{"id":"https://openalex.org/W4313417883","doi":"https://doi.org/10.1109/tpds.2022.3221085","title":"The Role of Idle Waves, Desynchronization, and Bottleneck Evasion in the Performance of Parallel Programs","display_name":"The Role of Idle Waves, Desynchronization, and Bottleneck Evasion in the Performance of Parallel Programs","publication_year":2022,"publication_date":"2022-11-10","ids":{"openalex":"https://openalex.org/W4313417883","doi":"https://doi.org/10.1109/tpds.2022.3221085"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2022.3221085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3221085","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed 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/A5079056246","display_name":"Ayesha Afzal","orcid":"https://orcid.org/0000-0001-5061-0438"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ayesha Afzal","raw_affiliation_strings":["Erlangen National High Performance Computing Center (NHR@FAU), Friedrich-Alexander-Universit&#x00E4;t Erlangen-N&#x00FC;rnberg, Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0001-5061-0438","affiliations":[{"raw_affiliation_string":"Erlangen National High Performance Computing Center (NHR@FAU), Friedrich-Alexander-Universit&#x00E4;t Erlangen-N&#x00FC;rnberg, Erlangen, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082552227","display_name":"Georg Hager","orcid":"https://orcid.org/0000-0002-8723-2781"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georg Hager","raw_affiliation_strings":["Erlangen National High Performance Computing Center (NHR@FAU), Friedrich-Alexander-Universit&#x00E4;t Erlangen-N&#x00FC;rnberg, Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0002-8723-2781","affiliations":[{"raw_affiliation_string":"Erlangen National High Performance Computing Center (NHR@FAU), Friedrich-Alexander-Universit&#x00E4;t Erlangen-N&#x00FC;rnberg, Erlangen, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070209050","display_name":"Gerhard Wellein","orcid":"https://orcid.org/0000-0001-7371-3026"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gerhard Wellein","raw_affiliation_strings":["Erlangen National High Performance Computing Center (NHR@FAU), Friedrich-Alexander-Universit&#x00E4;t Erlangen-N&#x00FC;rnberg, Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7371-3026","affiliations":[{"raw_affiliation_string":"Erlangen National High Performance Computing Center (NHR@FAU), Friedrich-Alexander-Universit&#x00E4;t Erlangen-N&#x00FC;rnberg, Erlangen, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3931,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89187102,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"34","issue":"2","first_page":"623","last_page":"638"},"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":0.9991999864578247,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9988999962806702,"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/bottleneck","display_name":"Bottleneck","score":0.8360774517059326},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7699999809265137},{"id":"https://openalex.org/keywords/idle","display_name":"Idle","score":0.7524832487106323},{"id":"https://openalex.org/keywords/evasion","display_name":"Evasion (ethics)","score":0.498699426651001},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.37546849250793457},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.34876665472984314},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3425496220588684},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14909565448760986},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.13838544487953186}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8360774517059326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7699999809265137},{"id":"https://openalex.org/C16320812","wikidata":"https://www.wikidata.org/wiki/Q1812200","display_name":"Idle","level":2,"score":0.7524832487106323},{"id":"https://openalex.org/C2781251061","wikidata":"https://www.wikidata.org/wiki/Q5416089","display_name":"Evasion (ethics)","level":3,"score":0.498699426651001},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.37546849250793457},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.34876665472984314},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3425496220588684},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14909565448760986},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.13838544487953186},{"id":"https://openalex.org/C8891405","wikidata":"https://www.wikidata.org/wiki/Q1059","display_name":"Immune system","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C203014093","wikidata":"https://www.wikidata.org/wiki/Q101929","display_name":"Immunology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2022.3221085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3221085","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1512455886","https://openalex.org/W1522241184","https://openalex.org/W1543047378","https://openalex.org/W1575775940","https://openalex.org/W1596846800","https://openalex.org/W1596860781","https://openalex.org/W1673943906","https://openalex.org/W1884004174","https://openalex.org/W1972865626","https://openalex.org/W2000882268","https://openalex.org/W2002505081","https://openalex.org/W2002555321","https://openalex.org/W2060404042","https://openalex.org/W2062011830","https://openalex.org/W2068975988","https://openalex.org/W2069578053","https://openalex.org/W2096714979","https://openalex.org/W2097406530","https://openalex.org/W2101511474","https://openalex.org/W2116493429","https://openalex.org/W2127245553","https://openalex.org/W2170902912","https://openalex.org/W2211971732","https://openalex.org/W2221817300","https://openalex.org/W2246786759","https://openalex.org/W2505455397","https://openalex.org/W2792804042","https://openalex.org/W2806938299","https://openalex.org/W2952756537","https://openalex.org/W2986407468","https://openalex.org/W3011377185","https://openalex.org/W3037519583","https://openalex.org/W3098878359","https://openalex.org/W3099293249","https://openalex.org/W3101951032","https://openalex.org/W3102705131","https://openalex.org/W3134636421","https://openalex.org/W3140689773","https://openalex.org/W4205602523","https://openalex.org/W6635938614","https://openalex.org/W6637121231","https://openalex.org/W6689006381","https://openalex.org/W6922273017"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W1987128138","https://openalex.org/W2748922771"],"abstract_inverted_index":{"The":[0],"performance":[1,15,23,209],"of":[2,31,73,86,98,103,149,160,172,179,223],"highly":[3],"parallel":[4,105],"applications":[5],"on":[6,151],"distributed-memory":[7],"systems":[8],"is":[9,121],"influenced":[10],"by":[11,218],"many":[12],"factors.":[13],"Analytic":[14],"modeling":[16],"techniques":[17],"aim":[18],"to":[19,46,83,94,145],"provide":[20],"insight":[21],"into":[22],"limitations":[24],"and":[25,55,61,78,127,138,168,182,192],"are":[26,64],"often":[27],"the":[28,39,48,52,56,71,99,147,158,170,221,224,227],"starting":[29],"point":[30],"optimization":[32],"efforts.":[33],"However,":[34],"coupling":[35],"analytic":[36],"models":[37],"across":[38],"system":[40],"hierarchy":[41],"(socket,":[42],"node,":[43],"network)":[44],"fails":[45],"encompass":[47],"intricate":[49],"interplay":[50],"between":[51],"program":[53],"code":[54,106,144,180],"hardware,":[57],"especially":[58],"when":[59],"execution":[60],"communication":[62,87,175,193,205],"bottlenecks":[63],"involved.":[65],"In":[66],"this":[67],"paper":[68],"we":[69,123],"investigate":[70,157],"effect":[72],"<italic":[74],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[75],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">bottleneck":[76],"evasion</i>":[77],"how":[79,198],"it":[80],"can":[81,215],"lead":[82],"automatic":[84,173],"overlap":[85],"overhead":[88,222],"with":[89],"computation.":[90],"Bottleneck":[91],"evasion":[92],"leads":[93],"a":[95,104,139,177],"gradual":[96],"loss":[97],"initial":[100],"bulk-synchronous":[101],"behavior":[102],"so":[107],"that":[108,211],"its":[109],"processes":[110],"become":[111],"desynchronized.":[112],"This":[113],"occurs":[114],"most":[115],"prominently":[116],"in":[117],"memory-bound":[118,125],"programs,":[119],"which":[120],"why":[122],"choose":[124],"benchmark":[126],"application":[128],"codes,":[129],"specifically":[130],"an":[131],"MPI-augmented":[132],"STREAM":[133],"Triad,":[134],"sparse":[135],"matrix-vector":[136],"multiplication,":[137],"collective-avoiding":[140],"Chebyshev":[141],"filter":[142],"diagonalization":[143],"demonstrate":[146],"consequences":[148],"desynchronization":[150,167],"two":[152],"different":[153],"supercomputing":[154],"platforms.":[155],"We":[156],"role":[159],"idle":[161],"waves":[162],"as":[163,185,203],"possible":[164],"triggers":[165],"for":[166,176],"show":[169],"impact":[171],"asynchronous":[174],"spectrum":[178],"properties":[181],"parameters,":[183],"such":[184],"saturation":[186],"point,":[187],"matrix":[188],"structures,":[189],"domain":[190],"decomposition,":[191],"concurrency.":[194],"Our":[195],"findings":[196],"reveal":[197],"eliminating":[199],"synchronization":[200],"points":[201],"(such":[202],"collective":[204,225],"or":[206],"barriers)":[207],"precipitates":[208],"improvements":[210],"go":[212],"beyond":[213],"what":[214],"be":[216],"expected":[217],"simply":[219],"subtracting":[220],"from":[226],"overall":[228],"runtime.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}