{"id":"https://openalex.org/W4407218673","doi":"https://doi.org/10.1145/3669940.3707216","title":"Composing Distributed Computations Through Task and Kernel Fusion","display_name":"Composing Distributed Computations Through Task and Kernel Fusion","publication_year":2025,"publication_date":"2025-02-06","ids":{"openalex":"https://openalex.org/W4407218673","doi":"https://doi.org/10.1145/3669940.3707216"},"language":"en","primary_location":{"id":"doi:10.1145/3669940.3707216","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3669940.3707216","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 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3669940.3707216","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047980263","display_name":"Rohan Yadav","orcid":"https://orcid.org/0000-0003-0746-066X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rohan Yadav","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0746-066X","affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048424118","display_name":"Shiv Sundram","orcid":"https://orcid.org/0000-0001-5228-1295"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiv Sundram","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5228-1295","affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103167846","display_name":"Wonchan Lee","orcid":"https://orcid.org/0000-0001-8364-5784"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wonchan Lee","raw_affiliation_strings":["NVIDIA, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8364-5784","affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024606205","display_name":"Michael Garland","orcid":"https://orcid.org/0000-0001-6093-7602"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Garland","raw_affiliation_strings":["NVIDIA, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-6093-7602","affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077152489","display_name":"Michael Bauer","orcid":"https://orcid.org/0000-0001-8928-3032"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Bauer","raw_affiliation_strings":["NVIDIA, Santa Clara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8928-3032","affiliations":[{"raw_affiliation_string":"NVIDIA, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087402475","display_name":"Alex Aiken","orcid":"https://orcid.org/0000-0002-3723-9555"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Aiken","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3723-9555","affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041886781","display_name":"Fredrik Kj\u00f8lstad","orcid":"https://orcid.org/0000-0002-2267-903X"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fredrik Kjolstad","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2267-903X","affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5047980263"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01367609,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"182","last_page":"197"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9929999709129333,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7559537887573242},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6427528858184814},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5936936736106873},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5695987343788147},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4694603979587555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32634082436561584},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32406139373779297},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18096378445625305},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09959414601325989},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06820917129516602}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7559537887573242},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6427528858184814},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5936936736106873},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5695987343788147},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4694603979587555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32634082436561584},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32406139373779297},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18096378445625305},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09959414601325989},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06820917129516602},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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:10.1145/3669940.3707216","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3669940.3707216","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 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3669940.3707216","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3669940.3707216","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 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6074738740","display_name":null,"funder_award_id":"CCF-2216964","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1493774699","https://openalex.org/W1915071989","https://openalex.org/W1966981171","https://openalex.org/W1981109753","https://openalex.org/W1984777596","https://openalex.org/W1998857607","https://openalex.org/W2008677874","https://openalex.org/W2010152440","https://openalex.org/W2094657370","https://openalex.org/W2152506070","https://openalex.org/W2153185479","https://openalex.org/W2289151794","https://openalex.org/W2590246587","https://openalex.org/W2767510344","https://openalex.org/W2901021204","https://openalex.org/W2909382770","https://openalex.org/W2981758446","https://openalex.org/W2981859891","https://openalex.org/W2984884442","https://openalex.org/W2987684178","https://openalex.org/W2987944157","https://openalex.org/W3174529902","https://openalex.org/W3183805942","https://openalex.org/W3187688612","https://openalex.org/W3209526830","https://openalex.org/W4211105367","https://openalex.org/W4220690649","https://openalex.org/W4220818654","https://openalex.org/W4220876151","https://openalex.org/W4221158240","https://openalex.org/W4237521714","https://openalex.org/W4248722156","https://openalex.org/W4251637954","https://openalex.org/W4290648346","https://openalex.org/W4318605726","https://openalex.org/W4321446115","https://openalex.org/W4390604611","https://openalex.org/W4394998532","https://openalex.org/W6810475161"],"related_works":["https://openalex.org/W4231775656","https://openalex.org/W2046435967","https://openalex.org/W2383646825","https://openalex.org/W2371018915","https://openalex.org/W2354191502","https://openalex.org/W1972225038","https://openalex.org/W3134658850","https://openalex.org/W2355938171","https://openalex.org/W2780079842","https://openalex.org/W814988660"],"abstract_inverted_index":{"We":[0,47,63],"introduce":[1],"Diffuse,":[2],"a":[3,44,52,75],"system":[4],"that":[5,29,66],"dynamically":[6],"performs":[7],"task":[8,49],"and":[9,83,93,110],"kernel":[10],"fusion":[11,36,50],"in":[12,43],"distributed,":[13],"task-based":[14,80,103],"runtime":[15],"systems.":[16],"The":[17],"key":[18],"component":[19],"of":[20,26,37,140],"Diffuse":[21,87,96,119],"is":[22,70],"an":[23,141],"intermediate":[24,68],"representation":[25,69],"distributed":[27,38],"computation":[28],"enables":[30],"the":[31,35,58,126,138],"necessary":[32],"analyses":[33],"for":[34,77],"tasks":[39],"to":[40,55,73,116,134],"be":[41,74],"performed":[42],"scalable":[45],"manner.":[46],"pair":[48],"with":[51],"JIT":[53],"compiler":[54],"fuse":[56],"together":[57],"kernels":[59],"within":[60],"fused":[61],"tasks.":[62],"show":[64],"empirically":[65],"Diffuse's":[67],"general":[71],"enough":[72],"target":[76],"two":[78],"real-world,":[79],"libraries":[81,104],"(cuPyNumeric":[82],"Legate":[84],"Sparse),":[85],"letting":[86],"find":[88],"optimization":[89,122],"opportunities":[90,123],"across":[91],"function":[92],"library":[94],"boundaries.":[95],"accelerates":[97],"unmodified":[98],"applications":[99],"developed":[100],"by":[101,105,111,125],"composing":[102],"1.86x":[106],"on":[107,114],"average":[108],"(geo-mean),":[109],"between":[112],"0.93x--10.7x":[113],"up":[115],"128":[117],"GPUs.":[118],"also":[120],"finds":[121],"missed":[124],"original":[127],"application":[128],"developers,":[129],"enabling":[130],"high-level":[131],"Python":[132],"programs":[133],"match":[135],"or":[136],"exceed":[137],"performance":[139],"explicitly":[142],"parallel":[143],"MPI":[144],"library.":[145]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
