000102519989},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4781000018119812},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.40310001373291016},{"id":"https://openalex.org/C47434764","wikidata":"https://www.wikidata.org/wiki/Q1770035","display_name":"Dead code","level":5,"score":0.35019999742507935},{"id":"https://openalex.org/C63435697","wikidata":"https://www.wikidata.org/wiki/Q864135","display_name":"Binary code","level":3,"score":0.3425000011920929},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.34209999442100525},{"id":"https://openalex.org/C139571649","wikidata":"https://www.wikidata.org/wiki/Q1156793","display_name":"Program optimization","level":3,"score":0.3264000117778778},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3172999918460846},{"id":"https://openalex.org/C111498074","wikidata":"https://www.wikidata.org/wiki/Q173326","display_name":"Formal verification","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C2988012377","wikidata":"https://www.wikidata.org/wiki/Q29966452","display_name":"Functional equivalence","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C62460635","wikidata":"https://www.wikidata.org/wiki/Q5508853","display_name":"Functional verification","level":3,"score":0.288100004196167},{"id":"https://openalex.org/C154526789","wikidata":"https://www.wikidata.org/wiki/Q157965","display_name":"Object code","level":4,"score":0.2806999981403351},{"id":"https://openalex.org/C2988963302","wikidata":"https://www.wikidata.org/wiki/Q629206","display_name":"Program code","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2768999934196472},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C97686452","wikidata":"https://www.wikidata.org/wiki/Q7604153","display_name":"Static analysis","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.20711","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20711","pdf_url":"https://arxiv.org/pdf/2608.20711","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.20711","doi":"https://doi.org/10.48550/arxiv.2608.20711","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.20711","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.20711","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20711","pdf_url":"https://arxiv.org/pdf/2608.20711","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204137916.pdf","grobid_xml":"https://content.openalex.org/works/W7204137916.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7117850884","https://openalex.org/W7137011890","https://openalex.org/W7212893619","https://openalex.org/W7172514901","https://openalex.org/W7163063282","https://openalex.org/W7155210327","https://openalex.org/W4407848455","https://openalex.org/W4415181444","https://openalex.org/W3016562408","https://openalex.org/W7140198594"],"abstract_inverted_index":{"High-performance":[0],"ML":[1],"systems":[2],"increasingly":[3],"rely":[4],"on":[5,33,134],"GPU":[6,75,137],"kernels":[7],"whose":[8],"editable":[9],"source":[10,39],"is":[11,61],"unavailable,":[12],"generated,":[13],"or":[14,37],"too":[15],"distant":[16],"from":[17],"final":[18],"machine":[19],"code":[20,55,80],"to":[21],"expose":[22],"remaining":[23],"optimizations.":[24],"Existing":[25],"LLM":[26],"kernel":[27],"optimizers":[28],"and":[29,40,100,123,152,166,173],"autotuners":[30],"mainly":[31],"operate":[32],"CUDA,":[34],"Triton,":[35],"HIP,":[36],"tensor-program":[38],"validate":[41],"against":[42,107],"reference":[43],"implementations.":[44],"We":[45,66,128],"study":[46],"a":[47,85,92],"stricter":[48],"setting:":[49],"optimizing":[50],"an":[51,69,78,96],"already":[52],"compiled":[53],"AMDGPU":[54,79],"object,":[56,99],"where":[57],"the":[58,62],"deployed":[59],"binary":[60],"only":[63,103],"behavioral":[64],"oracle.":[65],"present":[67],"AsmEvo,":[68],"agentic":[70],"assembly-level":[71],"optimizer":[72],"for":[73],"AMD":[74,136],"kernels.":[76,138],"Given":[77],"object":[81],"K0,":[82],"AsmEvo":[83,112,133,141],"reconstructs":[84],"reassemblable":[86],"representation,":[87],"proposes":[88],"low-level":[89],"edits":[90],"with":[91,132],"long-horizon":[93],"agent,":[94],"rebuilds":[95],"ABI-preserving":[97],"optimized":[98],"accepts":[101],"candidates":[102],"after":[104],"differential":[105],"verification":[106],"K0":[108],"under":[109],"identical":[110],"launches.":[111],"combines":[113],"code-object":[114],"recovery,":[115],"metadata-aware":[116],"rebuilding,":[117],"profiling-guided":[118],"hot-window":[119],"editing,":[120],"correctness-gated":[121],"timing,":[122],"conservative":[124],"in-place":[125],"patch":[126],"fallback.":[127],"conduct":[129],"extensive":[130],"experiments":[131],"various":[135],"On":[139,156],"MI308X,":[140],"improves":[142,161],"29":[143],"of":[144],"30":[145],"selected":[146],"KernelBench":[147],"kernels,":[148,170],"reaching":[149,171],"1.35x":[150],"geometric-mean":[151],"3.88x":[153],"maximum":[154],"speedup.":[155],"MI300X":[157],"production":[158],"workloads,":[159],"it":[160],"all":[162],"evaluated":[163],"AITer":[164],"binaries":[165],"vLLM/SGLang":[167],"Triton":[168],"assembly":[169],"1.09x/1.31x":[172],"1.18x/1.34x":[174],"geometric-mean/maximum":[175],"speedups,":[176],"respectively,":[177],"while":[178],"preserving":[179],"functional":[180],"equivalence.":[181]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-25T00:00:00"}
