{"id":"https://openalex.org/W3037519583","doi":"https://doi.org/10.1007/978-3-030-50743-5_20","title":"Desynchronization and Wave Pattern Formation in MPI-Parallel and Hybrid Memory-Bound Programs","display_name":"Desynchronization and Wave Pattern Formation in MPI-Parallel and Hybrid Memory-Bound Programs","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3037519583","doi":"https://doi.org/10.1007/978-3-030-50743-5_20","mag":"3037519583"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-50743-5_20","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-50743-5_20","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-50743-5_20.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-50743-5_20.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ayesha Afzal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ayesha Afzal","raw_affiliation_strings":["Erlangen Regional Computing Center (RRZE), 91058, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center (RRZE), 91058, Erlangen, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Georg Hager","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georg Hager","raw_affiliation_strings":["Erlangen Regional Computing Center (RRZE), 91058, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Erlangen Regional Computing Center (RRZE), 91058, Erlangen, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Gerhard Wellein","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Wellein","raw_affiliation_strings":["Department of Computer Science, University of Erlangen-N\u00fcrnberg, 91058, Erlangen, Germany","Erlangen Regional Computing Center (RRZE), 91058, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Erlangen-N\u00fcrnberg, 91058, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]},{"raw_affiliation_string":"Erlangen Regional Computing Center (RRZE), 91058, Erlangen, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":null,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"391","last_page":"411"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9453999996185303,"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":0.9453999996185303,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.02019999921321869,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.005900000222027302,"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/bottleneck","display_name":"Bottleneck","score":0.7206000089645386},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.641700029373169},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5685999989509583},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4390999972820282},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.40959998965263367},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.39800000190734863},{"id":"https://openalex.org/keywords/chebyshev-filter","display_name":"Chebyshev filter","score":0.374099999666214},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.3573000133037567},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.34459999203681946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.883899986743927},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7206000089645386},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.641700029373169},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5685999989509583},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46799999475479126},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4390999972820282},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.40959998965263367},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C21424316","wikidata":"https://www.wikidata.org/wiki/Q718621","display_name":"Chebyshev filter","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.3573000133037567},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.34459999203681946},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.33079999685287476},{"id":"https://openalex.org/C129785596","wikidata":"https://www.wikidata.org/wiki/Q619511","display_name":"Chebyshev polynomials","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.30979999899864197},{"id":"https://openalex.org/C2780505938","wikidata":"https://www.wikidata.org/wiki/Q17093282","display_name":"Unavailability","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C2781089630","wikidata":"https://www.wikidata.org/wiki/Q21856745","display_name":"Realization (probability)","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C101765175","wikidata":"https://www.wikidata.org/wiki/Q577764","display_name":"Communications system","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C207016750","wikidata":"https://www.wikidata.org/wiki/Q1955627","display_name":"Pattern formation","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C5297727","wikidata":"https://www.wikidata.org/wiki/Q786970","display_name":"Autocorrelation","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.26089999079704285}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/978-3-030-50743-5_20","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-50743-5_20","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-50743-5_20.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:arXiv.org:2002.02989","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2002.02989","pdf_url":"https://arxiv.org/pdf/2002.02989","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:pubmedcentral.nih.gov:7295361","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7295361","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"High Performance Computing","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1007/978-3-030-50743-5_20","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-50743-5_20","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-50743-5_20.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3037519583.pdf","grobid_xml":"https://content.openalex.org/works/W3037519583.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1884004174","https://openalex.org/W1972865626","https://openalex.org/W2002555321","https://openalex.org/W2009223344","https://openalex.org/W2029023406","https://openalex.org/W2048150445","https://openalex.org/W2059300917","https://openalex.org/W2068975988","https://openalex.org/W2069578053","https://openalex.org/W2078636996","https://openalex.org/W2138782497","https://openalex.org/W2211971732","https://openalex.org/W2492540006","https://openalex.org/W2505455397","https://openalex.org/W2791494644","https://openalex.org/W2792804042","https://openalex.org/W2806219932","https://openalex.org/W2806938299","https://openalex.org/W2986407468"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Analytic,":[1],"first-principles":[2],"performance":[3],"modeling":[4],"of":[5,36,68,73,118,132,135,151,167,204],"distributed-memory":[6],"parallel":[7,37],"codes":[8],"is":[9,162,199],"notoriously":[10],"imprecise.":[11],"Even":[12],"for":[13],"applications":[14],"with":[15],"extremely":[16],"regular":[17],"and":[18,56,70,78,137,170],"homogeneous":[19],"compute-communicate":[20],"phases,":[21],"simply":[22],"adding":[23],"communication":[24,54,120,136],"time":[25,28,94,142],"to":[26,40,108,143,157,201],"computation":[27],"does":[29,98],"often":[30],"not":[31,99],"yield":[32],"a":[33,130,209],"satisfactory":[34],"prediction":[35],"runtime":[38],"due":[39],"deviations":[41],"from":[42],"the":[43,65,127,140,149,165,171,189,205],"expected":[44],"simple":[45,83],"lockstep":[46],"pattern":[47],"caused":[48],"by":[49,187],"system":[50,128],"noise,":[51],"variations":[52],"in":[53,111,164,208],"time,":[55],"inherent":[57],"load":[58],"imbalance.":[59],"In":[60,116],"this":[61,168],"paper,":[62],"we":[63,85],"highlight":[64],"specific":[66],"cases":[67],"provoked":[69],"spontaneous":[71],"desynchronization":[72,89,186],"memory-bound,":[74],"bulk-synchronous":[75],"pure":[76],"MPI":[77],"hybrid":[79,180],"MPI+OpenMP":[80],"programs.":[81],"Using":[82],"microbenchmarks":[84],"observe":[86],"that":[87],"although":[88],"can":[90,106,125,183],"introduce":[91],"increased":[92],"waiting":[93],"per":[95,114,153],"process,":[96],"it":[97],"necessarily":[100],"cause":[101],"lower":[102],"resource":[103],"utilization":[104],"but":[105],"lead":[107],"an":[109],"increase":[110],"available":[112],"bandwidth":[113,190],"core.":[115],"case":[117],"significant":[119],"overhead,":[121],"even":[122],"natural":[123],"noise":[124],"shove":[126],"into":[129],"state":[131],"automatic":[133],"overlap":[134],"computation,":[138],"improving":[139],"overall":[141],"solution.":[144],"The":[145],"saturation":[146],"point,":[147],"i.e.,":[148],"number":[150],"processes":[152],"memory":[154,160],"domain":[155],"required":[156],"achieve":[158],"full":[159],"bandwidth,":[161],"pivotal":[163],"dynamics":[166],"process":[169],"emerging":[172],"stable":[173],"wave":[174],"pattern.":[175],"We":[176],"also":[177],"demonstrate":[178,202],"how":[179],"MPI-OpenMP":[181],"programming":[182],"prevent":[184],"desirable":[185],"eliminating":[188],"bottleneck":[191],"among":[192],"processes.":[193],"A":[194],"Chebyshev":[195],"filter":[196],"diagonalization":[197],"application":[198],"used":[200],"some":[203],"observed":[206],"effects":[207],"realistic":[210],"setting.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2020-07-02T00:00:00"}