{"id":"https://openalex.org/W1987588924","doi":"https://doi.org/10.1145/1542275.1542313","title":"Performance modeling and automatic ghost zone optimization for iterative stencil loops on GPUs","display_name":"Performance modeling and automatic ghost zone optimization for iterative stencil loops on GPUs","publication_year":2009,"publication_date":"2009-06-08","ids":{"openalex":"https://openalex.org/W1987588924","doi":"https://doi.org/10.1145/1542275.1542313","mag":"1987588924"},"language":"en","primary_location":{"id":"doi:10.1145/1542275.1542313","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1542275.1542313","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":"article","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/A5018781096","display_name":"Jiayuan Meng","orcid":"https://orcid.org/0000-0002-1135-6518"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiayuan Meng","raw_affiliation_strings":["University of Virginia, Charlottesville, VA, USA","University of Virginia, CHarlottesville, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"University of Virginia, CHarlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074818897","display_name":"Kevin Skadron","orcid":"https://orcid.org/0000-0002-8091-9302"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Skadron","raw_affiliation_strings":["University of Virginia, Charlottesville, VA, USA","University of Virginia, CHarlottesville, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]},{"raw_affiliation_string":"University of Virginia, CHarlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.5277,"has_fulltext":false,"cited_by_count":145,"citation_normalized_percentile":{"value":0.98732021,"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":"256","last_page":"265"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991999864578247,"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/T10049","display_name":"Magnetic properties of thin films","score":0.9933000206947327,"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/stencil","display_name":"Stencil","score":0.8957679867744446},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8534940481185913},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8389713764190674},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7786386013031006},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5989528894424438},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5730165839195251},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4604746401309967},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.4418160021305084},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.4261338412761688},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4242219030857086},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.23708966374397278},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1699059009552002},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.15320032835006714},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.10472160577774048},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.087922602891922}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.8957679867744446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8534940481185913},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8389713764190674},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7786386013031006},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5989528894424438},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5730165839195251},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4604746401309967},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.4418160021305084},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.4261338412761688},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4242219030857086},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.23708966374397278},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1699059009552002},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.15320032835006714},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.10472160577774048},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.087922602891922},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1542275.1542313","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1542275.1542313","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.217.861","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.217.861","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.virginia.edu/~skadron/Papers/meng_stencil_ics09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W21157182","https://openalex.org/W1507046864","https://openalex.org/W1537323515","https://openalex.org/W1561247983","https://openalex.org/W1825294837","https://openalex.org/W1964639877","https://openalex.org/W1967264375","https://openalex.org/W1968013322","https://openalex.org/W1988888548","https://openalex.org/W1997375049","https://openalex.org/W1997702398","https://openalex.org/W2003798513","https://openalex.org/W2028499920","https://openalex.org/W2028531867","https://openalex.org/W2037743346","https://openalex.org/W2055253125","https://openalex.org/W2057911989","https://openalex.org/W2090457779","https://openalex.org/W2097116331","https://openalex.org/W2100108901","https://openalex.org/W2100926459","https://openalex.org/W2110090002","https://openalex.org/W2119042753","https://openalex.org/W2125517938","https://openalex.org/W2127669603","https://openalex.org/W2128022558","https://openalex.org/W2138166974","https://openalex.org/W2148869717","https://openalex.org/W2149668662","https://openalex.org/W2154786353","https://openalex.org/W2156316655","https://openalex.org/W2156841718","https://openalex.org/W2795744704","https://openalex.org/W3021722416","https://openalex.org/W3138798301","https://openalex.org/W6630311386","https://openalex.org/W6639179668"],"related_works":["https://openalex.org/W3105129168","https://openalex.org/W2804920739","https://openalex.org/W4316371992","https://openalex.org/W2058965144","https://openalex.org/W2186216222","https://openalex.org/W2164382479","https://openalex.org/W2392765154","https://openalex.org/W2564509292","https://openalex.org/W2008005532","https://openalex.org/W1966837078"],"abstract_inverted_index":{"Iterative":[0],"stencil":[1,107],"loops":[2],"(ISLs)":[3],"are":[4,21,28,218],"used":[5,49],"in":[6,75,154],"many":[7],"applications":[8],"and":[9,37,59,111,142,145,179,198],"tiling":[10],"is":[11,47,72,204],"a":[12,24,155,168,176,181,222],"well-known":[13],"technique":[14],"to":[15,34,50,105,188,220],"localize":[16],"their":[17],"computation.":[18],"When":[19],"ISLs":[20],"tiled":[22],"across":[23,93],"parallel":[25,66],"architecture,":[26],"there":[27],"usually":[29],"halo":[30,55],"regions":[31],"that":[32,183,195],"need":[33],"be":[35,103],"updated":[36],"exchanged":[38],"among":[39],"different":[40],"processing":[41],"elements":[42],"(PEs).":[43],"In":[44],"addition,":[45],"synchronization":[46,60,112],"often":[48],"signal":[51],"the":[52,76,86,89,115,126,129,136,140,143,185,191,213,229],"completion":[53],"of":[54,78,88,117,128,138,228],"exchanges.":[56],"Both":[57],"communication":[58,110],"may":[61],"incur":[62],"significant":[63],"overhead":[64],"on":[65,122,135,162],"architectures":[67],"with":[68],"shared":[69,163],"memory.":[70],"This":[71],"especially":[73],"true":[74],"case":[77,177],"graphics":[79],"processors":[80],"(GPUs),":[81],"which":[82,212],"do":[83],"not":[84],"preserve":[85],"state":[87],"per-core":[90],"L1":[91],"storage":[92],"global":[94],"synchronizations.":[95],"To":[96,158],"reduce":[97],"these":[98],"overheads,":[99],"ghost":[100,131,192,215],"zones":[101],"can":[102],"created":[104],"replicate":[106],"operations,":[108],"reducing":[109],"costs":[113],"at":[114],"expense":[116],"redundantly":[118],"computing":[119],"some":[120],"values":[121],"multiple":[123],"PEs.":[124],"However,":[125],"selection":[127],"optimal":[130,230],"zone":[132,193,216],"size":[133,194],"depends":[134],"characteristics":[137],"both":[139],"architecture":[141,174],"application,":[144],"it":[146],"has":[147],"only":[148],"been":[149],"studied":[150],"for":[151,211],"message-passing":[152],"systems":[153],"grid":[156],"environment.":[157],"automate":[159],"this":[160],"process":[161],"memory":[164],"systems,":[165],"we":[166],"establish":[167],"performance":[169,186],"model":[170,187],"using":[171],"NVIDIA's":[172],"Tesla":[173],"as":[175],"study":[178],"propose":[180],"framework":[182],"uses":[184],"automatically":[189],"select":[190],"performs":[196],"best":[197],"generate":[199],"appropriate":[200],"code.":[201],"The":[202],"modeling":[203],"validated":[205],"by":[206],"four":[207],"diverse":[208],"ISL":[209],"applications,":[210],"predicted":[214],"configurations":[217],"able":[219],"achieve":[221],"speedup":[223],"no":[224],"less":[225],"than":[226],"98%":[227],"speedup.":[231]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":15},{"year":2014,"cited_by_count":13},{"year":2013,"cited_by_count":21},{"year":2012,"cited_by_count":19}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}