{"id":"https://openalex.org/W2170601541","doi":"https://doi.org/10.1109/ipdps.2014.22","title":"Scalar Waving: Improving the Efficiency of SIMD Execution on GPUs","display_name":"Scalar Waving: Improving the Efficiency of SIMD Execution on GPUs","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2170601541","doi":"https://doi.org/10.1109/ipdps.2014.22","mag":"2170601541"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2014.22","doi":"https://doi.org/10.1109/ipdps.2014.22","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2014.22","pdf_url":null,"source":{"id":"https://openalex.org/S4210174069","display_name":"IEEE International Parallel and Distributed Processing Symposium (IPDPS)","issn_l":"1530-2075","issn":["1530-2075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-2","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 28th International Parallel and Distributed Processing Symposium","raw_type":"proceedings-article"},"volume":null,"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/A5080582337","display_name":"Ayse Y\u0131lmazer","orcid":"https://orcid.org/0000-0003-4502-7365","observed_orcids":["https://orcid.org/0000-0003-4502-7365"]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ayse Yilmazer","raw_affiliation_strings":["Electrical and Computer Engineering Department, Northeastern University, Boston, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Northeastern University, Boston, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011432420","display_name":"Zhongliang Chen","orcid":"https://orcid.org/0000-0002-8881-2294","observed_orcids":["https://orcid.org/0000-0002-8881-2294"]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhongliang Chen","raw_affiliation_strings":["Electrical and Computer Engineering Department, Northeastern University, Boston, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Northeastern University, Boston, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061128237","display_name":"David R Kaeli","orcid":"https://orcid.org/0000-0002-5692-0151","observed_orcids":["https://orcid.org/0000-0002-5692-0151"]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Kaeli","raw_affiliation_strings":["Electrical and Computer Engineering Department, Northeastern University, Boston, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Northeastern University, Boston, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":1.5302,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.83505001,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"103","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gpu-architecture","display_name":"GPU architecture","score":0.6679999828338623},{"id":"https://openalex.org/keywords/thread-divergence","display_name":"thread divergence","score":0.6190000176429749},{"id":"https://openalex.org/keywords/gpu-optimization","display_name":"GPU optimization","score":0.32499998807907104}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.9352965950965881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8129787445068359},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.784313440322876},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.6275017261505127},{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.5468976497650146},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.4405999481678009},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.16748708486557007},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1541845202445984},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1076037585735321},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdps.2014.22","doi":"https://doi.org/10.1109/ipdps.2014.22","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2014.22","pdf_url":null,"source":{"id":"https://openalex.org/S4210174069","display_name":"IEEE International Parallel and Distributed Processing Symposium (IPDPS)","issn_l":"1530-2075","issn":["1530-2075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-2","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE 28th International Parallel and Distributed Processing Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1485193134","https://openalex.org/W1979527452","https://openalex.org/W1994316441","https://openalex.org/W2024001079","https://openalex.org/W2034804129","https://openalex.org/W2080592089","https://openalex.org/W2090584832","https://openalex.org/W2101430044","https://openalex.org/W2143798346","https://openalex.org/W2153963140","https://openalex.org/W2155568054","https://openalex.org/W2160428323","https://openalex.org/W2168921806","https://openalex.org/W2169880332","https://openalex.org/W2273440736","https://openalex.org/W3148394109"],"related_works":["https://openalex.org/W2486564422","https://openalex.org/W2153963140","https://openalex.org/W7043159614","https://openalex.org/W4238323557","https://openalex.org/W7096172707","https://openalex.org/W1973538724","https://openalex.org/W2021858587","https://openalex.org/W2042411977","https://openalex.org/W2292777913","https://openalex.org/W2081373884"],"abstract_inverted_index":{"GPUs":[0,80,95],"take":[1],"advantage":[2],"of":[3,49,78,129,163,174,199,229,242,250],"uniformity":[4],"in":[5,57,75,112,217],"program":[6,30],"control":[7],"flow":[8],"and":[9,32,67,84,147,247],"utilize":[10],"SIMD":[11,18,24,37,59,114,154,168,175],"execution":[12,15,124,128,162],"to":[13,26,105,121,125,139,170,213],"obtain":[14,211],"efficiency.":[16,157],"In":[17,116],"execution,":[19],"threads":[20,56,111],"are":[21],"batched":[22],"into":[23,226],"groups":[25,169],"share":[27],"a":[28,46,58,76,88,113,137,151,197,214,240],"common":[29,90],"counter":[31],"execute":[33,61,148],"identical":[34],"instructions":[35,51,53,104],"on":[36,153,219],"pipelines.":[38],"Previous":[39],"research":[40],"has":[41],"shown":[42],"that":[43,207,232],"there":[44],"is":[45],"significant":[47],"number":[48],"scalar":[50,99,123,130,134,141,165,208,237,244],"-":[52,73],"where":[54],"different":[55,186,192],"group":[60,152],"using":[62,184,201],"the":[63,69,110,144,172,227,243,251],"same":[64,71,145],"input":[65],"operands":[66],"generate":[68],"exact":[70],"output":[72],"present":[74],"range":[77,198],"applications.":[79],"eliminate":[81,126],"redundant":[82,127],"fetches":[83],"decodes":[85],"by":[86,109],"utilizing":[87],"shared":[89],"pipeline":[91],"front-end.":[92],"However,":[93],"most":[94],"do":[96],"not":[97],"handle":[98],"instruction":[100],"efficiently,":[101],"allowing":[102],"these":[103],"be":[106],"redundantly":[107],"executed":[108],"group.":[115],"this":[117],"paper,":[118],"we":[119,233],"propose":[120,160],"use":[122],"instructions.":[131],"We":[132,158,180,195],"introduce":[133],"waving":[135,209,238],"as":[136,150,239],"mechanism":[138],"batch":[140],"operations":[142],"possessing":[143],"PC":[146],"them":[149],"lanes":[155,176],"for":[156],"also":[159,223],"simultaneous":[161],"dynamically-formed":[164],"waves":[166],"with":[167,236],"overcome":[171],"under-utilization":[173],"when":[177],"encountering":[178],"divergence.":[179],"evaluate":[181,196],"our":[182],"work":[183],"22":[185],"GPU":[187],"benchmarks":[188],"taken":[189],"from":[190],"4":[191],"benchmark":[193],"suites.":[194],"configurations":[200],"timing":[202],"simulation.":[203],"Our":[204,221],"results":[205],"show":[206],"can":[210,234],"up":[212],"25%":[215],"improvement":[216],"performance":[218,230],"average.":[220],"experiments":[222],"provide":[224],"insight":[225],"amount":[228],"gain":[231],"expect":[235],"function":[241],"content,":[245],"occupancy,":[246],"memory":[248],"characteristics":[249],"target":[252],"application.":[253]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2016-06-24T00:00:00"}