{"id":"https://openalex.org/W2616707232","doi":"https://doi.org/10.1109/tmscs.2017.2705139","title":"Thoroughly Exploring GPU Buffering Options for Stencil Code by Using an Efficiency Measure and a Performance Model","display_name":"Thoroughly Exploring GPU Buffering Options for Stencil Code by Using an Efficiency Measure and a Performance Model","publication_year":2017,"publication_date":"2017-05-17","ids":{"openalex":"https://openalex.org/W2616707232","doi":"https://doi.org/10.1109/tmscs.2017.2705139","mag":"2616707232"},"language":"en","primary_location":{"id":"doi:10.1109/tmscs.2017.2705139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmscs.2017.2705139","pdf_url":null,"source":{"id":"https://openalex.org/S4210201583","display_name":"IEEE Transactions on Multi-Scale Computing Systems","issn_l":"2332-7766","issn":["2332-7766","2372-207X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multi-Scale Computing Systems","raw_type":"journal-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/A5057472134","display_name":"Yue Hu","orcid":"https://orcid.org/0000-0001-8959-6995"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yue Hu","raw_affiliation_strings":["Intel, Inc., Santa Clara, CA"],"raw_orcid":"https://orcid.org/0000-0001-8959-6995","affiliations":[{"raw_affiliation_string":"Intel, Inc., Santa Clara, CA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036726653","display_name":"David M. Koppelman","orcid":null},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David M. Koppelman","raw_affiliation_strings":["Division of Electrical and Computer Engineering and Center for Computation and Technology, Louisiana State University, Baton Rouge, LA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Electrical and Computer Engineering and Center for Computation and Technology, Louisiana State University, Baton Rouge, LA","institution_ids":["https://openalex.org/I121820613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077615987","display_name":"Steven R. Brandt","orcid":"https://orcid.org/0000-0002-7979-2906"},"institutions":[{"id":"https://openalex.org/I121820613","display_name":"Louisiana State University","ror":"https://ror.org/05ect4e57","country_code":"US","type":"education","lineage":["https://openalex.org/I121820613"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Robert Brandt","raw_affiliation_strings":["Division of Computer Science and Center for Computation and Technology, Louisiana State University, Baton Rouge, LA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Computer Science and Center for Computation and Technology, Louisiana State University, Baton Rouge, LA","institution_ids":["https://openalex.org/I121820613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5293,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67218935,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"4","issue":"3","first_page":"477","last_page":"490"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9997000098228455,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9937999844551086,"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/stencil","display_name":"Stencil","score":0.964479386806488},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6267470121383667},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5814992189407349},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5180535316467285},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.49199673533439636},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4652925729751587},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.4603253901004791},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.33638790249824524},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27619612216949463},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.2580268383026123},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25264668464660645},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13617771863937378}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.964479386806488},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6267470121383667},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5814992189407349},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5180535316467285},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.49199673533439636},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4652925729751587},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.4603253901004791},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.33638790249824524},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27619612216949463},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.2580268383026123},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25264668464660645},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13617771863937378},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tmscs.2017.2705139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmscs.2017.2705139","pdf_url":null,"source":{"id":"https://openalex.org/S4210201583","display_name":"IEEE Transactions on Multi-Scale Computing Systems","issn_l":"2332-7766","issn":["2332-7766","2372-207X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multi-Scale Computing Systems","raw_type":"journal-article"},{"id":"pmh:oai:digitalcommons.lsu.edu:eecs_pubs-1636","is_oa":false,"landing_page_url":"https://digitalcommons.lsu.edu/eecs_pubs/637","pdf_url":null,"source":{"id":"https://openalex.org/S4210169993","display_name":"Civil War Book Review","issn_l":"1528-6592","issn":["1528-6592"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310315936","host_organization_name":"Louisiana State University","host_organization_lineage":["https://openalex.org/P4310315936"],"host_organization_lineage_names":["Louisiana State University"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"},{"id":"pmh:oai:repository.lsu.edu:eecs_pubs-1636","is_oa":false,"landing_page_url":"https://repository.lsu.edu/eecs_pubs/637","pdf_url":null,"source":{"id":"https://openalex.org/S4210169993","display_name":"Civil War Book Review","issn_l":"1528-6592","issn":["1528-6592"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310315936","host_organization_name":"Louisiana State University","host_organization_lineage":["https://openalex.org/P4310315936"],"host_organization_lineage_names":["Louisiana State University"],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1552060988","https://openalex.org/W1584878351","https://openalex.org/W1936984751","https://openalex.org/W1975001341","https://openalex.org/W1987588924","https://openalex.org/W1988958079","https://openalex.org/W1997147891","https://openalex.org/W1997614470","https://openalex.org/W2001258868","https://openalex.org/W2016618963","https://openalex.org/W2023415862","https://openalex.org/W2028798345","https://openalex.org/W2039378765","https://openalex.org/W2041561387","https://openalex.org/W2048968833","https://openalex.org/W2078636996","https://openalex.org/W2084110734","https://openalex.org/W2091545779","https://openalex.org/W2110760914","https://openalex.org/W2113190809","https://openalex.org/W2118127549","https://openalex.org/W2122297544","https://openalex.org/W2124343275","https://openalex.org/W2126830109","https://openalex.org/W2130749431","https://openalex.org/W2154078685","https://openalex.org/W2154786353","https://openalex.org/W2157685422","https://openalex.org/W2160943542","https://openalex.org/W2183420951","https://openalex.org/W2186216222","https://openalex.org/W2511171334","https://openalex.org/W2560653225","https://openalex.org/W2997701623","https://openalex.org/W3139770841","https://openalex.org/W4239017056","https://openalex.org/W4248236105","https://openalex.org/W4250047567","https://openalex.org/W6633208249","https://openalex.org/W6634780678","https://openalex.org/W6647305348","https://openalex.org/W6647634003","https://openalex.org/W6647881808","https://openalex.org/W6649647257","https://openalex.org/W6660449994","https://openalex.org/W6673001458","https://openalex.org/W6676270890","https://openalex.org/W6677314870","https://openalex.org/W6677400419","https://openalex.org/W6677987228","https://openalex.org/W6682805176","https://openalex.org/W6682907825","https://openalex.org/W6683041335","https://openalex.org/W6684922296","https://openalex.org/W6686093555","https://openalex.org/W6686671479","https://openalex.org/W6725224610","https://openalex.org/W6730340063"],"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/W2008005532","https://openalex.org/W1971603802","https://openalex.org/W1795008753","https://openalex.org/W2131257462"],"abstract_inverted_index":{"Stencil":[0],"computations":[1,200],"form":[2],"the":[3,37,71,125,133,152,160,205,237,261,269],"basis":[4],"for":[5,106,132,198,229],"computer":[6],"simulations":[7],"across":[8],"almost":[9],"every":[10],"field":[11],"of":[12,36,43,65,68,77,83,96,98,119,127,130,155,162,180,182,207,235],"science,":[13],"such":[14],"as":[15],"computational":[16],"fluid":[17],"dynamics,":[18],"data":[19,27,41,48],"mining,":[20],"and":[21,40,50,90,100,203,210,241,267],"image":[22],"processing.":[23],"Their":[24],"mostly":[25],"regular":[26],"access":[28],"patterns":[29],"potentially":[30],"enable":[31],"them":[32],"to":[33,74,135,144],"take":[34],"advantage":[35],"high":[38],"computation":[39,150],"bandwidth":[42],"GPUs,":[44],"but":[45,123],"only":[46,114],"if":[47],"buffering":[49,163,170,227],"other":[51],"issues":[52],"are":[53],"handled":[54],"properly.":[55],"Finding":[56],"a":[57,63,91,116,148,224,230,233],"good":[58,117,265],"code":[59],"generation":[60],"strategy":[61,228,271],"presents":[62],"number":[64,154,161],"challenges,":[66],"one":[67],"which":[69,220],"is":[70,272],"best":[72],"way":[73],"make":[75],"use":[76],"memory.":[78],"GPUs":[79,202],"have":[80],"several":[81],"types":[82],"on-chip":[84,243],"storage":[85,99,131,138,244],"including":[86],"registers,":[87],"shared":[88],"memory,":[89],"read-only":[92,208],"cache.":[93,212],"The":[94],"choice":[95],"type":[97,129],"how":[101],"it\u2019s":[102],"used,":[103],"abuffering":[104],"strategy,":[105],"each":[107,128],"stencil":[108,121,149,176,199],"array":[109],"(grid":[110],"function,":[111],"[GF])":[112],"not":[113],"requires":[115],"understanding":[118],"its":[120],"pattern,":[122],"also":[124],"efficiency":[126],"GF,":[134],"avoid":[136],"squandering":[137],"that":[139,260,268],"would":[140],"be":[141,254],"more":[142],"beneficial":[143],"another":[145],"GF.":[146],"For":[147],"with$N$GFs,":[151],"total":[153],"possible":[156],"assignments":[157],"is$\\beta":[158],"^{N}$where$\\beta$is":[159],"strategies.":[164],"Our":[165],"code-generation":[166],"framework":[167],"supports":[168],"five":[169],"strategies":[171],"($\\beta":[172],"=5$).":[173],"Large,":[174],"complex":[175],"kernels":[177],"may":[178],"consist":[179],"dozens":[181],"GFs,":[183],"resulting":[184],"in":[185,226],"significant":[186],"search":[187],"overhead.":[188],"In":[189],"this":[190,248],"work,":[191],"we":[192,214],"present":[193],"an":[194,216,250],"analytic":[195],"performance":[196,262],"model":[197,263],"on":[201],"study":[204],"behavior":[206],"cache":[209],"L2":[211],"Next,":[213],"propose":[215],"efficiency-based":[217],"assignment":[218,251,270],"algorithm":[219],"operates":[221],"by":[222],"scoring":[223],"change":[225],"GF":[231],"using":[232,247],"combination":[234],"(a)":[236],"predicted":[238],"execution":[239],"time":[240],"(b)":[242],"usage.":[245],"By":[246],"scoring,":[249],"for$N$GFs":[252],"can":[253],"determined":[255],"in$(\\beta":[256],"-1)N(N+1)/2$steps.":[257],"Results":[258],"show":[259],"has":[264],"accuracy":[266],"highly":[273],"efficient.":[274]},"counts_by_year":[{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}