{"id":"https://openalex.org/W4411522856","doi":"https://doi.org/10.1145/3728959","title":"Dynamically Fusing Python HPC Kernels","display_name":"Dynamically Fusing Python HPC Kernels","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4411522856","doi":"https://doi.org/10.1145/3728959"},"language":"en","primary_location":{"id":"doi:10.1145/3728959","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3728959","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3728959","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045662707","display_name":"Nader Al Awar","orcid":"https://orcid.org/0000-0002-7390-5834"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nader Al Awar","raw_affiliation_strings":["University of Texas at Austin, Austin, USA"],"raw_orcid":"https://orcid.org/0000-0002-7390-5834","affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Muhammad Hannan Naeem","orcid":"https://orcid.org/0009-0000-3689-4163"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muhammad Hannan Naeem","raw_affiliation_strings":["University of Texas at Austin, Austin, USA"],"raw_orcid":"https://orcid.org/0009-0000-3689-4163","affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008536057","display_name":"James Almgren-Bell","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Almgren-Bell","raw_affiliation_strings":["University of Texas at Austin, Austin, USA"],"raw_orcid":"https://orcid.org/0009-0000-0287-675X","affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044137409","display_name":"George Biros","orcid":"https://orcid.org/0000-0002-0033-3994"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Biros","raw_affiliation_strings":["University of Texas at Austin, Austin, USA"],"raw_orcid":"https://orcid.org/0000-0002-0033-3994","affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063052820","display_name":"Milos Gligoric","orcid":"https://orcid.org/0000-0002-5894-7649"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Milos Gligoric","raw_affiliation_strings":["University of Texas at Austin, Austin, USA"],"raw_orcid":"https://orcid.org/0000-0002-5894-7649","affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5045662707"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13089974,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":"ISSTA","first_page":"1865","last_page":"1886"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9855999946594238,"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/T13650","display_name":"Computational Physics and Python Applications","score":0.9765999913215637,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8861408233642578},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.7664732336997986},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7045124769210815},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.6945208311080933},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6218501925468445},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5289231538772583},{"id":"https://openalex.org/keywords/porting","display_name":"Porting","score":0.5091807246208191},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.48182621598243713},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.45045381784439087},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.44938698410987854},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4375036060810089},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.25836822390556335}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8861408233642578},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7664732336997986},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7045124769210815},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.6945208311080933},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6218501925468445},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5289231538772583},{"id":"https://openalex.org/C106251023","wikidata":"https://www.wikidata.org/wiki/Q851989","display_name":"Porting","level":3,"score":0.5091807246208191},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.48182621598243713},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.45045381784439087},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.44938698410987854},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4375036060810089},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.25836822390556335},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3728959","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3728959","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Software Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3728959","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3728959","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1965742121","https://openalex.org/W1972783048","https://openalex.org/W1981896890","https://openalex.org/W1992558790","https://openalex.org/W2023415862","https://openalex.org/W2078794610","https://openalex.org/W2102394168","https://openalex.org/W2106329447","https://openalex.org/W2160105704","https://openalex.org/W2807799957","https://openalex.org/W2913310273","https://openalex.org/W2984884442","https://openalex.org/W2993781365","https://openalex.org/W3096835151","https://openalex.org/W3098506918","https://openalex.org/W3105115110","https://openalex.org/W3108779999","https://openalex.org/W3134465755","https://openalex.org/W3160781636","https://openalex.org/W3166310167","https://openalex.org/W3195293013","https://openalex.org/W3200743451","https://openalex.org/W3207945374","https://openalex.org/W4220818654","https://openalex.org/W4231684867","https://openalex.org/W4281768830","https://openalex.org/W4294089543","https://openalex.org/W4312068725","https://openalex.org/W4312794550","https://openalex.org/W4318605726","https://openalex.org/W4321184915","https://openalex.org/W4399426405","https://openalex.org/W6931846337"],"related_works":["https://openalex.org/W2356602486","https://openalex.org/W2351992668","https://openalex.org/W2324828474","https://openalex.org/W2374315191","https://openalex.org/W2391207559","https://openalex.org/W2384715785","https://openalex.org/W2349624418","https://openalex.org/W2064459023","https://openalex.org/W2062837242","https://openalex.org/W1987014004"],"abstract_inverted_index":{"Recent":[0],"trends":[1,27],"in":[2,8,35,66,75],"high-performance":[3],"computing":[4],"show":[5,163],"an":[6],"increase":[7],"the":[9,109,114,155],"adoption":[10],"of":[11,94,127,174],"performance":[12,95],"portable":[13,96],"frameworks":[14],"such":[15,21],"as":[16,22,53,181,183],"Kokkos":[17],"and":[18,28,61,104,132,178,185],"interpreted":[19],"languages":[20],"Python.":[23],"PyKokkos":[24,97,144],"follows":[25],"these":[26],"enables":[29],"programmers":[30,44,71],"to":[31,49,72,124,142,171],"write":[32],"performance-portable":[33],"kernels":[34,58,74,119,157,173],"Python":[36],"which":[37],"greatly":[38],"increases":[39],"productivity.":[40],"One":[41],"issue":[42],"that":[43,120,152,164],"still":[45],"face":[46],"is":[47,111],"how":[48],"organize":[50,73],"parallel":[51],"code,":[52],"splitting":[54],"code":[55,150],"into":[56],"separate":[57],"simplifies":[59],"testing":[60],"debugging":[62],"but":[63],"may":[64],"result":[65,110],"suboptimal":[67],"performance.":[68],"To":[69],"enable":[70],"any":[76,140],"way":[77],"they":[78],"prefer":[79],"while":[80,137],"ensuring":[81],"good":[82],"performance,":[83],"we":[84],"present":[85],"PyFuser,":[86],"a":[87],"program":[88],"analysis":[89],"framework":[90],"for":[91],"automatic":[92],"fusion":[93],"kernels.":[98],"PyFuser":[99,116,167],"dynamically":[100],"traces":[101],"kernel":[102,134],"calls":[103],"lazily":[105],"fuses":[106],"them":[107],"once":[108],"requested":[112],"by":[113,159],"application.":[115],"generates":[117],"fused":[118,156],"execute":[121],"faster":[122],"due":[123],"better":[125],"reuse":[126],"data,":[128],"improved":[129],"compiler":[130],"optimizations,":[131],"reduced":[133],"launch":[135],"overhead,":[136],"not":[138],"requiring":[139],"changes":[141],"existing":[143],"code.":[145],"We":[146],"also":[147],"introduce":[148],"automated":[149],"transformations":[151],"further":[153],"optimize":[154],"generated":[158],"PyFuser.":[160],"Our":[161],"experiments":[162],"on":[165,176],"average":[166],"achieves":[168],"speedups":[169],"compared":[170],"unfused":[172],"3.8x":[175],"NVIDIA":[177],"AMD":[179,186],"GPUs,":[180],"well":[182],"Intel":[184],"CPUs.":[187]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}