{"id":"https://openalex.org/W7167070220","doi":"https://doi.org/10.1145/3797905.3800535","title":"PolyKAN: A High-Performance and Universal GPU Operator Library for Polynomial Kolmogorov-Arnold Networks","display_name":"PolyKAN: A High-Performance and Universal GPU Operator Library for Polynomial Kolmogorov-Arnold Networks","publication_year":2026,"publication_date":"2026-07-02","ids":{"openalex":"https://openalex.org/W7167070220","doi":"https://doi.org/10.1145/3797905.3800535"},"language":null,"primary_location":{"id":"doi:10.1145/3797905.3800535","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3800535","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/10.1145/3797905.3800535","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139908924","display_name":"Mingkun Yu","orcid":"https://orcid.org/0009-0000-3593-9032"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingkun Yu","raw_affiliation_strings":["Sun Yat-sen University, GuangZhou, China"],"raw_orcid":"https://orcid.org/0009-0000-3593-9032","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, GuangZhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101302128","display_name":"Heming Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heming Zhong","raw_affiliation_strings":["Sun Yat-sen University, GuangZhou, China"],"raw_orcid":"https://orcid.org/0009-0005-9825-3181","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, GuangZhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048148542","display_name":"Jiazhi Jiang","orcid":"https://orcid.org/0000-0002-1417-3012"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiazhi Jiang","raw_affiliation_strings":["Sun Yat-sen University, GuangZhou, China"],"raw_orcid":"https://orcid.org/0000-0002-1417-3012","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, GuangZhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041534890","display_name":"Dan Huang","orcid":"https://orcid.org/0000-0001-5582-1031"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Huang","raw_affiliation_strings":["Sun Yat-sen University, GuangZhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5582-1031","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, GuangZhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101633465","display_name":"Yutong Lu","orcid":"https://orcid.org/0000-0001-5315-3375"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong Lu","raw_affiliation_strings":["Sun Yat-sen University, GuangZhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5315-3375","affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, GuangZhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157773358"],"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":"1102","last_page":"1114"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.289900004863739,"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"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.289900004863739,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.09430000185966492,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.07559999823570251,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6323000192642212},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.46140000224113464},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4602999985218048},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.4528000056743622},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43950000405311584},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.4198000133037567},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4142000079154968},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.3939000070095062},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.38119998574256897}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791700005531311},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6323000192642212},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5449000000953674},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.46140000224113464},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4602999985218048},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45649999380111694},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.4528000056743622},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43950000405311584},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.4198000133037567},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4142000079154968},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.38119998574256897},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35019999742507935},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.3330000042915344},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.33219999074935913},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C134765980","wikidata":"https://www.wikidata.org/wiki/Q879126","display_name":"Bitwise operation","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.26829999685287476},{"id":"https://openalex.org/C49766605","wikidata":"https://www.wikidata.org/wiki/Q207643","display_name":"Linear map","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3797905.3800535","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3800535","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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:10.1145/3797905.3800535","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3797905.3800535","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1855169650","https://openalex.org/W2002555321","https://openalex.org/W2093887103","https://openalex.org/W2103496339","https://openalex.org/W2919115771","https://openalex.org/W2945976633","https://openalex.org/W2954698171","https://openalex.org/W4238143865","https://openalex.org/W4401697219","https://openalex.org/W4404468356"],"related_works":[],"abstract_inverted_index":{"Kolmogorov\u2013Arnold":[0],"Networks":[1],"(KANs)":[2],"promise":[3],"higher":[4],"expressive":[5],"capability":[6],"and":[7,56,63,121,139,156,163],"stronger":[8],"interpretability":[9],"than":[10,144],"Multilayer":[11],"Perceptron,":[12],"particularly":[13],"in":[14],"the":[15,49,61,82,129],"domain":[16],"of":[17,31,54,66,74],"AI":[18],"for":[19],"Science.":[20],"However,":[21],"practical":[22],"adoption":[23],"has":[24],"been":[25],"hindered":[26],"by":[27],"low":[28],"GPU":[29,162],"utilization":[30],"existing":[32],"parallel":[33],"implementations.":[34],"To":[35],"address":[36],"this":[37],"challenge,":[38],"we":[39],"present":[40],"a":[41,71,107,116,145],"GPU-accelerated":[42],"operator":[43],"library,":[44],"named":[45],"PolyKAN,":[46],"which":[47],"is":[48],"first":[50],"general":[51],"open-source":[52],"implementation":[53],"KAN":[55,68],"its":[57],"variants.":[58],"PolyKAN":[59,132],"fuses":[60],"forward":[62],"backward":[64],"passes":[65],"polynomial":[67],"layers":[69],"into":[70,115],"concise":[72],"set":[73],"optimized":[75],"CUDA":[76],"kernels.":[77],"Four":[78],"orthogonal":[79],"techniques":[80],"underpin":[81],"design:":[83],"(i)":[84],"lookup-table":[85],"with":[86,102,150],"linear":[87],"interpolation":[88],"that":[89],"replaces":[90],"runtime":[91],"expensive":[92],"math-library":[93],"functions;":[94],"(ii)":[95],"2D":[96],"tiling":[97],"to":[98],"expose":[99],"thread-level":[100],"parallelism":[101],"preserving":[103],"memory":[104],"locality;":[105],"(iii)":[106],"two-stage":[108],"reduction":[109],"scheme":[110],"converting":[111],"scattered":[112],"atomic":[113],"updates":[114],"single":[117],"controllable":[118],"merge":[119],"step;":[120],"(iv)":[122],"coefficient-layout":[123],"reordering":[124],"yielding":[125],"unit-stride":[126],"reads":[127],"under":[128],"tiled":[130],"schedule.":[131],"can":[133],"deliver":[134],"1.2\u201310":[135],"\u00d7":[136,141],"faster":[137,142],"inference":[138],"1.4\u201312":[140],"training":[143],"Triton":[146],"+":[147],"cuBLAS":[148],"baseline,":[149],"identical":[151],"accuracy":[152],"on":[153,159],"speech,":[154],"audio-enhancement,":[155],"tabular-regression":[157],"workloads":[158],"both":[160],"highend":[161],"consumer-grade":[164],"GPU.":[165]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-07-03T00:00:00"}