{"id":"https://openalex.org/W2150527190","doi":"https://doi.org/10.1145/1693453.1693483","title":"Improving parallelism and locality with asynchronous algorithms","display_name":"Improving parallelism and locality with asynchronous algorithms","publication_year":2010,"publication_date":"2010-01-09","ids":{"openalex":"https://openalex.org/W2150527190","doi":"https://doi.org/10.1145/1693453.1693483","mag":"2150527190"},"language":"en","primary_location":{"id":"doi:10.1145/1693453.1693483","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1693453.1693483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","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/A5100698777","display_name":"Lixia Liu","orcid":"https://orcid.org/0000-0001-6132-4461"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lixia Liu","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100337917","display_name":"Zhiyuan Li","orcid":"https://orcid.org/0000-0001-5364-1598"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiyuan Li","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100698777"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":4.4944,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.95094921,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"213","last_page":"222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9969000220298767,"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":0.8665794134140015},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8090496063232422},{"id":"https://openalex.org/keywords/loop-tiling","display_name":"Loop tiling","score":0.7521796822547913},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6714444756507874},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.6632601022720337},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.6160379648208618},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.49179986119270325},{"id":"https://openalex.org/keywords/instruction-level-parallelism","display_name":"Instruction-level parallelism","score":0.45423030853271484},{"id":"https://openalex.org/keywords/loop-fission","display_name":"Loop fission","score":0.44978559017181396},{"id":"https://openalex.org/keywords/nested-loop-join","display_name":"Nested loop join","score":0.43429118394851685},{"id":"https://openalex.org/keywords/locality-of-reference","display_name":"Locality of reference","score":0.42291656136512756},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.42174533009529114},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.41146165132522583},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3451022505760193},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.3051820397377014},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.21592208743095398},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.09883654117584229}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8665794134140015},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8090496063232422},{"id":"https://openalex.org/C11799548","wikidata":"https://www.wikidata.org/wiki/Q6675847","display_name":"Loop tiling","level":3,"score":0.7521796822547913},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6714444756507874},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6632601022720337},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.6160379648208618},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.49179986119270325},{"id":"https://openalex.org/C140763907","wikidata":"https://www.wikidata.org/wiki/Q2714055","display_name":"Instruction-level parallelism","level":3,"score":0.45423030853271484},{"id":"https://openalex.org/C134718785","wikidata":"https://www.wikidata.org/wiki/Q6675821","display_name":"Loop fission","level":3,"score":0.44978559017181396},{"id":"https://openalex.org/C1306188","wikidata":"https://www.wikidata.org/wiki/Q4060687","display_name":"Nested loop join","level":2,"score":0.43429118394851685},{"id":"https://openalex.org/C27602214","wikidata":"https://www.wikidata.org/wiki/Q1868547","display_name":"Locality of reference","level":3,"score":0.42291656136512756},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.42174533009529114},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.41146165132522583},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3451022505760193},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.3051820397377014},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.21592208743095398},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.09883654117584229},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1693453.1693483","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1693453.1693483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W579331379","https://openalex.org/W1510263988","https://openalex.org/W1580560707","https://openalex.org/W1597668820","https://openalex.org/W1662982362","https://openalex.org/W1968347730","https://openalex.org/W1978564754","https://openalex.org/W1990832096","https://openalex.org/W1999912658","https://openalex.org/W2015935981","https://openalex.org/W2034761517","https://openalex.org/W2035701183","https://openalex.org/W2049032382","https://openalex.org/W2092763781","https://openalex.org/W2095875205","https://openalex.org/W2148925331","https://openalex.org/W2149668662","https://openalex.org/W2153166874","https://openalex.org/W2159560337","https://openalex.org/W2163059351","https://openalex.org/W3151489216","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2342605656","https://openalex.org/W2112391112","https://openalex.org/W2058764256","https://openalex.org/W1532159642","https://openalex.org/W154155438","https://openalex.org/W2062111218","https://openalex.org/W2040522199","https://openalex.org/W4254171597","https://openalex.org/W2165782970","https://openalex.org/W4245743015"],"abstract_inverted_index":{"As":[0],"multicore":[1,175],"chips":[2],"become":[3],"the":[4,21,29,32,49,78,94,103,121,146,168],"main":[5],"building":[6],"blocks":[7],"for":[8,39,82],"high":[9],"performance":[10,17,169],"computers,":[11],"many":[12],"numerical":[13,195],"applications":[14],"face":[15],"a":[16,83,90,107],"impediment":[18],"due":[19,177],"to":[20,25,65,70,76,119,124,144,178],"limited":[22],"hardware":[23],"capacity":[24],"move":[26],"data":[27,51,72,181],"between":[28,152],"CPU":[30],"and":[31,74,133,149,162,183],"off-chip":[33],"memory.":[34],"This":[35],"is":[36,157],"especially":[37],"true":[38],"large":[40,50],"computing":[41],"problems":[42],"solved":[43],"by":[44],"iterative":[45,86,172],"algorithms":[46,87,140,173],"because":[47,101],"of":[48,85,170],"set":[52],"typically":[53],"used.":[54],"Loop":[55],"tiling,":[56],"also":[57],"known":[58],"as":[59],"loop":[60,104,127,163],"blocking,":[61],"was":[62],"shown":[63],"previously":[64,142],"be":[66,111,136],"an":[67],"effective":[68,126],"way":[69],"enhance":[71],"locality,":[73],"hence":[75],"reduce":[77,145],"memory":[79],"bandwidth":[80],"pressure,":[81],"class":[84],"executed":[88],"on":[89,174],"single":[91,108],"processor.":[92],"Unfortunately,":[93],"tiled":[95],"programs":[96],"suffer":[97],"from":[98,190],"reduced":[99],"parallelism":[100,132],"only":[102],"iterations":[105],"within":[106],"tile":[109],"can":[110,135,165],"easily":[112],"parallelized.":[113],"In":[114],"this":[115],"work,":[116],"we":[117],"propose":[118],"use":[120],"asynchronous":[122],"model":[123],"enable":[125],"tiling":[128,164],"such":[129],"that":[130,158],"both":[131],"locality":[134,182],"attained":[137,180],"simultaneously.":[138],"Asynchronous":[139],"were":[141],"proposed":[143],"communication":[147],"cost":[148],"synchronization":[150],"overhead":[151],"processors.":[153],"Our":[154],"new":[155],"discovery":[156],"carefully":[159],"controlled":[160],"asynchrony":[161],"significantly":[166],"improve":[167],"parallel":[171],"processors":[176],"simultaneously":[179],"loop-level":[184],"parallelism.":[185],"We":[186],"present":[187],"supporting":[188],"evidence":[189],"experiments":[191],"with":[192],"three":[193],"well-known":[194],"kernels.":[196]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}