{"id":"https://openalex.org/W4407857728","doi":"https://doi.org/10.1145/3696443.3708939","title":"Proteus: Portable Runtime Optimization of GPU Kernel Execution with Just-in-Time Compilation","display_name":"Proteus: Portable Runtime Optimization of GPU Kernel Execution with Just-in-Time Compilation","publication_year":2025,"publication_date":"2025-02-22","ids":{"openalex":"https://openalex.org/W4407857728","doi":"https://doi.org/10.1145/3696443.3708939"},"language":"en","primary_location":{"id":"doi:10.1145/3696443.3708939","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3696443.3708939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM/IEEE International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081323651","display_name":"Giorgis Georgakoudis","orcid":"https://orcid.org/0000-0001-6542-3555"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Giorgis Georgakoudis","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, USA"],"raw_orcid":"https://orcid.org/0000-0001-6542-3555","affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060247025","display_name":"Konstantinos Parasyris","orcid":"https://orcid.org/0000-0002-8258-9693"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Konstantinos Parasyris","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, USA"],"raw_orcid":"https://orcid.org/0000-0002-8258-9693","affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012439480","display_name":"David Beckingsale","orcid":"https://orcid.org/0000-0003-2545-4837"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Beckingsale","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, USA"],"raw_orcid":"https://orcid.org/0000-0003-2545-4837","affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, USA","institution_ids":["https://openalex.org/I1282311441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1282311441"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"507","last_page":"522"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9975000023841858,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9937000274658203,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/computer-science","display_name":"Computer science","score":0.7658600807189941},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6103395819664001},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5766102075576782},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.42792218923568726},{"id":"https://openalex.org/keywords/execution-time","display_name":"Execution time","score":0.4101124405860901},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.330355167388916},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05173489451408386}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7658600807189941},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6103395819664001},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5766102075576782},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.42792218923568726},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.4101124405860901},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.330355167388916},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05173489451408386},{"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:10.1145/3696443.3708939","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3696443.3708939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM/IEEE International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1810396090","https://openalex.org/W1968815260","https://openalex.org/W1978506930","https://openalex.org/W1993335798","https://openalex.org/W1999500280","https://openalex.org/W1999926936","https://openalex.org/W2007920703","https://openalex.org/W2016889996","https://openalex.org/W2021951417","https://openalex.org/W2036830099","https://openalex.org/W2050291019","https://openalex.org/W2076812085","https://openalex.org/W2077436409","https://openalex.org/W2094269821","https://openalex.org/W2116136092","https://openalex.org/W2120575449","https://openalex.org/W2128457714","https://openalex.org/W2160756430","https://openalex.org/W2167728712","https://openalex.org/W2245493112","https://openalex.org/W2301928242","https://openalex.org/W2506163396","https://openalex.org/W2572804059","https://openalex.org/W2585893039","https://openalex.org/W2593390416","https://openalex.org/W2736325406","https://openalex.org/W2766807579","https://openalex.org/W2810631450","https://openalex.org/W2954698171","https://openalex.org/W2979470607","https://openalex.org/W2996849306","https://openalex.org/W2998595860","https://openalex.org/W3159859651","https://openalex.org/W3207677123","https://openalex.org/W4246166885","https://openalex.org/W4247335479","https://openalex.org/W4256499770","https://openalex.org/W4388483751","https://openalex.org/W4388665000"],"related_works":["https://openalex.org/W2418291489","https://openalex.org/W3096519538","https://openalex.org/W2744747300","https://openalex.org/W4241166160","https://openalex.org/W2068121105","https://openalex.org/W2384826897","https://openalex.org/W1973516247","https://openalex.org/W1997466117","https://openalex.org/W2795695574","https://openalex.org/W2607115797"],"abstract_inverted_index":{"In":[0],"High-performance":[1],"computing":[2],"(HPC)":[3],"fast":[4,31],"application":[5],"execution":[6],"is":[7,13,21],"the":[8],"primary":[9],"objective.":[10],"HPC":[11],"software":[12],"written":[14],"in":[15,157],"high-performance":[16],"languages":[17],"(C/C++,":[18],"Fortran)":[19],"and":[20,59,75,87,106,118,133,153],"statically":[22],"compiled":[23],"Ahead-of-Time":[24],"(AOT)":[25],"using":[26],"optimizing":[27],"compilers":[28],"to":[29,65,80,90,129,150],"generate":[30],"code.":[32],"AOT":[33,138],"compilation":[34,63,82],"optimizes":[35,76],"source":[36],"code":[37,156],"with":[38,144],"only":[39],"limited":[40],"information":[41],"available":[42],"at":[43,69],"compile":[44],"time,":[45],"which":[46],"precludes":[47],"possible":[48],"optimization":[49],"leveraging":[50],"runtime":[51],"information.":[52],"We":[53],"propose":[54],"Proteus,":[55],"an":[56,145],"easy-to-use,":[57],"portable,":[58],"lightweight":[60],"Just-In-Time":[61],"(JIT)":[62],"approach":[64],"optimize":[66],"GPU":[67,101],"kernels":[68,102],"runtime.":[70],"Proteus":[71,99,123],"dynamically":[72],"extracts,":[73],"compiles,":[74],"language-agnostic":[77],"LLVM":[78],"IR":[79],"reduce":[81],"overhead":[83,152],"while":[84,140],"enhancing":[85],"portability":[86],"versatility":[88],"compared":[89],"language-specific":[91],"solutions.":[92],"Using":[93],"a":[94,111],"minimally":[95],"intrusive":[96],"annotation-based":[97],"interface,":[98],"specializes":[100],"for":[103,131],"input":[104],"arguments":[105],"launch":[107],"parameters.":[108],"Evaluation":[109],"on":[110,116,135],"diverse":[112],"set":[113],"of":[114],"programs":[115],"AMD":[117,132],"NVIDIA":[119],"GPUs":[120],"shows":[121],"that":[122],"achieves":[124],"significant":[125],"end-to-end":[126],"speedup,":[127],"up":[128],"2.8\u00d7":[130],"1.78\u00d7":[134],"NVIDIA,":[136],"over":[137],"optimization,":[139],"outperforming":[141],"CUDA-specific":[142],"Jitify":[143],"average":[146],"1.23\u00d7":[147],"speedp,":[148],"thanks":[149],"reduced":[151],"faster":[154],"binary":[155],"certain":[158],"cases.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}