{"id":"https://openalex.org/W2015935981","doi":"https://doi.org/10.1145/1542275.1542312","title":"Tuned and wildly asynchronous stencil kernels for hybrid CPU/GPU systems","display_name":"Tuned and wildly asynchronous stencil kernels for hybrid CPU/GPU systems","publication_year":2009,"publication_date":"2009-06-08","ids":{"openalex":"https://openalex.org/W2015935981","doi":"https://doi.org/10.1145/1542275.1542312","mag":"2015935981"},"language":"en","primary_location":{"id":"doi:10.1145/1542275.1542312","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1542275.1542312","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 international conference on Supercomputing","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/A5072572139","display_name":"Sundaresan Venkatasubramanian","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sundaresan Venkatasubramanian","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA","Georgia Institute of Technology Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016738770","display_name":"Richard Vuduc","orcid":"https://orcid.org/0000-0003-2178-138X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard W. Vuduc","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA","Georgia Institute of Technology Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":7.1331,"has_fulltext":false,"cited_by_count":84,"citation_normalized_percentile":{"value":0.9782011,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"244","last_page":"255"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10739","display_name":"Electromagnetic Scattering and Analysis","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8614453077316284},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.7804884910583496},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7739826440811157},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.611923336982727},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.6050007343292236},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5140303373336792},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.5136715769767761},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4871758818626404},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.20652031898498535},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.16450509428977966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8614453077316284},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.7804884910583496},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7739826440811157},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.611923336982727},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.6050007343292236},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5140303373336792},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.5136715769767761},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4871758818626404},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.20652031898498535},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.16450509428977966},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1542275.1542312","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1542275.1542312","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 international conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1488895196","https://openalex.org/W1545748428","https://openalex.org/W1760551737","https://openalex.org/W1978564754","https://openalex.org/W1990832096","https://openalex.org/W1998773459","https://openalex.org/W2009790039","https://openalex.org/W2016358047","https://openalex.org/W2027622580","https://openalex.org/W2063186542","https://openalex.org/W2128069584","https://openalex.org/W2147974772","https://openalex.org/W2154118576","https://openalex.org/W2154786353","https://openalex.org/W2162241008","https://openalex.org/W2949464108","https://openalex.org/W4206566500","https://openalex.org/W4212782655"],"related_works":["https://openalex.org/W3105129168","https://openalex.org/W2804920739","https://openalex.org/W4316371992","https://openalex.org/W2186216222","https://openalex.org/W2392765154","https://openalex.org/W2564509292","https://openalex.org/W4294338060","https://openalex.org/W1491017262","https://openalex.org/W1494824878","https://openalex.org/W4297819361"],"abstract_inverted_index":{"We":[0],"describe":[1],"heterogeneous":[2],"multi-CPU":[3],"and":[4,23,45,84,153],"multi-GPU":[5],"implementations":[6,62,116],"of":[7,32,39,111,149],"Jacobi's":[8],"iterative":[9],"method":[10],"for":[11,107],"the":[12,33,69,132,146],"2-D":[13],"Poisson":[14],"equation":[15],"on":[16,41,47,80,117,141],"a":[17,42,48,53,108,118],"structured":[18],"grid,":[19],"in":[20,145],"both":[21],"single-":[22],"double-precision.":[24],"Properly":[25],"tuned,":[26],"our":[27,125],"best":[28,126],"implementation":[29,129],"achieves":[30],"98%":[31],"empirical":[34],"streaming":[35],"GPU":[36,119,128],"bandwidth":[37],"(66%":[38],"peak)":[40],"NVIDIA":[43],"C1060,":[44],"78%":[46],"C870.":[49],"Motivated":[50],"to":[51,105],"find":[52],"still":[54],"faster":[55,123],"implementation,":[56],"we":[57,87,98],"further":[58],"consider":[59],"\"wildly":[60],"asynchronous\"":[61],"that":[63],"can":[64,120],"reduce":[65],"or":[66,90,157],"even":[67],"eliminate":[68],"synchronization":[70,92,156],"bottleneck":[71],"between":[72,93],"iterations.":[73,94],"In":[74],"these":[75],"versions,":[76],"which":[77],"are":[78],"based":[79],"chaotic":[81],"relaxation":[82],"(Chazan":[83],"Miranker,":[85],"1969),":[86],"simply":[88],"remove":[89],"delay":[91],"By":[95],"doing":[96],"so,":[97],"trade-off":[99],"more":[100,103],"flops,":[101],"via":[102],"iterations":[104],"converge,":[106],"higher":[109],"degree":[110],"asynchronous":[112],"parallelism.":[113],"Our":[114],"wild":[115],"be":[121],"1.2-2.5x":[122],"than":[124],"synchronized":[127],"while":[130],"achieving":[131],"same":[133],"accuracy.":[134],"Looking":[135],"forward,":[136],"this":[137],"result":[138],"suggests":[139],"research":[140],"similarly":[142],"\"fast-and-loose\"":[143],"algorithms":[144],"coming":[147],"era":[148],"increasingly":[150],"massive":[151],"concurrency":[152],"relatively":[154],"high":[155],"communication":[158],"costs.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":18}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
