{"id":"https://openalex.org/W7167048161","doi":"https://doi.org/10.1145/3797905.3800551","title":"CKTI: A Domain-Specific Compiler for Lowering CUDA Kernels to Triton-IR","display_name":"CKTI: A Domain-Specific Compiler for Lowering CUDA Kernels to Triton-IR","publication_year":2026,"publication_date":"2026-07-02","ids":{"openalex":"https://openalex.org/W7167048161","doi":"https://doi.org/10.1145/3797905.3800551"},"language":null,"primary_location":{"id":"doi:10.1145/3797905.3800551","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3800551","pdf_url":null,"source":null,"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":"Proceedings of the 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3797905.3800551","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057724291","display_name":"Changqing Shi","orcid":"https://orcid.org/0009-0009-5732-2207"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changqing Shi","raw_affiliation_strings":["Nankai University, TianJin, China"],"raw_orcid":"https://orcid.org/0009-0009-5732-2207","affiliations":[{"raw_affiliation_string":"Nankai University, TianJin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100403642","display_name":"Rui Chen","orcid":"https://orcid.org/0000-0002-4341-2908"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Chen","raw_affiliation_strings":["Nankai University, TianJin, China"],"raw_orcid":"https://orcid.org/0009-0008-1786-2519","affiliations":[{"raw_affiliation_string":"Nankai University, TianJin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139887323","display_name":"Yufei Sun","orcid":"https://orcid.org/0009-0001-9778-9575"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufei Sun","raw_affiliation_strings":["Nankai University, TianJin, China"],"raw_orcid":"https://orcid.org/0009-0001-9778-9575","affiliations":[{"raw_affiliation_string":"Nankai University, TianJin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041756873","display_name":"Yicheng Sui","orcid":"https://orcid.org/0000-0001-9763-7435"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yicheng Sui","raw_affiliation_strings":["Nankai University, TianJin, China"],"raw_orcid":"https://orcid.org/0000-0001-9763-7435","affiliations":[{"raw_affiliation_string":"Nankai University, TianJin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377745","display_name":"Junhua Zhang","orcid":"https://orcid.org/0000-0002-8936-3822"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyu Zhang","raw_affiliation_strings":["Nankai University, TianJin, China"],"raw_orcid":"https://orcid.org/0009-0004-9906-940X","affiliations":[{"raw_affiliation_string":"Nankai University, TianJin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124115479","display_name":"Yudong Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yudong Xie","raw_affiliation_strings":["Nankai University, TianJin, China"],"raw_orcid":"https://orcid.org/0009-0005-3451-0206","affiliations":[{"raw_affiliation_string":"Nankai University, TianJin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139871838","display_name":"Mingda Wang","orcid":"https://orcid.org/0009-0002-6650-8029"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingda Wang","raw_affiliation_strings":["Nankai University, TianJin, China"],"raw_orcid":"https://orcid.org/0009-0002-6650-8029","affiliations":[{"raw_affiliation_string":"Nankai University, TianJin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139876879","display_name":"Shuangpeng Ming","orcid":"https://orcid.org/0009-0002-0995-7039"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuangpeng Ming","raw_affiliation_strings":["Nankai University, TianJin, China"],"raw_orcid":"https://orcid.org/0009-0002-0995-7039","affiliations":[{"raw_affiliation_string":"Nankai University, TianJin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450362","display_name":"Shuo Zhang","orcid":"https://orcid.org/0000-0002-2170-4299"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Zhang","raw_affiliation_strings":["Nankai University, TianJin, China"],"raw_orcid":"https://orcid.org/0009-0004-3454-1806","affiliations":[{"raw_affiliation_string":"Nankai University, TianJin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100657058","display_name":"Yuzhi Zhang","orcid":"https://orcid.org/0000-0002-6729-925X"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuzhi Zhang","raw_affiliation_strings":["Nankai University, TianJin, China"],"raw_orcid":"https://orcid.org/0000-0002-6729-925X","affiliations":[{"raw_affiliation_string":"Nankai University, TianJin, China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"132","last_page":"144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9208999872207642,"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":0.9208999872207642,"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":0.0203000009059906,"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/T14347","display_name":"Big Data and Digital Economy","score":0.009200000204145908,"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/cuda","display_name":"CUDA","score":0.8331000208854675},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7310000061988831},{"id":"https://openalex.org/keywords/software-portability","display_name":"Software portability","score":0.6532999873161316},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.590499997138977},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5163000226020813},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4133000075817108},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.38199999928474426},{"id":"https://openalex.org/keywords/multithreading","display_name":"Multithreading","score":0.34549999237060547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8623999953269958},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8331000208854675},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7310000061988831},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6814000010490417},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.6532999873161316},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.590499997138977},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5163000226020813},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4133000075817108},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.38199999928474426},{"id":"https://openalex.org/C201410400","wikidata":"https://www.wikidata.org/wiki/Q1064412","display_name":"Multithreading","level":3,"score":0.34549999237060547},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.3068000078201294},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.296099990606308},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.25679999589920044},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3797905.3800551","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3800551","pdf_url":null,"source":null,"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":"Proceedings of the 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3797905.3800551","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3800551","pdf_url":null,"source":null,"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":"Proceedings of the 40th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1934764390","display_name":null,"funder_award_id":"24HHXCSS00001","funder_id":"https://openalex.org/F4320336756","funder_display_name":"Tianjin Science and Technology Program"}],"funders":[{"id":"https://openalex.org/F4320336756","display_name":"Tianjin Science and Technology Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1984222112","https://openalex.org/W2014596857","https://openalex.org/W2026448279","https://openalex.org/W2052863973","https://openalex.org/W2065012482","https://openalex.org/W2122078011","https://openalex.org/W2128120785","https://openalex.org/W2194775991","https://openalex.org/W2346804249","https://openalex.org/W2540279855","https://openalex.org/W2613143750","https://openalex.org/W2912012512","https://openalex.org/W2954698171","https://openalex.org/W3004735627","https://openalex.org/W3122286897","https://openalex.org/W3157657667","https://openalex.org/W4213019189","https://openalex.org/W4239588678","https://openalex.org/W4251637954","https://openalex.org/W4321446270","https://openalex.org/W4392265915","https://openalex.org/W4413831423"],"related_works":[],"abstract_inverted_index":{"CUDA":[0,51],"kernels":[1,20,52],"are":[2,21],"essential":[3],"for":[4,157],"high-performance":[5],"computing,":[6],"yet":[7],"their":[8],"deployment":[9,148],"has":[10],"been":[11],"limited":[12],"to":[13,36,53,80,91,100],"vendor-specific":[14],"chips.":[15],"Unless":[16],"highly":[17],"efficient":[18],"computational":[19],"custom-implemented":[22],"by":[23],"experts,":[24],"other":[25],"chips":[26],"may":[27],"face":[28],"problems":[29],"such":[30],"as":[31],"low":[32],"utilization":[33],"and":[34,61,105,116,131,146,165],"inability":[35],"accelerate":[37],"AI":[38],"computing.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43,153],"introduce":[44],"CKTI,":[45],"a":[46,70,84,97],"domain-specific":[47],"compiler":[48],"that":[49,73,122],"lowers":[50],"Triton-IR,":[54],"thereby":[55],"decoupling":[56],"them":[57],"from":[58,78,87],"proprietary":[59],"hardware":[60,129],"fostering":[62],"diversity":[63],"across":[64,160],"the":[65,75,102,109],"computing":[66],"ecosystem.":[67],"CKTI":[68,123],"proposes":[69],"scheduling":[71],"algorithm":[72],"transforms":[74],"threading":[76],"model":[77],"thread-level":[79],"tile-level,":[81],"along":[82],"with":[83],"mapping":[85],"scheme":[86],"explicit":[88],"control-structure":[89],"characteristics":[90],"dynamic":[92],"masks.":[93],"It":[94],"also":[95],"incorporates":[96],"custom":[98],"dialect":[99],"express":[101],"complete":[103],"semantics":[104],"optimizable":[106],"properties":[107],"of":[108],"kernel.":[110],"These":[111],"collectively":[112],"ensure":[113],"performance":[114],"portability":[115],"cross-platform":[117],"deployment.":[118],"The":[119],"results":[120],"show":[121],"produces":[124],"correct":[125],"outputs":[126],"on":[127,138,141,144,149],"different":[128],"platforms":[130],"delivers":[132],"competitive":[133],"performance,":[134],"achieving":[135],"1.28X":[136],"speedup":[137],"NVIDIA,":[139],"1.17X":[140],"AMD,":[142],"1.14X":[143],"MetaX,":[145],"unlocking":[147],"Cambricon":[150],"platforms.":[151],"Additionally,":[152],"validate":[154],"CKTI\u2019s":[155],"support":[156],"end-to-end":[158],"workloads":[159],"multiple":[161],"architecture,":[162],"including":[163],"NPUs":[164],"GPGPUs.":[166]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-07-03T00:00:00"}