{"id":"https://openalex.org/W2150329270","doi":"https://doi.org/10.1109/iscas.2010.5537722","title":"To GPU synchronize or not GPU synchronize?","display_name":"To GPU synchronize or not GPU synchronize?","publication_year":2010,"publication_date":"2010-05-01","ids":{"openalex":"https://openalex.org/W2150329270","doi":"https://doi.org/10.1109/iscas.2010.5537722","mag":"2150329270"},"language":"en","primary_location":{"id":"doi:10.1109/iscas.2010.5537722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas.2010.5537722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2010 IEEE International Symposium on Circuits and Systems","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/A5058539554","display_name":"Wu-chun Feng","orcid":"https://orcid.org/0000-0002-6015-0727"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wu-chun Feng","raw_affiliation_strings":["Virginia Polytechnic Institute and State University, Blacksburg, VA, US"],"affiliations":[{"raw_affiliation_string":"Virginia Polytechnic Institute and State University, Blacksburg, VA, US","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107772525","display_name":"Shucai Xiao","orcid":"https://orcid.org/0009-0004-9688-015X"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shucai Xiao","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Virginia Polytechnic Institute and State University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Virginia Polytechnic Institute and State University, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5058539554"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":3.5377,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.93368059,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3801","last_page":"3804"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9954000115394592,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9943000078201294,"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":0.8238751292228699},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5992451310157776},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5767230987548828},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5011453628540039},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4926174283027649},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.1847357451915741}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8238751292228699},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5992451310157776},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5767230987548828},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5011453628540039},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4926174283027649},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.1847357451915741},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iscas.2010.5537722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas.2010.5537722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2010 IEEE International Symposium on Circuits and Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.192.9491","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.192.9491","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://synergy.cs.vt.edu/pubs/papers/feng-iscas2010-gpusync.pdf","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":13,"referenced_works":["https://openalex.org/W1504291959","https://openalex.org/W1978280181","https://openalex.org/W1992851788","https://openalex.org/W1999588960","https://openalex.org/W2084363500","https://openalex.org/W2087064593","https://openalex.org/W2108600626","https://openalex.org/W2109393352","https://openalex.org/W2111953042","https://openalex.org/W2117689653","https://openalex.org/W2121444153","https://openalex.org/W3147878143","https://openalex.org/W6677381316"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2505380084","https://openalex.org/W2390279801","https://openalex.org/W4400333498","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W1980160788"],"abstract_inverted_index":{"The":[0],"graphics":[1],"processing":[2],"unit":[3],"(GPU)":[4],"has":[5,74],"evolved":[6],"from":[7],"being":[8],"a":[9,16,55,72,109,115,167,186],"fixed-function":[10,21],"processor":[11,18,32],"with":[12,19],"programmable":[13,17],"stages":[14],"into":[15],"many":[20,49],"components":[22],"that":[23,42,66,137,188,205],"deliver":[24,150],"massive":[25,44],"parallelism.":[26],"By":[27],"modifying":[28],"the":[29,38,61,86,98,105,119,122,128,142,158,180,191,222,226],"GPU's":[30],"stream":[31],"to":[33,78,85,126],"support":[34,90],"\u201cgeneral-purpose":[35],"computation\u201d":[36],"on":[37,71,97,141],"GPU":[39,73,123,143,211,213,231,235],"(GPGPU),":[40],"applications":[41,83],"perform":[43],"vector":[45],"operations":[46],"can":[47,67,102,145,189],"realize":[48],"orders-of-magnitude":[50],"improvement":[51],"in":[52,124,153,183,209],"performance":[53,148],"over":[54],"traditional":[56],"processor,":[57],"i.e.,":[58],"CPU.":[59],"However,":[60,197],"breadth":[62],"of":[63,88,108,121,160,193,228],"general-purpose":[64],"computation":[65],"be":[68],"efficiently":[69],"supported":[70],"largely":[75],"been":[76],"limited":[77],"highly":[79],"dataparallel":[80],"or":[81,233],"task-parallel":[82],"due":[84],"lack":[87],"explicit":[89],"for":[91],"communication":[92,101,129,162],"between":[93,130],"streaming":[94],"multiprocessors":[95],"(SMs)":[96],"GPU.":[99],"Such":[100],"occur":[103],"via":[104,221],"global":[106],"memory":[107,168],"GPU,":[110],"but":[111],"it":[112,208],"then":[113],"requires":[114],"barrier":[116,139],"synchronization":[117,140,214,220],"across":[118],"SMs":[120],"order":[125],"complete":[127],"SMs.":[131],"Although":[132],"our":[133],"previous":[134],"work":[135],"demonstrated":[136],"implementing":[138],"itself":[144],"significantly":[146],"improve":[147],"and":[149],"correct":[151],"results":[152],"critical":[154],"bioinformatics":[155],"applications,":[156],"guaranteeing":[157],"correctness":[159,192],"inter-SM":[161,195],"is":[163,171],"only":[164],"possible":[165],"if":[166],"consistency":[169],"model":[170],"assumed.":[172],"To":[173],"address":[174],"this":[175,198],"problem,":[176],"NVIDIA":[177],"recently":[178],"introduced":[179],"_threadfence()":[181],"function":[182,187,199],"CUDA":[184],"2.2,":[185],"guarantee":[190],"GPU-based":[194],"communication.":[196],"currently":[200],"introduces":[201],"so":[202],"much":[203],"overhead":[204],"when":[206],"using":[207],"(direct)":[210],"synchronization,":[212],"actually":[215],"performs":[216],"worse":[217],"than":[218],"indirect":[219],"CPU,":[223],"thus":[224],"raising":[225],"question":[227],"whether":[229],"\u201cto":[230],"synchronize":[232],"not":[234],"synchronize?\u201d":[236]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":13},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}