{"id":"https://openalex.org/W4413411758","doi":"https://doi.org/10.1145/3721145.3728489","title":"Leonid: Exploring Automated Kernel Fusion in Performance-Portable Programming Models for Scientific Computation","display_name":"Leonid: Exploring Automated Kernel Fusion in Performance-Portable Programming Models for Scientific Computation","publication_year":2025,"publication_date":"2025-06-08","ids":{"openalex":"https://openalex.org/W4413411758","doi":"https://doi.org/10.1145/3721145.3728489"},"language":"en","primary_location":{"id":"doi:10.1145/3721145.3728489","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721145.3728489","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3721145.3728489","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3721145.3728489","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100408854","display_name":"Chenchen Zhang","orcid":"https://orcid.org/0000-0003-4276-0510"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenchen Zhang","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103423687","display_name":"Hao Luo","orcid":"https://orcid.org/0009-0008-1038-944X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Luo","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005718995","display_name":"Chao Yang","orcid":"https://orcid.org/0000-0001-7426-6248"},"institutions":[{"id":"https://openalex.org/I198357462","display_name":"Changsha University","ror":"https://ror.org/011d8sm39","country_code":"CN","type":"education","lineage":["https://openalex.org/I198357462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Yang","raw_affiliation_strings":["Peking University, Beijing, China and PKU-Changsha Institute of Computing and Digital Economy, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China and PKU-Changsha Institute of Computing and Digital Economy, Changsha, China","institution_ids":["https://openalex.org/I198357462"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100408854"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22103313,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"928","last_page":"942"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9988999962806702,"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":0.9988999962806702,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7046680450439453},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5986307263374329},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5522735118865967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4002669155597687},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3463352918624878},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.23783448338508606},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10018843412399292}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7046680450439453},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5986307263374329},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5522735118865967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4002669155597687},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3463352918624878},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.23783448338508606},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10018843412399292},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3721145.3728489","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721145.3728489","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3721145.3728489","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3721145.3728489","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3721145.3728489","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3721145.3728489","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th ACM International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1455953252","display_name":null,"funder_award_id":"1228810","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2519258023","display_name":null,"funder_award_id":"12288101","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3632975512","display_name":null,"funder_award_id":"01170","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4176251304","display_name":null,"funder_award_id":"12131002","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413411758.pdf","grobid_xml":"https://content.openalex.org/works/W4413411758.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1252105715","https://openalex.org/W1595783387","https://openalex.org/W1967810725","https://openalex.org/W1973897068","https://openalex.org/W1974133504","https://openalex.org/W1986982278","https://openalex.org/W2001611463","https://openalex.org/W2019793962","https://openalex.org/W2022039320","https://openalex.org/W2023415862","https://openalex.org/W2049571791","https://openalex.org/W2050129046","https://openalex.org/W2059473569","https://openalex.org/W2066060292","https://openalex.org/W2078794610","https://openalex.org/W2153190325","https://openalex.org/W2159959523","https://openalex.org/W2160650521","https://openalex.org/W2323178299","https://openalex.org/W2399715892","https://openalex.org/W2913114028","https://openalex.org/W2915753052","https://openalex.org/W2964624821","https://openalex.org/W2970909703","https://openalex.org/W2996807164","https://openalex.org/W3013569554","https://openalex.org/W3120676137","https://openalex.org/W3127736057","https://openalex.org/W3161200675","https://openalex.org/W3195293013","https://openalex.org/W3199181189","https://openalex.org/W3210190478","https://openalex.org/W4210953084","https://openalex.org/W4220818654","https://openalex.org/W4244917406","https://openalex.org/W4251637954","https://openalex.org/W4281390154","https://openalex.org/W4294734199","https://openalex.org/W4309467950","https://openalex.org/W4388316717","https://openalex.org/W4404997833"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"With":[0],"advances":[1],"in":[2,125],"hardware":[3,24],"performance,":[4],"architectural":[5],"divergence":[6,25],"and":[7,14,58,62,66,91,115,117,128,131],"the":[8,86,119],"growing":[9],"gap":[10],"between":[11],"computational":[12],"power":[13],"memory":[15,60],"bandwidth":[16],"have":[17],"become":[18],"increasingly":[19],"pronounced.Existing":[20],"performance-portable":[21,43,141],"models":[22,142],"address":[23,36],"but":[26],"lack":[27,144],"automated":[28,49,74,80,95,145],"kernel":[29,50,75,81,96,146],"fusion":[30,82,147],"to":[31,47,104],"optimize":[32],"memory-bound":[33],"scientific":[34],"applications.To":[35],"this":[37],"issue,":[38],"we":[39],"propose":[40],"Leonid,":[41],"a":[42,136],"programming":[44],"model":[45],"designed":[46],"support":[48],"fusion.Leonid":[51],"integrates":[52],"separate":[53],"modules":[54],"for":[55,63,73,94],"unified":[56,64],"global":[57],"scratchpad":[59],"management,":[61],"parallel":[65],"serial":[67],"execution":[68],"patterns,":[69],"both":[70],"specifically":[71],"tailored":[72],"fusion,":[76],"alongside":[77],"an":[78],"integrated":[79],"module.These":[83],"components":[84],"ensure":[85],"compatibility":[87],"across":[88],"CPUs,":[89],"GPUs,":[90],"Sunway":[92],"platforms":[93],"fusion.Performance":[97],"evaluations":[98],"demonstrate":[99],"that":[100,143],"Leonid":[101,134],"achieves":[102],"up":[103],"1.52":[105],"speedup":[106],"(averaging":[107],"1.19)":[108],"over":[109,139],"manually":[110,122],"implemented":[111],"code,":[112,133],"outperforms":[113],"Kokkos":[114],"RAJA,":[116],"matches":[118],"efficiency":[120],"of":[121],"fused":[123],"code":[124],"bandwidthlimited":[126],"algorithms":[127],"applications.For":[129],"bandwidth-limited":[130],"fusion-eligible":[132],"offers":[135],"significant":[137],"advantage":[138],"other":[140],"capabilities.":[148]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}